| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC system registers handling functions for AArch64 mode */ #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include "vgic/vgic.h" #include "sys_regs.h" static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u32 host_pri_bits, host_id_bits, host_seis, host_a3v, seis, a3v; struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); /* * Disallow restoring VM state if not supported by this * hardware. */ host_pri_bits = FIELD_GET(ICC_CTLR_EL1_PRI_BITS_MASK, val) + 1; if (host_pri_bits > vgic_v3_cpu->num_pri_bits) return -EINVAL; vgic_v3_cpu->num_pri_bits = host_pri_bits; host_id_bits = FIELD_GET(ICC_CTLR_EL1_ID_BITS_MASK, val); if (host_id_bits > vgic_v3_cpu->num_id_bits) return -EINVAL; vgic_v3_cpu->num_id_bits = host_id_bits; host_seis = FIELD_GET(ICH_VTR_SEIS_MASK, kvm_vgic_global_state.ich_vtr_el2); seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val); if (host_seis != seis) return -EINVAL; host_a3v = FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2); a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val); if (host_a3v != a3v) return -EINVAL; /* * Here set VMCR.CTLR in ICC_CTLR_EL1 layout. * The vgic_set_vmcr() will convert to ICH_VMCR layout. */ vmcr.cbpr = FIELD_GET(ICC_CTLR_EL1_CBPR_MASK, val); vmcr.eoim = FIELD_GET(ICC_CTLR_EL1_EOImode_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *valp) { struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; struct vgic_vmcr vmcr; u64 val; vgic_get_vmcr(vcpu, &vmcr); val = 0; val |= FIELD_PREP(ICC_CTLR_EL1_PRI_BITS_MASK, vgic_v3_cpu->num_pri_bits - 1); val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits); val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK, FIELD_GET(ICH_VTR_SEIS_MASK, kvm_vgic_global_state.ich_vtr_el2)); val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK, FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2)); /* * The VMCR.CTLR value is in ICC_CTLR_EL1 layout. * Extract it directly using ICC_CTLR_EL1 reg definitions. */ val |= FIELD_PREP(ICC_CTLR_EL1_CBPR_MASK, vmcr.cbpr); val |= FIELD_PREP(ICC_CTLR_EL1_EOImode_MASK, vmcr.eoim); *valp = val; return 0; } static int set_gic_pmr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.pmr = FIELD_GET(ICC_PMR_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_pmr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_PMR_EL1_MASK, vmcr.pmr); return 0; } static int set_gic_bpr0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.bpr = FIELD_GET(ICC_BPR0_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_bpr0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_BPR0_EL1_MASK, vmcr.bpr); return 0; } static int set_gic_bpr1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); if (!vmcr.cbpr) { vmcr.abpr = FIELD_GET(ICC_BPR1_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); } return 0; } static int get_gic_bpr1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); if (!vmcr.cbpr) *val = FIELD_PREP(ICC_BPR1_EL1_MASK, vmcr.abpr); else *val = min((vmcr.bpr + 1), 7U); return 0; } static int set_gic_grpen0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.grpen0 = FIELD_GET(ICC_IGRPEN0_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_grpen0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_IGRPEN0_EL1_MASK, vmcr.grpen0); return 0; } static int set_gic_grpen1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.grpen1 = FIELD_GET(ICC_IGRPEN1_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_grpen1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_GET(ICC_IGRPEN1_EL1_MASK, vmcr.grpen1); return 0; } static void set_apr_reg(struct kvm_vcpu *vcpu, u64 val, u8 apr, u8 idx) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; if (apr) vgicv3->vgic_ap1r[idx] = val; else vgicv3->vgic_ap0r[idx] = val; } static u64 get_apr_reg(struct kvm_vcpu *vcpu, u8 apr, u8 idx) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; if (apr) return vgicv3->vgic_ap1r[idx]; else return vgicv3->vgic_ap0r[idx]; } static int set_gic_ap0r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; set_apr_reg(vcpu, val, 0, idx); return 0; } static int get_gic_ap0r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; *val = get_apr_reg(vcpu, 0, idx); return 0; } static int set_gic_ap1r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; set_apr_reg(vcpu, val, 1, idx); return 0; } static int get_gic_ap1r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; *val = get_apr_reg(vcpu, 1, idx); return 0; } static int set_gic_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { /* Validate SRE bit */ if (!(val & ICC_SRE_EL1_SRE)) return -EINVAL; return 0; } static int get_gic_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; *val = vgicv3->vgic_sre; return 0; } static const struct sys_reg_desc gic_v3_icc_reg_descs[] = { { SYS_DESC(SYS_ICC_PMR_EL1), .set_user = set_gic_pmr, .get_user = get_gic_pmr, }, { SYS_DESC(SYS_ICC_BPR0_EL1), .set_user = set_gic_bpr0, .get_user = get_gic_bpr0, }, { SYS_DESC(SYS_ICC_AP0R0_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R1_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R2_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R3_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP1R0_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R1_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R2_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R3_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_BPR1_EL1), .set_user = set_gic_bpr1, .get_user = get_gic_bpr1, }, { SYS_DESC(SYS_ICC_CTLR_EL1), .set_user = set_gic_ctlr, .get_user = get_gic_ctlr, }, { SYS_DESC(SYS_ICC_SRE_EL1), .set_user = set_gic_sre, .get_user = get_gic_sre, }, { SYS_DESC(SYS_ICC_IGRPEN0_EL1), .set_user = set_gic_grpen0, .get_user = get_gic_grpen0, }, { SYS_DESC(SYS_ICC_IGRPEN1_EL1), .set_user = set_gic_grpen1, .get_user = get_gic_grpen1, }, }; static u64 attr_to_id(u64 attr) { return ARM64_SYS_REG(FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP0_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP1_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_CRN_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_CRM_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP2_MASK, attr)); } int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { if (get_reg_by_id(attr_to_id(attr->attr), gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs))) return 0; return -ENXIO; } int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr, bool is_write) { struct kvm_one_reg reg = { .id = attr_to_id(attr->attr), .addr = attr->addr, }; if (is_write) return kvm_sys_reg_set_user(vcpu, ®, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); else return kvm_sys_reg_get_user(vcpu, ®, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); } |
| 154 289 175 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/processor.h * * Copyright (C) 1995-1999 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PROCESSOR_H #define __ASM_PROCESSOR_H /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is * no point in shifting all network buffers by 2 bytes just to make some IP * header fields appear aligned in memory, potentially sacrificing some DMA * performance on some platforms. */ #define NET_IP_ALIGN 0 #define MTE_CTRL_GCR_USER_EXCL_SHIFT 0 #define MTE_CTRL_GCR_USER_EXCL_MASK 0xffff #define MTE_CTRL_TCF_SYNC (1UL << 16) #define MTE_CTRL_TCF_ASYNC (1UL << 17) #define MTE_CTRL_TCF_ASYMM (1UL << 18) #ifndef __ASSEMBLY__ #include <linux/build_bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/thread_info.h> #include <vdso/processor.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> #include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> #include <asm/ptrace.h> #include <asm/spectre.h> #include <asm/types.h> /* * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ #define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) #define TASK_SIZE_64 (UL(1) << vabits_actual) #define TASK_SIZE_MAX (UL(1) << VA_BITS) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) /* * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied * by the compat vectors page. */ #define TASK_SIZE_32 UL(0x100000000) #else #define TASK_SIZE_32 (UL(0x100000000) - PAGE_SIZE) #endif /* CONFIG_ARM64_64K_PAGES */ #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define DEFAULT_MAP_WINDOW (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : DEFAULT_MAP_WINDOW_64) #else #define TASK_SIZE TASK_SIZE_64 #define DEFAULT_MAP_WINDOW DEFAULT_MAP_WINDOW_64 #endif /* CONFIG_COMPAT */ #ifdef CONFIG_ARM64_FORCE_52BIT #define STACK_TOP_MAX TASK_SIZE_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) #else #define STACK_TOP_MAX DEFAULT_MAP_WINDOW_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(DEFAULT_MAP_WINDOW / 4)) #endif /* CONFIG_ARM64_FORCE_52BIT */ #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ AARCH32_VECTORS_BASE : STACK_TOP_MAX) #else #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ #ifndef CONFIG_ARM64_FORCE_52BIT #define arch_get_mmap_end(addr, len, flags) \ (((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW) #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ base) #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; #define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT /* Have we suspended stepping by a debugger? */ int suspended_step; /* Allow breakpoints and watchpoints to be disabled for this thread. */ int bps_disabled; int wps_disabled; /* Hardware breakpoints pinned to this task. */ struct perf_event *hbp_break[ARM_MAX_BRP]; struct perf_event *hbp_watch[ARM_MAX_WRP]; #endif }; enum vec_type { ARM64_VEC_SVE = 0, ARM64_VEC_SME, ARM64_VEC_MAX, }; enum fp_type { FP_STATE_CURRENT, /* Save based on current task state. */ FP_STATE_FPSIMD, FP_STATE_SVE, }; struct cpu_context { unsigned long x19; unsigned long x20; unsigned long x21; unsigned long x22; unsigned long x23; unsigned long x24; unsigned long x25; unsigned long x26; unsigned long x27; unsigned long x28; unsigned long fp; unsigned long sp; unsigned long pc; }; struct thread_struct { struct cpu_context cpu_context; /* cpu context */ /* * Whitelisted fields for hardened usercopy: * Maintainers must ensure manually that this contains no * implicit padding. */ struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; u64 fpmr; unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; enum fp_type fp_type; /* registers FPSIMD or SVE? */ unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ void *sme_state; /* ZA and ZT state, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ struct user_fpsimd_state kernel_fpsimd_state; unsigned int kernel_fpsimd_cpu; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL struct ptrauth_keys_kernel keys_kernel; #endif #endif #ifdef CONFIG_ARM64_MTE u64 mte_ctrl; #endif u64 sctlr_user; u64 svcr; u64 tpidr2_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, enum vec_type type) { return thread->vl[type]; } static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SVE); } static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SME); } static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) { if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK)) return thread_get_sme_vl(thread); else return thread_get_sve_vl(thread); } unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); void task_set_vl_onexec(struct task_struct *task, enum vec_type type, unsigned long vl); unsigned int task_get_vl_onexec(const struct task_struct *task, enum vec_type type); static inline unsigned int task_get_sve_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SVE); } static inline unsigned int task_get_sme_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SME); } static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); } static inline unsigned int task_get_sve_vl_onexec(const struct task_struct *task) { return task_get_vl_onexec(task, ARM64_VEC_SVE); } static inline void task_set_sve_vl_onexec(struct task_struct *task, unsigned long vl) { task_set_vl_onexec(task, ARM64_VEC_SVE, vl); } #define SCTLR_USER_MASK \ (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB | \ SCTLR_EL1_TCF0_MASK) static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Verify that there is no padding among the whitelisted fields: */ BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + sizeof_field(struct thread_struct, uw.fpmr) + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); *size = sizeof_field(struct thread_struct, uw); } #ifdef CONFIG_COMPAT #define task_user_tls(t) \ ({ \ unsigned long *__tls; \ if (is_compat_thread(task_thread_info(t))) \ __tls = &(t)->thread.uw.tp2_value; \ else \ __tls = &(t)->thread.uw.tp_value; \ __tls; \ }) #else #define task_user_tls(t) (&(t)->thread.uw.tp_value) #endif /* Sync TPIDR_EL0 back to thread_struct for current */ void tls_preserve_current_state(void); #define INIT_THREAD { \ .fpsimd_cpu = NR_CPUS, \ } static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) { s32 previous_syscall = regs->syscallno; memset(regs, 0, sizeof(*regs)); regs->syscallno = previous_syscall; regs->pc = pc; if (system_uses_irq_prio_masking()) regs->pmr_save = GIC_PRIO_IRQON; } static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); regs->pstate = PSR_MODE_EL0t; spectre_v4_enable_task_mitigation(current); regs->sp = sp; } #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); regs->pstate = PSR_AA32_MODE_USR; if (pc & 1) regs->pstate |= PSR_AA32_T_BIT; #ifdef __AARCH64EB__ regs->pstate |= PSR_AA32_E_BIT; #endif spectre_v4_enable_task_mitigation(current); regs->compat_sp = sp; } #endif static __always_inline bool is_ttbr0_addr(unsigned long addr) { /* entry assembly clears tags for TTBR0 addrs */ return addr < TASK_SIZE; } static __always_inline bool is_ttbr1_addr(unsigned long addr) { /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } /* Forward declaration, a strange C thing */ struct task_struct; unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) #define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk)) /* * Prefetching support */ #define ARCH_HAS_PREFETCH static inline void prefetch(const void *ptr) { asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr)); } #define ARCH_HAS_PREFETCHW static inline void prefetchw(const void *ptr) { asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr)); } extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */ extern void __init minsigstksz_setup(void); /* * Not at the top of the file due to a direct #include cycle between * <asm/fpsimd.h> and <asm/processor.h>. Deferring this #include * ensures that contents of processor.h are visible to fpsimd.h even if * processor.h is included first. * * These prctl helpers are the only things in this file that require * fpsimd.h. The core code expects them to be in this header. */ #include <asm/fpsimd.h> /* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() #define SME_SET_VL(arg) sme_set_current_vl(arg) #define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) /* PR_PAC_{SET,GET}_ENABLED_KEYS prctl */ #define PAC_SET_ENABLED_KEYS(tsk, keys, enabled) \ ptrauth_set_enabled_keys(tsk, keys, enabled) #define PAC_GET_ENABLED_KEYS(tsk) ptrauth_get_enabled_keys(tsk) #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI /* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg); long get_tagged_addr_ctrl(struct task_struct *task); #define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg) #define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) #endif #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ |
| 454 455 457 455 457 454 454 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/kernel/return_address.c * * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> */ #include <linux/export.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/stacktrace.h> #include <asm/stack_pointer.h> struct return_address_data { unsigned int level; void *addr; }; static bool save_return_addr(void *d, unsigned long pc) { struct return_address_data *data = d; if (!data->level) { data->addr = (void *)pc; return false; } else { --data->level; return true; } } NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { struct return_address_data data; data.level = level + 2; data.addr = NULL; arch_stack_walk(save_return_addr, &data, current, NULL); if (!data.level) return data.addr; else return NULL; } EXPORT_SYMBOL_GPL(return_address); NOKPROBE_SYMBOL(return_address); |
| 132 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 | // SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork() * * Copyright (C) 2008-2009 Red Hat, Inc. * Authors: * Izik Eidus * Andrea Arcangeli * Chris Wright * Hugh Dickins */ #include <linux/errno.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/cputime.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/spinlock.h> #include <linux/xxhash.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/memory.h> #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> #include <linux/hashtable.h> #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/pagewalk.h> #include <asm/tlbflush.h> #include "internal.h" #include "mm_slot.h" #define CREATE_TRACE_POINTS #include <trace/events/ksm.h> #ifdef CONFIG_NUMA #define NUMA(x) (x) #define DO_NUMA(x) do { (x); } while (0) #else #define NUMA(x) (0) #define DO_NUMA(x) do { } while (0) #endif typedef u8 rmap_age_t; /** * DOC: Overview * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * * In order to reduce excessive scanning, KSM sorts the memory pages by their * contents into a data structure that holds pointers to the pages' locations. * * Since the contents of the pages may change at any moment, KSM cannot just * insert the pages into a normal sorted tree and expect it to find anything. * Therefore KSM uses two data structures - the stable and the unstable tree. * * The stable tree holds pointers to all the merged pages (ksm pages), sorted * by their contents. Because each such page is write-protected, searching on * this tree is fully assured to be working (except when pages are unmapped), * and therefore this tree is called the stable tree. * * The stable tree node includes information required for reverse * mapping from a KSM page to virtual addresses that map this page. * * In order to avoid large latencies of the rmap walks on KSM pages, * KSM maintains two types of nodes in the stable tree: * * * the regular nodes that keep the reverse mapping structures in a * linked list * * the "chains" that link nodes ("dups") that represent the same * write protected memory content, but each "dup" corresponds to a * different KSM page copy of that content * * Internally, the regular nodes, "dups" and "chains" are represented * using the same struct ksm_stable_node structure. * * In addition to the stable tree, KSM uses a second data structure called the * unstable tree: this tree holds pointers to pages which have been found to * be "unchanged for a period of time". The unstable tree sorts these pages * by their contents, but since they are not write-protected, KSM cannot rely * upon the unstable tree to work correctly - the unstable tree is liable to * be corrupted as its contents are modified, and so it is called unstable. * * KSM solves this problem by several techniques: * * 1) The unstable tree is flushed every time KSM completes scanning all * memory areas, and then the tree is rebuilt again from the beginning. * 2) KSM will only insert into the unstable tree, pages whose hash value * has not changed since the previous scan of all memory areas. * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the * colors of the nodes and not on their contents, assuring that even when * the tree gets "corrupted" it won't get out of balance, so scanning time * remains the same (also, searching and inserting nodes in an rbtree uses * the same algorithm, so we have no overhead when we flush and rebuild). * 4) KSM never flushes the stable tree, which means that even if it were to * take 10 attempts to find a page in the unstable tree, once it is found, * it is secured in the stable tree. (When we scan a new page, we first * compare it against the stable tree, and then against the unstable tree.) * * If the merge_across_nodes tunable is unset, then KSM maintains multiple * stable trees and multiple unstable trees: one of each for each NUMA node. */ /** * struct ksm_mm_slot - ksm information per mm that is being scanned * @slot: hash lookup from mm to mm_slot * @rmap_list: head for this mm_slot's singly-linked list of rmap_items */ struct ksm_mm_slot { struct mm_slot slot; struct ksm_rmap_item *rmap_list; }; /** * struct ksm_scan - cursor for scanning * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * @rmap_list: link to the next rmap to be scanned in the rmap_list * @seqnr: count of completed full scans (needed when removing unstable node) * * There is only the one ksm_scan instance of this cursor structure. */ struct ksm_scan { struct ksm_mm_slot *mm_slot; unsigned long address; struct ksm_rmap_item **rmap_list; unsigned long seqnr; }; /** * struct ksm_stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list * @hlist_dup: linked into the stable_node->hlist with a stable_node chain * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) * @chain_prune_time: time of the last full garbage collection * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ struct ksm_stable_node { union { struct rb_node node; /* when node of stable tree */ struct { /* when listed for migration */ struct list_head *head; struct { struct hlist_node hlist_dup; struct list_head list; }; }; }; struct hlist_head hlist; union { unsigned long kpfn; unsigned long chain_prune_time; }; /* * STABLE_NODE_CHAIN can be any negative number in * rmap_hlist_len negative range, but better not -1 to be able * to reliably detect underflows. */ #define STABLE_NODE_CHAIN -1024 int rmap_hlist_len; #ifdef CONFIG_NUMA int nid; #endif }; /** * struct ksm_rmap_item - reverse mapping item for virtual addresses * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree * @nid: NUMA node id of unstable tree in which linked (may not match page) * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node * @age: number of scan iterations since creation * @remaining_skips: how many scans to skip */ struct ksm_rmap_item { struct ksm_rmap_item *rmap_list; union { struct anon_vma *anon_vma; /* when stable */ #ifdef CONFIG_NUMA int nid; /* when node of unstable tree */ #endif }; struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ rmap_age_t age; rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ struct ksm_stable_node *head; struct hlist_node hlist; }; }; }; #define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ #define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ #define STABLE_FLAG 0x200 /* is listed from the stable tree */ /* The stable and unstable tree heads */ static struct rb_root one_stable_tree[1] = { RB_ROOT }; static struct rb_root one_unstable_tree[1] = { RB_ROOT }; static struct rb_root *root_stable_tree = one_stable_tree; static struct rb_root *root_unstable_tree = one_unstable_tree; /* Recently migrated nodes of stable tree, pending proper placement */ static LIST_HEAD(migrate_nodes); #define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev) #define MM_SLOTS_HASH_BITS 10 static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct ksm_mm_slot ksm_mm_head = { .slot.mm_node = LIST_HEAD_INIT(ksm_mm_head.slot.mm_node), }; static struct ksm_scan ksm_scan = { .mm_slot = &ksm_mm_head, }; static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; /* Default number of pages to scan per batch */ #define DEFAULT_PAGES_TO_SCAN 100 /* The number of pages scanned */ static unsigned long ksm_pages_scanned; /* The number of nodes in the stable tree */ static unsigned long ksm_pages_shared; /* The number of page slots additionally sharing those nodes */ static unsigned long ksm_pages_sharing; /* The number of nodes in the unstable tree */ static unsigned long ksm_pages_unshared; /* The number of rmap_items in use: to calculate pages_volatile */ static unsigned long ksm_rmap_items; /* The number of stable_node chains */ static unsigned long ksm_stable_node_chains; /* The number of stable_node dups linked to the stable_node chains */ static unsigned long ksm_stable_node_dups; /* Delay in pruning stale stable_node_dups in the stable_node_chains */ static unsigned int ksm_stable_node_chains_prune_millisecs = 2000; /* Maximum number of page slots sharing a stable node */ static int ksm_max_page_sharing = 256; /* Number of pages ksmd should scan in one batch */ static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; /* Checksum of an empty (zeroed) page */ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; /* Skip pages that couldn't be de-duplicated previously */ /* Default to true at least temporarily, for testing */ static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; /* Don't scan more than max pages per batch. */ static unsigned long ksm_advisor_max_pages_to_scan = 30000; /* Min CPU for scanning pages per scan */ #define KSM_ADVISOR_MIN_CPU 10 /* Max CPU for scanning pages per scan */ static unsigned int ksm_advisor_max_cpu = 70; /* Target scan time in seconds to analyze all KSM candidate pages. */ static unsigned long ksm_advisor_target_scan_time = 200; /* Exponentially weighted moving average. */ #define EWMA_WEIGHT 30 /** * struct advisor_ctx - metadata for KSM advisor * @start_scan: start time of the current scan * @scan_time: scan time of previous scan * @change: change in percent to pages_to_scan parameter * @cpu_time: cpu time consumed by the ksmd thread in the previous scan */ struct advisor_ctx { ktime_t start_scan; unsigned long scan_time; unsigned long change; unsigned long long cpu_time; }; static struct advisor_ctx advisor_ctx; /* Define different advisor's */ enum ksm_advisor_type { KSM_ADVISOR_NONE, KSM_ADVISOR_SCAN_TIME, }; static enum ksm_advisor_type ksm_advisor; #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ /* At least scan this many pages per batch. */ static unsigned long ksm_advisor_min_pages_to_scan = 500; static void set_advisor_defaults(void) { if (ksm_advisor == KSM_ADVISOR_NONE) { ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; } else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) { advisor_ctx = (const struct advisor_ctx){ 0 }; ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan; } } #endif /* CONFIG_SYSFS */ static inline void advisor_start_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) advisor_ctx.start_scan = ktime_get(); } /* * Use previous scan time if available, otherwise use current scan time as an * approximation for the previous scan time. */ static inline unsigned long prev_scan_time(struct advisor_ctx *ctx, unsigned long scan_time) { return ctx->scan_time ? ctx->scan_time : scan_time; } /* Calculate exponential weighted moving average */ static unsigned long ewma(unsigned long prev, unsigned long curr) { return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100; } /* * The scan time advisor is based on the current scan rate and the target * scan rate. * * new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time) * * To avoid perturbations it calculates a change factor of previous changes. * A new change factor is calculated for each iteration and it uses an * exponentially weighted moving average. The new pages_to_scan value is * multiplied with that change factor: * * new_pages_to_scan *= change facor * * The new_pages_to_scan value is limited by the cpu min and max values. It * calculates the cpu percent for the last scan and calculates the new * estimated cpu percent cost for the next scan. That value is capped by the * cpu min and max setting. * * In addition the new pages_to_scan value is capped by the max and min * limits. */ static void scan_time_advisor(void) { unsigned int cpu_percent; unsigned long cpu_time; unsigned long cpu_time_diff; unsigned long cpu_time_diff_ms; unsigned long pages; unsigned long per_page_cost; unsigned long factor; unsigned long change; unsigned long last_scan_time; unsigned long scan_time; /* Convert scan time to seconds */ scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan), MSEC_PER_SEC); scan_time = scan_time ? scan_time : 1; /* Calculate CPU consumption of ksmd background thread */ cpu_time = task_sched_runtime(current); cpu_time_diff = cpu_time - advisor_ctx.cpu_time; cpu_time_diff_ms = cpu_time_diff / 1000 / 1000; cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000); cpu_percent = cpu_percent ? cpu_percent : 1; last_scan_time = prev_scan_time(&advisor_ctx, scan_time); /* Calculate scan time as percentage of target scan time */ factor = ksm_advisor_target_scan_time * 100 / scan_time; factor = factor ? factor : 1; /* * Calculate scan time as percentage of last scan time and use * exponentially weighted average to smooth it */ change = scan_time * 100 / last_scan_time; change = change ? change : 1; change = ewma(advisor_ctx.change, change); /* Calculate new scan rate based on target scan rate. */ pages = ksm_thread_pages_to_scan * 100 / factor; /* Update pages_to_scan by weighted change percentage. */ pages = pages * change / 100; /* Cap new pages_to_scan value */ per_page_cost = ksm_thread_pages_to_scan / cpu_percent; per_page_cost = per_page_cost ? per_page_cost : 1; pages = min(pages, per_page_cost * ksm_advisor_max_cpu); pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU); pages = min(pages, ksm_advisor_max_pages_to_scan); /* Update advisor context */ advisor_ctx.change = change; advisor_ctx.scan_time = scan_time; advisor_ctx.cpu_time = cpu_time; ksm_thread_pages_to_scan = pages; trace_ksm_advisor(scan_time, pages, cpu_percent); } static void advisor_stop_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) scan_time_advisor(); } #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; static int ksm_nr_node_ids = 1; #else #define ksm_merge_across_nodes 1U #define ksm_nr_node_ids 1 #endif #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 #define KSM_RUN_OFFLINE 4 static unsigned long ksm_run = KSM_RUN_STOP; static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait); static DEFINE_MUTEX(ksm_thread_mutex); static DEFINE_SPINLOCK(ksm_mmlist_lock); static int __init ksm_slab_init(void) { rmap_item_cache = KMEM_CACHE(ksm_rmap_item, 0); if (!rmap_item_cache) goto out; stable_node_cache = KMEM_CACHE(ksm_stable_node, 0); if (!stable_node_cache) goto out_free1; mm_slot_cache = KMEM_CACHE(ksm_mm_slot, 0); if (!mm_slot_cache) goto out_free2; return 0; out_free2: kmem_cache_destroy(stable_node_cache); out_free1: kmem_cache_destroy(rmap_item_cache); out: return -ENOMEM; } static void __init ksm_slab_free(void) { kmem_cache_destroy(mm_slot_cache); kmem_cache_destroy(stable_node_cache); kmem_cache_destroy(rmap_item_cache); mm_slot_cache = NULL; } static __always_inline bool is_stable_node_chain(struct ksm_stable_node *chain) { return chain->rmap_hlist_len == STABLE_NODE_CHAIN; } static __always_inline bool is_stable_node_dup(struct ksm_stable_node *dup) { return dup->head == STABLE_NODE_DUP_HEAD; } static inline void stable_node_chain_add_dup(struct ksm_stable_node *dup, struct ksm_stable_node *chain) { VM_BUG_ON(is_stable_node_dup(dup)); dup->head = STABLE_NODE_DUP_HEAD; VM_BUG_ON(!is_stable_node_chain(chain)); hlist_add_head(&dup->hlist_dup, &chain->hlist); ksm_stable_node_dups++; } static inline void __stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(!is_stable_node_dup(dup)); hlist_del(&dup->hlist_dup); ksm_stable_node_dups--; } static inline void stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(is_stable_node_chain(dup)); if (is_stable_node_dup(dup)) __stable_node_dup_del(dup); else rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid)); #ifdef CONFIG_DEBUG_VM dup->head = NULL; #endif } static inline struct ksm_rmap_item *alloc_rmap_item(void) { struct ksm_rmap_item *rmap_item; rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; } static inline void free_rmap_item(struct ksm_rmap_item *rmap_item) { ksm_rmap_items--; rmap_item->mm->ksm_rmap_items--; rmap_item->mm = NULL; /* debug safety */ kmem_cache_free(rmap_item_cache, rmap_item); } static inline struct ksm_stable_node *alloc_stable_node(void) { /* * The allocation can take too long with GFP_KERNEL when memory is under * pressure, which may lead to hung task warnings. Adding __GFP_HIGH * grants access to memory reserves, helping to avoid this problem. */ return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); } static inline void free_stable_node(struct ksm_stable_node *stable_node) { VM_BUG_ON(stable_node->rmap_hlist_len && !is_stable_node_chain(stable_node)); kmem_cache_free(stable_node_cache, stable_node); } /* * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's * page tables after it has passed through ksm_exit() - which, if necessary, * takes mmap_lock briefly to serialize against them. ksm_exit() does not set * a special flag: they can just back out as soon as mm_users goes to zero. * ksm_test_exit() is used throughout to make this test for exit: in some * places for correctness, in some places just to avoid unnecessary work. */ static inline bool ksm_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { struct page *page = NULL; spinlock_t *ptl; pte_t *pte; pte_t ptent; int ret; pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) return 0; ptent = ptep_get(pte); if (pte_present(ptent)) { page = vm_normal_page(walk->vma, addr, ptent); } else if (!pte_none(ptent)) { swp_entry_t entry = pte_to_swp_entry(ptent); /* * As KSM pages remain KSM pages until freed, no need to wait * here for migration to end. */ if (is_migration_entry(entry)) page = pfn_swap_entry_to_page(entry); } /* return 1 if the page is an normal ksm page or KSM-placed zero page */ ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent); pte_unmap_unlock(pte, ptl); return ret; } static const struct mm_walk_ops break_ksm_ops = { .pmd_entry = break_ksm_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops break_ksm_lock_vma_ops = { .pmd_entry = break_ksm_pmd_entry, .walk_lock = PGWALK_WRLOCK, }; /* * We use break_ksm to break COW on a ksm page by triggering unsharing, * such that the ksm page will get replaced by an exclusive anonymous page. * * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP * mmap of /dev/mem, where we would not want to touch it. * * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma) { vm_fault_t ret = 0; const struct mm_walk_ops *ops = lock_vma ? &break_ksm_lock_vma_ops : &break_ksm_ops; do { int ksm_page; cond_resched(); ksm_page = walk_page_range_vma(vma, addr, addr + 1, ops, NULL); if (WARN_ON_ONCE(ksm_page < 0)) return ksm_page; if (!ksm_page) return 0; ret = handle_mm_fault(vma, addr, FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, NULL); } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop until we no longer find a KSM page because * handle_mm_fault() may back out if there's any difficulty e.g. if * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's * okay, that truncation will have unmapped the PageKsm for us. * * VM_FAULT_OOM: at the time of writing (late July 2009), setting * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the * current task has TIF_MEMDIE set, and will be OOM killed on return * to user; and ksmd, having no mm, would never be chosen for that. * * But if the mm is in a limited mem_cgroup, then the fault may fail * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and * even ksmd can fail in this way - though it's usually breaking ksm * just to undo a merge it made a moment before, so unlikely to oom. * * That's a pity: we might therefore have more kernel pages allocated * than we're counting as nodes in the stable tree; but ksm_do_scan * will retry to break_cow on each pass, so should recover the page * in due course. The important thing is to not let VM_MERGEABLE * be cleared while any such pages might remain in the area. */ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } static bool vma_ksm_compatible(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_HUGETLB | VM_MIXEDMAP| VM_DROPPABLE)) return false; /* just ignore the advice */ if (vma_is_dax(vma)) return false; #ifdef VM_SAO if (vma->vm_flags & VM_SAO) return false; #endif #ifdef VM_SPARC_ADI if (vma->vm_flags & VM_SPARC_ADI) return false; #endif return true; } static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; vma = vma_lookup(mm, addr); if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } static void break_cow(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; /* * It is not an accident that whenever we want to break COW * to undo, we also need to drop a reference to the anon_vma. */ put_anon_vma(rmap_item->anon_vma); mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (vma) break_ksm(vma, addr, false); mmap_read_unlock(mm); } static struct page *get_mergeable_page(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; struct page *page; mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (!vma) goto out; page = follow_page(vma, addr, FOLL_GET); if (IS_ERR_OR_NULL(page)) goto out; if (is_zone_device_page(page)) goto out_putpage; if (PageAnon(page)) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } else { out_putpage: put_page(page); out: page = NULL; } mmap_read_unlock(mm); return page; } /* * This helper is used for getting right index into array of tree roots. * When merge_across_nodes knob is set to 1, there are only two rb-trees for * stable and unstable pages from all nodes with roots in index 0. Otherwise, * every node has its own stable and unstable tree. */ static inline int get_kpfn_nid(unsigned long kpfn) { return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); } static struct ksm_stable_node *alloc_stable_node_chain(struct ksm_stable_node *dup, struct rb_root *root) { struct ksm_stable_node *chain = alloc_stable_node(); VM_BUG_ON(is_stable_node_chain(dup)); if (likely(chain)) { INIT_HLIST_HEAD(&chain->hlist); chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; /* * Put the stable node chain in the first dimension of * the stable tree and at the same time remove the old * stable node. */ rb_replace_node(&dup->node, &chain->node, root); /* * Move the old stable node to the second dimension * queued in the hlist_dup. The invariant is that all * dup stable_nodes in the chain->hlist point to pages * that are write protected and have the exact same * content. */ stable_node_chain_add_dup(dup, chain); } return chain; } static inline void free_stable_node_chain(struct ksm_stable_node *chain, struct rb_root *root) { rb_erase(&chain->node, root); free_stable_node(chain); ksm_stable_node_chains--; } static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) { struct ksm_rmap_item *rmap_item; /* check it's not STABLE_NODE_CHAIN or negative */ BUG_ON(stable_node->rmap_hlist_len < 0); hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) { ksm_pages_sharing--; trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm); } else { ksm_pages_shared--; } rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->address &= PAGE_MASK; cond_resched(); } /* * We need the second aligned pointer of the migrate_nodes * list_head to stay clear from the rb_parent_color union * (aligned and different than any node) and also different * from &migrate_nodes. This will verify that future list.h changes * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. */ BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); else stable_node_dup_del(stable_node); free_stable_node(stable_node); } enum ksm_get_folio_flags { KSM_GET_FOLIO_NOLOCK, KSM_GET_FOLIO_LOCK, KSM_GET_FOLIO_TRYLOCK }; /* * ksm_get_folio: checks if the page indicated by the stable node * is still its ksm page, despite having held no reference to it. * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, * remove the stale node from the stable tree and return NULL. * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for * ksmd to come around again before it can free the page, which may take * seconds or even minutes: much too unresponsive. So instead we use a * "keyhole reference": access to the ksm page from the stable node peeps * out through its keyhole to see if that page still holds the right key, * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * a page to put something that might look like our key in page->mapping. * is on its way to being freed; but it is an anomaly to bear in mind. */ static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node, enum ksm_get_folio_flags flags) { struct folio *folio; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ folio = pfn_folio(kpfn); if (READ_ONCE(folio->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * the same is in reuse_ksm_page() case; but if page is swapcache * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ while (!folio_try_get(folio)) { /* * Another check for page->mapping != expected_mapping would * work here too. We have chosen the !PageSwapCache test to * optimize the common case, when the page is or is about to * be freed: PageSwapCache is cleared (under spin_lock_irq) * in the ref_freeze section of __remove_mapping(); but Anon * folio->mapping reset to NULL later, in free_pages_prepare(). */ if (!folio_test_swapcache(folio)) goto stale; cpu_relax(); } if (READ_ONCE(folio->mapping) != expected_mapping) { folio_put(folio); goto stale; } if (flags == KSM_GET_FOLIO_TRYLOCK) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EBUSY); } } else if (flags == KSM_GET_FOLIO_LOCK) folio_lock(folio); if (flags != KSM_GET_FOLIO_NOLOCK) { if (READ_ONCE(folio->mapping) != expected_mapping) { folio_unlock(folio); folio_put(folio); goto stale; } } return folio; stale: /* * We come here from above when page->mapping or !PageSwapCache * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; } /* * Removing rmap_item from stable or unstable tree. * This function will clean the information from the stable/unstable tree. */ static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { struct ksm_stable_node *stable_node; struct folio *folio; stable_node = rmap_item->head; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) goto out; hlist_del(&rmap_item->hlist); folio_unlock(folio); folio_put(folio); if (!hlist_empty(&stable_node->hlist)) ksm_pages_sharing--; else ksm_pages_shared--; rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { unsigned char age; /* * Usually ksmd can and must skip the rb_erase, because * root_unstable_tree was already reset to RB_ROOT. * But be careful when an mm is exiting: do the rb_erase * if this rmap_item was inserted by this scan, rather * than left over from before. */ age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) rb_erase(&rmap_item->node, root_unstable_tree + NUMA(rmap_item->nid)); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } out: cond_resched(); /* we're called from many long loops */ } static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list) { while (*rmap_list) { struct ksm_rmap_item *rmap_item = *rmap_list; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } } /* * Though it's very tempting to unmerge rmap_items from stable tree rather * than check every pte of a given vma, the locking doesn't quite work for * that - an rmap_item is assigned to the stable tree after inserting ksm * page and upping mmap_lock. Nor does it fit with the way we skip dup'ing * rmap_items from parent to child at fork time (so as not to waste time * if exit comes before the next scan reaches it). * * Similarly, although we'd like to remove rmap_items (so updating counts * and freeing memory) when unmerging an area, it's easier to leave that * to the next pass of ksmd - consider, for example, how ksmd might be * in cmp_and_merge_page on one of the rmap_items we would be removing. */ static int unmerge_ksm_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool lock_vma) { unsigned long addr; int err = 0; for (addr = start; addr < end && !err; addr += PAGE_SIZE) { if (ksm_test_exit(vma->vm_mm)) break; if (signal_pending(current)) err = -ERESTARTSYS; else err = break_ksm(vma, addr, lock_vma); } return err; } static inline struct ksm_stable_node *folio_stable_node(struct folio *folio) { return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; } static inline struct ksm_stable_node *page_stable_node(struct page *page) { return folio_stable_node(page_folio(page)); } static inline void folio_set_stable_node(struct folio *folio, struct ksm_stable_node *stable_node) { VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio); folio->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ static int remove_stable_node(struct ksm_stable_node *stable_node) { struct folio *folio; int err; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) { /* * ksm_get_folio did remove_node_from_stable_tree itself. */ return 0; } /* * Page could be still mapped if this races with __mmput() running in * between ksm_exit() and exit_mmap(). Just refuse to let * merge_across_nodes/max_page_sharing be switched. */ err = -EBUSY; if (!folio_mapped(folio)) { /* * The stable node did not yet appear stale to ksm_get_folio(), * since that allows for an unmapped ksm folio to be recognized * right up until it is freed; but the node is safe to remove. * This folio might be in an LRU cache waiting to be freed, * or it might be in the swapcache (perhaps under writeback), * or it might have been removed from swapcache a moment ago. */ folio_set_stable_node(folio, NULL); remove_node_from_stable_tree(stable_node); err = 0; } folio_unlock(folio); folio_put(folio); return err; } static int remove_stable_node_chain(struct ksm_stable_node *stable_node, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); if (remove_stable_node(stable_node)) return true; else return false; } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); if (remove_stable_node(dup)) return true; } BUG_ON(!hlist_empty(&stable_node->hlist)); free_stable_node_chain(stable_node, root); return false; } static int remove_all_stable_nodes(void) { struct ksm_stable_node *stable_node, *next; int nid; int err = 0; for (nid = 0; nid < ksm_nr_node_ids; nid++) { while (root_stable_tree[nid].rb_node) { stable_node = rb_entry(root_stable_tree[nid].rb_node, struct ksm_stable_node, node); if (remove_stable_node_chain(stable_node, root_stable_tree + nid)) { err = -EBUSY; break; /* proceed to next nid */ } cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (remove_stable_node(stable_node)) err = -EBUSY; cond_resched(); } return err; } static int unmerge_and_remove_all_rmap_items(void) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int err = 0; spin_lock(&ksm_mmlist_lock); slot = list_entry(ksm_mm_head.slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); spin_unlock(&ksm_mmlist_lock); for (mm_slot = ksm_scan.mm_slot; mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) { VMA_ITERATOR(vmi, mm_slot->slot.mm, 0); mm = mm_slot->slot.mm; mmap_read_lock(mm); /* * Exit right away if mm is exiting to avoid lockdep issue in * the maple tree */ if (ksm_test_exit(mm)) goto mm_exiting; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, false); if (err) goto error; } mm_exiting: remove_trailing_rmap_items(&mm_slot->rmap_list); mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_test_exit(mm)) { hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmdrop(mm); } else spin_unlock(&ksm_mmlist_lock); } /* Clean up stable nodes, but don't worry if some are still busy */ remove_all_stable_nodes(); ksm_scan.seqnr = 0; return 0; error: mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = &ksm_mm_head; spin_unlock(&ksm_mmlist_lock); return err; } #endif /* CONFIG_SYSFS */ static u32 calc_checksum(struct page *page) { u32 checksum; void *addr = kmap_local_page(page); checksum = xxhash(addr, PAGE_SIZE, 0); kunmap_local(addr); return checksum; } static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0); int swapped; int err = -EFAULT; struct mmu_notifier_range range; bool anon_exclusive; pte_t entry; if (WARN_ON_ONCE(folio_test_large(folio))) return err; pvmw.address = page_address_in_vma(&folio->page, vma); if (pvmw.address == -EFAULT) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, pvmw.address + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); if (!page_vma_mapped_walk(&pvmw)) goto out_mn; if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; anon_exclusive = PageAnonExclusive(&folio->page); entry = ptep_get(pvmw.pte); if (pte_write(entry) || pte_dirty(entry) || anon_exclusive || mm_tlb_flush_pending(mm)) { swapped = folio_test_swapcache(folio); flush_cache_page(vma, pvmw.address, folio_pfn(folio)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make * with the pagecount against the mapcount is racy and * O_DIRECT can happen right after the check. * So we clear the pte and flush the tlb before the check * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. * * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * * See Documentation/mm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, &folio->page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } if (pte_dirty(entry)) folio_mark_dirty(folio); entry = pte_mkclean(entry); if (pte_write(entry)) entry = pte_wrprotect(entry); set_pte_at(mm, pvmw.address, pvmw.pte, entry); } *orig_pte = entry; err = 0; out_unlock: page_vma_mapped_walk_done(&pvmw); out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /** * replace_page - replace page in vma by new ksm page * @vma: vma that holds the pte pointing to page * @page: the page we are replacing by kpage * @kpage: the ksm page we replace page by * @orig_pte: the original value of the pte * * Returns 0 on success, -EFAULT on failure. */ static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; struct folio *folio; pmd_t *pmd; pmd_t pmde; pte_t *ptep; pte_t newpte; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; struct mmu_notifier_range range; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) goto out; pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = pmdp_get_lockless(pmd); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!ptep) goto out_mn; if (!pte_same(ptep_get(ptep), orig_pte)) { pte_unmap_unlock(ptep, ptl); goto out_mn; } VM_BUG_ON_PAGE(PageAnonExclusive(page), page); VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage), kfolio); /* * No need to check ksm_use_zero_pages here: we can only have a * zero_page here if ksm_use_zero_pages was enabled already. */ if (!is_zero_pfn(page_to_pfn(kpage))) { folio_get(kfolio); folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { /* * Use pte_mkdirty to mark the zero page mapped by KSM, and then * we can easily track all KSM-placed zero pages by checking if * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we * will get wrong values in /proc, and a BUG message in dmesg * when tearing down the mm. */ dec_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep))); /* * No need to notify as we are replacing a read only page with another * read only page with the same content. * * See Documentation/mm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at(mm, addr, ptep, newpte); folio = page_folio(page); folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio)) folio_free_swap(folio); folio_put(folio); pte_unmap_unlock(ptep, ptl); err = 0; out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page * @page: the PageAnon page that we want to replace with kpage * @kpage: the PageKsm page that we want to map instead of page, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; if (!PageAnon(page)) goto out; /* * We need the page lock to read a stable PageSwapCache in * write_protect_page(). We use trylock_page() instead of * lock_page() because we don't want to wait here - we * prefer to continue scanning and merging different pages, * then come back to this page when it is unlocked. */ if (!trylock_page(page)) goto out; if (PageTransCompound(page)) { if (split_huge_page(page)) goto out_unlock; } /* * If this anonymous page is mapped only here, its pte may need * to be write-protected. If it's mapped elsewhere, all of its * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ if (write_protect_page(vma, page_folio(page), &orig_pte) == 0) { if (!kpage) { /* * While we hold page lock, upgrade page from * PageAnon+anon_vma to PageKsm+NULL stable_node: * stable_tree_insert() will update stable_node. */ folio_set_stable_node(page_folio(page), NULL); mark_page_accessed(page); /* * Page reclaim just frees a clean page with no dirty * ptes: make sure that the ksm page would be swapped. */ if (!PageDirty(page)) SetPageDirty(page); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); } out_unlock: unlock_page(page); out: return err; } /* * This function returns 0 if the pages were merged or if they are * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise. */ static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item, struct page *page) { struct mm_struct *mm = rmap_item->mm; int err = -EFAULT; /* * Same checksum as an empty page. We attempt to merge it with the * appropriate zero page if the user enabled this via sysfs. */ if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) { struct vm_area_struct *vma; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (vma) { err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); trace_ksm_merge_one_page( page_to_pfn(ZERO_PAGE(rmap_item->address)), rmap_item, mm, err); } else { /* * If the vma is out of date, we do not need to * continue. */ err = 0; } mmap_read_unlock(mm); } return err; } /* * try_to_merge_with_ksm_page - like try_to_merge_two_pages, * but no new kernel page is allocated: kpage must already be a ksm page. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), rmap_item, mm, err); return err; } /* * try_to_merge_two_pages - take two identical pages and prepare them * to be merged into one page. * * This function returns the kpage if we successfully merged two identical * pages into one ksm page, NULL otherwise. * * Note that this function upgrades page to ksm page: if one of the pages * is already a ksm page, try_to_merge_with_ksm_page should be used. */ static struct page *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) { err = try_to_merge_with_ksm_page(tree_rmap_item, tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it. */ if (err) break_cow(rmap_item); } return err ? NULL : page; } static __always_inline bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset) { VM_BUG_ON(stable_node->rmap_hlist_len < 0); /* * Check that at least one mapping still exists, otherwise * there's no much point to merge and share with this * stable_node, as the underlying tree_page of the other * sharer is going to be freed soon. */ return stable_node->rmap_hlist_len && stable_node->rmap_hlist_len + offset < ksm_max_page_sharing; } static __always_inline bool is_page_sharing_candidate(struct ksm_stable_node *stable_node) { return __is_page_sharing_candidate(stable_node, 0); } static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node; struct hlist_node *hlist_safe; struct folio *folio, *tree_folio = NULL; int found_rmap_hlist_len; if (!prune_stale_stable_nodes || time_before(jiffies, stable_node->chain_prune_time + msecs_to_jiffies( ksm_stable_node_chains_prune_millisecs))) prune_stale_stable_nodes = false; else stable_node->chain_prune_time = jiffies; hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { cond_resched(); /* * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * * ksm_get_folio can drop the nodes from the * stable_node->hlist if they point to freed pages * (that's why we do a _safe walk). The "dup" * stable_node parameter itself will be freed from * under us if it returns NULL. */ folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK); if (!folio) continue; /* Pick the best candidate if possible. */ if (!found || (is_page_sharing_candidate(dup) && (!is_page_sharing_candidate(found) || dup->rmap_hlist_len > found_rmap_hlist_len))) { if (found) folio_put(tree_folio); found = dup; found_rmap_hlist_len = found->rmap_hlist_len; tree_folio = folio; /* skip put_page for found candidate */ if (!prune_stale_stable_nodes && is_page_sharing_candidate(found)) break; continue; } folio_put(folio); } if (found) { if (hlist_is_singular_node(&found->hlist_dup, &stable_node->hlist)) { /* * If there's not just one entry it would * corrupt memory, better BUG_ON. In KSM * context with no lock held it's not even * fatal. */ BUG_ON(stable_node->hlist.first->next); /* * There's just one entry and it is below the * deduplication limit so drop the chain. */ rb_replace_node(&stable_node->node, &found->node, root); free_stable_node(stable_node); ksm_stable_node_chains--; ksm_stable_node_dups--; /* * NOTE: the caller depends on the stable_node * to be equal to stable_node_dup if the chain * was collapsed. */ *_stable_node = found; /* * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time. */ stable_node = NULL; } else if (stable_node->hlist.first != &found->hlist_dup && __is_page_sharing_candidate(found, 1)) { /* * If the found stable_node dup can accept one * more future merge (in addition to the one * that is underway) and is not at the head of * the chain, put it there so next search will * be quicker in the !prune_stale_stable_nodes * case. * * NOTE: it would be inaccurate to use nr > 1 * instead of checking the hlist.first pointer * directly, because in the * prune_stale_stable_nodes case "nr" isn't * the position of the found dup in the chain, * but the total number of dups in the chain. */ hlist_del(&found->hlist_dup); hlist_add_head(&found->hlist_dup, &stable_node->hlist); } } else { /* Its hlist must be empty if no one found. */ free_stable_node_chain(stable_node, root); } *_stable_node_dup = found; return tree_folio; } /* * Like for ksm_get_folio, this function can free the *_stable_node and * *_stable_node_dup if the returned tree_page is NULL. * * It can also free and overwrite *_stable_node with the found * stable_node_dup if the chain is collapsed (in which case * *_stable_node will be equal to *_stable_node_dup like if the chain * never existed). It's up to the caller to verify tree_page is not * NULL before dereferencing *_stable_node or *_stable_node_dup. * * *_stable_node_dup is really a second output parameter of this * function and will be overwritten in all cases, the caller doesn't * need to initialize it. */ static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *stable_node = *_stable_node; if (!is_stable_node_chain(stable_node)) { *_stable_node_dup = stable_node; return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); } return stable_node_dup(_stable_node_dup, _stable_node, root, prune_stale_stable_nodes); } static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, true); } static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, false); } /* * stable_tree_search - search for page inside the stable tree * * This function checks if there is a page inside the stable tree * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, * NULL otherwise. */ static struct page *stable_tree_search(struct page *page) { int nid; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; struct ksm_stable_node *page_node; struct folio *folio; folio = page_folio(page); page_node = folio_stable_node(folio); if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ folio_get(folio); return &folio->page; } nid = get_kpfn_nid(folio_pfn(folio)); root = root_stable_tree + nid; again: new = &root->rb_node; parent = NULL; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain_prune(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); /* * If the mapcount of our migrated KSM folio is * at most 1, we can merge it with another * KSM folio where we know that we have space * for one more mapping without exceeding the * ksm_max_page_sharing limit: see * chain_prune(). This way, we can avoid adding * this stable node to the chain. */ if (folio_mapcount(folio) > 1) goto chain_append; } if (!is_page_sharing_candidate(stable_node_dup)) { /* * If the stable_node is a chain and * we got a payload match in memcmp * but we cannot merge the scanned * page in any of the existing * stable_node dups because they're * all full, we need to wait the * scanned page to find itself a match * in the unstable tree to create a * brand new KSM page to add later to * the dups of this stable_node. */ return NULL; } /* * Lock and unlock the stable_node's page (which * might already have been migrated) so that page * migration is sure to notice its raised count. * It would be more elegant to return stable_node * than kpage, but that involves more changes. */ tree_folio = ksm_get_folio(stable_node_dup, KSM_GET_FOLIO_TRYLOCK); if (PTR_ERR(tree_folio) == -EBUSY) return ERR_PTR(-EBUSY); if (unlikely(!tree_folio)) /* * The tree may have been rebalanced, * so re-evaluate parent and new. */ goto again; folio_unlock(tree_folio); if (get_kpfn_nid(stable_node_dup->kpfn) != NUMA(stable_node_dup->nid)) { folio_put(tree_folio); goto replace; } return &tree_folio->page; } } if (!page_node) return NULL; list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_link_node(&page_node->node, parent, new); rb_insert_color(&page_node->node, root); out: if (is_page_sharing_candidate(page_node)) { folio_get(folio); return &folio->page; } else return NULL; replace: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_chain(stable_node_dup)); VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* there is no chain */ if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_replace_node(&stable_node_dup->node, &page_node->node, root); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { rb_erase(&stable_node_dup->node, root); folio = NULL; } } else { VM_BUG_ON(!is_stable_node_chain(stable_node)); __stable_node_dup_del(stable_node_dup); if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { folio = NULL; } } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); return &folio->page; chain_append: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* chain is missing so create it */ stable_node = alloc_stable_node_chain(stable_node_dup, root); if (!stable_node) return NULL; } /* * Add this stable_node dup that was * migrated to the stable_node chain * of the current nid for this page * content. */ VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); goto out; } /* * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, * NULL otherwise. */ static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio) { int nid; unsigned long kpfn; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; bool need_chain = false; kpfn = folio_pfn(kfolio); nid = get_kpfn_nid(kpfn); root = root_stable_tree + nid; again: parent = NULL; new = &root->rb_node; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(&kfolio->page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { need_chain = true; break; } } stable_node_dup = alloc_stable_node(); if (!stable_node_dup) return NULL; INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { rb_link_node(&stable_node_dup->node, parent, new); rb_insert_color(&stable_node_dup->node, root); } else { if (!is_stable_node_chain(stable_node)) { struct ksm_stable_node *orig = stable_node; /* chain is missing so create it */ stable_node = alloc_stable_node_chain(orig, root); if (!stable_node) { free_stable_node(stable_node_dup); return NULL; } } stable_node_chain_add_dup(stable_node_dup, stable_node); } folio_set_stable_node(kfolio, stable_node_dup); return stable_node_dup; } /* * unstable_tree_search_insert - search for identical page, * else insert rmap_item into the unstable tree. * * This function searches for a page in the unstable tree identical to the * page currently being scanned; and if no identical page is found in the * tree, we insert rmap_item as a new object into the unstable tree. * * This function returns pointer to rmap_item found to be identical * to the currently scanned page, NULL otherwise. * * This function does both searching and inserting, because they share * the same walking algorithm in an rbtree. */ static struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item, struct page *page, struct page **tree_pagep) { struct rb_node **new; struct rb_root *root; struct rb_node *parent = NULL; int nid; nid = get_kpfn_nid(page_to_pfn(page)); root = root_unstable_tree + nid; new = &root->rb_node; while (*new) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page; int ret; cond_resched(); tree_rmap_item = rb_entry(*new, struct ksm_rmap_item, node); tree_page = get_mergeable_page(tree_rmap_item); if (!tree_page) return NULL; /* * Don't substitute a ksm page for a forked page. */ if (page == tree_page) { put_page(tree_page); return NULL; } ret = memcmp_pages(page, tree_page); parent = *new; if (ret < 0) { put_page(tree_page); new = &parent->rb_left; } else if (ret > 0) { put_page(tree_page); new = &parent->rb_right; } else if (!ksm_merge_across_nodes && page_to_nid(tree_page) != nid) { /* * If tree_page has been migrated to another NUMA node, * it will be flushed out and put in the right unstable * tree next time: only merge with it when across_nodes. */ put_page(tree_page); return NULL; } else { *tree_pagep = tree_page; return tree_rmap_item; } } rmap_item->address |= UNSTABLE_FLAG; rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); DO_NUMA(rmap_item->nid = nid); rb_link_node(&rmap_item->node, parent, new); rb_insert_color(&rmap_item->node, root); ksm_pages_unshared++; return NULL; } /* * stable_tree_append - add another rmap_item to the linked list of * rmap_items hanging off a given node of the stable tree, all sharing * the same ksm page. */ static void stable_tree_append(struct ksm_rmap_item *rmap_item, struct ksm_stable_node *stable_node, bool max_page_sharing_bypass) { /* * rmap won't find this mapping if we don't insert the * rmap_item in the right stable_node * duplicate. page_migration could break later if rmap breaks, * so we can as well crash here. We really need to check for * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check * for other negative values as an underflow if detected here * for the first time (and not when decreasing rmap_hlist_len) * would be sign of memory corruption in the stable_node. */ BUG_ON(stable_node->rmap_hlist_len < 0); stable_node->rmap_hlist_len++; if (!max_page_sharing_bypass) /* possibly non fatal but unexpected overflow, only warn */ WARN_ON_ONCE(stable_node->rmap_hlist_len > ksm_max_page_sharing); rmap_item->head = stable_node; rmap_item->address |= STABLE_FLAG; hlist_add_head(&rmap_item->hlist, &stable_node->hlist); if (rmap_item->hlist.next) ksm_pages_sharing++; else ksm_pages_shared++; rmap_item->mm->ksm_merging_pages++; } /* * cmp_and_merge_page - first see if page can be merged into the stable tree; * if not, compare checksum to previous and if it's the same, see if page can * be inserted into the unstable tree, or merged with a page already there and * both transferred to the stable tree. * * @page: the page that we are searching identical page to. * @rmap_item: the reverse mapping into the virtual address of this page */ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct ksm_stable_node *stable_node; struct page *kpage; unsigned int checksum; int err; bool max_page_sharing_bypass = false; stable_node = page_stable_node(page); if (stable_node) { if (stable_node->head != &migrate_nodes && get_kpfn_nid(READ_ONCE(stable_node->kpfn)) != NUMA(stable_node->nid)) { stable_node_dup_del(stable_node); stable_node->head = &migrate_nodes; list_add(&stable_node->list, stable_node->head); } if (stable_node->head != &migrate_nodes && rmap_item->head == stable_node) return; /* * If it's a KSM fork, allow it to go over the sharing limit * without warnings. */ if (!is_page_sharing_candidate(stable_node)) max_page_sharing_bypass = true; } else { remove_rmap_item_from_tree(rmap_item); /* * If the hash value of the page has changed from the last time * we calculated it, this page is changing frequently: therefore we * don't want to insert it in the unstable tree, and we don't want * to waste our time searching for something identical to it there. */ checksum = calc_checksum(page); if (rmap_item->oldchecksum != checksum) { rmap_item->oldchecksum = checksum; return; } if (!try_to_merge_with_zero_page(rmap_item, page)) return; } /* We first start with searching the page inside the stable tree */ kpage = stable_tree_search(page); if (kpage == page && rmap_item->head == stable_node) { put_page(kpage); return; } remove_rmap_item_from_tree(rmap_item); if (kpage) { if (PTR_ERR(kpage) == -EBUSY) return; err = try_to_merge_with_ksm_page(rmap_item, page, kpage); if (!err) { /* * The page was successfully merged: * add its rmap_item to the stable tree. */ lock_page(kpage); stable_tree_append(rmap_item, page_stable_node(kpage), max_page_sharing_bypass); unlock_page(kpage); } put_page(kpage); return; } tree_rmap_item = unstable_tree_search_insert(rmap_item, page, &tree_page); if (tree_rmap_item) { bool split; kpage = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); /* * If both pages we tried to merge belong to the same compound * page, then we actually ended up increasing the reference * count of the same compound page twice, and split_huge_page * failed. * Here we set a flag if that happened, and we use it later to * try split_huge_page again. Since we call put_page right * afterwards, the reference count will be correct and * split_huge_page should succeed. */ split = PageTransCompound(page) && compound_head(page) == compound_head(tree_page); put_page(tree_page); if (kpage) { /* * The pages were successfully merged: insert new * node in the stable tree and add both rmap_items. */ lock_page(kpage); stable_node = stable_tree_insert(page_folio(kpage)); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); stable_tree_append(rmap_item, stable_node, false); } unlock_page(kpage); /* * If we fail to insert the page into the stable tree, * we will have 2 virtual addresses that are pointing * to a ksm page left outside the stable tree, * in which case we need to break_cow on both. */ if (!stable_node) { break_cow(tree_rmap_item); break_cow(rmap_item); } } else if (split) { /* * We are here if we tried to merge two pages and * failed because they both belonged to the same * compound page. We will split the page now, but no * merging will take place. * We do not want to add the cost of a full lock; if * the page is locked, it is better to skip it and * perhaps try again later. */ if (!trylock_page(page)) return; split_huge_page(page); unlock_page(page); } } } static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, struct ksm_rmap_item **rmap_list, unsigned long addr) { struct ksm_rmap_item *rmap_item; while (*rmap_list) { rmap_item = *rmap_list; if ((rmap_item->address & PAGE_MASK) == addr) return rmap_item; if (rmap_item->address > addr) break; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } rmap_item = alloc_rmap_item(); if (rmap_item) { /* It has already been zeroed */ rmap_item->mm = mm_slot->slot.mm; rmap_item->mm->ksm_rmap_items++; rmap_item->address = addr; rmap_item->rmap_list = *rmap_list; *rmap_list = rmap_item; } return rmap_item; } /* * Calculate skip age for the ksm page age. The age determines how often * de-duplicating has already been tried unsuccessfully. If the age is * smaller, the scanning of this page is skipped for less scans. * * @age: rmap_item age of page */ static unsigned int skip_age(rmap_age_t age) { if (age <= 3) return 1; if (age <= 5) return 2; if (age <= 8) return 4; return 8; } /* * Determines if a page should be skipped for the current scan. * * @page: page to check * @rmap_item: associated rmap_item of page */ static bool should_skip_rmap_item(struct page *page, struct ksm_rmap_item *rmap_item) { rmap_age_t age; if (!ksm_smart_scan) return false; /* * Never skip pages that are already KSM; pages cmp_and_merge_page() * will essentially ignore them, but we still have to process them * properly. */ if (PageKsm(page)) return false; age = rmap_item->age; if (age != U8_MAX) rmap_item->age++; /* * Smaller ages are not skipped, they need to get a chance to go * through the different phases of the KSM merging. */ if (age < 3) return false; /* * Are we still allowed to skip? If not, then don't skip it * and determine how much more often we are allowed to skip next. */ if (!rmap_item->remaining_skips) { rmap_item->remaining_skips = skip_age(age); return false; } /* Skip this page */ ksm_pages_skipped++; rmap_item->remaining_skips--; remove_rmap_item_from_tree(rmap_item); return true; } static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct vm_area_struct *vma; struct ksm_rmap_item *rmap_item; struct vma_iterator vmi; int nid; if (list_empty(&ksm_mm_head.slot.mm_node)) return NULL; mm_slot = ksm_scan.mm_slot; if (mm_slot == &ksm_mm_head) { advisor_start_scan(); trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); /* * A number of pages can hang around indefinitely in per-cpu * LRU cache, raised page count preventing write_protect_page * from merging them. Though it doesn't really matter much, * it is puzzling to see some stuck in pages_volatile until * other activity jostles them out, and they also prevented * LTP's KSM test from succeeding deterministically; so drain * them here (here rather than on entry to ksm_do_scan(), * so we don't IPI too often when pages_to_scan is set low). */ lru_add_drain_all(); /* * Whereas stale stable_nodes on the stable_tree itself * get pruned in the regular course of stable_tree_search(), * those moved out to the migrate_nodes list can accumulate: * so prune them once before each full scan. */ if (!ksm_merge_across_nodes) { struct ksm_stable_node *stable_node, *next; struct folio *folio; list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); if (folio) folio_put(folio); cond_resched(); } } for (nid = 0; nid < ksm_nr_node_ids; nid++) root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); ksm_scan.mm_slot = mm_slot; spin_unlock(&ksm_mmlist_lock); /* * Although we tested list_empty() above, a racing __ksm_exit * of the last mm on the list may have removed it since then. */ if (mm_slot == &ksm_mm_head) return NULL; next_mm: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } slot = &mm_slot->slot; mm = slot->mm; vma_iter_init(&vmi, mm, ksm_scan.address); mmap_read_lock(mm); if (ksm_test_exit(mm)) goto no_vmas; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE)) continue; if (ksm_scan.address < vma->vm_start) ksm_scan.address = vma->vm_start; if (!vma->anon_vma) ksm_scan.address = vma->vm_end; while (ksm_scan.address < vma->vm_end) { if (ksm_test_exit(mm)) break; *page = follow_page(vma, ksm_scan.address, FOLL_GET); if (IS_ERR_OR_NULL(*page)) { ksm_scan.address += PAGE_SIZE; cond_resched(); continue; } if (is_zone_device_page(*page)) goto next_page; if (PageAnon(*page)) { flush_anon_page(vma, *page, ksm_scan.address); flush_dcache_page(*page); rmap_item = get_next_rmap_item(mm_slot, ksm_scan.rmap_list, ksm_scan.address); if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; if (should_skip_rmap_item(*page, rmap_item)) goto next_page; ksm_scan.address += PAGE_SIZE; } else put_page(*page); mmap_read_unlock(mm); return rmap_item; } next_page: put_page(*page); ksm_scan.address += PAGE_SIZE; cond_resched(); } } if (ksm_test_exit(mm)) { no_vmas: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } /* * Nuke all the rmap_items that are above this current rmap: * because there were no VM_MERGEABLE vmas with such addresses. */ remove_trailing_rmap_items(ksm_scan.rmap_list); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_scan.address == 0) { /* * We've completed a full scan of all vmas, holding mmap_lock * throughout, and found no VM_MERGEABLE: so do the same as * __ksm_exit does to remove this mm from all our lists now. * This applies either when cleaning up after __ksm_exit * (but beware: we can reach here even before __ksm_exit), * or when all VM_MERGEABLE areas have been unmapped (and * mmap_lock then protects against race with MADV_MERGEABLE). */ hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmap_read_unlock(mm); mmdrop(mm); } else { mmap_read_unlock(mm); /* * mmap_read_unlock(mm) first because after * spin_unlock(&ksm_mmlist_lock) run, the "mm" may * already have been freed under us by __ksm_exit() * because the "mm_slot" is still hashed and * ksm_scan.mm_slot doesn't point to it anymore. */ spin_unlock(&ksm_mmlist_lock); } /* Repeat until we've completed scanning the whole list */ mm_slot = ksm_scan.mm_slot; if (mm_slot != &ksm_mm_head) goto next_mm; advisor_stop_scan(); trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; } /** * ksm_do_scan - the ksm scanner main worker function. * @scan_npages: number of pages we want to scan before we return. */ static void ksm_do_scan(unsigned int scan_npages) { struct ksm_rmap_item *rmap_item; struct page *page; while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; cmp_and_merge_page(page, rmap_item); put_page(page); ksm_pages_scanned++; } } static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); } static int ksm_scan_thread(void *nothing) { unsigned int sleep_ms; set_freezable(); set_user_nice(current, 5); while (!kthread_should_stop()) { mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksmd_should_run()) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); if (ksmd_should_run()) { sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); wait_event_freezable_timeout(ksm_iter_wait, sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), msecs_to_jiffies(sleep_ms)); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); } } return 0; } static void __ksm_add_vma(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; if (vm_flags & VM_MERGEABLE) return; if (vma_ksm_compatible(vma)) vm_flags_set(vma, VM_MERGEABLE); } static int __ksm_del_vma(struct vm_area_struct *vma) { int err; if (!(vma->vm_flags & VM_MERGEABLE)) return 0; if (vma->anon_vma) { err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true); if (err) return err; } vm_flags_clear(vma, VM_MERGEABLE); return 0; } /** * ksm_add_vma - Mark vma as mergeable if compatible * * @vma: Pointer to vma */ void ksm_add_vma(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) __ksm_add_vma(vma); } static void ksm_add_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) __ksm_add_vma(vma); } static int ksm_del_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; int err; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) { err = __ksm_del_vma(vma); if (err) return err; } return 0; } /** * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all * compatible VMA's * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_enable_merge_any(struct mm_struct *mm) { int err; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } set_bit(MMF_VM_MERGE_ANY, &mm->flags); ksm_add_vmas(mm); return 0; } /** * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm, * previously enabled via ksm_enable_merge_any(). * * Disabling merging implies unmerging any merged pages, like setting * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and * merging on all compatible VMA's remains enabled. * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_disable_merge_any(struct mm_struct *mm) { int err; if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; err = ksm_del_vmas(mm); if (err) { ksm_add_vmas(mm); return err; } clear_bit(MMF_VM_MERGE_ANY, &mm->flags); return 0; } int ksm_disable(struct mm_struct *mm) { mmap_assert_write_locked(mm); if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) return 0; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return ksm_disable_merge_any(mm); return ksm_del_vmas(mm); } int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; int err; switch (advice) { case MADV_MERGEABLE: if (vma->vm_flags & VM_MERGEABLE) return 0; if (!vma_ksm_compatible(vma)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } *vm_flags |= VM_MERGEABLE; break; case MADV_UNMERGEABLE: if (!(*vm_flags & VM_MERGEABLE)) return 0; /* just ignore the advice */ if (vma->anon_vma) { err = unmerge_ksm_pages(vma, start, end, true); if (err) return err; } *vm_flags &= ~VM_MERGEABLE; break; } return 0; } EXPORT_SYMBOL_GPL(ksm_madvise); int __ksm_enter(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int needs_wakeup; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return -ENOMEM; slot = &mm_slot->slot; /* Check ksm_run too? Would need tighter locking */ needs_wakeup = list_empty(&ksm_mm_head.slot.mm_node); spin_lock(&ksm_mmlist_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * When KSM_RUN_MERGE (or KSM_RUN_STOP), * insert just behind the scanning cursor, to let the area settle * down a little; when fork is followed by immediate exec, we don't * want ksmd to waste time setting up and tearing down an rmap_list. * * But when KSM_RUN_UNMERGE, it's important to insert ahead of its * scanning cursor, otherwise KSM pages in newly forked mms will be * missed: then we might as well insert at the end of the list. */ if (ksm_run & KSM_RUN_UNMERGE) list_add_tail(&slot->mm_node, &ksm_mm_head.slot.mm_node); else list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); mmgrab(mm); if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); trace_ksm_enter(mm); return 0; } void __ksm_exit(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int easy_to_free = 0; /* * This process is exiting: if it's straightforward (as is the * case when ksmd was never running), free mm_slot immediately. * But if it's at the cursor or has rmap_items linked to it, use * mmap_lock to synchronize with any break_cows before pagetables * are freed, and leave the mm_slot on the list for ksmd to free. * Beware: ksm may already have noticed it exiting and freed the slot. */ spin_lock(&ksm_mmlist_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (mm_slot && ksm_scan.mm_slot != mm_slot) { if (!mm_slot->rmap_list) { hash_del(&slot->hash); list_del(&slot->mm_node); easy_to_free = 1; } else { list_move(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); } } spin_unlock(&ksm_mmlist_lock); if (easy_to_free) { mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); clear_bit(MMF_VM_MERGEABLE, &mm->flags); mmdrop(mm); } else if (mm_slot) { mmap_write_lock(mm); mmap_write_unlock(mm); } trace_ksm_exit(mm); } struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { struct page *page = folio_page(folio, 0); struct anon_vma *anon_vma = folio_anon_vma(folio); struct folio *new_folio; if (folio_test_large(folio)) return folio; if (folio_test_ksm(folio)) { if (folio_stable_node(folio) && !(ksm_run & KSM_RUN_UNMERGE)) return folio; /* no need to copy it */ } else if (!anon_vma) { return folio; /* no need to copy it */ } else if (folio->index == linear_page_index(vma, addr) && anon_vma->root == vma->anon_vma->root) { return folio; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); if (!folio_test_uptodate(folio)) return folio; /* let do_swap_page report the error */ new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false); if (new_folio && mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { folio_put(new_folio); new_folio = NULL; } if (new_folio) { if (copy_mc_user_highpage(folio_page(new_folio, 0), page, addr, vma)) { folio_put(new_folio); return ERR_PTR(-EHWPOISON); } folio_set_dirty(new_folio); __folio_mark_uptodate(new_folio); __folio_set_locked(new_folio); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } return new_folio; } void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; int search_new_forks = 0; VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio); /* * Rely on the page lock to protect against concurrent modifications * to that page's node of the stable tree. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); stable_node = folio_stable_node(folio); if (!stable_node) return; again: hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; cond_resched(); if (!anon_vma_trylock_read(anon_vma)) { if (rwc->try_lock) { rwc->contended = true; return; } anon_vma_lock_read(anon_vma); } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { unsigned long addr; cond_resched(); vma = vmac->vma; /* Ignore the stable/unstable/sqnr flags */ addr = rmap_item->address & PAGE_MASK; if (addr < vma->vm_start || addr >= vma->vm_end) continue; /* * Initially we examine only the vma which covers this * rmap_item; but later, if there is still work to do, * we examine covering vmas in other mms: in case they * were forked from the original since ksmd passed. */ if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) { anon_vma_unlock_read(anon_vma); return; } if (rwc->done && rwc->done(folio)) { anon_vma_unlock_read(anon_vma); return; } } anon_vma_unlock_read(anon_vma); } if (!search_new_forks++) goto again; } #ifdef CONFIG_MEMORY_FAILURE /* * Collect processes when the error hit an ksm page. */ void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; struct vm_area_struct *vma; struct task_struct *tsk; stable_node = folio_stable_node(folio); if (!stable_node) return; hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *av = rmap_item->anon_vma; anon_vma_lock_read(av); rcu_read_lock(); for_each_process(tsk) { struct anon_vma_chain *vmac; unsigned long addr; struct task_struct *t = task_early_kill(tsk, force_early); if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0, ULONG_MAX) { vma = vmac->vma; if (vma->vm_mm == t->mm) { addr = rmap_item->address & PAGE_MASK; add_to_kill_ksm(t, page, vma, to_kill, addr); } } } rcu_read_unlock(); anon_vma_unlock_read(av); } } #endif #ifdef CONFIG_MIGRATION void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { struct ksm_stable_node *stable_node; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); stable_node = folio_stable_node(folio); if (stable_node) { VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); stable_node->kpfn = folio_pfn(newfolio); /* * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible * to ksm_get_folio() before it can see that folio->mapping * has gone stale (or that folio_test_swapcache has been cleared). */ smp_wmb(); folio_set_stable_node(folio, NULL); } } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) { /* * Don't ksm_get_folio, page has already gone: * which is why we keep kpfn instead of page* */ remove_node_from_stable_tree(stable_node); return true; } return false; } static bool stable_node_chain_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); return stable_node_dup_remove_range(stable_node, start_pfn, end_pfn); } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); stable_node_dup_remove_range(dup, start_pfn, end_pfn); } if (hlist_empty(&stable_node->hlist)) { free_stable_node_chain(stable_node, root); return true; /* notify caller that tree was rebalanced */ } else return false; } static void ksm_check_stable_tree(unsigned long start_pfn, unsigned long end_pfn) { struct ksm_stable_node *stable_node, *next; struct rb_node *node; int nid; for (nid = 0; nid < ksm_nr_node_ids; nid++) { node = rb_first(root_stable_tree + nid); while (node) { stable_node = rb_entry(node, struct ksm_stable_node, node); if (stable_node_chain_remove_range(stable_node, start_pfn, end_pfn, root_stable_tree + nid)) node = rb_first(root_stable_tree + nid); else node = rb_next(node); cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) remove_node_from_stable_tree(stable_node); cond_resched(); } } static int ksm_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; switch (action) { case MEM_GOING_OFFLINE: /* * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() * and remove_all_stable_nodes() while memory is going offline: * it is unsafe for them to touch the stable tree at this time. * But unmerge_ksm_pages(), rmap lookups and other entry points * which do not need the ksm_thread_mutex are all safe. */ mutex_lock(&ksm_thread_mutex); ksm_run |= KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); break; case MEM_OFFLINE: /* * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct * pages which have been offlined: prune those from the tree, * otherwise ksm_get_folio() might later try to access a * non-existent struct page. */ ksm_check_stable_tree(mn->start_pfn, mn->start_pfn + mn->nr_pages); fallthrough; case MEM_CANCEL_OFFLINE: mutex_lock(&ksm_thread_mutex); ksm_run &= ~KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); smp_mb(); /* wake_up_bit advises this */ wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); break; } return NOTIFY_OK; } #else static void wait_while_offlining(void) { } #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *mm) { return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSFS /* * This all compiles without CONFIG_SYSFS, but is a waste of space. */ #define KSM_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define KSM_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_sleep_millisecs); } static ssize_t sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; ksm_thread_sleep_millisecs = msecs; wake_up_interruptible(&ksm_iter_wait); return count; } KSM_ATTR(sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int nr_pages; int err; if (ksm_advisor != KSM_ADVISOR_NONE) return -EINVAL; err = kstrtouint(buf, 10, &nr_pages); if (err) return -EINVAL; ksm_thread_pages_to_scan = nr_pages; return count; } KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int flags; int err; err = kstrtouint(buf, 10, &flags); if (err) return -EINVAL; if (flags > KSM_RUN_UNMERGE) return -EINVAL; /* * KSM_RUN_MERGE sets ksmd running, and 0 stops it running. * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items, * breaking COW to free the pages_shared (but leaves mm_slots * on the list for when ksmd may be set running again). */ mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { set_current_oom_origin(); err = unmerge_and_remove_all_rmap_items(); clear_current_oom_origin(); if (err) { ksm_run = KSM_RUN_STOP; count = err; } } } mutex_unlock(&ksm_thread_mutex); if (flags & KSM_RUN_MERGE) wake_up_interruptible(&ksm_thread_wait); return count; } KSM_ATTR(run); #ifdef CONFIG_NUMA static ssize_t merge_across_nodes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_merge_across_nodes); } static ssize_t merge_across_nodes_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long knob; err = kstrtoul(buf, 10, &knob); if (err) return err; if (knob > 1) return -EINVAL; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_merge_across_nodes != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else if (root_stable_tree == one_stable_tree) { struct rb_root *buf; /* * This is the first time that we switch away from the * default of merging across nodes: must now allocate * a buffer to hold as many roots as may be needed. * Allocate stable and unstable together: * MAXSMP NODES_SHIFT 10 will use 16kB. */ buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), GFP_KERNEL); /* Let us assume that RB_ROOT is NULL is zero */ if (!buf) err = -ENOMEM; else { root_stable_tree = buf; root_unstable_tree = buf + nr_node_ids; /* Stable tree is empty but not the unstable */ root_unstable_tree[0] = one_unstable_tree[0]; } } if (!err) { ksm_merge_across_nodes = knob; ksm_nr_node_ids = knob ? 1 : nr_node_ids; } } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(merge_across_nodes); #endif static ssize_t use_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_use_zero_pages); } static ssize_t use_zero_pages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_use_zero_pages = value; return count; } KSM_ATTR(use_zero_pages); static ssize_t max_page_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_max_page_sharing); } static ssize_t max_page_sharing_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; int knob; err = kstrtoint(buf, 10, &knob); if (err) return err; /* * When a KSM page is created it is shared by 2 mappings. This * being a signed comparison, it implicitly verifies it's not * negative. */ if (knob < 2) return -EINVAL; if (READ_ONCE(ksm_max_page_sharing) == knob) return count; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_max_page_sharing != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else ksm_max_page_sharing = knob; } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(max_page_sharing); static ssize_t pages_scanned_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_scanned); } KSM_ATTR_RO(pages_scanned); static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_shared); } KSM_ATTR_RO(pages_shared); static ssize_t pages_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_sharing); } KSM_ATTR_RO(pages_sharing); static ssize_t pages_unshared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_unshared); } KSM_ATTR_RO(pages_unshared); static ssize_t pages_volatile_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long ksm_pages_volatile; ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared - ksm_pages_sharing - ksm_pages_unshared; /* * It was not worth any locking to calculate that statistic, * but it might therefore sometimes be negative: conceal that. */ if (ksm_pages_volatile < 0) ksm_pages_volatile = 0; return sysfs_emit(buf, "%ld\n", ksm_pages_volatile); } KSM_ATTR_RO(pages_volatile); static ssize_t pages_skipped_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); } KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); static ssize_t general_profit_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long general_profit; general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); } KSM_ATTR_RO(general_profit); static ssize_t stable_node_dups_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_dups); } KSM_ATTR_RO(stable_node_dups); static ssize_t stable_node_chains_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_chains); } KSM_ATTR_RO(stable_node_chains); static ssize_t stable_node_chains_prune_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); } static ssize_t stable_node_chains_prune_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; ksm_stable_node_chains_prune_millisecs = msecs; return count; } KSM_ATTR(stable_node_chains_prune_millisecs); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_scan.seqnr); } KSM_ATTR_RO(full_scans); static ssize_t smart_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_smart_scan); } static ssize_t smart_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_smart_scan = value; return count; } KSM_ATTR(smart_scan); static ssize_t advisor_mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (ksm_advisor == KSM_ADVISOR_NONE) output = "[none] scan-time"; else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) output = "none [scan-time]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t advisor_mode_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { enum ksm_advisor_type curr_advisor = ksm_advisor; if (sysfs_streq("scan-time", buf)) ksm_advisor = KSM_ADVISOR_SCAN_TIME; else if (sysfs_streq("none", buf)) ksm_advisor = KSM_ADVISOR_NONE; else return -EINVAL; /* Set advisor default values */ if (curr_advisor != ksm_advisor) set_advisor_defaults(); return count; } KSM_ATTR(advisor_mode); static ssize_t advisor_max_cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu); } static ssize_t advisor_max_cpu_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_cpu = value; return count; } KSM_ATTR(advisor_max_cpu); static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan); } static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_min_pages_to_scan = value; return count; } KSM_ATTR(advisor_min_pages_to_scan); static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan); } static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_pages_to_scan = value; return count; } KSM_ATTR(advisor_max_pages_to_scan); static ssize_t advisor_target_scan_time_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time); } static ssize_t advisor_target_scan_time_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; if (value < 1) return -EINVAL; ksm_advisor_target_scan_time = value; return count; } KSM_ATTR(advisor_target_scan_time); static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, &run_attr.attr, &pages_scanned_attr.attr, &pages_shared_attr.attr, &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, &pages_skipped_attr.attr, &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, #endif &max_page_sharing_attr.attr, &stable_node_chains_attr.attr, &stable_node_dups_attr.attr, &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, &general_profit_attr.attr, &smart_scan_attr.attr, &advisor_mode_attr.attr, &advisor_max_cpu_attr.attr, &advisor_min_pages_to_scan_attr.attr, &advisor_max_pages_to_scan_attr.attr, &advisor_target_scan_time_attr.attr, NULL, }; static const struct attribute_group ksm_attr_group = { .attrs = ksm_attrs, .name = "ksm", }; #endif /* CONFIG_SYSFS */ static int __init ksm_init(void) { struct task_struct *ksm_thread; int err; /* The correct value depends on page size and endianness */ zero_checksum = calc_checksum(ZERO_PAGE(0)); /* Default to false for backwards compatibility */ ksm_use_zero_pages = false; err = ksm_slab_init(); if (err) goto out; ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd"); if (IS_ERR(ksm_thread)) { pr_err("ksm: creating kthread failed\n"); err = PTR_ERR(ksm_thread); goto out_free; } #ifdef CONFIG_SYSFS err = sysfs_create_group(mm_kobj, &ksm_attr_group); if (err) { pr_err("ksm: register sysfs failed\n"); kthread_stop(ksm_thread); goto out_free; } #else ksm_run = KSM_RUN_MERGE; /* no way for user to start it */ #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MEMORY_HOTREMOVE /* There is no significance to this priority 100 */ hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI); #endif return 0; out_free: ksm_slab_free(); out: return err; } subsys_initcall(ksm_init); |
| 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash func */ int (*cmp)(const void *key1, const void *key2); /* comparison func */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; u64 chain2_len_sum; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig, int (*copy)(struct hashtab_node *new, const struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #else static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info) { return; } #endif #endif /* _SS_HASHTAB_H */ |
| 375 373 376 375 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif /* * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ if (this_cpu_read(printk_context) || in_nmi()) return vprintk_deferred(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 167 167 345 345 167 373 342 166 167 166 166 166 343 345 345 1 167 167 167 167 167 345 344 345 344 342 344 342 345 345 167 167 167 167 167 160 17 167 167 167 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/file.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /* * Mapping table from "enum tomoyo_path_acl_index" to "enum tomoyo_mac_index". */ static const u8 tomoyo_p2mac[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = TOMOYO_MAC_FILE_EXECUTE, [TOMOYO_TYPE_READ] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_WRITE] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_APPEND] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_UNLINK] = TOMOYO_MAC_FILE_UNLINK, [TOMOYO_TYPE_GETATTR] = TOMOYO_MAC_FILE_GETATTR, [TOMOYO_TYPE_RMDIR] = TOMOYO_MAC_FILE_RMDIR, [TOMOYO_TYPE_TRUNCATE] = TOMOYO_MAC_FILE_TRUNCATE, [TOMOYO_TYPE_SYMLINK] = TOMOYO_MAC_FILE_SYMLINK, [TOMOYO_TYPE_CHROOT] = TOMOYO_MAC_FILE_CHROOT, [TOMOYO_TYPE_UMOUNT] = TOMOYO_MAC_FILE_UMOUNT, }; /* * Mapping table from "enum tomoyo_mkdev_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION] = { [TOMOYO_TYPE_MKBLOCK] = TOMOYO_MAC_FILE_MKBLOCK, [TOMOYO_TYPE_MKCHAR] = TOMOYO_MAC_FILE_MKCHAR, }; /* * Mapping table from "enum tomoyo_path2_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION] = { [TOMOYO_TYPE_LINK] = TOMOYO_MAC_FILE_LINK, [TOMOYO_TYPE_RENAME] = TOMOYO_MAC_FILE_RENAME, [TOMOYO_TYPE_PIVOT_ROOT] = TOMOYO_MAC_FILE_PIVOT_ROOT, }; /* * Mapping table from "enum tomoyo_path_number_acl_index" to * "enum tomoyo_mac_index". */ const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION] = { [TOMOYO_TYPE_CREATE] = TOMOYO_MAC_FILE_CREATE, [TOMOYO_TYPE_MKDIR] = TOMOYO_MAC_FILE_MKDIR, [TOMOYO_TYPE_MKFIFO] = TOMOYO_MAC_FILE_MKFIFO, [TOMOYO_TYPE_MKSOCK] = TOMOYO_MAC_FILE_MKSOCK, [TOMOYO_TYPE_IOCTL] = TOMOYO_MAC_FILE_IOCTL, [TOMOYO_TYPE_CHMOD] = TOMOYO_MAC_FILE_CHMOD, [TOMOYO_TYPE_CHOWN] = TOMOYO_MAC_FILE_CHOWN, [TOMOYO_TYPE_CHGRP] = TOMOYO_MAC_FILE_CHGRP, }; /** * tomoyo_put_name_union - Drop reference on "struct tomoyo_name_union". * * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ void tomoyo_put_name_union(struct tomoyo_name_union *ptr) { tomoyo_put_group(ptr->group); tomoyo_put_name(ptr->filename); } /** * tomoyo_compare_name_union - Check whether a name matches "struct tomoyo_name_union" or not. * * @name: Pointer to "struct tomoyo_path_info". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns "struct tomoyo_path_info" if @name matches @ptr, NULL otherwise. */ const struct tomoyo_path_info * tomoyo_compare_name_union(const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr) { if (ptr->group) return tomoyo_path_matches_group(name, ptr->group); if (tomoyo_path_matches_pattern(name, ptr->filename)) return ptr->filename; return NULL; } /** * tomoyo_put_number_union - Drop reference on "struct tomoyo_number_union". * * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ void tomoyo_put_number_union(struct tomoyo_number_union *ptr) { tomoyo_put_group(ptr->group); } /** * tomoyo_compare_number_union - Check whether a value matches "struct tomoyo_number_union" or not. * * @value: Number to check. * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true if @value matches @ptr, false otherwise. */ bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr) { if (ptr->group) return tomoyo_number_matches_group(value, value, ptr->group); return value >= ptr->values[0] && value <= ptr->values[1]; } /** * tomoyo_add_slash - Add trailing '/' if needed. * * @buf: Pointer to "struct tomoyo_path_info". * * Returns nothing. * * @buf must be generated by tomoyo_encode() because this function does not * allocate memory for adding '/'. */ static void tomoyo_add_slash(struct tomoyo_path_info *buf) { if (buf->is_dir) return; /* * This is OK because tomoyo_encode() reserves space for appending "/". */ strcat((char *) buf->name, "/"); tomoyo_fill_path_info(buf); } /** * tomoyo_get_realpath - Get realpath. * * @buf: Pointer to "struct tomoyo_path_info". * @path: Pointer to "struct path". * * Returns true on success, false otherwise. */ static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path) { buf->name = tomoyo_realpath_from_path(path); if (buf->name) { tomoyo_fill_path_info(buf); return true; } return false; } /** * tomoyo_audit_path_log - Audit path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s\n", tomoyo_path_keyword [r->param.path.operation], r->param.path.filename->name); } /** * tomoyo_audit_path2_log - Audit path/path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path2_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pp2mac[r->param.path2.operation]], r->param.path2.filename1->name, r->param.path2.filename2->name); } /** * tomoyo_audit_mkdev_log - Audit path/number/number/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_mkdev_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s 0%o %u %u\n", tomoyo_mac_keywords [tomoyo_pnnn2mac[r->param.mkdev.operation]], r->param.mkdev.filename->name, r->param.mkdev.mode, r->param.mkdev.major, r->param.mkdev.minor); } /** * tomoyo_audit_path_number_log - Audit path/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_number_log(struct tomoyo_request_info *r) { const u8 type = r->param.path_number.operation; u8 radix; char buffer[64]; switch (type) { case TOMOYO_TYPE_CREATE: case TOMOYO_TYPE_MKDIR: case TOMOYO_TYPE_MKFIFO: case TOMOYO_TYPE_MKSOCK: case TOMOYO_TYPE_CHMOD: radix = TOMOYO_VALUE_TYPE_OCTAL; break; case TOMOYO_TYPE_IOCTL: radix = TOMOYO_VALUE_TYPE_HEXADECIMAL; break; default: radix = TOMOYO_VALUE_TYPE_DECIMAL; break; } tomoyo_print_ulong(buffer, sizeof(buffer), r->param.path_number.number, radix); return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pn2mac[type]], r->param.path_number.filename->name, buffer); } /** * tomoyo_check_path_acl - Check permission for path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. * * To be able to use wildcard for domain transition, this function sets * matching entry on success. Since the caller holds tomoyo_read_lock(), * it is safe to set matching entry. */ static bool tomoyo_check_path_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_acl *acl = container_of(ptr, typeof(*acl), head); if (acl->perm & (1 << r->param.path.operation)) { r->param.path.matched_path = tomoyo_compare_name_union(r->param.path.filename, &acl->name); return r->param.path.matched_path != NULL; } return false; } /** * tomoyo_check_path_number_acl - Check permission for path number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path_number_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_number_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path_number.operation)) && tomoyo_compare_number_union(r->param.path_number.number, &acl->number) && tomoyo_compare_name_union(r->param.path_number.filename, &acl->name); } /** * tomoyo_check_path2_acl - Check permission for path path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path2_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path2_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path2.operation)) && tomoyo_compare_name_union(r->param.path2.filename1, &acl->name1) && tomoyo_compare_name_union(r->param.path2.filename2, &acl->name2); } /** * tomoyo_check_mkdev_acl - Check permission for path number number number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_mkdev_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_mkdev_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.mkdev.operation)) && tomoyo_compare_number_union(r->param.mkdev.mode, &acl->mode) && tomoyo_compare_number_union(r->param.mkdev.major, &acl->major) && tomoyo_compare_number_union(r->param.mkdev.minor, &acl->minor) && tomoyo_compare_name_union(r->param.mkdev.filename, &acl->name); } /** * tomoyo_same_path_acl - Check for duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name); } /** * tomoyo_merge_path_acl - Merge duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u16 * const a_perm = &container_of(a, struct tomoyo_path_acl, head) ->perm; u16 perm = READ_ONCE(*a_perm); const u16 b_perm = container_of(b, struct tomoyo_path_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_acl - Update "struct tomoyo_path_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path_acl(const u16 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_acl e = { .head.type = TOMOYO_TYPE_PATH_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_acl, tomoyo_merge_path_acl); tomoyo_put_name_union(&e.name); return error; } /** * tomoyo_same_mkdev_acl - Check for duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_mkdev_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mkdev_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mkdev_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->mode, &p2->mode) && tomoyo_same_number_union(&p1->major, &p2->major) && tomoyo_same_number_union(&p1->minor, &p2->minor); } /** * tomoyo_merge_mkdev_acl - Merge duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_mkdev_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 *const a_perm = &container_of(a, struct tomoyo_mkdev_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_mkdev_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_mkdev_acl - Update "struct tomoyo_mkdev_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mkdev_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_mkdev_acl e = { .head.type = TOMOYO_TYPE_MKDEV_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.mode) || !tomoyo_parse_number_union(param, &e.major) || !tomoyo_parse_number_union(param, &e.minor)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mkdev_acl, tomoyo_merge_mkdev_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.mode); tomoyo_put_number_union(&e.major); tomoyo_put_number_union(&e.minor); return error; } /** * tomoyo_same_path2_acl - Check for duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path2_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path2_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path2_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name1, &p2->name1) && tomoyo_same_name_union(&p1->name2, &p2->name2); } /** * tomoyo_merge_path2_acl - Merge duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path2_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path2_acl, head) ->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path2_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path2_acl - Update "struct tomoyo_path2_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path2_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path2_acl e = { .head.type = TOMOYO_TYPE_PATH2_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name1) || !tomoyo_parse_name_union(param, &e.name2)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path2_acl, tomoyo_merge_path2_acl); tomoyo_put_name_union(&e.name1); tomoyo_put_name_union(&e.name2); return error; } /** * tomoyo_path_permission - Check permission for single path operation. * * @r: Pointer to "struct tomoyo_request_info". * @operation: Type of operation. * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, const struct tomoyo_path_info *filename) { int error; r->type = tomoyo_p2mac[operation]; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); if (r->mode == TOMOYO_CONFIG_DISABLED) return 0; r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = operation; do { tomoyo_check_acl(r, tomoyo_check_path_acl); error = tomoyo_audit_path_log(r); } while (error == TOMOYO_RETRY_REQUEST); return error; } /** * tomoyo_execute_permission - Check permission for execute operation. * * @r: Pointer to "struct tomoyo_request_info". * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename) { /* * Unlike other permission checks, this check is done regardless of * profile mode settings in order to check for domain transition * preference. */ r->type = TOMOYO_MAC_FILE_EXECUTE; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = TOMOYO_TYPE_EXECUTE; tomoyo_check_acl(r, tomoyo_check_path_acl); r->ee->transition = r->matched_acl && r->matched_acl->cond ? r->matched_acl->cond->transit : NULL; if (r->mode != TOMOYO_CONFIG_DISABLED) return tomoyo_audit_path_log(r); return 0; } /** * tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_number_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_number_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_number_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->number, &p2->number); } /** * tomoyo_merge_path_number_acl - Merge duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_number_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path_number_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path_number_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_number_acl - Update ioctl/chmod/chown/chgrp ACL. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_update_path_number_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_number_acl e = { .head.type = TOMOYO_TYPE_PATH_NUMBER_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.number)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_number_acl, tomoyo_merge_path_number_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.number); return error; } /** * tomoyo_path_number_perm - Check permission for "create", "mkdir", "mkfifo", "mksock", "ioctl", "chmod", "chown", "chgrp". * * @type: Type of operation. * @path: Pointer to "struct path". * @number: Number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_number_perm(const u8 type, const struct path *path, unsigned long number) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pn2mac[type]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; if (type == TOMOYO_TYPE_MKDIR) tomoyo_add_slash(&buf); r.param_type = TOMOYO_TYPE_PATH_NUMBER_ACL; r.param.path_number.operation = type; r.param.path_number.filename = &buf; r.param.path_number.number = number; do { tomoyo_check_acl(&r, tomoyo_check_path_number_acl); error = tomoyo_audit_path_number_log(&r); } while (error == TOMOYO_RETRY_REQUEST); kfree(buf.name); out: tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_check_open_permission - Check permission for "read" and "write". * * @domain: Pointer to "struct tomoyo_domain_info". * @path: Pointer to "struct path". * @flag: Flags for open(). * * Returns 0 on success, negative value otherwise. */ int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag) { const u8 acc_mode = ACC_MODE(flag); int error = 0; struct tomoyo_path_info buf; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int idx; buf.name = NULL; r.mode = TOMOYO_CONFIG_DISABLED; idx = tomoyo_read_lock(); if (acc_mode && tomoyo_init_request_info(&r, domain, TOMOYO_MAC_FILE_OPEN) != TOMOYO_CONFIG_DISABLED) { if (!tomoyo_get_realpath(&buf, path)) { error = -ENOMEM; goto out; } r.obj = &obj; if (acc_mode & MAY_READ) error = tomoyo_path_permission(&r, TOMOYO_TYPE_READ, &buf); if (!error && (acc_mode & MAY_WRITE)) error = tomoyo_path_permission(&r, (flag & O_APPEND) ? TOMOYO_TYPE_APPEND : TOMOYO_TYPE_WRITE, &buf); } out: kfree(buf.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path_perm - Check permission for "unlink", "rmdir", "truncate", "symlink", "append", "chroot" and "unmount". * * @operation: Type of operation. * @path: Pointer to "struct path". * @target: Symlink's target if @operation is TOMOYO_TYPE_SYMLINK, * NULL otherwise. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error; struct tomoyo_path_info buf; bool is_enforce; struct tomoyo_path_info symlink_target; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_p2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; is_enforce = (r.mode == TOMOYO_CONFIG_ENFORCING); error = -ENOMEM; buf.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; switch (operation) { case TOMOYO_TYPE_RMDIR: case TOMOYO_TYPE_CHROOT: tomoyo_add_slash(&buf); break; case TOMOYO_TYPE_SYMLINK: symlink_target.name = tomoyo_encode(target); if (!symlink_target.name) goto out; tomoyo_fill_path_info(&symlink_target); obj.symlink_target = &symlink_target; break; } error = tomoyo_path_permission(&r, operation, &buf); if (operation == TOMOYO_TYPE_SYMLINK) kfree(symlink_target.name); out: kfree(buf.name); tomoyo_read_unlock(idx); if (!is_enforce) error = 0; return error; } /** * tomoyo_mkdev_perm - Check permission for "mkblock" and "mkchar". * * @operation: Type of operation. (TOMOYO_TYPE_MKCHAR or TOMOYO_TYPE_MKBLOCK) * @path: Pointer to "struct path". * @mode: Create mode. * @dev: Device number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pnnn2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); error = -ENOMEM; if (tomoyo_get_realpath(&buf, path)) { r.obj = &obj; dev = new_decode_dev(dev); r.param_type = TOMOYO_TYPE_MKDEV_ACL; r.param.mkdev.filename = &buf; r.param.mkdev.operation = operation; r.param.mkdev.mode = mode; r.param.mkdev.major = MAJOR(dev); r.param.mkdev.minor = MINOR(dev); tomoyo_check_acl(&r, tomoyo_check_mkdev_acl); error = tomoyo_audit_mkdev_log(&r); kfree(buf.name); } tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path2_perm - Check permission for "rename", "link" and "pivot_root". * * @operation: Type of operation. * @path1: Pointer to "struct path". * @path2: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2) { int error = -ENOMEM; struct tomoyo_path_info buf1; struct tomoyo_path_info buf2; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path1->mnt, .dentry = path1->dentry }, .path2 = { .mnt = path2->mnt, .dentry = path2->dentry } }; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pp2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; buf1.name = NULL; buf2.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf1, path1) || !tomoyo_get_realpath(&buf2, path2)) goto out; switch (operation) { case TOMOYO_TYPE_RENAME: case TOMOYO_TYPE_LINK: if (!d_is_dir(path1->dentry)) break; fallthrough; case TOMOYO_TYPE_PIVOT_ROOT: tomoyo_add_slash(&buf1); tomoyo_add_slash(&buf2); break; } r.obj = &obj; r.param_type = TOMOYO_TYPE_PATH2_ACL; r.param.path2.operation = operation; r.param.path2.filename1 = &buf1; r.param.path2.filename2 = &buf2; do { tomoyo_check_acl(&r, tomoyo_check_path2_acl); error = tomoyo_audit_path2_log(&r); } while (error == TOMOYO_RETRY_REQUEST); out: kfree(buf1.name); kfree(buf2.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_same_mount_acl - Check for duplicated "struct tomoyo_mount_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_mount_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mount_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mount_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->dev_name, &p2->dev_name) && tomoyo_same_name_union(&p1->dir_name, &p2->dir_name) && tomoyo_same_name_union(&p1->fs_type, &p2->fs_type) && tomoyo_same_number_union(&p1->flags, &p2->flags); } /** * tomoyo_update_mount_acl - Write "struct tomoyo_mount_acl" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mount_acl(struct tomoyo_acl_param *param) { struct tomoyo_mount_acl e = { .head.type = TOMOYO_TYPE_MOUNT_ACL }; int error; if (!tomoyo_parse_name_union(param, &e.dev_name) || !tomoyo_parse_name_union(param, &e.dir_name) || !tomoyo_parse_name_union(param, &e.fs_type) || !tomoyo_parse_number_union(param, &e.flags)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mount_acl, NULL); tomoyo_put_name_union(&e.dev_name); tomoyo_put_name_union(&e.dir_name); tomoyo_put_name_union(&e.fs_type); tomoyo_put_number_union(&e.flags); return error; } /** * tomoyo_write_file - Update file related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_file(struct tomoyo_acl_param *param) { u16 perm = 0; u8 type; const char *operation = tomoyo_read_token(param); for (type = 0; type < TOMOYO_MAX_PATH_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_path_keyword[type])) perm |= 1 << type; if (perm) return tomoyo_update_path_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH2_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pp2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path2_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH_NUMBER_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path_number_acl(perm, param); for (type = 0; type < TOMOYO_MAX_MKDEV_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pnnn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_mkdev_acl(perm, param); if (tomoyo_permstr(operation, tomoyo_mac_keywords[TOMOYO_MAC_FILE_MOUNT])) return tomoyo_update_mount_acl(param); return -EINVAL; } |
| 1 1 1 1 7 7 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_asm.h> #include "vgic.h" static bool group0_trap; static bool group1_trap; static bool common_trap; static bool dir_trap; static bool gicv4_enable; void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; cpuif->vgic_hcr |= ICH_HCR_UIE; } static bool lr_signals_eoi_mi(u64 lr_val) { return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && !(lr_val & ICH_LR_HW); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; int lr; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); cpuif->vgic_hcr &= ~ICH_HCR_UIE; for (lr = 0; lr < cpuif->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; u32 intid, cpuid; struct vgic_irq *irq; bool is_v2_sgi = false; bool deactivated; cpuid = val & GICH_LR_PHYSID_CPUID; cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { intid = val & ICH_LR_VIRTUAL_ID_MASK; } else { intid = val & GICH_LR_VIRTUALID; is_v2_sgi = vgic_irq_is_sgi(intid); } /* Notify fds when the guest EOI'ed a level-triggered IRQ */ if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) kvm_notify_acked_irq(vcpu->kvm, 0, intid - VGIC_NR_PRIVATE_IRQS); irq = vgic_get_irq(vcpu->kvm, vcpu, intid); if (!irq) /* An LPI could have been unmapped. */ continue; raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit, note deactivation */ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT); irq->active = !!(val & ICH_LR_ACTIVE_BIT); if (irq->active && is_v2_sgi) irq->active_source = cpuid; /* Edge is the only case where we preserve the pending bit */ if (irq->config == VGIC_CONFIG_EDGE && (val & ICH_LR_PENDING_BIT)) { irq->pending_latch = true; if (is_v2_sgi) irq->source |= (1 << cpuid); } /* * Clear soft pending state when level irqs have been acked. */ if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) irq->pending_latch = false; /* Handle resampling for mapped interrupts if required */ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } cpuif->used_lrs = 0; } /* Requires the irq to be locked already */ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) { u32 model = vcpu->kvm->arch.vgic.vgic_model; u64 val = irq->intid; bool allow_pending = true, is_v2_sgi; is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2); if (irq->active) { val |= ICH_LR_ACTIVE_BIT; if (is_v2_sgi) val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; if (vgic_irq_is_multi_sgi(irq)) { allow_pending = false; val |= ICH_LR_EOI; } } if (irq->hw && !vgic_irq_needs_resampling(irq)) { val |= ICH_LR_HW; val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; /* * Never set pending+active on a HW interrupt, as the * pending state is kept at the physical distributor * level. */ if (irq->active) allow_pending = false; } else { if (irq->config == VGIC_CONFIG_LEVEL) { val |= ICH_LR_EOI; /* * Software resampling doesn't work very well * if we allow P+A, so let's not do that. */ if (irq->active) allow_pending = false; } } if (allow_pending && irq_is_pending(irq)) { val |= ICH_LR_PENDING_BIT; if (irq->config == VGIC_CONFIG_EDGE) irq->pending_latch = false; if (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2) { u32 src = ffs(irq->source); if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", irq->intid)) return; val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; irq->source &= ~(1 << (src - 1)); if (irq->source) { irq->pending_latch = true; val |= ICH_LR_EOI; } } } /* * Level-triggered mapped IRQs are special because we only observe * rising edges as input to the VGIC. We therefore lower the line * level here, so that we can take new virtual IRQs. See * vgic_v3_fold_lr_state for more info. */ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) irq->line_level = false; if (irq->group) val |= ICH_LR_GROUP; val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; } void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) { vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; } void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & ICH_VMCR_ACK_CTL_MASK; vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & ICH_VMCR_FIQ_EN_MASK; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcr = ICH_VMCR_FIQ_EN_MASK; } vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; cpu_if->vgic_vmcr = vmcr; } void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; vmcr = cpu_if->vgic_vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> ICH_VMCR_ACK_CTL_SHIFT; vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> ICH_VMCR_FIQ_EN_SHIFT; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcrp->fiqen = 1; vmcrp->ackctl = 0; } vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; } #define INITIAL_PENDBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) void vgic_v3_enable(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* * By forcing VMCR to zero, the GIC will restore the binary * points to their reset values. Anything else resets to zero * anyway. */ vgic_v3->vgic_vmcr = 0; /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; } vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_ID_BITS_MASK) >> ICH_VTR_ID_BITS_SHIFT; vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_PRI_BITS_MASK) >> ICH_VTR_PRI_BITS_SHIFT) + 1; /* Get the show on the road... */ vgic_v3->vgic_hcr = ICH_HCR_EN; if (group0_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL0; if (group1_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL1; if (common_trap) vgic_v3->vgic_hcr |= ICH_HCR_TC; if (dir_trap) vgic_v3->vgic_hcr |= ICH_HCR_TDIR; } int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) { struct kvm_vcpu *vcpu; int byte_offset, bit_nr; gpa_t pendbase, ptr; bool status; u8 val; int ret; unsigned long flags; retry: vcpu = irq->target_vcpu; if (!vcpu) return 0; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; status = val & (1 << bit_nr); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } return 0; } /* * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ static void unmap_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } static void map_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), dist->its_vm.vpes[i]->irq)); } /* * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; bool vlpi_avail = false; unsigned long index; int ret = 0; u8 val; if (unlikely(!vgic_initialized(kvm))) return -ENXIO; /* * A preparation for getting any VLPI states. * The above vgic initialized check also ensures that the allocation * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { unmap_all_vpes(kvm); vlpi_avail = true; } xa_for_each(&dist->lpi_xa, index, irq) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; bool is_pending; bool stored; vcpu = irq->target_vcpu; if (!vcpu) continue; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); is_pending = irq->pending_latch; if (irq->hw && vlpi_avail) vgic_v4_get_vlpi_state(irq, &is_pending); if (stored == is_pending) continue; if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) map_all_vpes(kvm); return ret; } /** * vgic_v3_rdist_overlap - check if a region overlaps with any * existing redistributor region * * @kvm: kvm handle * @base: base of the region * @size: size of region * * Return: true if there is an overlap */ bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, &d->rd_regions, list) { if ((base + size > rdreg->base) && (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) return true; } return false; } /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. */ bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; list_for_each_entry(rdreg, &d->rd_regions, list) { size_t sz = vgic_v3_rd_region_size(kvm, rdreg); if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF, rdreg->base, SZ_64K, sz)) return false; } if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, KVM_VGIC_V3_DIST_SIZE); } /** * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one * which has free space to put a new rdist region. * * @rd_regions: redistributor region list head * * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). * Stride between redistributors is 0 and regions are filled in the index order. * * Return: the redist region handle, if any, that has space to map a new rdist * region. */ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) { struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (!vgic_v3_redist_region_full(rdreg)) return rdreg; } return NULL; } struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index) { struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (rdreg->index == index) return rdreg; } return NULL; } int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_debug("Need to set vgic distributor addresses first\n"); return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_debug("VGIC redist and dist frames overlap\n"); return -EINVAL; } /* * For a VGICv3 we require the userland to explicitly initialize * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { return -EBUSY; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; static bool vgic_v3_broken_seis(void) { return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && is_midr_in_range_list(read_cpuid_id(), broken_seis)); } /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description * * Returns 0 if the VGICv3 has been probed successfully, returns an error code * otherwise */ int vgic_v3_probe(const struct gic_kvm_info *info) { u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config); bool has_v2; int ret; has_v2 = ich_vtr_el2 >> 63; ich_vtr_el2 = (u32)ich_vtr_el2; /* * The ListRegs field is 5 bits, but there is an architectural * maximum of 16 list registers. Just ignore bit 4... */ kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; kvm_vgic_global_state.can_emulate_gicv2 = false; kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; /* GICv4 support? */ if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; kvm_info("GICv4%s support %sabled\n", kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", gicv4_enable ? "en" : "dis"); } kvm_vgic_global_state.vcpu_base = 0; if (!info->vcpu.start) { kvm_info("GICv3: no GICV resource entry\n"); } else if (!has_v2) { pr_warn(FW_BUG "CPU interface incapable of MMIO access\n"); } else if (!PAGE_ALIGNED(info->vcpu.start)) { pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); } else if (kvm_get_mode() != KVM_MODE_PROTECTED) { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); if (ret) { kvm_err("Cannot register GICv2 KVM device.\n"); return ret; } kvm_info("vgic-v2@%llx\n", info->vcpu.start); } ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) { kvm_err("Cannot register GICv3 KVM device.\n"); kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); return ret; } if (kvm_vgic_global_state.vcpu_base == 0) kvm_info("disabling GICv2 emulation\n"); if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) { group0_trap = true; group1_trap = true; } if (vgic_v3_broken_seis()) { kvm_info("GICv3 with broken locally generated SEI\n"); kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) dir_trap = true; else common_trap = true; } if (group0_trap || group1_trap || common_trap | dir_trap) { kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n", group0_trap ? "G0" : "", group1_trap ? "G1" : "", common_trap ? "C" : "", dir_trap ? "D" : ""); static_branch_enable(&vgic_v3_cpuif_trap); } kvm_vgic_global_state.vctrl_base = NULL; kvm_vgic_global_state.type = VGIC_V3; kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; return 0; } void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); if (has_vhe()) __vgic_v3_activate_traps(cpu_if); WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); if (has_vhe()) __vgic_v3_deactivate_traps(cpu_if); } |
| 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ARM64_KVM_HYP_DEBUG_SR_H__ #define __ARM64_KVM_HYP_DEBUG_SR_H__ #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #define read_debug(r,n) read_sysreg(r##n##_el1) #define write_debug(v,r,n) write_sysreg(v, r##n##_el1) #define save_debug(ptr,reg,nr) \ switch (nr) { \ case 15: ptr[15] = read_debug(reg, 15); \ fallthrough; \ case 14: ptr[14] = read_debug(reg, 14); \ fallthrough; \ case 13: ptr[13] = read_debug(reg, 13); \ fallthrough; \ case 12: ptr[12] = read_debug(reg, 12); \ fallthrough; \ case 11: ptr[11] = read_debug(reg, 11); \ fallthrough; \ case 10: ptr[10] = read_debug(reg, 10); \ fallthrough; \ case 9: ptr[9] = read_debug(reg, 9); \ fallthrough; \ case 8: ptr[8] = read_debug(reg, 8); \ fallthrough; \ case 7: ptr[7] = read_debug(reg, 7); \ fallthrough; \ case 6: ptr[6] = read_debug(reg, 6); \ fallthrough; \ case 5: ptr[5] = read_debug(reg, 5); \ fallthrough; \ case 4: ptr[4] = read_debug(reg, 4); \ fallthrough; \ case 3: ptr[3] = read_debug(reg, 3); \ fallthrough; \ case 2: ptr[2] = read_debug(reg, 2); \ fallthrough; \ case 1: ptr[1] = read_debug(reg, 1); \ fallthrough; \ default: ptr[0] = read_debug(reg, 0); \ } #define restore_debug(ptr,reg,nr) \ switch (nr) { \ case 15: write_debug(ptr[15], reg, 15); \ fallthrough; \ case 14: write_debug(ptr[14], reg, 14); \ fallthrough; \ case 13: write_debug(ptr[13], reg, 13); \ fallthrough; \ case 12: write_debug(ptr[12], reg, 12); \ fallthrough; \ case 11: write_debug(ptr[11], reg, 11); \ fallthrough; \ case 10: write_debug(ptr[10], reg, 10); \ fallthrough; \ case 9: write_debug(ptr[9], reg, 9); \ fallthrough; \ case 8: write_debug(ptr[8], reg, 8); \ fallthrough; \ case 7: write_debug(ptr[7], reg, 7); \ fallthrough; \ case 6: write_debug(ptr[6], reg, 6); \ fallthrough; \ case 5: write_debug(ptr[5], reg, 5); \ fallthrough; \ case 4: write_debug(ptr[4], reg, 4); \ fallthrough; \ case 3: write_debug(ptr[3], reg, 3); \ fallthrough; \ case 2: write_debug(ptr[2], reg, 2); \ fallthrough; \ case 1: write_debug(ptr[1], reg, 1); \ fallthrough; \ default: write_debug(ptr[0], reg, 0); \ } static void __debug_save_state(struct kvm_guest_debug_arch *dbg, struct kvm_cpu_context *ctxt) { u64 aa64dfr0; int brps, wrps; aa64dfr0 = read_sysreg(id_aa64dfr0_el1); brps = (aa64dfr0 >> 12) & 0xf; wrps = (aa64dfr0 >> 20) & 0xf; save_debug(dbg->dbg_bcr, dbgbcr, brps); save_debug(dbg->dbg_bvr, dbgbvr, brps); save_debug(dbg->dbg_wcr, dbgwcr, wrps); save_debug(dbg->dbg_wvr, dbgwvr, wrps); ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1); } static void __debug_restore_state(struct kvm_guest_debug_arch *dbg, struct kvm_cpu_context *ctxt) { u64 aa64dfr0; int brps, wrps; aa64dfr0 = read_sysreg(id_aa64dfr0_el1); brps = (aa64dfr0 >> 12) & 0xf; wrps = (aa64dfr0 >> 20) & 0xf; restore_debug(dbg->dbg_bcr, dbgbcr, brps); restore_debug(dbg->dbg_bvr, dbgbvr, brps); restore_debug(dbg->dbg_wcr, dbgwcr, wrps); restore_debug(dbg->dbg_wvr, dbgwvr, wrps); write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1); } static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; if (!vcpu_get_flag(vcpu, DEBUG_DIRTY)) return; host_ctxt = host_data_ptr(host_ctxt); guest_ctxt = &vcpu->arch.ctxt; host_dbg = host_data_ptr(host_debug_state.regs); guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); __debug_save_state(host_dbg, host_ctxt); __debug_restore_state(guest_dbg, guest_ctxt); } static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; if (!vcpu_get_flag(vcpu, DEBUG_DIRTY)) return; host_ctxt = host_data_ptr(host_ctxt); guest_ctxt = &vcpu->arch.ctxt; host_dbg = host_data_ptr(host_debug_state.regs); guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); __debug_save_state(guest_dbg, guest_ctxt); __debug_restore_state(host_dbg, host_ctxt); vcpu_clear_flag(vcpu, DEBUG_DIRTY); } #endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */ |
| 147 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SMP_H #define __LINUX_SMP_H /* * Generic SMP support * Alan Cox. <alan@redhat.com> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/list.h> #include <linux/cpumask.h> #include <linux/init.h> #include <linux/smp_types.h> typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); /* * structure shares (partial) layout with struct irq_work */ struct __call_single_data { struct __call_single_node node; smp_call_func_t func; void *info; }; #define CSD_INIT(_func, _info) \ (struct __call_single_data){ .func = (_func), .info = (_info), } /* Use __aligned() to avoid to use 2 cache lines for 1 csd */ typedef struct __call_single_data call_single_data_t __aligned(sizeof(struct __call_single_data)); #define INIT_CSD(_csd, _func, _info) \ do { \ *(_csd) = CSD_INIT((_func), (_info)); \ } while (0) /* * Enqueue a llist_node on the call_single_queue; be very careful, read * flush_smp_call_function_queue() in detail. */ extern void __smp_call_single_queue(int cpu, struct llist_node *node); /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, int wait); void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); int smp_call_function_single_async(int cpu, call_single_data_t *csd); /* * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ void __noreturn panic_smp_self_stop(void); void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); /* * Call a function on all processors */ static inline void on_each_cpu(smp_call_func_t func, void *info, int wait) { on_each_cpu_cond_mask(NULL, func, info, wait, cpu_online_mask); } /** * on_each_cpu_mask(): Run a function on processors specified by * cpumask, which may include the local processor. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. The * exception is that it may be used during early boot while * early_boot_irqs_disabled is set. */ static inline void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(NULL, func, info, wait, mask); } /* * Call a function on each processor for which the supplied function * cond_func returns a positive value. This may include the local * processor. May be used during early boot while early_boot_irqs_disabled is * set. Use local_irq_save/restore() instead of local_irq_disable/enable(). */ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } /* * Architecture specific boot CPU setup. Defined as empty weak function in * init/main.c. Architectures can override it. */ void smp_prepare_boot_cpu(void); #ifdef CONFIG_SMP #include <linux/preempt.h> #include <linux/compiler.h> #include <linux/thread_info.h> #include <asm/smp.h> /* * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc. * (defined in asm header): */ /* * stops all CPUs but the current one: */ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ extern void arch_smp_send_reschedule(int cpu); /* * scheduler_ipi() is inline so can't be passed as callback reason, but the * callsite IP should be sufficient for root-causing IPIs sent from here. */ #define smp_send_reschedule(cpu) ({ \ trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ arch_smp_send_reschedule(cpu); \ }) /* * Prepare machine for booting other CPUs. */ extern void smp_prepare_cpus(unsigned int max_cpus); /* * Bring a CPU up */ extern int __cpu_up(unsigned int cpunum, struct task_struct *tidle); /* * Final polishing of CPUs */ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ void smp_call_function(smp_call_func_t func, void *info, int wait); void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait); int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait); void kick_all_cpus_sync(void); void wake_up_all_idle_cpus(void); /* * Generic and arch helpers */ void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); #define generic_smp_call_function_interrupt \ generic_smp_call_function_single_interrupt extern unsigned int setup_max_cpus; extern void __init setup_nr_cpu_ids(void); extern void __init smp_init(void); extern int __boot_cpu_id; static inline int get_boot_cpu_id(void) { return __boot_cpu_id; } #else /* !SMP */ static inline void smp_send_stop(void) { } /* * These macros fold the SMP functionality into a single CPU system */ #define raw_smp_processor_id() 0 static inline void up_smp_call_function(smp_call_func_t func, void *info) { } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) static inline void smp_send_reschedule(int cpu) { } #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) static inline void call_function_init(void) { } static inline int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { return smp_call_function_single(0, func, info, wait); } static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } #define setup_max_cpus 0 #ifdef CONFIG_UP_LATE_INIT extern void __init up_late_init(void); static inline void smp_init(void) { up_late_init(); } #else static inline void smp_init(void) { } #endif static inline int get_boot_cpu_id(void) { return 0; } #endif /* !SMP */ /** * raw_processor_id() - get the current (unstable) CPU id * * For then you know what you are doing and need an unstable * CPU id. */ /** * smp_processor_id() - get the current (stable) CPU id * * This is the normal accessor to the CPU id and should be used * whenever possible. * * The CPU id is stable when: * * - IRQs are disabled; * - preemption is disabled; * - the task is CPU affine. * * When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN * when smp_processor_id() is used when the CPU id is not stable. */ /* * Allow the architecture to differentiate between a stable and unstable read. * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a * regular asm read for the stable. */ #ifndef __smp_processor_id #define __smp_processor_id() raw_smp_processor_id() #endif #ifdef CONFIG_DEBUG_PREEMPT extern unsigned int debug_smp_processor_id(void); # define smp_processor_id() debug_smp_processor_id() #else # define smp_processor_id() __smp_processor_id() #endif #define get_cpu() ({ preempt_disable(); __smp_processor_id(); }) #define put_cpu() preempt_enable() /* * Callback to arch code if there's nosmp or maxcpus=0 on the * boot command line: */ extern void arch_disable_smp_support(void); extern void arch_thaw_secondary_cpus_begin(void); extern void arch_thaw_secondary_cpus_end(void); void smp_setup_processor_id(void); int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys); /* SMP core functions */ int smpcfd_prepare_cpu(unsigned int cpu); int smpcfd_dead_cpu(unsigned int cpu); int smpcfd_dying_cpu(unsigned int cpu); #endif /* __LINUX_SMP_H */ |
| 457 446 445 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <linux/jump_label.h> #include <linux/thread_info.h> #define PREEMPT_NEED_RESCHED BIT(32) #define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED) static inline int preempt_count(void) { return READ_ONCE(current_thread_info()->preempt.count); } static inline void preempt_count_set(u64 pc) { /* Preserve existing value of PREEMPT_NEED_RESCHED */ WRITE_ONCE(current_thread_info()->preempt.count, pc); } #define init_task_preempt_count(p) do { \ task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \ } while (0) #define init_idle_preempt_count(p, cpu) do { \ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \ } while (0) static inline void set_preempt_need_resched(void) { current_thread_info()->preempt.need_resched = 0; } static inline void clear_preempt_need_resched(void) { current_thread_info()->preempt.need_resched = 1; } static inline bool test_preempt_need_resched(void) { return !current_thread_info()->preempt.need_resched; } static inline void __preempt_count_add(int val) { u32 pc = READ_ONCE(current_thread_info()->preempt.count); pc += val; WRITE_ONCE(current_thread_info()->preempt.count, pc); } static inline void __preempt_count_sub(int val) { u32 pc = READ_ONCE(current_thread_info()->preempt.count); pc -= val; WRITE_ONCE(current_thread_info()->preempt.count, pc); } static inline bool __preempt_count_dec_and_test(void) { struct thread_info *ti = current_thread_info(); u64 pc = READ_ONCE(ti->preempt_count); /* Update only the count field, leaving need_resched unchanged */ WRITE_ONCE(ti->preempt.count, --pc); /* * If we wrote back all zeroes, then we're preemptible and in * need of a reschedule. Otherwise, we need to reload the * preempt_count in case the need_resched flag was cleared by an * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE * pair. */ return !pc || !READ_ONCE(ti->preempt_count); } static inline bool should_resched(int preempt_offset) { u64 pc = READ_ONCE(current_thread_info()->preempt_count); return pc == preempt_offset; } #ifdef CONFIG_PREEMPTION void preempt_schedule(void); void preempt_schedule_notrace(void); #ifdef CONFIG_PREEMPT_DYNAMIC DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_preempt_schedule(void); #define __preempt_schedule() dynamic_preempt_schedule() void dynamic_preempt_schedule_notrace(void); #define __preempt_schedule_notrace() dynamic_preempt_schedule_notrace() #else /* CONFIG_PREEMPT_DYNAMIC */ #define __preempt_schedule() preempt_schedule() #define __preempt_schedule_notrace() preempt_schedule_notrace() #endif /* CONFIG_PREEMPT_DYNAMIC */ #endif /* CONFIG_PREEMPTION */ #endif /* __ASM_PREEMPT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * * Workqueue internal header file. Only to be included by workqueue and * core kernel subsystems. */ #ifndef _KERNEL_WORKQUEUE_INTERNAL_H #define _KERNEL_WORKQUEUE_INTERNAL_H #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/preempt.h> struct worker_pool; /* * The poor guys doing the actual heavy lifting. All on-duty workers are * either serving the manager role, on idle list or on busy hash. For * details on the locking annotation (L, I, X...), refer to workqueue.c. * * Only to be used in workqueue and async. */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { struct list_head entry; /* L: while idle */ struct hlist_node hentry; /* L: while busy */ }; struct work_struct *current_work; /* K: work being processed and its */ work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ /* used by the scheduler to determine a worker's last known identity */ work_func_t last_func; /* K: last work's fn */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ unsigned long last_active; /* K: last active timestamp */ unsigned int flags; /* L: flags */ int id; /* I: worker id */ /* * Opaque string set with work_set_desc(). Printed out with task * dump for debugging - WARN, BUG, panic or sysrq. */ char desc[WORKER_DESC_LEN]; /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; /** * current_wq_worker - return struct worker if %current is a workqueue worker */ static inline struct worker *current_wq_worker(void) { if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } /* * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); void wq_worker_tick(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |
| 34 34 23 23 23 14 14 14 13 14 14 14 14 12 12 2 12 12 12 10 10 10 10 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/mm/hugetlbpage.c * * Copyright (C) 2013 Linaro Ltd. * * Based on arch/x86/mm/hugetlbpage.c. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> /* * HugeTLB Support Matrix * * --------------------------------------------------- * | Page Size | CONT PTE | PMD | CONT PMD | PUD | * --------------------------------------------------- * | 4K | 64K | 2M | 32M | 1G | * | 16K | 2M | 32M | 1G | | * | 64K | 2M | 512M | 16G | | * --------------------------------------------------- */ /* * Reserve CMA areas for the largest supported gigantic * huge page when requested. Any other smaller gigantic * huge pages could still be served from those areas. */ #ifdef CONFIG_CMA void __init arm64_hugetlb_cma_reserve(void) { int order; if (pud_sect_supported()) order = PUD_SHIFT - PAGE_SHIFT; else order = CONT_PMD_SHIFT - PAGE_SHIFT; hugetlb_cma_reserve(order); } #endif /* CONFIG_CMA */ static bool __hugetlb_valid_size(unsigned long size) { switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return pud_sect_supported(); #endif case CONT_PMD_SIZE: case PMD_SIZE: case CONT_PTE_SIZE: return true; } return false; } #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { size_t pagesize = huge_page_size(h); if (!__hugetlb_valid_size(pagesize)) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); return false; } return true; } #endif static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { pgd_t *pgdp = pgd_offset(mm, addr); p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; *pgsize = PAGE_SIZE; p4dp = p4d_offset(pgdp, addr); pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } return CONT_PTES; } static inline int num_contig_ptes(unsigned long size, size_t *pgsize) { int contig_ptes = 0; *pgsize = size; switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: if (pud_sect_supported()) contig_ptes = 1; break; #endif case PMD_SIZE: contig_ptes = 1; break; case CONT_PMD_SIZE: *pgsize = PMD_SIZE; contig_ptes = CONT_PMDS; break; case CONT_PTE_SIZE: *pgsize = PAGE_SIZE; contig_ptes = CONT_PTES; break; } return contig_ptes; } pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig, i; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_present(orig_pte) || !pte_cont(orig_pte)) return orig_pte; ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize); for (i = 0; i < ncontig; i++, ptep++) { pte_t pte = __ptep_get(ptep); if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step. */ static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = __ptep_get(ptep); unsigned long i; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = __ptep_get_and_clear(mm, addr, ptep); /* * If HW_AFDBM is enabled, then the HW could turn on * the dirty or accessed bit for any page in the set, * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig); struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, addr, addr + (pgsize * ncontig)); return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step for use cases where the * original pte is not needed. */ static void clear_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __ptep_get_and_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; int ncontig; unsigned long pfn, dpfn; pgprot_t hugeprot; ncontig = num_contig_ptes(sz, &pgsize); if (!pte_present(pte)) { for (i = 0; i < ncontig; i++, ptep++, addr += pgsize) __set_ptes(mm, addr, ptep, pte, 1); return; } if (!pte_cont(pte)) { __set_ptes(mm, addr, ptep, pte, 1); return; } pfn = pte_pfn(pte); dpfn = pgsize >> PAGE_SHIFT; hugeprot = pte_pgprot(pte); clear_flush(mm, addr, ptep, pgsize, ncontig); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); p4dp = p4d_alloc(mm, pgdp, addr); if (!p4dp) return NULL; pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; if (sz == PUD_SIZE) { ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); if (!pmdp) return NULL; WARN_ON(addr & (sz - 1)); ptep = pte_alloc_huge(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (CONT_PMD_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); return (pte_t *)pmdp; } return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp, pud; pmd_t *pmdp, pmd; pgdp = pgd_offset(mm, addr); if (!pgd_present(READ_ONCE(*pgdp))) return NULL; p4dp = p4d_offset(pgdp, addr); if (!p4d_present(READ_ONCE(*p4dp))) return NULL; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) return pte_offset_huge(pmdp, (addr & CONT_PTE_MASK)); return NULL; } unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); switch (hp_size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return PGDIR_SIZE - PUD_SIZE; #endif case CONT_PMD_SIZE: return PUD_SIZE - CONT_PMD_SIZE; case PMD_SIZE: return PUD_SIZE - PMD_SIZE; case CONT_PTE_SIZE: return PMD_SIZE - CONT_PTE_SIZE; default: break; } return 0UL; } pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { size_t pagesize = 1UL << shift; entry = pte_mkhuge(entry); if (pagesize == CONT_PTE_SIZE) { entry = pte_mkcont(entry); } else if (pagesize == CONT_PMD_SIZE) { entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); } return entry; } void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { int i, ncontig; size_t pgsize; ncontig = num_contig_ptes(sz, &pgsize); for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __pte_clear(mm, addr, ptep); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_cont(orig_pte)) return __ptep_get_and_clear(mm, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig(mm, addr, ptep, pgsize, ncontig); } /* * huge_ptep_set_access_flags will update access flags (dirty, accesssed) * and write permission. * * For a contiguous huge pte range we need to check whether or not write * permission has to change only on the first pte in the set. Then for * all the contiguous ptes we need to check whether or not there is a * discrepancy between dirty or young. */ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) { int i; if (pte_write(pte) != pte_write(__ptep_get(ptep))) return 1; for (i = 0; i < ncontig; i++) { pte_t orig_pte = __ptep_get(ptep + i); if (pte_dirty(pte) != pte_dirty(orig_pte)) return 1; if (pte_young(pte) != pte_young(orig_pte)) return 1; } return 0; } int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; struct mm_struct *mm = vma->vm_mm; pgprot_t hugeprot; pte_t orig_pte; if (!pte_cont(pte)) return __ptep_set_access_flags(vma, addr, ptep, pte, dirty); ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; if (!__cont_access_flags_changed(ptep, pte, ncontig)) return 0; orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); if (pte_young(orig_pte)) pte = pte_mkyoung(pte); hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long pfn, dpfn; pgprot_t hugeprot; int ncontig, i; size_t pgsize; pte_t pte; if (!pte_cont(__ptep_get(ptep))) { __ptep_set_wrprotect(mm, addr, ptep); return; } ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); pte = pte_wrprotect(pte); hugeprot = pte_pgprot(pte); pfn = pte_pfn(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { struct mm_struct *mm = vma->vm_mm; size_t pgsize; int ncontig; if (!pte_cont(__ptep_get(ptep))) return ptep_clear_flush(vma, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); } static int __init hugetlbpage_init(void) { if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT); return 0; } arch_initcall(hugetlbpage_init); bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ if (pte_user_exec(__ptep_get(ptep))) return huge_ptep_clear_flush(vma, addr, ptep); } return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } |
| 300 300 300 300 300 300 300 301 301 301 300 301 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/page_ext.h> #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/kmemleak.h> #include <linux/page_owner.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> #include <linux/pgalloc_tag.h> /* * struct page extension * * This is the feature to manage memory for extended data per page. * * Until now, we must modify struct page itself to store extra data per page. * This requires rebuilding the kernel and it is really time consuming process. * And, sometimes, rebuild is impossible due to third party module dependency. * At last, enlarging struct page could cause un-wanted system behaviour change. * * This feature is intended to overcome above mentioned problems. This feature * allocates memory for extended data per page in certain place rather than * the struct page itself. This memory can be accessed by the accessor * functions provided by this code. During the boot process, it checks whether * allocation of huge chunk of memory is needed or not. If not, it avoids * allocating memory at all. With this advantage, we can include this feature * into the kernel in default and can avoid rebuild and solve related problems. * * To help these things to work well, there are two callbacks for clients. One * is the need callback which is mandatory if user wants to avoid useless * memory allocation at boot-time. The other is optional, init callback, which * is used to do proper initialization after memory is allocated. * * The need callback is used to decide whether extended memory allocation is * needed or not. Sometimes users want to deactivate some features in this * boot and extra memory would be unnecessary. In this case, to avoid * allocating huge chunk of memory, each clients represent their need of * extra memory through the need callback. If one of the need callbacks * returns true, it means that someone needs extra memory so that * page extension core should allocates memory for page extension. If * none of need callbacks return true, memory isn't needed at all in this boot * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * * When need callback returns true, page_ext checks if there is a request for * extra memory through size in struct page_ext_operations. If it is non-zero, * extra space is allocated for each page_ext entry and offset is returned to * user through offset in struct page_ext_operations. * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime * of memory for page extension isn't same with memmap for struct page. * Therefore, clients can't store extra data until page extension is * initialized, even if pages are allocated and used freely. This could * cause inadequate state of extra data per page, so, to prevent it, client * can utilize this callback to initialize the state of it correctly. */ #ifdef CONFIG_SPARSEMEM #define PAGE_EXT_INVALID (0x1) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) static bool need_page_idle(void) { return true; } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, .need_shared_flags = true, }; #endif static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif #ifdef CONFIG_MEM_ALLOC_PROFILING &page_alloc_tagging_ops, #endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif }; unsigned long page_ext_size; static unsigned long total_usage; #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG /* * To ensure correct allocation tagging for pages, page_ext should be available * before the first page allocation. Otherwise early task stacks will be * allocated before page_ext initialization and missing tags will be flagged. */ bool early_page_ext __meminitdata = true; #else bool early_page_ext __meminitdata; #endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; return 0; } early_param("early_page_ext", setup_early_page_ext); static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); bool need = false; for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { if (page_ext_ops[i]->need_shared_flags) { page_ext_size = sizeof(struct page_ext); break; } } } for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; } } return need; } static void __init invoke_init_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); for (i = 0; i < entries; i++) { if (page_ext_ops[i]->init) page_ext_ops[i]->init(); } } static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } #ifndef CONFIG_SPARSEMEM void __init page_ext_init_flatmem_late(void) { invoke_init_callbacks(); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { pgdat->node_page_ext = NULL; } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned long index; struct page_ext *base; WARN_ON_ONCE(!rcu_read_lock_held()); base = NODE_DATA(page_to_nid(page))->node_page_ext; /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (unlikely(!base)) return NULL; index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) { struct page_ext *base; unsigned long table_size; unsigned long nr_pages; nr_pages = NODE_DATA(nid)->node_spanned_pages; if (!nr_pages) return 0; /* * Need extra space if node range is not aligned with * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm * checks buddy's status, range could be out of exact node range. */ if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } void __init page_ext_init_flatmem(void) { int nid, fail; if (!invoke_need_callbacks()) return; for_each_online_node(nid) { fail = alloc_node_page_ext(nid); if (fail) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); return; fail: pr_crit("allocation of page_ext failed.\n"); panic("Out of memory"); } #else /* CONFIG_SPARSEMEM */ static bool page_ext_invalid(struct page_ext *page_ext) { return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID); } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); struct page_ext *page_ext = READ_ONCE(section->page_ext); WARN_ON_ONCE(!rcu_read_lock_held()); /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (page_ext_invalid(page_ext)) return NULL; return get_entry(page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) { gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; void *addr = NULL; addr = alloc_pages_exact_nid(nid, size, flags); if (addr) kmemleak_alloc(addr, size, 1, flags); else addr = vzalloc_node(size, nid); if (addr) { mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, DIV_ROUND_UP(size, PAGE_SIZE)); } return addr; } static int __meminit init_section_page_ext(unsigned long pfn, int nid) { struct mem_section *section; struct page_ext *base; unsigned long table_size; section = __pfn_to_section(pfn); if (section->page_ext) return 0; table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* * The value stored in section->page_ext is (base - pfn) * and it does not point to the memory block allocated above, * causing kmemleak false positives. */ kmemleak_not_leak(base); if (!base) { pr_err("page ext allocation failure\n"); return -ENOMEM; } /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } static void free_page_ext(void *addr) { size_t table_size; struct page *page; struct pglist_data *pgdat; table_size = page_ext_size * PAGES_PER_SECTION; if (is_vmalloc_addr(addr)) { page = vmalloc_to_page(addr); pgdat = page_pgdat(page); vfree(addr); } else { page = virt_to_page(addr); pgdat = page_pgdat(page); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } mod_node_page_state(pgdat, NR_MEMMAP, -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); } static void __free_page_ext(unsigned long pfn) { struct mem_section *ms; struct page_ext *base; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; base = READ_ONCE(ms->page_ext); /* * page_ext here can be valid while doing the roll back * operation in online_page_ext(). */ if (page_ext_invalid(base)) base = (void *)base - PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, NULL); base = get_entry(base, pfn); free_page_ext(base); } static void __invalidate_page_ext(unsigned long pfn) { struct mem_section *ms; void *val; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; val = (void *)ms->page_ext + PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, val); } static int __meminit online_page_ext(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; int fail = 0; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) fail = init_section_page_ext(pfn, nid); if (!fail) return 0; /* rollback */ end = pfn - PAGES_PER_SECTION; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); return -ENOMEM; } static void __meminit offline_page_ext(unsigned long start_pfn, unsigned long nr_pages) { unsigned long start, end, pfn; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); /* * Freeing of page_ext is done in 3 steps to avoid * use-after-free of it: * 1) Traverse all the sections and mark their page_ext * as invalid. * 2) Wait for all the existing users of page_ext who * started before invalidation to finish. * 3) Free the page_ext. */ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __invalidate_page_ext(pfn); synchronize_rcu(); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); } static int __meminit page_ext_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; int ret = 0; switch (action) { case MEM_GOING_ONLINE: ret = online_page_ext(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; case MEM_OFFLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_CANCEL_ONLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } return notifier_from_errno(ret); } void __init page_ext_init(void) { unsigned long pfn; int nid; if (!invoke_need_callbacks()) return; for_each_node_state(nid, N_MEMORY) { unsigned long start_pfn, end_pfn; start_pfn = node_start_pfn(nid); end_pfn = node_end_pfn(nid); /* * start_pfn and end_pfn may not be aligned to SECTION and the * page->flags of out of node pages are not initialized. So we * scan [start_pfn, the biggest section's pfn < end_pfn) here. */ for (pfn = start_pfn; pfn < end_pfn; pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { if (!pfn_valid(pfn)) continue; /* * Nodes's pfns can be overlapping. * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... */ if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; cond_resched(); } } hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; oom: panic("Out of memory"); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { } #endif /** * page_ext_get() - Get the extended information for a page. * @page: The page we're interested in. * * Ensures that the page_ext will remain valid until page_ext_put() * is called. * * Return: NULL if no page_ext exists for this page. * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; rcu_read_lock(); page_ext = lookup_page_ext(page); if (!page_ext) { rcu_read_unlock(); return NULL; } return page_ext; } /** * page_ext_put() - Working with page extended information is done. * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. * * Return: None. * Context: Any context with corresponding page_ext_get() is called. */ void page_ext_put(struct page_ext *page_ext) { if (unlikely(!page_ext)) return; rcu_read_unlock(); } |
| 23 23 23 23 23 23 23 23 6 25 6 7 5 21 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/coproc.h * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__ #define __ARM64_KVM_SYS_REGS_LOCAL_H__ #include <linux/bsearch.h> #define reg_to_encoding(x) \ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) struct sys_reg_params { u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; u64 regval; bool is_write; }; #define encoding_to_params(reg) \ ((struct sys_reg_params){ .Op0 = sys_reg_Op0(reg), \ .Op1 = sys_reg_Op1(reg), \ .CRn = sys_reg_CRn(reg), \ .CRm = sys_reg_CRm(reg), \ .Op2 = sys_reg_Op2(reg) }) #define esr_sys64_to_params(esr) \ ((struct sys_reg_params){ .Op0 = ((esr) >> 20) & 3, \ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) #define esr_cp1x_32_to_params(esr) \ ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, struct sys_reg_params *, const struct sys_reg_desc *); /* * Initialization for vcpu. Return initialized value, or KVM * sanitized value for ID registers. */ u64 (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *); /* Index into sys_reg[], or 0 if we don't need to save it. */ int reg; /* Value (usually reset value), or write mask for idregs */ u64 val; /* Custom get/set_user functions, fallback to generic if NULL */ int (*get_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val); int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val); /* Return mask of REG_* runtime visibility overrides */ unsigned int (*visibility)(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd); }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ #define REG_HIDDEN_USER (1 << 1) /* hidden from userspace only */ #define REG_RAZ (1 << 2) /* RAZ from userspace and guest */ #define REG_USER_WI (1 << 3) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, char *fmt, ...) { va_list va; va_start(va, fmt); /* Look, we even formatted it for you to paste into the table! */ kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", &(struct va_format){ fmt, &va }, p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); va_end(va); } static inline void print_sys_reg_instr(const struct sys_reg_params *p) { /* GCC warns on an empty format string */ print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, const struct sys_reg_params *p) { return true; } static inline bool read_zero(struct kvm_vcpu *vcpu, struct sys_reg_params *p) { p->regval = 0; return true; } /* Reset functions */ static inline u64 reset_unknown(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL; return __vcpu_sys_reg(vcpu, r->reg); } static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = r->val; return __vcpu_sys_reg(vcpu, r->reg); } static inline unsigned int sysreg_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return 0; return r->visibility(vcpu, r); } static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_HIDDEN; } static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER); } static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_RAZ; } static inline bool sysreg_user_write_ignore(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_USER_WI; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, const struct sys_reg_desc *i2) { BUG_ON(i1 == i2); if (!i1) return 1; else if (!i2) return -1; if (i1->Op0 != i2->Op0) return i1->Op0 - i2->Op0; if (i1->Op1 != i2->Op1) return i1->Op1 - i2->Op1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; return i1->Op2 - i2->Op2; } static inline int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; const struct sys_reg_desc *r = elt; return pval - reg_to_encoding(r); } static inline const struct sys_reg_desc * find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[], unsigned int num) { unsigned long pval = reg_to_encoding(params); return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg); } const struct sys_reg_desc *get_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num); int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index); #define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x #define Op2(_x) .Op2 = _x #define SYS_DESC(reg) \ .name = #reg, \ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ |
| 455 10 87 455 452 455 454 455 416 163 323 323 234 321 282 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS 0x1 // Task needs a quiescent state. #define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); void rcu_tasks_trace_qs_blkd(struct task_struct *t); # define rcu_tasks_trace_qs(t) \ do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static inline bool lockdep_assert_rcu_helper(bool c) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible())) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() do { } while (0) #define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) #define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) #define lockdep_assert_in_rcu_reader() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)); \ }) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also * wait for regions of code with preemption disabled, including regions of * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which * define synchronize_sched(), only code enclosed within rcu_read_lock() * and rcu_read_unlock() are guaranteed to be waited for. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * In recent kernels that have consolidated synchronize_sched() and * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity * also extends to the scheduler's runqueue and priority-inheritance * spinlocks, courtesy of the quiescent-state deferral that is carried * out when rcu_read_unlock() is invoked with interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc() or * kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { rcu_read_lock(); /* * sparse doesn't call the cleanup function, * so just release immediately and don't track * the context. We don't need to anyway, since * the whole point of the guard is to not need * the explicit unlock. */ __release(RCU); } while (0), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ |
| 167 170 170 163 155 62 170 170 169 218 167 170 167 217 18 18 167 167 167 62 62 155 12 12 155 10 168 168 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path; /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; path = &file->f_path; /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ if (mask & ALL_FSNOTIFY_PERM_EVENTS && !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, FSNOTIFY_PRIO_CONTENT)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { __u32 fsnotify_mask = FS_ACCESS_PERM; /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & MAY_READ)) return 0; return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_file_perm - permission hook before file access */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } /* * fsnotify_open_perm - permission hook before file open */ static inline int fsnotify_open_perm(struct file *file) { int ret; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } return fsnotify_file(file, FS_OPEN_PERM); } #else static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } static inline int fsnotify_open_perm(struct file *file) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 288 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ #define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ /** * __ffs - find first bit in word. * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ static __always_inline unsigned int __ffs(unsigned long word) { return __builtin_ctzl(word); } #endif |
| 162 162 162 162 162 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGALLOC_TRACK_H #define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pgd_none(*pgd))) { if (__p4d_alloc(mm, pgd, address)) return NULL; *mod_mask |= PGTBL_PGD_MODIFIED; } return p4d_offset(pgd, address); } static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(p4d_none(*p4d))) { if (__pud_alloc(mm, p4d, address)) return NULL; *mod_mask |= PGTBL_P4D_MODIFIED; } return pud_offset(p4d, address); } static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pud_none(*pud))) { if (__pmd_alloc(mm, pud, address)) return NULL; *mod_mask |= PGTBL_PUD_MODIFIED; } return pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #define pte_alloc_kernel_track(pmd, address, mask) \ ((unlikely(pmd_none(*(pmd))) && \ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) #endif /* _LINUX_PGALLOC_TRACK_H */ |
| 154 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif #define PERF_GUEST_ACTIVE 0x01 #define PERF_GUEST_USER 0x02 struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/rhashtable-types.h> #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ #define PERF_EVENT_FLAG_ARCH 0x000fffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_pmu_context __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 struct bpf_prog; struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; /* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING #define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else #define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; struct rcuwait pending_work_wait; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie; #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; /* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ __u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; /* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx; struct list_head pmu_ctx_entry; struct list_head pinned_active; struct list_head flexible_active; /* Used to avoid freeing per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; void *task_ctx_data; /* pmu specific data */ /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary; }; static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) { return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); } struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_user; int is_active; int nr_task_data; int nr_stat; int nr_freq; int rotate_disable; refcount_t refcount; /* event <-> ctx */ struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif struct rcu_head rcu_head; /* * Sum (event->pending_work + event->pending_work) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_pending; }; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; struct list_head sched_cb_entry; int sched_cb_usage; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; #endif /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); static inline bool branch_sample_no_flags(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; } static inline bool branch_sample_no_cycles(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; } static inline bool branch_sample_type(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; } static inline bool branch_sample_hw_index(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; } static inline bool branch_sample_priv(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } static inline bool branch_sample_counters(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; } static inline bool branch_sample_call_stack(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size; /* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0; if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; } } static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { int size = 1; data->callchain = perf_callchain(event, regs); size += data->callchain->nr; data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN; } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1); size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum; data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW; } static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr) { int size = sizeof(u64); /* nr */ if (branch_sample_hw_index(event)) size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); /* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64); data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event) { u32 size = sizeof(struct perf_event_header); size += event->header_size + event->id_header_size; size += data->dyn_size; return size; } /* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { perf_overflow_handler_t overflow_handler = event->overflow_handler; if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); #else static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } #endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) { /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR_SHOW(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ #define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); /* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */ /* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); #ifndef PERF_NEEDS_LOPWR_CB static inline void perf_lopwr_cb(bool mode) { } #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 153 147 153 153 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * * Based on arch/arm/kernel/jump_label.c */ #include <linux/kernel.h> #include <linux/jump_label.h> #include <linux/smp.h> #include <asm/insn.h> #include <asm/patching.h> bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { void *addr = (void *)jump_entry_code(entry); u32 insn; if (type == JUMP_LABEL_JMP) { insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry), jump_entry_target(entry), AARCH64_INSN_BRANCH_NOLINK); } else { insn = aarch64_insn_gen_nop(); } aarch64_insn_patch_text_nosync(addr, insn); return true; } void arch_jump_label_transform_apply(void) { kick_all_cpus_sync(); } |
| 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" #include "internal.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) { struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } /* Data lost, invalid, or otherwise unavailable. */ return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */ static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq; /* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */ return __ulseq_to_u64seq(rb, ulseq); } static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count); /* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */ static void desc_update_last_finalized(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq; try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1; /* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; } /* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return; oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq); /* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; } } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); } } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); desc_update_last_finalized(e->rb); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err; /* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */ try_again: last_finalized_seq = desc_last_finalized_seq(rb); /* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var; /* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var)); /* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0; /* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } } /* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id; /* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1); } /* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless it is * at or beyond the head, in which case it is not * possible to continue. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) (*seq)++; else return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq; seq = desc_last_finalized_seq(rb); /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 34 13 34 34 34 34 34 34 34 13 34 13 34 34 34 34 34 13 13 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 | /* * * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * Cgroup v2 * Copyright (C) 2019 Red Hat, Inc. * Author: Giuseppe Scrivano <gscrivan@redhat.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #include <linux/cgroup.h> #include <linux/page_counter.h> #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) /* Use t->m[0] to encode the offset */ #define MEMFILE_OFFSET(t, m0) (((offsetof(t, m0) << 16) | sizeof_field(t, m0))) #define MEMFILE_OFFSET0(val) (((val) >> 16) & 0xffff) #define MEMFILE_FIELD_SIZE(val) ((val) & 0xffff) #define DFL_TMPL_SIZE ARRAY_SIZE(hugetlb_dfl_tmpl) #define LEGACY_TMPL_SIZE ARRAY_SIZE(hugetlb_legacy_tmpl) static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static struct cftype *dfl_files; static struct cftype *legacy_files; static inline struct page_counter * __hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx, bool rsvd) { if (rsvd) return &h_cg->rsvd_hugepage[idx]; return &h_cg->hugepage[idx]; } static inline struct page_counter * hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx) { return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, false); } static inline struct page_counter * hugetlb_cgroup_counter_from_cgroup_rsvd(struct hugetlb_cgroup *h_cg, int idx) { return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, true); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) { return (h_cg == root_h_cgroup); } static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { return hugetlb_cgroup_from_css(h_cg->css.parent); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) { struct hstate *h; for_each_hstate(h) { if (page_counter_read( hugetlb_cgroup_counter_from_cgroup(h_cg, hstate_index(h)))) return true; } return false; } static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, struct hugetlb_cgroup *parent_h_cgroup) { int idx; for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { struct page_counter *fault_parent = NULL; struct page_counter *rsvd_parent = NULL; unsigned long limit; int ret; if (parent_h_cgroup) { fault_parent = hugetlb_cgroup_counter_from_cgroup( parent_h_cgroup, idx); rsvd_parent = hugetlb_cgroup_counter_from_cgroup_rsvd( parent_h_cgroup, idx); } page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), fault_parent); page_counter_init( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), rsvd_parent); limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); ret = page_counter_set_max( hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), limit); VM_BUG_ON(ret); ret = page_counter_set_max( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), limit); VM_BUG_ON(ret); } } static void hugetlb_cgroup_free(struct hugetlb_cgroup *h_cgroup) { int node; for_each_node(node) kfree(h_cgroup->nodeinfo[node]); kfree(h_cgroup); } static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; int node; h_cgroup = kzalloc(struct_size(h_cgroup, nodeinfo, nr_node_ids), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); if (!parent_h_cgroup) root_h_cgroup = h_cgroup; /* * TODO: this routine can waste much memory for nodes which will * never be onlined. It's better to use memory hotplug callback * function. */ for_each_node(node) { /* Set node_to_alloc to NUMA_NO_NODE for offline nodes. */ int node_to_alloc = node_state(node, N_NORMAL_MEMORY) ? node : NUMA_NO_NODE; h_cgroup->nodeinfo[node] = kzalloc_node(sizeof(struct hugetlb_cgroup_per_node), GFP_KERNEL, node_to_alloc); if (!h_cgroup->nodeinfo[node]) goto fail_alloc_nodeinfo; } hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; fail_alloc_nodeinfo: hugetlb_cgroup_free(h_cgroup); return ERR_PTR(-ENOMEM); } static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { hugetlb_cgroup_free(hugetlb_cgroup_from_css(css)); } /* * Should be called with hugetlb_lock held. * Since we are holding hugetlb_lock, pages cannot get moved from * active list or uncharged from the cgroup, So no need to get * page reference and test for page active here. This function * cannot fail. */ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page *page) { unsigned int nr_pages; struct page_counter *counter; struct hugetlb_cgroup *page_hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); struct folio *folio = page_folio(page); page_hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely * ignore those pages. */ if (!page_hcg || page_hcg != h_cg) goto out; nr_pages = compound_nr(page); if (!parent) { parent = root_h_cgroup; /* root has no limit */ page_counter_charge(&parent->hugepage[idx], nr_pages); } counter = &h_cg->hugepage[idx]; /* Take the pages off the local counter */ page_counter_cancel(counter, nr_pages); set_hugetlb_cgroup(folio, parent); out: return; } /* * Force the hugetlb cgroup to empty the hugetlb resources by moving them to * the parent cgroup. */ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; do { for_each_hstate(h) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) hugetlb_cgroup_move_parent(hstate_index(h), h_cg, page); spin_unlock_irq(&hugetlb_lock); } cond_resched(); } while (hugetlb_cgroup_have_usage(h_cg)); } static inline void hugetlb_event(struct hugetlb_cgroup *hugetlb, int idx, enum hugetlb_memory_event event) { atomic_long_inc(&hugetlb->events_local[idx][event]); cgroup_file_notify(&hugetlb->events_local_file[idx]); do { atomic_long_inc(&hugetlb->events[idx][event]); cgroup_file_notify(&hugetlb->events_file[idx]); } while ((hugetlb = parent_hugetlb_cgroup(hugetlb)) && !hugetlb_cgroup_is_root(hugetlb)); } static int __hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr, bool rsvd) { int ret = 0; struct page_counter *counter; struct hugetlb_cgroup *h_cg = NULL; if (hugetlb_cgroup_disabled()) goto done; again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); if (!css_tryget(&h_cg->css)) { rcu_read_unlock(); goto again; } rcu_read_unlock(); if (!page_counter_try_charge( __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages, &counter)) { ret = -ENOMEM; hugetlb_event(h_cg, idx, HUGETLB_MAX); css_put(&h_cg->css); goto done; } /* Reservations take a reference to the css because they do not get * reparented. */ if (!rsvd) css_put(&h_cg->css); done: *ptr = h_cg; return ret; } int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, false); } int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, true); } /* Should be called with hugetlb_lock held */ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio, bool rsvd) { if (hugetlb_cgroup_disabled() || !h_cg) return; lockdep_assert_held(&hugetlb_lock); __set_hugetlb_cgroup(folio, h_cg, rsvd); if (!rsvd) { unsigned long usage = h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage + nr_pages); } } void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, false); } void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, true); } /* * Should be called with hugetlb_lock held */ static void __hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio, bool rsvd) { struct hugetlb_cgroup *h_cg; if (hugetlb_cgroup_disabled()) return; lockdep_assert_held(&hugetlb_lock); h_cg = __hugetlb_cgroup_from_folio(folio, rsvd); if (unlikely(!h_cg)) return; __set_hugetlb_cgroup(folio, NULL, rsvd); page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); if (rsvd) css_put(&h_cg->css); else { unsigned long usage = h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage - nr_pages); } } void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio) { __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, false); } void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio) { __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, true); } static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, bool rsvd) { if (hugetlb_cgroup_disabled() || !h_cg) return; page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); if (rsvd) css_put(&h_cg->css); } void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, false); } void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, true); } void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end) { if (hugetlb_cgroup_disabled() || !resv || !resv->reservation_counter || !resv->css) return; page_counter_uncharge(resv->reservation_counter, (end - start) * resv->pages_per_hpage); css_put(resv->css); } void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; if (rg->reservation_counter && resv->pages_per_hpage && !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); /* * Only do css_put(rg->css) when we delete the entire region * because one file_region must hold exactly one css reference. */ if (region_del) css_put(rg->css); } } enum { RES_USAGE, RES_RSVD_USAGE, RES_LIMIT, RES_RSVD_LIMIT, RES_MAX_USAGE, RES_RSVD_MAX_USAGE, RES_FAILCNT, RES_RSVD_FAILCNT, }; static int hugetlb_cgroup_read_numa_stat(struct seq_file *seq, void *dummy) { int nid; struct cftype *cft = seq_cft(seq); int idx = MEMFILE_IDX(cft->private); bool legacy = !cgroup_subsys_on_dfl(hugetlb_cgrp_subsys); struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); struct cgroup_subsys_state *css; unsigned long usage; if (legacy) { /* Add up usage across all nodes for the non-hierarchical total. */ usage = 0; for_each_node_state(nid, N_MEMORY) usage += READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]); seq_printf(seq, "total=%lu", usage * PAGE_SIZE); /* Simply print the per-node usage for the non-hierarchical total. */ for_each_node_state(nid, N_MEMORY) seq_printf(seq, " N%d=%lu", nid, READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]) * PAGE_SIZE); seq_putc(seq, '\n'); } /* * The hierarchical total is pretty much the value recorded by the * counter, so use that. */ seq_printf(seq, "%stotal=%lu", legacy ? "hierarchical_" : "", page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE); /* * For each node, transverse the css tree to obtain the hierarchical * node usage. */ for_each_node_state(nid, N_MEMORY) { usage = 0; rcu_read_lock(); css_for_each_descendant_pre(css, &h_cg->css) { usage += READ_ONCE(hugetlb_cgroup_from_css(css) ->nodeinfo[nid] ->usage[idx]); } rcu_read_unlock(); seq_printf(seq, " N%d=%lu", nid, usage * PAGE_SIZE); } seq_putc(seq, '\n'); return 0; } static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct page_counter *counter; struct page_counter *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(cft->private)]; switch (MEMFILE_ATTR(cft->private)) { case RES_USAGE: return (u64)page_counter_read(counter) * PAGE_SIZE; case RES_RSVD_USAGE: return (u64)page_counter_read(rsvd_counter) * PAGE_SIZE; case RES_LIMIT: return (u64)counter->max * PAGE_SIZE; case RES_RSVD_LIMIT: return (u64)rsvd_counter->max * PAGE_SIZE; case RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE; case RES_RSVD_MAX_USAGE: return (u64)rsvd_counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; case RES_RSVD_FAILCNT: return rsvd_counter->failcnt; default: BUG(); } } static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v) { int idx; u64 val; struct cftype *cft = seq_cft(seq); unsigned long limit; struct page_counter *counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); idx = MEMFILE_IDX(cft->private); counter = &h_cg->hugepage[idx]; limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); switch (MEMFILE_ATTR(cft->private)) { case RES_RSVD_USAGE: counter = &h_cg->rsvd_hugepage[idx]; fallthrough; case RES_USAGE: val = (u64)page_counter_read(counter); seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; case RES_RSVD_LIMIT: counter = &h_cg->rsvd_hugepage[idx]; fallthrough; case RES_LIMIT: val = (u64)counter->max; if (val == limit) seq_puts(seq, "max\n"); else seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; default: BUG(); } return 0; } static DEFINE_MUTEX(hugetlb_limit_mutex); static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, const char *max) { int ret, idx; unsigned long nr_pages; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); bool rsvd = false; if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ return -EINVAL; buf = strstrip(buf); ret = page_counter_memparse(buf, max, &nr_pages); if (ret) return ret; idx = MEMFILE_IDX(of_cft(of)->private); nr_pages = round_down(nr_pages, pages_per_huge_page(&hstates[idx])); switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_RSVD_LIMIT: rsvd = true; fallthrough; case RES_LIMIT: mutex_lock(&hugetlb_limit_mutex); ret = page_counter_set_max( __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); mutex_unlock(&hugetlb_limit_mutex); break; default: ret = -EINVAL; break; } return ret ?: nbytes; } static ssize_t hugetlb_cgroup_write_legacy(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return hugetlb_cgroup_write(of, buf, nbytes, off, "-1"); } static ssize_t hugetlb_cgroup_write_dfl(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return hugetlb_cgroup_write(of, buf, nbytes, off, "max"); } static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret = 0; struct page_counter *counter, *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(of_cft(of)->private)]; switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_MAX_USAGE: page_counter_reset_watermark(counter); break; case RES_RSVD_MAX_USAGE: page_counter_reset_watermark(rsvd_counter); break; case RES_FAILCNT: counter->failcnt = 0; break; case RES_RSVD_FAILCNT: rsvd_counter->failcnt = 0; break; default: ret = -EINVAL; break; } return ret ?: nbytes; } static char *mem_fmt(char *buf, int size, unsigned long hsize) { if (hsize >= SZ_1G) snprintf(buf, size, "%luGB", hsize / SZ_1G); else if (hsize >= SZ_1M) snprintf(buf, size, "%luMB", hsize / SZ_1M); else snprintf(buf, size, "%luKB", hsize / SZ_1K); return buf; } static int __hugetlb_events_show(struct seq_file *seq, bool local) { int idx; long max; struct cftype *cft = seq_cft(seq); struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); idx = MEMFILE_IDX(cft->private); if (local) max = atomic_long_read(&h_cg->events_local[idx][HUGETLB_MAX]); else max = atomic_long_read(&h_cg->events[idx][HUGETLB_MAX]); seq_printf(seq, "max %lu\n", max); return 0; } static int hugetlb_events_show(struct seq_file *seq, void *v) { return __hugetlb_events_show(seq, false); } static int hugetlb_events_local_show(struct seq_file *seq, void *v) { return __hugetlb_events_show(seq, true); } static struct cftype hugetlb_dfl_tmpl[] = { { .name = "max", .private = RES_LIMIT, .seq_show = hugetlb_cgroup_read_u64_max, .write = hugetlb_cgroup_write_dfl, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "rsvd.max", .private = RES_RSVD_LIMIT, .seq_show = hugetlb_cgroup_read_u64_max, .write = hugetlb_cgroup_write_dfl, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .private = RES_USAGE, .seq_show = hugetlb_cgroup_read_u64_max, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "rsvd.current", .private = RES_RSVD_USAGE, .seq_show = hugetlb_cgroup_read_u64_max, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events", .seq_show = hugetlb_events_show, .file_offset = MEMFILE_OFFSET(struct hugetlb_cgroup, events_file[0]), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events.local", .seq_show = hugetlb_events_local_show, .file_offset = MEMFILE_OFFSET(struct hugetlb_cgroup, events_local_file[0]), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "numa_stat", .seq_show = hugetlb_cgroup_read_numa_stat, .flags = CFTYPE_NOT_ON_ROOT, }, /* don't need terminator here */ }; static struct cftype hugetlb_legacy_tmpl[] = { { .name = "limit_in_bytes", .private = RES_LIMIT, .read_u64 = hugetlb_cgroup_read_u64, .write = hugetlb_cgroup_write_legacy, }, { .name = "rsvd.limit_in_bytes", .private = RES_RSVD_LIMIT, .read_u64 = hugetlb_cgroup_read_u64, .write = hugetlb_cgroup_write_legacy, }, { .name = "usage_in_bytes", .private = RES_USAGE, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.usage_in_bytes", .private = RES_RSVD_USAGE, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "max_usage_in_bytes", .private = RES_MAX_USAGE, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.max_usage_in_bytes", .private = RES_RSVD_MAX_USAGE, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "failcnt", .private = RES_FAILCNT, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.failcnt", .private = RES_RSVD_FAILCNT, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "numa_stat", .seq_show = hugetlb_cgroup_read_numa_stat, }, /* don't need terminator here */ }; static void __init hugetlb_cgroup_cfttypes_init(struct hstate *h, struct cftype *cft, struct cftype *tmpl, int tmpl_size) { char buf[32]; int i, idx = hstate_index(h); /* format the size */ mem_fmt(buf, sizeof(buf), huge_page_size(h)); for (i = 0; i < tmpl_size; cft++, tmpl++, i++) { *cft = *tmpl; /* rebuild the name */ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.%s", buf, tmpl->name); /* rebuild the private */ cft->private = MEMFILE_PRIVATE(idx, tmpl->private); /* rebuild the file_offset */ if (tmpl->file_offset) { unsigned int offset = tmpl->file_offset; cft->file_offset = MEMFILE_OFFSET0(offset) + MEMFILE_FIELD_SIZE(offset) * idx; } lockdep_register_key(&cft->lockdep_key); } } static void __init __hugetlb_cgroup_file_dfl_init(struct hstate *h) { int idx = hstate_index(h); hugetlb_cgroup_cfttypes_init(h, dfl_files + idx * DFL_TMPL_SIZE, hugetlb_dfl_tmpl, DFL_TMPL_SIZE); } static void __init __hugetlb_cgroup_file_legacy_init(struct hstate *h) { int idx = hstate_index(h); hugetlb_cgroup_cfttypes_init(h, legacy_files + idx * LEGACY_TMPL_SIZE, hugetlb_legacy_tmpl, LEGACY_TMPL_SIZE); } static void __init __hugetlb_cgroup_file_init(struct hstate *h) { __hugetlb_cgroup_file_dfl_init(h); __hugetlb_cgroup_file_legacy_init(h); } static void __init __hugetlb_cgroup_file_pre_init(void) { int cft_count; cft_count = hugetlb_max_hstate * DFL_TMPL_SIZE + 1; /* add terminator */ dfl_files = kcalloc(cft_count, sizeof(struct cftype), GFP_KERNEL); BUG_ON(!dfl_files); cft_count = hugetlb_max_hstate * LEGACY_TMPL_SIZE + 1; /* add terminator */ legacy_files = kcalloc(cft_count, sizeof(struct cftype), GFP_KERNEL); BUG_ON(!legacy_files); } static void __init __hugetlb_cgroup_file_post_init(void) { WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, dfl_files)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, legacy_files)); } void __init hugetlb_cgroup_file_init(void) { struct hstate *h; __hugetlb_cgroup_file_pre_init(); for_each_hstate(h) __hugetlb_cgroup_file_init(h); __hugetlb_cgroup_file_post_init(); } /* * hugetlb_lock will make sure a parallel cgroup rmdir won't happen * when we migrate hugepages */ void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { struct hugetlb_cgroup *h_cg; struct hugetlb_cgroup *h_cg_rsvd; struct hstate *h = folio_hstate(old_folio); if (hugetlb_cgroup_disabled()) return; spin_lock_irq(&hugetlb_lock); h_cg = hugetlb_cgroup_from_folio(old_folio); h_cg_rsvd = hugetlb_cgroup_from_folio_rsvd(old_folio); set_hugetlb_cgroup(old_folio, NULL); set_hugetlb_cgroup_rsvd(old_folio, NULL); /* move the h_cg details to new cgroup */ set_hugetlb_cgroup(new_folio, h_cg); set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd); list_move(&new_folio->lru, &h->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); return; } static struct cftype hugetlb_files[] = { {} /* terminate */ }; struct cgroup_subsys hugetlb_cgrp_subsys = { .css_alloc = hugetlb_cgroup_css_alloc, .css_offline = hugetlb_cgroup_css_offline, .css_free = hugetlb_cgroup_css_free, .dfl_cftypes = hugetlb_files, .legacy_cftypes = hugetlb_files, }; |
| 8 10 9 10 8 8 7 7 4 4 4 1 1 1 5 5 4 3 20 4 4 4 4 4 4 4 4 1 1 1 1 1 2 2 2 2 1 2 2 1 1 2 2 9 1 1 2 2 2 1 1 1 1 1 1 1 1 20 19 20 5 9 9 4 4 4 4 1 1 1 1 1 1 1 2 2 2 2 2 4 1 1 1 4 4 1 1 1 4 3 2 1 3 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/guest.c: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/bits.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/nospec.h> #include <linux/kvm_host.h> #include <linux/module.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <kvm/arm_hypercalls.h> #include <asm/cputype.h> #include <linux/uaccess.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_nested.h> #include <asm/sigcontext.h> #include "trace.h" const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vm_stats_desc), }; const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, hvc_exit_stat), STATS_DESC_COUNTER(VCPU, wfe_exit_stat), STATS_DESC_COUNTER(VCPU, wfi_exit_stat), STATS_DESC_COUNTER(VCPU, mmio_exit_user), STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, exits) }; const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vcpu_stats_desc), }; static bool core_reg_offset_is_vreg(u64 off) { return off >= KVM_REG_ARM_CORE_REG(fp_regs.vregs) && off < KVM_REG_ARM_CORE_REG(fp_regs.fpsr); } static u64 core_reg_offset_from_id(u64 id) { return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { int size; switch (off) { case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... KVM_REG_ARM_CORE_REG(regs.regs[30]): case KVM_REG_ARM_CORE_REG(regs.sp): case KVM_REG_ARM_CORE_REG(regs.pc): case KVM_REG_ARM_CORE_REG(regs.pstate): case KVM_REG_ARM_CORE_REG(sp_el1): case KVM_REG_ARM_CORE_REG(elr_el1): case KVM_REG_ARM_CORE_REG(spsr[0]) ... KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): size = sizeof(__u64); break; case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): size = sizeof(__uint128_t); break; case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): size = sizeof(__u32); break; default: return -EINVAL; } if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* * The KVM_REG_ARM64_SVE regs must be used instead of * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on * SVE-enabled vcpus: */ if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; return size; } static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { u64 off = core_reg_offset_from_id(reg->id); int size = core_reg_size_from_offset(vcpu, off); if (size < 0) return NULL; if (KVM_REG_SIZE(reg->id) != size) return NULL; switch (off) { case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... KVM_REG_ARM_CORE_REG(regs.regs[30]): off -= KVM_REG_ARM_CORE_REG(regs.regs[0]); off /= 2; return &vcpu->arch.ctxt.regs.regs[off]; case KVM_REG_ARM_CORE_REG(regs.sp): return &vcpu->arch.ctxt.regs.sp; case KVM_REG_ARM_CORE_REG(regs.pc): return &vcpu->arch.ctxt.regs.pc; case KVM_REG_ARM_CORE_REG(regs.pstate): return &vcpu->arch.ctxt.regs.pstate; case KVM_REG_ARM_CORE_REG(sp_el1): return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1); case KVM_REG_ARM_CORE_REG(elr_el1): return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1); case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]): return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1); case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]): return &vcpu->arch.ctxt.spsr_abt; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]): return &vcpu->arch.ctxt.spsr_und; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]): return &vcpu->arch.ctxt.spsr_irq; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]): return &vcpu->arch.ctxt.spsr_fiq; case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]); off /= 4; return &vcpu->arch.ctxt.fp_regs.vregs[off]; case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): return &vcpu->arch.ctxt.fp_regs.fpsr; case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): return &vcpu->arch.ctxt.fp_regs.fpcr; default: return NULL; } } static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* * Because the kvm_regs structure is a mix of 32, 64 and * 128bit fields, we index it as if it was a 32bit * array. Hence below, nr_regs is the number of entries, and * off the index in the "array". */ __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); void *addr; u32 off; /* Our ID is an index into the kvm_regs struct. */ off = core_reg_offset_from_id(reg->id); if (off >= nr_regs || (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; addr = core_reg_addr(vcpu, reg); if (!addr) return -EINVAL; if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; } static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); __uint128_t tmp; void *valp = &tmp, *addr; u64 off; int err = 0; /* Our ID is an index into the kvm_regs struct. */ off = core_reg_offset_from_id(reg->id); if (off >= nr_regs || (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; addr = core_reg_addr(vcpu, reg); if (!addr) return -EINVAL; if (KVM_REG_SIZE(reg->id) > sizeof(tmp)) return -EINVAL; if (copy_from_user(valp, uaddr, KVM_REG_SIZE(reg->id))) { err = -EFAULT; goto out; } if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK; switch (mode) { case PSR_AA32_MODE_USR: if (!kvm_supports_32bit_el0()) return -EINVAL; break; case PSR_AA32_MODE_FIQ: case PSR_AA32_MODE_IRQ: case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: case PSR_AA32_MODE_SYS: if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; case PSR_MODE_EL2h: case PSR_MODE_EL2t: if (!vcpu_has_nv(vcpu)) return -EINVAL; fallthrough; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: if (vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; default: err = -EINVAL; goto out; } } memcpy(addr, valp, KVM_REG_SIZE(reg->id)); if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { int i, nr_reg; switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) { /* * Either we are dealing with user mode, and only the * first 15 registers (+ PC) must be narrowed to 32bit. * AArch32 r0-r14 conveniently map to AArch64 x0-x14. */ case PSR_AA32_MODE_USR: case PSR_AA32_MODE_SYS: nr_reg = 15; break; /* * Otherwise, this is a privileged mode, and *all* the * registers must be narrowed to 32bit. */ default: nr_reg = 31; break; } for (i = 0; i < nr_reg; i++) vcpu_set_reg(vcpu, i, (u32)vcpu_get_reg(vcpu, i)); *vcpu_pc(vcpu) = (u32)*vcpu_pc(vcpu); } out: return err; } #define vq_word(vq) (((vq) - SVE_VQ_MIN) / 64) #define vq_mask(vq) ((u64)1 << ((vq) - SVE_VQ_MIN) % 64) #define vq_present(vqs, vq) (!!((vqs)[vq_word(vq)] & vq_mask(vq))) static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { unsigned int max_vq, vq; u64 vqs[KVM_ARM64_SVE_VLS_WORDS]; if (!vcpu_has_sve(vcpu)) return -ENOENT; if (WARN_ON(!sve_vl_valid(vcpu->arch.sve_max_vl))) return -EINVAL; memset(vqs, 0, sizeof(vqs)); max_vq = vcpu_sve_max_vq(vcpu); for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq) if (sve_vq_available(vq)) vqs[vq_word(vq)] |= vq_mask(vq); if (copy_to_user((void __user *)reg->addr, vqs, sizeof(vqs))) return -EFAULT; return 0; } static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { unsigned int max_vq, vq; u64 vqs[KVM_ARM64_SVE_VLS_WORDS]; if (!vcpu_has_sve(vcpu)) return -ENOENT; if (kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; /* too late! */ if (WARN_ON(vcpu->arch.sve_state)) return -EINVAL; if (copy_from_user(vqs, (const void __user *)reg->addr, sizeof(vqs))) return -EFAULT; max_vq = 0; for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; ++vq) if (vq_present(vqs, vq)) max_vq = vq; if (max_vq > sve_vq_from_vl(kvm_sve_max_vl)) return -EINVAL; /* * Vector lengths supported by the host can't currently be * hidden from the guest individually: instead we can only set a * maximum via ZCR_EL2.LEN. So, make sure the available vector * lengths match the set requested exactly up to the requested * maximum: */ for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq) if (vq_present(vqs, vq) != sve_vq_available(vq)) return -EINVAL; /* Can't run with no vector lengths at all: */ if (max_vq < SVE_VQ_MIN) return -EINVAL; /* vcpu->arch.sve_state will be alloc'd by kvm_vcpu_finalize_sve() */ vcpu->arch.sve_max_vl = sve_vl_from_vq(max_vq); return 0; } #define SVE_REG_SLICE_SHIFT 0 #define SVE_REG_SLICE_BITS 5 #define SVE_REG_ID_SHIFT (SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS) #define SVE_REG_ID_BITS 5 #define SVE_REG_SLICE_MASK \ GENMASK(SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS - 1, \ SVE_REG_SLICE_SHIFT) #define SVE_REG_ID_MASK \ GENMASK(SVE_REG_ID_SHIFT + SVE_REG_ID_BITS - 1, SVE_REG_ID_SHIFT) #define SVE_NUM_SLICES (1 << SVE_REG_SLICE_BITS) #define KVM_SVE_ZREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_ZREG(0, 0)) #define KVM_SVE_PREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_PREG(0, 0)) /* * Number of register slices required to cover each whole SVE register. * NOTE: Only the first slice every exists, for now. * If you are tempted to modify this, you must also rework sve_reg_to_region() * to match: */ #define vcpu_sve_slices(vcpu) 1 /* Bounds of a single SVE register slice within vcpu->arch.sve_state */ struct sve_state_reg_region { unsigned int koffset; /* offset into sve_state in kernel memory */ unsigned int klen; /* length in kernel memory */ unsigned int upad; /* extra trailing padding in user memory */ }; /* * Validate SVE register ID and get sanitised bounds for user/kernel SVE * register copy */ static int sve_reg_to_region(struct sve_state_reg_region *region, struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* reg ID ranges for Z- registers */ const u64 zreg_id_min = KVM_REG_ARM64_SVE_ZREG(0, 0); const u64 zreg_id_max = KVM_REG_ARM64_SVE_ZREG(SVE_NUM_ZREGS - 1, SVE_NUM_SLICES - 1); /* reg ID ranges for P- registers and FFR (which are contiguous) */ const u64 preg_id_min = KVM_REG_ARM64_SVE_PREG(0, 0); const u64 preg_id_max = KVM_REG_ARM64_SVE_FFR(SVE_NUM_SLICES - 1); unsigned int vq; unsigned int reg_num; unsigned int reqoffset, reqlen; /* User-requested offset and length */ unsigned int maxlen; /* Maximum permitted length */ size_t sve_state_size; const u64 last_preg_id = KVM_REG_ARM64_SVE_PREG(SVE_NUM_PREGS - 1, SVE_NUM_SLICES - 1); /* Verify that the P-regs and FFR really do have contiguous IDs: */ BUILD_BUG_ON(KVM_REG_ARM64_SVE_FFR(0) != last_preg_id + 1); /* Verify that we match the UAPI header: */ BUILD_BUG_ON(SVE_NUM_SLICES != KVM_ARM64_SVE_MAX_SLICES); reg_num = (reg->id & SVE_REG_ID_MASK) >> SVE_REG_ID_SHIFT; if (reg->id >= zreg_id_min && reg->id <= zreg_id_max) { if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT; vq = vcpu_sve_max_vq(vcpu); reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; reqlen = KVM_SVE_ZREG_SIZE; maxlen = SVE_SIG_ZREG_SIZE(vq); } else if (reg->id >= preg_id_min && reg->id <= preg_id_max) { if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT; vq = vcpu_sve_max_vq(vcpu); reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; reqlen = KVM_SVE_PREG_SIZE; maxlen = SVE_SIG_PREG_SIZE(vq); } else { return -EINVAL; } sve_state_size = vcpu_sve_state_size(vcpu); if (WARN_ON(!sve_state_size)) return -EINVAL; region->koffset = array_index_nospec(reqoffset, sve_state_size); region->klen = min(maxlen, reqlen); region->upad = reqlen - region->klen; return 0; } static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { int ret; struct sve_state_reg_region region; char __user *uptr = (char __user *)reg->addr; /* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */ if (reg->id == KVM_REG_ARM64_SVE_VLS) return get_sve_vls(vcpu, reg); /* Try to interpret reg ID as an architectural SVE register... */ ret = sve_reg_to_region(®ion, vcpu, reg); if (ret) return ret; if (!kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset, region.klen) || clear_user(uptr + region.klen, region.upad)) return -EFAULT; return 0; } static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { int ret; struct sve_state_reg_region region; const char __user *uptr = (const char __user *)reg->addr; /* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */ if (reg->id == KVM_REG_ARM64_SVE_VLS) return set_sve_vls(vcpu, reg); /* Try to interpret reg ID as an architectural SVE register... */ ret = sve_reg_to_region(®ion, vcpu, reg); if (ret) return ret; if (!kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr, region.klen)) return -EFAULT; return 0; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { return -EINVAL; } static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, u64 __user *uindices) { unsigned int i; int n = 0; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; int size = core_reg_size_from_offset(vcpu, i); if (size < 0) continue; switch (size) { case sizeof(__u32): reg |= KVM_REG_SIZE_U32; break; case sizeof(__u64): reg |= KVM_REG_SIZE_U64; break; case sizeof(__uint128_t): reg |= KVM_REG_SIZE_U128; break; default: WARN_ON(1); continue; } if (uindices) { if (put_user(reg, uindices)) return -EFAULT; uindices++; } n++; } return n; } static unsigned long num_core_regs(const struct kvm_vcpu *vcpu) { return copy_core_reg_indices(vcpu, NULL); } static const u64 timer_reg_list[] = { KVM_REG_ARM_TIMER_CTL, KVM_REG_ARM_TIMER_CNT, KVM_REG_ARM_TIMER_CVAL, KVM_REG_ARM_PTIMER_CTL, KVM_REG_ARM_PTIMER_CNT, KVM_REG_ARM_PTIMER_CVAL, }; #define NUM_TIMER_REGS ARRAY_SIZE(timer_reg_list) static bool is_timer_reg(u64 index) { switch (index) { case KVM_REG_ARM_TIMER_CTL: case KVM_REG_ARM_TIMER_CNT: case KVM_REG_ARM_TIMER_CVAL: case KVM_REG_ARM_PTIMER_CTL: case KVM_REG_ARM_PTIMER_CNT: case KVM_REG_ARM_PTIMER_CVAL: return true; } return false; } static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { for (int i = 0; i < NUM_TIMER_REGS; i++) { if (put_user(timer_reg_list[i], uindices)) return -EFAULT; uindices++; } return 0; } static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; int ret; ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)); if (ret != 0) return -EFAULT; return kvm_arm_timer_set_reg(vcpu, reg->id, val); } static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu) { const unsigned int slices = vcpu_sve_slices(vcpu); if (!vcpu_has_sve(vcpu)) return 0; /* Policed by KVM_GET_REG_LIST: */ WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */) + 1; /* KVM_REG_ARM64_SVE_VLS */ } static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu, u64 __user *uindices) { const unsigned int slices = vcpu_sve_slices(vcpu); u64 reg; unsigned int i, n; int num_regs = 0; if (!vcpu_has_sve(vcpu)) return 0; /* Policed by KVM_GET_REG_LIST: */ WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); /* * Enumerate this first, so that userspace can save/restore in * the order reported by KVM_GET_REG_LIST: */ reg = KVM_REG_ARM64_SVE_VLS; if (put_user(reg, uindices++)) return -EFAULT; ++num_regs; for (i = 0; i < slices; i++) { for (n = 0; n < SVE_NUM_ZREGS; n++) { reg = KVM_REG_ARM64_SVE_ZREG(n, i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } for (n = 0; n < SVE_NUM_PREGS; n++) { reg = KVM_REG_ARM64_SVE_PREG(n, i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } reg = KVM_REG_ARM64_SVE_FFR(i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } return num_regs; } /** * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG * @vcpu: the vCPU pointer * * This is for all registers. */ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { unsigned long res = 0; res += num_core_regs(vcpu); res += num_sve_regs(vcpu); res += kvm_arm_num_sys_reg_descs(vcpu); res += kvm_arm_get_fw_num_regs(vcpu); res += NUM_TIMER_REGS; return res; } /** * kvm_arm_copy_reg_indices - get indices of all registers. * @vcpu: the vCPU pointer * @uindices: register list to copy * * We do core registers right here, then we append system regs. */ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int ret; ret = copy_core_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += ret; ret = copy_sve_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += ret; ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += kvm_arm_get_fw_num_regs(vcpu); ret = copy_timer_indices(vcpu, uindices); if (ret < 0) return ret; uindices += NUM_TIMER_REGS; return kvm_arm_copy_sys_reg_indices(vcpu, uindices); } int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* We currently use nothing arch-specific in upper 32 bits */ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32) return -EINVAL; switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return get_core_reg(vcpu, reg); case KVM_REG_ARM_FW: case KVM_REG_ARM_FW_FEAT_BMAP: return kvm_arm_get_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return get_sve_reg(vcpu, reg); } if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); return kvm_arm_sys_reg_get_reg(vcpu, reg); } int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* We currently use nothing arch-specific in upper 32 bits */ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32) return -EINVAL; switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return set_core_reg(vcpu, reg); case KVM_REG_ARM_FW: case KVM_REG_ARM_FW_FEAT_BMAP: return kvm_arm_set_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return set_sve_reg(vcpu, reg); } if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); return kvm_arm_sys_reg_set_reg(vcpu, reg); } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { return -EINVAL; } int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { events->exception.serror_pending = !!(vcpu->arch.hcr_el2 & HCR_VSE); events->exception.serror_has_esr = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); if (events->exception.serror_pending && events->exception.serror_has_esr) events->exception.serror_esr = vcpu_get_vsesr(vcpu); /* * We never return a pending ext_dabt here because we deliver it to * the virtual CPU directly when setting the event and it's no longer * 'pending' at this point. */ return 0; } int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { bool serror_pending = events->exception.serror_pending; bool has_esr = events->exception.serror_has_esr; bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) { if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) return -EINVAL; if (!((events->exception.serror_esr) & ~ESR_ELx_ISS_MASK)) kvm_set_sei_esr(vcpu, events->exception.serror_esr); else return -EINVAL; } else if (serror_pending) { kvm_inject_vabt(vcpu); } if (ext_dabt_pending) kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 0; } u32 __attribute_const__ kvm_target_cpu(void) { unsigned long implementor = read_cpuid_implementor(); unsigned long part_number = read_cpuid_part_number(); switch (implementor) { case ARM_CPU_IMP_ARM: switch (part_number) { case ARM_CPU_PART_AEM_V8: return KVM_ARM_TARGET_AEM_V8; case ARM_CPU_PART_FOUNDATION: return KVM_ARM_TARGET_FOUNDATION_V8; case ARM_CPU_PART_CORTEX_A53: return KVM_ARM_TARGET_CORTEX_A53; case ARM_CPU_PART_CORTEX_A57: return KVM_ARM_TARGET_CORTEX_A57; } break; case ARM_CPU_IMP_APM: switch (part_number) { case APM_CPU_PART_XGENE: return KVM_ARM_TARGET_XGENE_POTENZA; } break; } /* Return a default generic target */ return KVM_ARM_TARGET_GENERIC_V8; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; } int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { return -EINVAL; } /** * kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging * @vcpu: the vCPU pointer * @dbg: the ioctl data buffer * * This sets up and enables the VM for guest debugging. Userspace * passes in a control flag to enable different debug types and * potentially other architecture specific information in the rest of * the structure. */ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { int ret = 0; trace_kvm_set_guest_debug(vcpu, dbg->control); if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) { ret = -EINVAL; goto out; } if (dbg->control & KVM_GUESTDBG_ENABLE) { vcpu->guest_debug = dbg->control; /* Hardware assisted Break and Watch points */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { vcpu->arch.external_debug_state = dbg->arch; } } else { /* If not enabled clear all flags */ vcpu->guest_debug = 0; vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING); } out: return ret; } int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_arm_pmu_v3_set_attr(vcpu, attr); mutex_unlock(&vcpu->kvm->arch.config_lock); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_set_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: ret = kvm_arm_pmu_v3_get_attr(vcpu, attr); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_get_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_get_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: ret = kvm_arm_pmu_v3_has_attr(vcpu, attr); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_has_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_has_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags) { gpa_t guest_ipa = copy_tags->guest_ipa; size_t length = copy_tags->length; void __user *tags = copy_tags->addr; gpa_t gfn; bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST); int ret = 0; if (!kvm_has_mte(kvm)) return -EINVAL; if (copy_tags->reserved[0] || copy_tags->reserved[1]) return -EINVAL; if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST) return -EINVAL; if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK) return -EINVAL; /* Lengths above INT_MAX cannot be represented in the return value */ if (length > INT_MAX) return -EINVAL; gfn = gpa_to_gfn(guest_ipa); mutex_lock(&kvm->slots_lock); while (length > 0) { kvm_pfn_t pfn = gfn_to_pfn_prot(kvm, gfn, write, NULL); void *maddr; unsigned long num_tags; struct page *page; if (is_error_noslot_pfn(pfn)) { ret = -EFAULT; goto out; } page = pfn_to_online_page(pfn); if (!page) { /* Reject ZONE_DEVICE memory */ ret = -EFAULT; goto out; } maddr = page_address(page); if (!write) { if (page_mte_tagged(page)) num_tags = mte_copy_tags_to_user(tags, maddr, MTE_GRANULES_PER_PAGE); else /* No tags in memory, so write zeros */ num_tags = MTE_GRANULES_PER_PAGE - clear_user(tags, MTE_GRANULES_PER_PAGE); kvm_release_pfn_clean(pfn); } else { /* * Only locking to serialise with a concurrent * __set_ptes() in the VMM but still overriding the * tags, hence ignoring the return value. */ try_page_mte_tagging(page); num_tags = mte_copy_tags_from_user(maddr, tags, MTE_GRANULES_PER_PAGE); /* uaccess failed, don't leave stale tags */ if (num_tags != MTE_GRANULES_PER_PAGE) mte_clear_page_tags(maddr); set_page_mte_tagged(page); kvm_release_pfn_dirty(pfn); } if (num_tags != MTE_GRANULES_PER_PAGE) { ret = -EFAULT; goto out; } gfn++; tags += num_tags; length -= PAGE_SIZE; } out: mutex_unlock(&kvm->slots_lock); /* If some data has been copied report the number of bytes copied */ if (length != copy_tags->length) return copy_tags->length - length; return ret; } |
| 264 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MNT_IDMAPPING_H #define _LINUX_MNT_IDMAPPING_H #include <linux/types.h> #include <linux/uidgid.h> struct mnt_idmap; struct user_namespace; extern struct mnt_idmap nop_mnt_idmap; extern struct user_namespace init_user_ns; typedef struct { uid_t val; } vfsuid_t; typedef struct { gid_t val; } vfsgid_t; static_assert(sizeof(vfsuid_t) == sizeof(kuid_t)); static_assert(sizeof(vfsgid_t) == sizeof(kgid_t)); static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val)); static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val)); #ifdef CONFIG_MULTIUSER static inline uid_t __vfsuid_val(vfsuid_t uid) { return uid.val; } static inline gid_t __vfsgid_val(vfsgid_t gid) { return gid.val; } #else static inline uid_t __vfsuid_val(vfsuid_t uid) { return 0; } static inline gid_t __vfsgid_val(vfsgid_t gid) { return 0; } #endif static inline bool vfsuid_valid(vfsuid_t uid) { return __vfsuid_val(uid) != (uid_t)-1; } static inline bool vfsgid_valid(vfsgid_t gid) { return __vfsgid_val(gid) != (gid_t)-1; } static inline bool vfsuid_eq(vfsuid_t left, vfsuid_t right) { return vfsuid_valid(left) && __vfsuid_val(left) == __vfsuid_val(right); } static inline bool vfsgid_eq(vfsgid_t left, vfsgid_t right) { return vfsgid_valid(left) && __vfsgid_val(left) == __vfsgid_val(right); } /** * vfsuid_eq_kuid - check whether kuid and vfsuid have the same value * @vfsuid: the vfsuid to compare * @kuid: the kuid to compare * * Check whether @vfsuid and @kuid have the same values. * * Return: true if @vfsuid and @kuid have the same value, false if not. * Comparison between two invalid uids returns false. */ static inline bool vfsuid_eq_kuid(vfsuid_t vfsuid, kuid_t kuid) { return vfsuid_valid(vfsuid) && __vfsuid_val(vfsuid) == __kuid_val(kuid); } /** * vfsgid_eq_kgid - check whether kgid and vfsgid have the same value * @vfsgid: the vfsgid to compare * @kgid: the kgid to compare * * Check whether @vfsgid and @kgid have the same values. * * Return: true if @vfsgid and @kgid have the same value, false if not. * Comparison between two invalid gids returns false. */ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid) { return vfsgid_valid(vfsgid) && __vfsgid_val(vfsgid) == __kgid_val(kgid); } /* * vfs{g,u}ids are created from k{g,u}ids. * We don't allow them to be created from regular {u,g}id. */ #define VFSUIDT_INIT(val) (vfsuid_t){ __kuid_val(val) } #define VFSGIDT_INIT(val) (vfsgid_t){ __kgid_val(val) } #define INVALID_VFSUID VFSUIDT_INIT(INVALID_UID) #define INVALID_VFSGID VFSGIDT_INIT(INVALID_GID) /* * Allow a vfs{g,u}id to be used as a k{g,u}id where we want to compare * whether the mapped value is identical to value of a k{g,u}id. */ #define AS_KUIDT(val) (kuid_t){ __vfsuid_val(val) } #define AS_KGIDT(val) (kgid_t){ __vfsgid_val(val) } int vfsgid_in_group_p(vfsgid_t vfsgid); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); vfsuid_t make_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kuid_t kuid); vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid); kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid); kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid); /** * vfsuid_has_fsmapping - check whether a vfsuid maps into the filesystem * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid: vfsuid to be mapped * * Check whether @vfsuid has a mapping in the filesystem idmapping. Use this * function to check whether the filesystem idmapping has a mapping for * @vfsuid. * * Return: true if @vfsuid has a mapping in the filesystem, false if not. */ static inline bool vfsuid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { return uid_valid(from_vfsuid(idmap, fs_userns, vfsuid)); } static inline bool vfsuid_has_mapping(struct user_namespace *userns, vfsuid_t vfsuid) { return from_kuid(userns, AS_KUIDT(vfsuid)) != (uid_t)-1; } /** * vfsuid_into_kuid - convert vfsuid into kuid * @vfsuid: the vfsuid to convert * * This can be used when a vfsuid is committed as a kuid. * * Return: a kuid with the value of @vfsuid */ static inline kuid_t vfsuid_into_kuid(vfsuid_t vfsuid) { return AS_KUIDT(vfsuid); } /** * vfsgid_has_fsmapping - check whether a vfsgid maps into the filesystem * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid: vfsgid to be mapped * * Check whether @vfsgid has a mapping in the filesystem idmapping. Use this * function to check whether the filesystem idmapping has a mapping for * @vfsgid. * * Return: true if @vfsgid has a mapping in the filesystem, false if not. */ static inline bool vfsgid_has_fsmapping(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { return gid_valid(from_vfsgid(idmap, fs_userns, vfsgid)); } static inline bool vfsgid_has_mapping(struct user_namespace *userns, vfsgid_t vfsgid) { return from_kgid(userns, AS_KGIDT(vfsgid)) != (gid_t)-1; } /** * vfsgid_into_kgid - convert vfsgid into kgid * @vfsgid: the vfsgid to convert * * This can be used when a vfsgid is committed as a kgid. * * Return: a kgid with the value of @vfsgid */ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) { return AS_KGIDT(vfsgid); } /** * mapped_fsuid - return caller's fsuid mapped according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of * a newly allocated inode triggered by a creation event such as mkdir or * O_CREAT. Other examples include the allocation of quotas for a specific * user. * * Return: the caller's current fsuid mapped up according to @idmap. */ static inline kuid_t mapped_fsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { return from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(current_fsuid())); } /** * mapped_fsgid - return caller's fsgid mapped according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of * a newly allocated inode triggered by a creation event such as mkdir or * O_CREAT. Other examples include the allocation of quotas for a specific * user. * * Return: the caller's current fsgid mapped up according to @idmap. */ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns) { return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid())); } #endif /* _LINUX_MNT_IDMAPPING_H */ |
| 160 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk), TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->rx_sk, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 247 37 90 270 270 240 241 90 14 90 90 90 90 90 90 177 177 177 176 258 257 258 13 250 249 250 249 87 78 1 78 78 78 232 234 234 162 162 162 162 162 162 162 162 162 220 220 219 16 16 40 40 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support four policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma( folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return z->zone ? zone_to_nid(z->zone) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node_noprof(nid, gfp | __GFP_THISNODE | __GFP_NORETRY, order); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, nid)); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * @hugepage: Unused (was: For hugepages try only preferred node if possible). * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of alloc_pages_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, NULL, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, NULL, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, NULL, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, NULL, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_array_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_array_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, NULL, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zone_to_nid(z->zone); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 344 345 344 344 345 82 82 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { refcount_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred_many - Get references on a new set of credentials * @cred: The new credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of new credentials. The caller must * release all acquired references. */ static inline struct cred *get_new_cred_many(struct cred *cred, int nr) { atomic_long_add(nr, &cred->usage); return cred; } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { return get_new_cred_many(cred, 1); } /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of credentials. The caller must release * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; nonconst_cred->non_rcu = 0; return get_new_cred_many(nonconst_cred, nr); } /* * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. */ static inline const struct cred *get_cred(const struct cred *cred) { return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } /* * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. */ static inline void put_cred(const struct cred *cred) { put_cred_many(cred, 1); } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) #define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 3 11 11 58 58 58 41 41 41 41 41 1 1 41 14 14 14 14 38 51 51 51 11 11 20 20 20 20 20 20 20 11 11 11 11 11 11 11 11 20 11 11 11 38 38 38 38 37 38 38 38 49 49 57 57 57 49 48 49 49 49 49 49 49 49 45 49 49 49 49 45 45 57 57 57 49 49 49 49 49 49 48 49 49 49 49 57 57 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void mapping_set_update(struct xa_state *xas, struct address_space *mapping) { if (dax_mapping(mapping) || shmem_mapping(mapping)) return; xas_set_update(xas, workingset_update_node); xas_set_lru(xas, &shadow_nodes); } static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); int refs = 1; free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @wbc: the writeback_control controlling the writeout * * Call writepages on the mapping using the provided wbc to control the * writeout. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(wbc, mapping->host); ret = do_writepages(mapping, wbc); wbc_detach_inode(wbc); return ret; } EXPORT_SYMBOL(filemap_fdatawrite_wbc); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); folio_clear_error(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) __lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) __lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) __lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); void *alloced_shadow = NULL; int alloced_order = 0; bool huge; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1, split_order = 0; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } /* entry may have changed before we re-acquire the lock */ if (alloced_order && (old != alloced_shadow || order != alloced_order)) { xas_destroy(&xas); alloced_order = 0; } if (old) { if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); if (!alloced_order) { split_order = order; goto unlock; } xas_split(&xas, old, order); xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); /* split needed, alloc here and retry. */ if (split_order) { xas_split_alloc(&xas, old, split_order, gfp); if (xas_error(&xas)) goto error; alloced_shadow = old; alloced_order = split_order; xas_reset(&xas); continue; } if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; ret = mem_cgroup_charge(folio, NULL, gfp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags)) return false; } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * migration_entry_wait_on_locked - Wait for a migration entry to be removed * @entry: migration swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page to be removed. This is * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for the migration entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = pfn_swap_entry_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(folio_add_wait_queue); /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned order = FGF_GET_ORDER(fgp_flags); int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (!mapping_large_folio_support(mapping)) order = 0; if (order > MAX_PAGECACHE_ORDER) order = MAX_PAGECACHE_ORDER; /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > 0) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > 0); if (err == -EEXIST) goto repeat; if (err) return ERR_PTR(err); /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); return folio; } EXPORT_SYMBOL(__filemap_get_folio); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } rcu_read_unlock(); if (folio_batch_count(fbatch)) { unsigned long nr = 1; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { if (!xa_is_value(folio)) { if (folio->index < *start) goto put; if (folio_next_index(folio) - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); if (folio_batch_count(fbatch)) { unsigned long nr = 1; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* * A previous I/O error may have been due to temporary failures, * eg. multipath errors. PG_error will be set again if read_folio * fails. */ folio_clear_error(folio); /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct file *file, struct address_space *mapping, pgoff_t index, struct folio_batch *fbatch) { struct folio *folio; int error; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); if (!folio) return -ENOMEM; /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; err = filemap_create_folio(filp, mapping, iocb->ki_pos >> PAGE_SHIFT, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if ((iocb->ki_flags & IOCB_WAITQ) && folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) folio_put(fbatch.folios[i]); folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; int ret; if (iocb->ki_flags & IOCB_NOWAIT) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~(bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); return fpin; } #endif /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_locked(folio)) continue; if (!folio_try_get(folio)) continue; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) return ret; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) return ret; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; folio_ref_inc(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; if (filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, 0); if (!folio) return ERR_PTR(-ENOMEM); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: err = filemap_read_folio(file, filler, folio); if (err) { folio_put(folio); if (err == AOP_TRUNCATED_PAGE) goto repeat; return ERR_PTR(err); } out: folio_mark_accessed(folio); return folio; } /** * read_cache_folio - Read into page cache, fill it if needed. * @mapping: The address_space to read from. * @index: The index to read. * @filler: Function to perform the read, or NULL to use aops->read_folio(). * @file: Passed to filler function, may be NULL if not required. * * Read one page into the page cache. If it succeeds, the folio returned * will contain @index, but it may not be the first page of the folio. * * If the filler function returns an error, it will be returned to the * caller. * * Context: May sleep. Expects mapping->invalidate_lock to be held. * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file) { return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); /** * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. * @mapping: The address_space for the folio. * @index: The index that the allocated folio will contain. * @gfp: The page allocator flags to use if allocating. * * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with * any new memory allocations done using the specified allocation flags. * * The most likely error from this function is EIO, but ENOMEM is * possible and so is EINTR. If ->read_folio returns another error, * that will be returned to the caller. * * The function expects mapping->invalidate_lock to be already held. * * Return: Uptodate folio on success, ERR_PTR() on failure. */ struct folio *mapping_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_folio(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(mapping_read_folio_gfp); static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file) { return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * The function expects mapping->invalidate_lock to be already held. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); /* * Warn about a page cache invalidation failure during a direct I/O write. */ static void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; char *path; errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (mapping->nrpages && invalidate_inode_pages2_range(mapping, iocb->ki_pos >> PAGE_SHIFT, (iocb->ki_pos + count - 1) >> PAGE_SHIFT)) dio_warn_stale_pagecache(iocb->ki_filp); } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct address_space *mapping = iocb->ki_filp->f_mapping; size_t write_len = iov_iter_count(from); ssize_t written; /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ written = kiocb_invalidate_pages(iocb, write_len); if (written) { if (written == -EBUSY) return 0; return written; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0) { struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; kiocb_invalidate_post_direct_write(iocb, written); pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } if (written != -EIOCBQUEUED) iov_iter_revert(from, write_len - iov_iter_count(from)); return written; } EXPORT_SYMBOL(generic_file_direct_write); ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; size_t chunk = mapping_max_folio_size(mapping); long status = 0; ssize_t written = 0; do { struct page *page; struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; bytes = iov_iter_count(i); retry: offset = pos & (chunk - 1); bytes = min(chunk - offset, bytes); balance_dirty_pages_ratelimited(mapping); /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. */ if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, &page, &fsdata); if (unlikely(status < 0)) break; folio = page_folio(page); offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); flush_dcache_folio(folio); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) break; } cond_resched(); if (unlikely(status == 0)) { /* * A short copy made ->write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } } else { pos += status; written += status; } } while (iov_iter_count(i)); if (!written) return status; iocb->ki_pos += written; return written; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; ret = file_remove_privs(file); if (ret) return ret; ret = file_update_time(file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT) { ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) return ret; return direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } return generic_perform_write(iocb, from); } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * filemap_release_folio() - Release fs-specific metadata on a folio. * @folio: The folio which the kernel is trying to free. * @gfp: Memory allocation flags (and I/O mode). * * The address_space is trying to release any data attached to a folio * (presumably at folio->private). * * This will also be called if the private_2 flag is set on a page, * indicating that the folio has other metadata associated with it. * * The @gfp argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block * (__GFP_RECLAIM & __GFP_FS). * * Return: %true if the release was successful, otherwise %false. */ bool filemap_release_folio(struct folio *folio, gfp_t gfp) { struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); if (!folio_needs_release(folio)) return true; if (folio_test_writeback(folio)) return false; if (mapping && mapping->a_ops->release_folio) return mapping->a_ops->release_folio(folio, gfp); return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); /** * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache * @inode: The inode to flush * @flush: Set to write back rather than simply invalidate. * @start: First byte to in range. * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start * onwards. * * Invalidate all the folios on an inode that contribute to the specified * range, possibly writing them back first. Whilst the operation is * undertaken, the invalidate lock is held to prevent new folios from being * installed. */ int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end) { struct address_space *mapping = inode->i_mapping; pgoff_t first = start >> PAGE_SHIFT; pgoff_t last = end >> PAGE_SHIFT; pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; if (!mapping || !mapping->nrpages || end < start) goto out; /* Prevent new folios from being added to the inode. */ filemap_invalidate_lock(mapping); if (!mapping->nrpages) goto unlock; unmap_mapping_pages(mapping, first, nr, false); /* Write back the data if we're asked to. */ if (flush) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; filemap_fdatawrite_wbc(mapping, &wbc); } /* Wait for writeback to complete on all folios and discard. */ truncate_inode_pages_range(mapping, start, end); unlock: filemap_invalidate_unlock(mapping); out: return filemap_check_errors(mapping); } EXPORT_SYMBOL_GPL(filemap_invalidate_inode); #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping * @mapping: The mapping to compute the statistics for. * @first_index: The starting page cache index. * @last_index: The final page index (inclusive). * @cs: the cachestat struct to write the result to. * * This will query the page cache statistics of a mapping in the * page range of [first_index, last_index] (inclusive). The statistics * queried include: number of dirty pages, number of pages marked for * writeback, and the number of (recently) evicted pages. */ static void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) { XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; /* Flush stats (and potentially sleep) outside the RCU read section. */ mem_cgroup_flush_stats_ratelimited(NULL); rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; unsigned long nr_pages; pgoff_t folio_first_index, folio_last_index; /* * Don't deref the folio. It is not pinned, and might * get freed (and reused) underneath us. * * We *could* pin it, but that would be expensive for * what should be a fast and lightweight syscall. * * Instead, derive all information of interest from * the rcu-protected xarray. */ if (xas_retry(&xas, folio)) continue; order = xa_get_order(xas.xa, xas.xa_index); nr_pages = 1 << order; folio_first_index = round_down(xas.xa_index, 1 << order); folio_last_index = folio_first_index + nr_pages - 1; /* Folios might straddle the range boundaries, only count covered pages */ if (folio_first_index < first_index) nr_pages -= first_index - folio_first_index; if (folio_last_index > last_index) nr_pages -= folio_last_index - last_index; if (xa_is_value(folio)) { /* page is evicted */ void *shadow = (void *)folio; bool workingset; /* not used */ cs->nr_evicted += nr_pages; #ifdef CONFIG_SWAP /* implies CONFIG_MMU */ if (shmem_mapping(mapping)) { /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); /* swapin error results in poisoned entry */ if (non_swap_entry(swp)) goto resched; /* * Getting a swap entry from the shmem * inode means we beat * shmem_unuse(). rcu_read_lock() * ensures swapoff waits for us before * freeing the swapper space. However, * we can race with swapping and * invalidation, so there might not be * a shadow in the swapcache (yet). */ shadow = get_shadow_from_swap_cache(swp); if (!shadow) goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; } /* page is in cache */ cs->nr_cache += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY)) cs->nr_dirty += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK)) cs->nr_writeback += nr_pages; resched: if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); } /* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the * bytes range specified by `off` and `len`: number of cached pages, * number of dirty pages, number of pages marked for writeback, * number of evicted pages, and number of recently evicted pages. * * An evicted page is a page that is previously in the page cache * but has been evicted since. A page is recently evicted if its last * eviction was recent enough that its reentry to the cache would * indicate that it is actively being used by the system, and that * there is memory pressure on the system. * * `off` and `len` must be non-negative integers. If `len` > 0, * the queried range is [`off`, `off` + `len`]. If `len` == 0, * we will query in the range from `off` to the end of the file. * * The `flags` argument is unused for now, but is included for future * extensibility. User should pass 0 (i.e no flag specified). * * Currently, hugetlbfs is not supported. * * Because the status of a page can change after cachestat() checks it * but before it returns to the application, the returned values may * contain stale information. * * return values: * zero - success * -EFAULT - cstat or cstat_range points to an illegal address * -EINVAL - invalid flags * -EBADF - invalid file descriptor * -EOPNOTSUPP - file descriptor is of a hugetlbfs file */ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat_range __user *, cstat_range, struct cachestat __user *, cstat, unsigned int, flags) { struct fd f = fdget(fd); struct address_space *mapping; struct cachestat_range csr; struct cachestat cs; pgoff_t first_index, last_index; if (!f.file) return -EBADF; if (copy_from_user(&csr, cstat_range, sizeof(struct cachestat_range))) { fdput(f); return -EFAULT; } /* hugetlbfs is not supported */ if (is_file_hugepages(f.file)) { fdput(f); return -EOPNOTSUPP; } if (flags != 0) { fdput(f); return -EINVAL; } first_index = csr.off >> PAGE_SHIFT; last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); mapping = f.file->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); fdput(f); if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) return -EFAULT; return 0; } #endif /* CONFIG_CACHESTAT_SYSCALL */ |
| 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_COMPAT_H #define _LINUX_COMPAT_H /* * These are the type definitions for the architecture specific * syscall compatibility layer. */ #include <linux/types.h> #include <linux/time.h> #include <linux/stat.h> #include <linux/param.h> /* for HZ */ #include <linux/sem.h> #include <linux/socket.h> #include <linux/if.h> #include <linux/fs.h> #include <linux/aio_abi.h> /* for aio_context_t */ #include <linux/uaccess.h> #include <linux/unistd.h> #include <asm/compat.h> #include <asm/siginfo.h> #include <asm/signal.h> #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* * It may be useful for an architecture to override the definitions of the * COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular * to use a different calling convention for syscalls. To allow for that, + the prototypes for the compat_sys_*() functions below will *not* be included * if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #include <asm/syscall_wrapper.h> #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ #ifndef COMPAT_USE_64BIT_TIME #define COMPAT_USE_64BIT_TIME 0 #endif #ifndef __SC_DELOUSE #define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #ifndef COMPAT_SYSCALL_DEFINE0 #define COMPAT_SYSCALL_DEFINE0(name) \ asmlinkage long compat_sys_##name(void); \ ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) #endif /* COMPAT_SYSCALL_DEFINE0 */ #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE2(name, ...) \ COMPAT_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE3(name, ...) \ COMPAT_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE4(name, ...) \ COMPAT_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE5(name, ...) \ COMPAT_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) /* * The asmlinkage stub is aliased to a function named __se_compat_sys_*() which * sign-extends 32-bit ints to longs whenever needed. The actual work is * done within __do_compat_sys_*(). */ #ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ __diag_push(); \ __diag_ignore(GCC, 8, "-Wattribute-alias", \ "Type aliasing is used to sanitize syscall arguments");\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_compat_sys##name)))); \ ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ return ret; \ } \ __diag_pop(); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; }; #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif #ifndef compat_sigaltstack /* we'll need that for MIPS */ typedef struct compat_sigaltstack { compat_uptr_t ss_sp; int ss_flags; compat_size_t ss_size; } compat_stack_t; #endif #ifndef COMPAT_MINSIGSTKSZ #define COMPAT_MINSIGSTKSZ MINSIGSTKSZ #endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; struct old_itimerval32; struct compat_tms { compat_clock_t tms_utime; compat_clock_t tms_stime; compat_clock_t tms_cutime; compat_clock_t tms_cstime; }; #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); struct compat_sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION compat_uptr_t sa_handler; compat_ulong_t sa_flags; #else compat_uint_t sa_flags; compat_uptr_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER compat_uptr_t sa_restorer; #endif compat_sigset_t sa_mask __packed; }; typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; } compat_sigval_t; typedef struct compat_siginfo { int si_signo; #ifndef __ARCH_HAS_SWAPPED_SIGINFO int si_errno; int si_code; #else int si_code; int si_errno; #endif union { int _pad[128/sizeof(int) - 3]; /* kill() */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ } _kill; /* POSIX.1b timers */ struct { compat_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ compat_sigval_t _sigval; /* same as below */ } _timer; /* POSIX.1b signals */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ compat_sigval_t _sigval; } _rt; /* SIGCHLD */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_clock_t _utime; compat_clock_t _stime; } _sigchld; #ifdef CONFIG_X86_X32_ABI /* SIGCHLD (x32 version) */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_s64 _utime; compat_s64 _stime; } _sigchld_x32; #endif /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { compat_uptr_t _addr; /* faulting insn/memory ref. */ #define __COMPAT_ADDR_BND_PKEY_PAD (__alignof__(compat_uptr_t) < sizeof(short) ? \ sizeof(short) : __alignof__(compat_uptr_t)) union { /* used on alpha and sparc */ int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO */ short int _addr_lsb; /* Valid LSB of the reported address. */ /* used when si_code=SEGV_BNDERR */ struct { char _dummy_bnd[__COMPAT_ADDR_BND_PKEY_PAD]; compat_uptr_t _lower; compat_uptr_t _upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { char _dummy_pkey[__COMPAT_ADDR_BND_PKEY_PAD]; u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ struct { compat_ulong_t _data; u32 _type; u32 _flags; } _perf; }; } _sigfault; /* SIGPOLL */ struct { compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; struct { compat_uptr_t _call_addr; /* calling user insn */ int _syscall; /* triggering system call number */ unsigned int _arch; /* AUDIT_ARCH_* of syscall */ } _sigsys; } _sifields; } compat_siginfo_t; struct compat_rlimit { compat_ulong_t rlim_cur; compat_ulong_t rlim_max; }; #ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED #define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) #else #define __ARCH_COMPAT_FLOCK64_PACK #endif struct compat_flock { short l_type; short l_whence; compat_off_t l_start; compat_off_t l_len; #ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID __ARCH_COMPAT_FLOCK_EXTRA_SYSID #endif compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK_PAD __ARCH_COMPAT_FLOCK_PAD #endif }; struct compat_flock64 { short l_type; short l_whence; compat_loff_t l_start; compat_loff_t l_len; compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK64_PAD __ARCH_COMPAT_FLOCK64_PAD #endif } __ARCH_COMPAT_FLOCK64_PACK; struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; compat_long_t ru_isrss; compat_long_t ru_minflt; compat_long_t ru_majflt; compat_long_t ru_nswap; compat_long_t ru_inblock; compat_long_t ru_oublock; compat_long_t ru_msgsnd; compat_long_t ru_msgrcv; compat_long_t ru_nsignals; compat_long_t ru_nvcsw; compat_long_t ru_nivcsw; }; extern int put_compat_rusage(const struct rusage *, struct compat_rusage __user *); struct compat_siginfo; struct __compat_aio_sigset; struct compat_dirent { u32 d_ino; compat_off_t d_off; u16 d_reclen; char d_name[256]; }; struct compat_ustat { compat_daddr_t f_tfree; compat_ino_t f_tinode; char f_fname[6]; char f_fpack[6]; }; #define COMPAT_SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3) typedef struct compat_sigevent { compat_sigval_t sigev_value; compat_int_t sigev_signo; compat_int_t sigev_notify; union { compat_int_t _pad[COMPAT_SIGEV_PAD_SIZE]; compat_int_t _tid; struct { compat_uptr_t _function; compat_uptr_t _attribute; } _sigev_thread; } _sigev_un; } compat_sigevent_t; struct compat_ifmap { compat_ulong_t mem_start; compat_ulong_t mem_end; unsigned short base_addr; unsigned char irq; unsigned char dma; unsigned char port; }; struct compat_if_settings { unsigned int type; /* Type of physical device or protocol */ unsigned int size; /* Size of the data allocated by the caller */ compat_uptr_t ifs_ifsu; /* union of pointers */ }; struct compat_ifreq { union { char ifrn_name[IFNAMSIZ]; /* if name, e.g. "en0" */ } ifr_ifrn; union { struct sockaddr ifru_addr; struct sockaddr ifru_dstaddr; struct sockaddr ifru_broadaddr; struct sockaddr ifru_netmask; struct sockaddr ifru_hwaddr; short ifru_flags; compat_int_t ifru_ivalue; compat_int_t ifru_mtu; struct compat_ifmap ifru_map; char ifru_slave[IFNAMSIZ]; /* Just fits the size */ char ifru_newname[IFNAMSIZ]; compat_caddr_t ifru_data; struct compat_if_settings ifru_settings; } ifr_ifru; }; struct compat_ifconf { compat_int_t ifc_len; /* size of buffer */ compat_caddr_t ifcbuf; }; struct compat_robust_list { compat_uptr_t next; }; struct compat_robust_list_head { struct compat_robust_list list; compat_long_t futex_offset; compat_uptr_t list_op_pending; }; #ifdef CONFIG_COMPAT_OLD_SIGACTION struct compat_old_sigaction { compat_uptr_t sa_handler; compat_old_sigset_t sa_mask; compat_ulong_t sa_flags; compat_uptr_t sa_restorer; }; #endif struct compat_keyctl_kdf_params { compat_uptr_t hashname; compat_uptr_t otherinfo; __u32 otherinfolen; __u32 __spare[8]; }; struct compat_stat; struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; struct compat_linux_dirent; struct linux_dirent64; struct compat_msghdr; struct compat_mmsghdr; struct compat_sysinfo; struct compat_sysctl_args; struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from); int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); int __copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); #ifndef copy_siginfo_to_user32 #define copy_siginfo_to_user32 __copy_siginfo_to_user32 #endif int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* * Defined inline such that size can be compile time constant, which avoids * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct */ static inline int put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, unsigned int size) { /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ #if defined(__BIG_ENDIAN) && defined(CONFIG_64BIT) compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; #else return copy_to_user(compat, set, size) ? -EFAULT : 0; #endif } #ifdef CONFIG_CPU_BIG_ENDIAN #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_put_user(__s->sig[3] >> 32, &__c->sig[7], label); \ unsafe_put_user(__s->sig[3], &__c->sig[6], label); \ fallthrough; \ case 3: \ unsafe_put_user(__s->sig[2] >> 32, &__c->sig[5], label); \ unsafe_put_user(__s->sig[2], &__c->sig[4], label); \ fallthrough; \ case 2: \ unsafe_put_user(__s->sig[1] >> 32, &__c->sig[3], label); \ unsafe_put_user(__s->sig[1], &__c->sig[2], label); \ fallthrough; \ case 1: \ unsafe_put_user(__s->sig[0] >> 32, &__c->sig[1], label); \ unsafe_put_user(__s->sig[0], &__c->sig[0], label); \ } \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ compat_sigset_word hi, lo; \ sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_get_user(lo, &__c->sig[7], label); \ unsafe_get_user(hi, &__c->sig[6], label); \ __s->sig[3] = hi | (((long)lo) << 32); \ fallthrough; \ case 3: \ unsafe_get_user(lo, &__c->sig[5], label); \ unsafe_get_user(hi, &__c->sig[4], label); \ __s->sig[2] = hi | (((long)lo) << 32); \ fallthrough; \ case 2: \ unsafe_get_user(lo, &__c->sig[3], label); \ unsafe_get_user(hi, &__c->sig[2], label); \ __s->sig[1] = hi | (((long)lo) << 32); \ fallthrough; \ case 1: \ unsafe_get_user(lo, &__c->sig[1], label); \ unsafe_get_user(hi, &__c->sig[0], label); \ __s->sig[0] = hi | (((long)lo) << 32); \ } \ } while (0) #else #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ unsafe_copy_to_user(__c, __s, sizeof(*__c), label); \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ sigset_t *__s = set; \ \ unsafe_copy_from_user(__s, __c, sizeof(*__c), label); \ } while (0) #endif extern int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); struct epoll_event; /* fortunately, this one is fixed-layout */ int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define unsafe_compat_save_altstack(uss, sp, label) do { \ compat_stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user(ptr_to_compat((void __user *)t->sas_ss_sp), \ &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ } while (0); /* * These syscall function prototypes are kept in the same order as * include/uapi/asm-generic/unistd.h. Deprecated or obsolete system calls * go below. * * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. * * As the syscall calling convention may be different from the default * for architectures overriding the syscall calling convention, do not * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_io_pgetevents_time64(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct __kernel_timespec __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_epoll_pwait2(int epfd, struct epoll_event __user *events, int maxevents, const struct __kernel_timespec __user *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf); asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf); asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t); /* No generic prototype for truncate64, ftruncate64, fallocate */ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_getdents(unsigned int fd, struct compat_linux_dirent __user *dirent, unsigned int count); asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); /* No generic prototype for pread64 and pwrite64 */ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 asmlinkage long compat_sys_pwritev64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, compat_size_t count); asmlinkage long compat_sys_pselect6_time32(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_pselect6_time64(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct __kernel_timespec __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll_time32(struct pollfd __user *ufds, unsigned int nfds, struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_ppoll_time64(struct pollfd __user *ufds, unsigned int nfds, struct __kernel_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user *filename, struct compat_stat __user *statbuf, int flag); asmlinkage long compat_sys_newfstat(unsigned int fd, struct compat_stat __user *statbuf); /* No generic prototype for sync_file_range and sync_file_range2 */ asmlinkage long compat_sys_waitid(int, compat_pid_t, struct compat_siginfo __user *, int, struct compat_rusage __user *); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, compat_size_t len); asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); asmlinkage long compat_sys_getitimer(int which, struct old_itimerval32 __user *it); asmlinkage long compat_sys_setitimer(int which, struct old_itimerval32 __user *in, struct old_itimerval32 __user *out); asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, compat_ulong_t nr_segments, struct compat_kexec_segment __user *, compat_ulong_t flags); asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, compat_long_t addr, compat_long_t data); asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long compat_sys_rt_sigaction(int, const struct compat_sigaction __user *, struct compat_sigaction __user *, compat_size_t); #endif asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time32(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct __kernel_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf); asmlinkage long compat_sys_getrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_setrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_mq_open(const char __user *u_name, int oflag, compat_mode_t mode, struct compat_mq_attr __user *u_attr); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, const struct compat_mq_attr __user *u_mqstat, struct compat_mq_attr __user *u_omqstat); asmlinkage long compat_sys_msgctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned flags, struct sockaddr __user *addr, int __user *addrlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); /* No generic prototype for readahead */ asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp); /* No generic prototype for fadvise64_64 */ /* CONFIG_MMU only */ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg_time64(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct __kernel_timespec __user *timeout); asmlinkage long compat_sys_recvmmsg_time32(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, int, const char __user *); asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp, int flags); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 asmlinkage long compat_sys_preadv64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 asmlinkage long compat_sys_pwritev64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif /* * Deprecated system calls which are still defined in * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch */ /* __ARCH_WANT_SYSCALL_NO_AT */ asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); /* __ARCH_WANT_SYSCALL_OFF_T */ asmlinkage long compat_sys_newstat(const char __user *filename, struct compat_stat __user *statbuf); asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); /* obsolete */ asmlinkage long compat_sys_old_readdir(unsigned int fd, struct compat_old_linux_dirent __user *, unsigned int count); /* obsolete */ asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg); /* obsolete */ asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); /* obsolete */ #ifdef __ARCH_WANT_SYS_SIGPENDING asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, compat_old_sigset_t __user *oset); #endif #ifdef CONFIG_COMPAT_OLD_SIGACTION asmlinkage long compat_sys_sigaction(int sig, const struct compat_old_sigaction __user *act, struct compat_old_sigaction __user *oact); #endif /* obsolete */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); #ifdef __ARCH_WANT_COMPAT_TRUNCATE64 asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FALLOCATE asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_PREAD64 asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_PWRITE64 asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), compat_arg_u64(nbytes), unsigned int flags); #endif #ifdef __ARCH_WANT_COMPAT_FADVISE64_64 asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), compat_arg_u64(len), int advice); #endif #ifdef __ARCH_WANT_COMPAT_READAHEAD asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); #endif #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * * Returns the old_timeval32 representation of the nsec parameter. */ static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct __kernel_old_timeval tv; struct old_timeval32 ctv; tv = ns_to_kernel_old_timeval(nsec); ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; return ctv; } /* * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz()) * directly. Instead, use one of the functions which work equivalently, such * as the kcompat_sys_xyzyyz() functions prototyped below. */ int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf); int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf); #ifdef CONFIG_COMPAT /* * For most but not all architectures, "am I in a compat syscall?" and * "am I a compat task?" are the same question. For architectures on which * they aren't the same question, arch code can override in_compat_syscall. */ #ifndef in_compat_syscall static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) /* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ #define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); /* * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit * types, and will need special compat treatment for that. Most architectures * don't need that special handling even for compat syscalls. */ #ifndef compat_need_64bit_alignment_fixup #define compat_need_64bit_alignment_fixup() false #endif /* * A pointer passed in from user mode. This should not * be used for syscall parameters, just declare them * as pointers because the syscall entry code will have * appropriately converted them already. */ #ifndef compat_ptr static inline void __user *compat_ptr(compat_uptr_t uptr) { return (void __user *)(unsigned long)uptr; } #endif static inline compat_uptr_t ptr_to_compat(void __user *uptr) { return (u32)(unsigned long)uptr; } #endif /* _LINUX_COMPAT_H */ |
| 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 34 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 4 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 1 35 35 35 35 35 35 35 35 35 35 35 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/signal.c * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-11-02 Modified for POSIX.1b signals by Richard Henderson * * 2003-06-02 Jim Houston - Concurrent Computer Corp. * Changes to use preallocated sigqueue structures * to allow signals to be sent reliably. */ #include <linux/slab.h> #include <linux/export.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/debug.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/coredump.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/signalfd.h> #include <linux/ratelimit.h> #include <linux/task_work.h> #include <linux/capability.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/uprobes.h> #include <linux/compat.h> #include <linux/cn_proc.h> #include <linux/compiler.h> #include <linux/posix-timers.h> #include <linux/cgroup.h> #include <linux/audit.h> #include <linux/sysctl.h> #include <uapi/linux/pidfd.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> #include <asm/param.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/siginfo.h> #include <asm/cacheflush.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * SLAB caches for signal bits. */ static struct kmem_cache *sigqueue_cachep; int print_fatal_signals __read_mostly; static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; } static inline bool sig_handler_ignored(void __user *handler, int sig) { /* Is it explicitly or implicitly ignored? */ return handler == SIG_IGN || (handler == SIG_DFL && sig_kernel_ignore(sig)); } static bool sig_task_ignored(struct task_struct *t, int sig, bool force) { void __user *handler; handler = sig_handler(t, sig); /* SIGKILL and SIGSTOP may not be sent to the global init */ if (unlikely(is_global_init(t) && sig_kernel_only(sig))) return true; if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && handler == SIG_DFL && !(force && sig_kernel_only(sig))) return true; /* Only allow kernel generated signals to this kthread */ if (unlikely((t->flags & PF_KTHREAD) && (handler == SIG_KTHREAD_KERNEL) && !force)) return true; return sig_handler_ignored(handler, sig); } static bool sig_ignored(struct task_struct *t, int sig, bool force) { /* * Blocked signals are never ignored, since the * signal handler may change by the time it is * unblocked. */ if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return false; /* * Tracers may want to know about even ignored signal unless it * is SIGKILL which can't be reported anyway but can be ignored * by SIGNAL_UNKILLABLE task. */ if (t->ptrace && sig != SIGKILL) return false; return sig_task_ignored(t, sig, force); } /* * Re-calculate pending state from the set of locally pending * signals, globally pending signals, and blocked signals. */ static inline bool has_pending_signals(sigset_t *signal, sigset_t *blocked) { unsigned long ready; long i; switch (_NSIG_WORDS) { default: for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;) ready |= signal->sig[i] &~ blocked->sig[i]; break; case 4: ready = signal->sig[3] &~ blocked->sig[3]; ready |= signal->sig[2] &~ blocked->sig[2]; ready |= signal->sig[1] &~ blocked->sig[1]; ready |= signal->sig[0] &~ blocked->sig[0]; break; case 2: ready = signal->sig[1] &~ blocked->sig[1]; ready |= signal->sig[0] &~ blocked->sig[0]; break; case 1: ready = signal->sig[0] &~ blocked->sig[0]; } return ready != 0; } #define PENDING(p,b) has_pending_signals(&(p)->signal, (b)) static bool recalc_sigpending_tsk(struct task_struct *t) { if ((t->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) || PENDING(&t->pending, &t->blocked) || PENDING(&t->signal->shared_pending, &t->blocked) || cgroup_task_frozen(t)) { set_tsk_thread_flag(t, TIF_SIGPENDING); return true; } /* * We must never clear the flag in another thread, or in current * when it's possible the current syscall is returning -ERESTART*. * So we don't clear it here, and only callers who know they should do. */ return false; } void recalc_sigpending(void) { if (!recalc_sigpending_tsk(current) && !freezing(current)) clear_thread_flag(TIF_SIGPENDING); } EXPORT_SYMBOL(recalc_sigpending); void calculate_sigpending(void) { /* Have any signals or users of TIF_SIGPENDING been delayed * until after fork? */ spin_lock_irq(¤t->sighand->siglock); set_tsk_thread_flag(current, TIF_SIGPENDING); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); } /* Given the mask, find the first available signal that should be serviced. */ #define SYNCHRONOUS_MASK \ (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS)) int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; int sig = 0; s = pending->signal.sig; m = mask->sig; /* * Handle the first word specially: it contains the * synchronous signals that need to be dequeued first. */ x = *s &~ *m; if (x) { if (x & SYNCHRONOUS_MASK) x &= SYNCHRONOUS_MASK; sig = ffz(~x) + 1; return sig; } switch (_NSIG_WORDS) { default: for (i = 1; i < _NSIG_WORDS; ++i) { x = *++s &~ *++m; if (!x) continue; sig = ffz(~x) + i*_NSIG_BPW + 1; break; } break; case 2: x = s[1] &~ m[1]; if (!x) break; sig = ffz(~x) + _NSIG_BPW + 1; break; case 1: /* Nothing to do */ break; } return sig; } static inline void print_dropped_signal(int sig) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); if (!print_fatal_signals) return; if (!__ratelimit(&ratelimit_state)) return; pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", current->comm, current->pid, sig); } /** * task_set_jobctl_pending - set jobctl pending bits * @task: target task * @mask: pending bits to set * * Clear @mask from @task->jobctl. @mask must be subset of * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK | * %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is * cleared. If @task is already being killed or exiting, this function * becomes noop. * * CONTEXT: * Must be called with @task->sighand->siglock held. * * RETURNS: * %true if @mask is set, %false if made noop because @task was dying. */ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) return false; if (mask & JOBCTL_STOP_SIGMASK) task->jobctl &= ~JOBCTL_STOP_SIGMASK; task->jobctl |= mask; return true; } /** * task_clear_jobctl_trapping - clear jobctl trapping bit * @task: target task * * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED. * Clear it and wake up the ptracer. Note that we don't need any further * locking. @task->siglock guarantees that @task->parent points to the * ptracer. * * CONTEXT: * Must be called with @task->sighand->siglock held. */ void task_clear_jobctl_trapping(struct task_struct *task) { if (unlikely(task->jobctl & JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_TRAPPING; smp_mb(); /* advised by wake_up_bit() */ wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT); } } /** * task_clear_jobctl_pending - clear jobctl pending bits * @task: target task * @mask: pending bits to clear * * Clear @mask from @task->jobctl. @mask must be subset of * %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other * STOP bits are cleared together. * * If clearing of @mask leaves no stop or trap pending, this function calls * task_clear_jobctl_trapping(). * * CONTEXT: * Must be called with @task->sighand->siglock held. */ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~JOBCTL_PENDING_MASK); if (mask & JOBCTL_STOP_PENDING) mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED; task->jobctl &= ~mask; if (!(task->jobctl & JOBCTL_PENDING_MASK)) task_clear_jobctl_trapping(task); } /** * task_participate_group_stop - participate in a group stop * @task: task participating in a group stop * * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. * Group stop states are cleared and the group stop count is consumed if * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group * stop, the appropriate `SIGNAL_*` flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. * * RETURNS: * %true if group stop completion should be notified to the parent, %false * otherwise. */ static bool task_participate_group_stop(struct task_struct *task) { struct signal_struct *sig = task->signal; bool consume = task->jobctl & JOBCTL_STOP_CONSUME; WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)); task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING); if (!consume) return false; if (!WARN_ON_ONCE(sig->group_stop_count == 0)) sig->group_stop_count--; /* * Tell the caller to notify completion iff we are entering into a * fresh group stop. Read comment in do_signal_stop() for details. */ if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED); return true; } return false; } void task_join_group_stop(struct task_struct *task) { unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK; struct signal_struct *sig = current->signal; if (sig->group_stop_count) { sig->group_stop_count++; mask |= JOBCTL_STOP_CONSUME; } else if (!(sig->flags & SIGNAL_STOP_STOPPED)) return; /* Have the new thread join an on-going signal group stop */ task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, int override_rlimit, const unsigned int sigqueue_flags) { struct sigqueue *q = NULL; struct ucounts *ucounts; long sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. * * NOTE! A pending signal will hold on to the user refcount, * and we get/put the refcount only when the sigpending count * changes from/to zero. */ rcu_read_lock(); ucounts = task_ucounts(t); sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); if (!sigpending) return NULL; if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); } else { INIT_LIST_HEAD(&q->list); q->flags = sigqueue_flags; q->ucounts = ucounts; } return q; } static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; if (q->ucounts) { dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING); q->ucounts = NULL; } kmem_cache_free(sigqueue_cachep, q); } void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; sigemptyset(&queue->signal); while (!list_empty(&queue->list)) { q = list_entry(queue->list.next, struct sigqueue , list); list_del_init(&q->list); __sigqueue_free(q); } } /* * Flush all pending signals for this kthread. */ void flush_signals(struct task_struct *t) { unsigned long flags; spin_lock_irqsave(&t->sighand->siglock, flags); clear_tsk_thread_flag(t, TIF_SIGPENDING); flush_sigqueue(&t->pending); flush_sigqueue(&t->signal->shared_pending); spin_unlock_irqrestore(&t->sighand->siglock, flags); } EXPORT_SYMBOL(flush_signals); #ifdef CONFIG_POSIX_TIMERS static void __flush_itimer_signals(struct sigpending *pending) { sigset_t signal, retain; struct sigqueue *q, *n; signal = pending->signal; sigemptyset(&retain); list_for_each_entry_safe(q, n, &pending->list, list) { int sig = q->info.si_signo; if (likely(q->info.si_code != SI_TIMER)) { sigaddset(&retain, sig); } else { sigdelset(&signal, sig); list_del_init(&q->list); __sigqueue_free(q); } } sigorsets(&pending->signal, &signal, &retain); } void flush_itimer_signals(void) { struct task_struct *tsk = current; unsigned long flags; spin_lock_irqsave(&tsk->sighand->siglock, flags); __flush_itimer_signals(&tsk->pending); __flush_itimer_signals(&tsk->signal->shared_pending); spin_unlock_irqrestore(&tsk->sighand->siglock, flags); } #endif void ignore_signals(struct task_struct *t) { int i; for (i = 0; i < _NSIG; ++i) t->sighand->action[i].sa.sa_handler = SIG_IGN; flush_signals(t); } /* * Flush all handlers for a task. */ void flush_signal_handlers(struct task_struct *t, int force_default) { int i; struct k_sigaction *ka = &t->sighand->action[0]; for (i = _NSIG ; i != 0 ; i--) { if (force_default || ka->sa.sa_handler != SIG_IGN) ka->sa.sa_handler = SIG_DFL; ka->sa.sa_flags = 0; #ifdef __ARCH_HAS_SA_RESTORER ka->sa.sa_restorer = NULL; #endif sigemptyset(&ka->sa.sa_mask); ka++; } } bool unhandled_signal(struct task_struct *tsk, int sig) { void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler; if (is_global_init(tsk)) return true; if (handler != SIG_IGN && handler != SIG_DFL) return false; /* If dying, we handle all new signals by ignoring them */ if (fatal_signal_pending(tsk)) return false; /* if ptraced, let the tracer determine */ return !tsk->ptrace; } static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, bool *resched_timer) { struct sigqueue *q, *first = NULL; /* * Collect the siginfo appropriate to this signal. Check if * there is another siginfo for the same signal. */ list_for_each_entry(q, &list->list, list) { if (q->info.si_signo == sig) { if (first) goto still_pending; first = q; } } sigdelset(&list->signal, sig); if (first) { still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); *resched_timer = (first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER) && (info->si_sys_private); __sigqueue_free(first); } else { /* * Ok, it wasn't in the queue. This must be * a fast-pathed signal or we must have been * out of queue space. So zero out the info. */ clear_siginfo(info); info->si_signo = sig; info->si_errno = 0; info->si_code = SI_USER; info->si_pid = 0; info->si_uid = 0; } } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, kernel_siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) collect_signal(sig, pending, info, resched_timer); return sig; } /* * Dequeue a signal and return the element to the caller, which is * expected to free it. * * All callers have to hold the siglock. */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS /* * itimer signal ? * * itimers are process shared and we restart periodic * itimers in the signal delivery path to prevent DoS * attacks in the high resolution timer case. This is * compliant with the old way of self-restarting * itimers, as the SIGALRM is a legacy signal and only * queued once. Changing the restart behaviour to * restart the timer in the signal dequeue path is * reducing the timer noise on heavy loaded !highres * systems too. */ if (unlikely(signr == SIGALRM)) { struct hrtimer *tmr = &tsk->signal->real_timer; if (!hrtimer_is_queued(tmr) && tsk->signal->it_real_incr != 0) { hrtimer_forward(tmr, tmr->base->get_time(), tsk->signal->it_real_incr); hrtimer_restart(tmr); } } #endif } recalc_sigpending(); if (!signr) return 0; if (unlikely(sig_kernel_stop(signr))) { /* * Set a marker that we have dequeued a stop signal. Our * caller might release the siglock and then the pending * stop signal it is about to process is no longer in the * pending bitmasks, but must still be cleared by a SIGCONT * (and overruled by a SIGKILL). So those cases clear this * shared flag after we've set it. Note that this flag may * remain set after the signal we return is ignored or * handled. That doesn't matter because its only purpose * is to alert stop-signal processing code when another * processor has come along and cleared the flag. */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } #ifdef CONFIG_POSIX_TIMERS if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave * irqs disabled here, since the posix-timers code is * about to disable them again anyway. */ spin_unlock(&tsk->sighand->siglock); posixtimer_rearm(info); spin_lock(&tsk->sighand->siglock); /* Don't expose the si_sys_private value to userspace */ info->si_sys_private = 0; } #endif return signr; } EXPORT_SYMBOL_GPL(dequeue_signal); static int dequeue_synchronous_signal(kernel_siginfo_t *info) { struct task_struct *tsk = current; struct sigpending *pending = &tsk->pending; struct sigqueue *q, *sync = NULL; /* * Might a synchronous signal be in the queue? */ if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) return 0; /* * Return the first synchronous signal in the queue. */ list_for_each_entry(q, &pending->list, list) { /* Synchronous signals have a positive si_code */ if ((q->info.si_code > SI_USER) && (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { sync = q; goto next; } } return 0; next: /* * Check if there is another siginfo for the same signal. */ list_for_each_entry_continue(q, &pending->list, list) { if (q->info.si_signo == sync->info.si_signo) goto still_pending; } sigdelset(&pending->signal, sync->info.si_signo); recalc_sigpending(); still_pending: list_del_init(&sync->list); copy_siginfo(info, &sync->info); __sigqueue_free(sync); return info->si_signo; } /* * Tell a process that it has a new active signal.. * * NOTE! we rely on the previous spin_lock to * lock interrupts for us! We can only be called with * "siglock" held, and the local interrupt must * have been disabled when that got acquired! * * No need to set need_resched since signal event passing * goes through ->blocked */ void signal_wake_up_state(struct task_struct *t, unsigned int state) { lockdep_assert_held(&t->sighand->siglock); set_tsk_thread_flag(t, TIF_SIGPENDING); /* * TASK_WAKEKILL also means wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it * executing another processor and just now entering stopped state. * By using wake_up_state, we ensure the process will wake up and * handle its death signal. */ if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t); } /* * Remove signals in mask from the pending set and queue. * Returns 1 if any signals were found. * * All callers must be holding the siglock. */ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) { struct sigqueue *q, *n; sigset_t m; sigandsets(&m, mask, &s->signal); if (sigisemptyset(&m)) return; sigandnsets(&s->signal, &s->signal, mask); list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); __sigqueue_free(q); } } } static inline int is_si_special(const struct kernel_siginfo *info) { return info <= SEND_SIG_PRIV; } static inline bool si_fromuser(const struct kernel_siginfo *info) { return info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)); } /* * called with RCU read lock from check_kill_permission() */ static bool kill_ok_by_cred(struct task_struct *t) { const struct cred *cred = current_cred(); const struct cred *tcred = __task_cred(t); return uid_eq(cred->euid, tcred->suid) || uid_eq(cred->euid, tcred->uid) || uid_eq(cred->uid, tcred->suid) || uid_eq(cred->uid, tcred->uid) || ns_capable(tcred->user_ns, CAP_KILL); } /* * Bad permissions for sending the signal * - the caller must hold the RCU read lock */ static int check_kill_permission(int sig, struct kernel_siginfo *info, struct task_struct *t) { struct pid *sid; int error; if (!valid_signal(sig)) return -EINVAL; if (!si_fromuser(info)) return 0; error = audit_signal_info(sig, t); /* Let audit system see the signal */ if (error) return error; if (!same_thread_group(current, t) && !kill_ok_by_cred(t)) { switch (sig) { case SIGCONT: sid = task_session(t); /* * We don't return the error if sid == NULL. The * task was unhashed, the caller must notice this. */ if (!sid || sid == task_session(current)) break; fallthrough; default: return -EPERM; } } return security_task_kill(t, info, sig, NULL); } /** * ptrace_trap_notify - schedule trap to notify ptracer * @t: tracee wanting to notify tracer * * This function schedules sticky ptrace trap which is cleared on the next * TRAP_STOP to notify ptracer of an event. @t must have been seized by * ptracer. * * If @t is running, STOP trap will be taken. If trapped for STOP and * ptracer is listening for events, tracee is woken up so that it can * re-trap for the new event. If trapped otherwise, STOP trap will be * eventually taken without returning to userland after the existing traps * are finished by PTRACE_CONT. * * CONTEXT: * Must be called with @task->sighand->siglock held. */ static void ptrace_trap_notify(struct task_struct *t) { WARN_ON_ONCE(!(t->ptrace & PT_SEIZED)); lockdep_assert_held(&t->sighand->siglock); task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); } /* * Handle magic process-wide effects of stop/continue signals. Unlike * the signal actions, these happen immediately at signal-generation * time regardless of blocking, ignoring, or handling. This does the * actual continuing for SIGCONT, but not the actual stopping for stop * signals. The process stop is done as a signal action for SIG_DFL. * * Returns true if the signal should be actually delivered, otherwise * it should be dropped. */ static bool prepare_signal(int sig, struct task_struct *p, bool force) { struct signal_struct *signal = p->signal; struct task_struct *t; sigset_t flush; if (signal->flags & SIGNAL_GROUP_EXIT) { if (signal->core_state) return sig == SIGKILL; /* * The process is in the middle of dying, drop the signal. */ return false; } else if (sig_kernel_stop(sig)) { /* * This is a stop signal. Remove SIGCONT from all queues. */ siginitset(&flush, sigmask(SIGCONT)); flush_sigqueue_mask(&flush, &signal->shared_pending); for_each_thread(p, t) flush_sigqueue_mask(&flush, &t->pending); } else if (sig == SIGCONT) { unsigned int why; /* * Remove all stop signals from all queues, wake all threads. */ siginitset(&flush, SIG_KERNEL_STOP_MASK); flush_sigqueue_mask(&flush, &signal->shared_pending); for_each_thread(p, t) { flush_sigqueue_mask(&flush, &t->pending); task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); if (likely(!(t->ptrace & PT_SEIZED))) { t->jobctl &= ~JOBCTL_STOPPED; wake_up_state(t, __TASK_STOPPED); } else ptrace_trap_notify(t); } /* * Notify the parent with CLD_CONTINUED if we were stopped. * * If we were in the middle of a group stop, we pretend it * was already finished, and then continued. Since SIGCHLD * doesn't queue we report only CLD_STOPPED, as if the next * CLD_CONTINUED was dropped. */ why = 0; if (signal->flags & SIGNAL_STOP_STOPPED) why |= SIGNAL_CLD_CONTINUED; else if (signal->group_stop_count) why |= SIGNAL_CLD_STOPPED; if (why) { /* * The first thread which returns from do_signal_stop() * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal(). */ signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED); signal->group_stop_count = 0; signal->group_exit_code = 0; } } return !sig_ignored(p, sig, force); } /* * Test if P wants to take SIG. After we've checked all threads with this, * it's equivalent to finding no threads not blocking SIG. Any threads not * blocking SIG were ruled out because they are not running and already * have pending signals. Such threads will dequeue from the shared queue * as soon as they're available, so putting the signal on the shared queue * will be equivalent to sending it to one such thread. */ static inline bool wants_signal(int sig, struct task_struct *p) { if (sigismember(&p->blocked, sig)) return false; if (p->flags & PF_EXITING) return false; if (sig == SIGKILL) return true; if (task_is_stopped_or_traced(p)) return false; return task_curr(p) || !task_sigpending(p); } static void complete_signal(int sig, struct task_struct *p, enum pid_type type) { struct signal_struct *signal = p->signal; struct task_struct *t; /* * Now find a thread we can wake up to take the signal off the queue. * * Try the suggested task first (may or may not be the main thread). */ if (wants_signal(sig, p)) t = p; else if ((type == PIDTYPE_PID) || thread_group_empty(p)) /* * There is just one thread and it does not need to be woken. * It will dequeue unblocked signals before it runs again. */ return; else { /* * Otherwise try to find a suitable thread. */ t = signal->curr_target; while (!wants_signal(sig, t)) { t = next_thread(t); if (t == signal->curr_target) /* * No thread needs to be woken. * Any eligible threads will see * the signal in the queue soon. */ return; } signal->curr_target = t; } /* * Found a killable thread. If the signal will be fatal, * then start taking the whole group down immediately. */ if (sig_fatal(p, sig) && (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || !p->ptrace)) { /* * This signal will be fatal to the whole group. */ if (!sig_kernel_coredump(sig)) { /* * Start a group exit and wake everybody up. * This way we don't have other threads * running and doing things after a slower * thread has the fatal signal pending. */ signal->flags = SIGNAL_GROUP_EXIT; signal->group_exit_code = sig; signal->group_stop_count = 0; __for_each_thread(signal, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } return; } } /* * The signal is already in the shared-pending queue. * Tell the chosen thread to wake up and dequeue it. */ signal_wake_up(t, sig == SIGKILL); return; } static inline bool legacy_queue(struct sigpending *signals, int sig) { return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } static int __send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type, bool force) { struct sigpending *pending; struct sigqueue *q; int override_rlimit; int ret = 0, result; lockdep_assert_held(&t->sighand->siglock); result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, force)) goto ret; pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; /* * Short-circuit ignored signals and support queuing * exactly one non-rt signal, so that we can get more * detailed information about the cause of the signal. */ result = TRACE_SIGNAL_ALREADY_PENDING; if (legacy_queue(pending, sig)) goto ret; result = TRACE_SIGNAL_DELIVERED; /* * Skip useless siginfo allocation for SIGKILL and kernel threads. */ if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* * Real-time signals must be queued if sent by sigqueue, or * some other real-time mechanism. It is implementation * defined whether kill() does so. We attempt to do so, on * the principle of least surprise, but since kill is not * allowed to fail with EAGAIN when low on memory we just * make sure at least one signal gets delivered and don't * pass on the info struct. */ if (sig < SIGRTMIN) override_rlimit = (is_si_special(info) || info->si_code >= 0); else override_rlimit = 0; q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0); if (q) { list_add_tail(&q->list, &pending->list); switch ((unsigned long) info) { case (unsigned long) SEND_SIG_NOINFO: clear_siginfo(&q->info); q->info.si_signo = sig; q->info.si_errno = 0; q->info.si_code = SI_USER; q->info.si_pid = task_tgid_nr_ns(current, task_active_pid_ns(t)); rcu_read_lock(); q->info.si_uid = from_kuid_munged(task_cred_xxx(t, user_ns), current_uid()); rcu_read_unlock(); break; case (unsigned long) SEND_SIG_PRIV: clear_siginfo(&q->info); q->info.si_signo = sig; q->info.si_errno = 0; q->info.si_code = SI_KERNEL; q->info.si_pid = 0; q->info.si_uid = 0; break; default: copy_siginfo(&q->info, info); break; } } else if (!is_si_special(info) && sig >= SIGRTMIN && info->si_code != SI_USER) { /* * Queue overflow, abort. We may abort if the * signal was rt and sent by user using something * other than kill(). */ result = TRACE_SIGNAL_OVERFLOW_FAIL; ret = -EAGAIN; goto ret; } else { /* * This is a silent loss of information. We still * send the signal, but the *info bits are lost. */ result = TRACE_SIGNAL_LOSE_INFO; } out_set: signalfd_notify(t, sig); sigaddset(&pending->signal, sig); /* Let multiprocess signals appear after on-going forks */ if (type > PIDTYPE_TGID) { struct multiprocess_signals *delayed; hlist_for_each_entry(delayed, &t->signal->multiprocess, node) { sigset_t *signal = &delayed->signal; /* Can't queue both a stop and a continue signal */ if (sig == SIGCONT) sigdelsetmask(signal, SIG_KERNEL_STOP_MASK); else if (sig_kernel_stop(sig)) sigdelset(signal, SIGCONT); sigaddset(signal, sig); } } complete_signal(sig, t, type); ret: trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result); return ret; } static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) { bool ret = false; switch (siginfo_layout(info->si_signo, info->si_code)) { case SIL_KILL: case SIL_CHLD: case SIL_RT: ret = true; break; case SIL_TIMER: case SIL_POLL: case SIL_FAULT: case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: case SIL_FAULT_PERF_EVENT: case SIL_SYS: ret = false; break; } return ret; } int send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type) { /* Should SIGKILL or SIGSTOP be received by a pid namespace init? */ bool force = false; if (info == SEND_SIG_NOINFO) { /* Force if sent from an ancestor pid namespace */ force = !task_pid_nr_ns(current, task_active_pid_ns(t)); } else if (info == SEND_SIG_PRIV) { /* Don't ignore kernel generated signals */ force = true; } else if (has_si_pid_and_uid(info)) { /* SIGKILL and SIGSTOP is special or has ids */ struct user_namespace *t_user_ns; rcu_read_lock(); t_user_ns = task_cred_xxx(t, user_ns); if (current_user_ns() != t_user_ns) { kuid_t uid = make_kuid(current_user_ns(), info->si_uid); info->si_uid = from_kuid_munged(t_user_ns, uid); } rcu_read_unlock(); /* A kernel generated signal? */ force = (info->si_code == SI_KERNEL); /* From an ancestor pid namespace? */ if (!task_pid_nr_ns(current, task_active_pid_ns(t))) { info->si_pid = 0; force = true; } } return __send_signal_locked(sig, info, t, type, force); } static void print_fatal_signal(int signr) { struct pt_regs *regs = task_pt_regs(current); struct file *exe_file; exe_file = get_task_exe_file(current); if (exe_file) { pr_info("%pD: %s: potentially unexpected fatal signal %d.\n", exe_file, current->comm, signr); fput(exe_file); } else { pr_info("%s: potentially unexpected fatal signal %d.\n", current->comm, signr); } #if defined(__i386__) && !defined(__arch_um__) pr_info("code at %08lx: ", regs->ip); { int i; for (i = 0; i < 16; i++) { unsigned char insn; if (get_user(insn, (unsigned char *)(regs->ip + i))) break; pr_cont("%02x ", insn); } } pr_cont("\n"); #endif preempt_disable(); show_regs(regs); preempt_enable(); } static int __init setup_print_fatal_signals(char *str) { get_option (&str, &print_fatal_signals); return 1; } __setup("print-fatal-signals=", setup_print_fatal_signals); int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { unsigned long flags; int ret = -ESRCH; if (lock_task_sighand(p, &flags)) { ret = send_signal_locked(sig, info, p, type); unlock_task_sighand(p, &flags); } return ret; } enum sig_handler { HANDLER_CURRENT, /* If reachable use the current handler */ HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */ HANDLER_EXIT, /* Only visible as the process exit code */ }; /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. * * Note: If we unblock the signal, we always reset it to SIG_DFL, * since we do not want to have a signal handler that was blocked * be invoked when user space had explicitly blocked it. * * We don't want to have recursive SIGSEGV's etc, for example, * that is why we also clear SIGNAL_UNKILLABLE. */ static int force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, enum sig_handler handler) { unsigned long int flags; int ret, blocked, ignored; struct k_sigaction *action; int sig = info->si_signo; spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; blocked = sigismember(&t->blocked, sig); if (blocked || ignored || (handler != HANDLER_CURRENT)) { action->sa.sa_handler = SIG_DFL; if (handler == HANDLER_EXIT) action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) sigdelset(&t->blocked, sig); } /* * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect * debugging to leave init killable. But HANDLER_EXIT is always fatal. */ if (action->sa.sa_handler == SIG_DFL && (!t->ptrace || (handler == HANDLER_EXIT))) t->signal->flags &= ~SIGNAL_UNKILLABLE; ret = send_signal_locked(sig, info, t, PIDTYPE_PID); /* This can happen if the signal was already pending and blocked */ if (!task_sigpending(t)) signal_wake_up(t, 0); spin_unlock_irqrestore(&t->sighand->siglock, flags); return ret; } int force_sig_info(struct kernel_siginfo *info) { return force_sig_info_to_task(info, current, HANDLER_CURRENT); } /* * Nuke all other threads in the group. */ int zap_other_threads(struct task_struct *p) { struct task_struct *t; int count = 0; p->signal->group_stop_count = 0; for_other_threads(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); count++; /* Don't bother with already dead threads */ if (t->exit_state) continue; sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } return count; } struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags) { struct sighand_struct *sighand; rcu_read_lock(); for (;;) { sighand = rcu_dereference(tsk->sighand); if (unlikely(sighand == NULL)) break; /* * This sighand can be already freed and even reused, but * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which * initializes ->siglock: this slab can't go away, it has * the same object type, ->siglock can't be reinitialized. * * We need to ensure that tsk->sighand is still the same * after we take the lock, we can race with de_thread() or * __exit_signal(). In the latter case the next iteration * must see ->sighand == NULL. */ spin_lock_irqsave(&sighand->siglock, *flags); if (likely(sighand == rcu_access_pointer(tsk->sighand))) break; spin_unlock_irqrestore(&sighand->siglock, *flags); } rcu_read_unlock(); return sighand; } #ifdef CONFIG_LOCKDEP void lockdep_assert_task_sighand_held(struct task_struct *task) { struct sighand_struct *sighand; rcu_read_lock(); sighand = rcu_dereference(task->sighand); if (sighand) lockdep_assert_held(&sighand->siglock); else WARN_ON_ONCE(1); rcu_read_unlock(); } #endif /* * send signal info to all the members of a thread group or to the * individual thread if type == PIDTYPE_PID. */ int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { int ret; rcu_read_lock(); ret = check_kill_permission(sig, info, p); rcu_read_unlock(); if (!ret && sig) ret = do_send_sig_info(sig, info, p, type); return ret; } /* * __kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) * - the caller must hold at least a readlock on tasklist_lock */ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int ret = -ESRCH; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID); /* * If group_send_sig_info() succeeds at least once ret * becomes 0 and after that the code below has no effect. * Otherwise we return the last err or -ESRCH if this * process group is empty. */ if (ret) ret = err; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return ret; } static int kill_pid_info_type(int sig, struct kernel_siginfo *info, struct pid *pid, enum pid_type type) { int error = -ESRCH; struct task_struct *p; for (;;) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) error = group_send_sig_info(sig, info, p, type); rcu_read_unlock(); if (likely(!p || error != -ESRCH)) return error; /* * The task was unhashed in between, try again. If it * is dead, pid_task() will return NULL, if we race with * de_thread() it will find the new leader. */ } } int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) { return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID); } static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; rcu_read_lock(); error = kill_pid_info(sig, info, find_vpid(pid)); rcu_read_unlock(); return error; } static inline bool kill_as_cred_perm(const struct cred *cred, struct task_struct *target) { const struct cred *pcred = __task_cred(target); return uid_eq(cred->euid, pcred->suid) || uid_eq(cred->euid, pcred->uid) || uid_eq(cred->uid, pcred->suid) || uid_eq(cred->uid, pcred->uid); } /* * The usb asyncio usage of siginfo is wrong. The glibc support * for asyncio which uses SI_ASYNCIO assumes the layout is SIL_RT. * AKA after the generic fields: * kernel_pid_t si_pid; * kernel_uid32_t si_uid; * sigval_t si_value; * * Unfortunately when usb generates SI_ASYNCIO it assumes the layout * after the generic fields is: * void __user *si_addr; * * This is a practical problem when there is a 64bit big endian kernel * and a 32bit userspace. As the 32bit address will encoded in the low * 32bits of the pointer. Those low 32bits will be stored at higher * address than appear in a 32 bit pointer. So userspace will not * see the address it was expecting for it's completions. * * There is nothing in the encoding that can allow * copy_siginfo_to_user32 to detect this confusion of formats, so * handle this by requiring the caller of kill_pid_usb_asyncio to * notice when this situration takes place and to store the 32bit * pointer in sival_int, instead of sival_addr of the sigval_t addr * parameter. */ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *pid, const struct cred *cred) { struct kernel_siginfo info; struct task_struct *p; unsigned long flags; int ret = -EINVAL; if (!valid_signal(sig)) return ret; clear_siginfo(&info); info.si_signo = sig; info.si_errno = errno; info.si_code = SI_ASYNCIO; *((sigval_t *)&info.si_pid) = addr; rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (!p) { ret = -ESRCH; goto out_unlock; } if (!kill_as_cred_perm(cred, p)) { ret = -EPERM; goto out_unlock; } ret = security_task_kill(p, &info, sig, cred); if (ret) goto out_unlock; if (sig) { if (lock_task_sighand(p, &flags)) { ret = __send_signal_locked(sig, &info, p, PIDTYPE_TGID, false); unlock_task_sighand(p, &flags); } else ret = -ESRCH; } out_unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(kill_pid_usb_asyncio); /* * kill_something_info() interprets pid in interesting ways just like kill(2). * * POSIX specifies that kill(-1,sig) is unspecified, but what we have * is probably wrong. Should make it like BSD or SYSV. */ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid) { int ret; if (pid > 0) return kill_proc_info(sig, info, pid); /* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */ if (pid == INT_MIN) return -ESRCH; read_lock(&tasklist_lock); if (pid != -1) { ret = __kill_pgrp_info(sig, info, pid ? find_vpid(-pid) : task_pgrp(current)); } else { int retval = 0, count = 0; struct task_struct * p; for_each_process(p) { if (task_pid_vnr(p) > 1 && !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p, PIDTYPE_MAX); ++count; if (err != -EPERM) retval = err; } } ret = count ? retval : -ESRCH; } read_unlock(&tasklist_lock); return ret; } /* * These are for backward compatibility with the rest of the kernel source. */ int send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { /* * Make sure legacy kernel users don't send in bad values * (normal paths check this in check_kill_permission). */ if (!valid_signal(sig)) return -EINVAL; return do_send_sig_info(sig, info, p, PIDTYPE_PID); } EXPORT_SYMBOL(send_sig_info); #define __si_special(priv) \ ((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO) int send_sig(int sig, struct task_struct *p, int priv) { return send_sig_info(sig, __si_special(priv), p); } EXPORT_SYMBOL(send_sig); void force_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info(&info); } EXPORT_SYMBOL(force_sig); void force_fatal_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info_to_task(&info, current, HANDLER_SIG_DFL); } void force_exit_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info_to_task(&info, current, HANDLER_EXIT); } /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused * the problem was already a SIGSEGV, we'll want to * make sure we don't even try to deliver the signal.. */ void force_sigsegv(int sig) { if (sig == SIGSEGV) force_fatal_sig(SIGSEGV); else force_sig(SIGSEGV); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; return force_sig_info_to_task(&info, t, HANDLER_CURRENT); } int force_sig_fault(int sig, int code, void __user *addr) { return force_sig_fault_to_task(sig, code, addr, current); } int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; return send_sig_info(info.si_signo, &info, t); } int force_sig_mceerr(int code, void __user *addr, short lsb) { struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_addr_lsb = lsb; return force_sig_info(&info); } int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_addr_lsb = lsb; return send_sig_info(info.si_signo, &info, t); } EXPORT_SYMBOL(send_sig_mceerr); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; info.si_errno = 0; info.si_code = SEGV_BNDERR; info.si_addr = addr; info.si_lower = lower; info.si_upper = upper; return force_sig_info(&info); } #ifdef SEGV_PKUERR int force_sig_pkuerr(void __user *addr, u32 pkey) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; info.si_errno = 0; info.si_code = SEGV_PKUERR; info.si_addr = addr; info.si_pkey = pkey; return force_sig_info(&info); } #endif int send_sig_perf(void __user *addr, u32 type, u64 sig_data) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; info.si_code = TRAP_PERF; info.si_addr = addr; info.si_perf_data = sig_data; info.si_perf_type = type; /* * Signals generated by perf events should not terminate the whole * process if SIGTRAP is blocked, however, delivering the signal * asynchronously is better than not delivering at all. But tell user * space if the signal was asynchronous, so it can clearly be * distinguished from normal synchronous ones. */ info.si_perf_flags = sigismember(¤t->blocked, info.si_signo) ? TRAP_PERF_FLAG_ASYNC : 0; return send_sig_info(info.si_signo, &info, current); } /** * force_sig_seccomp - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland * @reason: filter-supplied reason code to send to userland (via si_errno) * @force_coredump: true to trigger a coredump * * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. */ int force_sig_seccomp(int syscall, int reason, bool force_coredump) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSYS; info.si_code = SYS_SECCOMP; info.si_call_addr = (void __user *)KSTK_EIP(current); info.si_errno = reason; info.si_arch = syscall_get_arch(current); info.si_syscall = syscall; return force_sig_info_to_task(&info, current, force_coredump ? HANDLER_EXIT : HANDLER_CURRENT); } /* For the crazy architectures that include trap information in * the errno field, instead of an actual errno value. */ int force_sig_ptrace_errno_trap(int errno, void __user *addr) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = errno; info.si_code = TRAP_HWBKPT; info.si_addr = addr; return force_sig_info(&info); } /* For the rare architectures that include trap information using * si_trapno. */ int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_trapno = trapno; return force_sig_info(&info); } /* For the rare architectures that include trap information using * si_trapno. */ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_trapno = trapno; return send_sig_info(info.si_signo, &info, t); } static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { int ret; read_lock(&tasklist_lock); ret = __kill_pgrp_info(sig, info, pgrp); read_unlock(&tasklist_lock); return ret; } int kill_pgrp(struct pid *pid, int sig, int priv) { return kill_pgrp_info(sig, __si_special(priv), pid); } EXPORT_SYMBOL(kill_pgrp); int kill_pid(struct pid *pid, int sig, int priv) { return kill_pid_info(sig, __si_special(priv), pid); } EXPORT_SYMBOL(kill_pid); /* * These functions support sending signals using preallocated sigqueue * structures. This is needed "because realtime applications cannot * afford to lose notifications of asynchronous events, like timer * expirations or I/O completions". In the case of POSIX Timers * we allocate the sigqueue structure from the timer_create. If this * allocation fails we are able to report the failure to the application * with an EAGAIN error. */ struct sigqueue *sigqueue_alloc(void) { return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); } void sigqueue_free(struct sigqueue *q) { unsigned long flags; spinlock_t *lock = ¤t->sighand->siglock; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); /* * We must hold ->siglock while testing q->list * to serialize with collect_signal() or with * __exit_signal()->flush_sigqueue(). */ spin_lock_irqsave(lock, flags); q->flags &= ~SIGQUEUE_PREALLOC; /* * If it is queued it will be freed when dequeued, * like the "regular" sigqueue. */ if (!list_empty(&q->list)) q = NULL; spin_unlock_irqrestore(lock, flags); if (q) __sigqueue_free(q); } int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) { int sig = q->info.si_signo; struct sigpending *pending; struct task_struct *t; unsigned long flags; int ret, result; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); ret = -1; rcu_read_lock(); /* * This function is used by POSIX timers to deliver a timer signal. * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID * set), the signal must be delivered to the specific thread (queues * into t->pending). * * Where type is not PIDTYPE_PID, signals must be delivered to the * process. In this case, prefer to deliver to current if it is in * the same thread group as the target process, which avoids * unnecessarily waking up a potentially idle task. */ t = pid_task(pid, type); if (!t) goto ret; if (type != PIDTYPE_PID && same_thread_group(t, current)) t = current; if (!likely(lock_task_sighand(t, &flags))) goto ret; ret = 1; /* the signal is ignored */ result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, false)) goto out; ret = 0; if (unlikely(!list_empty(&q->list))) { /* * If an SI_TIMER entry is already queue just increment * the overrun count. */ BUG_ON(q->info.si_code != SI_TIMER); q->info.si_overrun++; result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } q->info.si_overrun = 0; signalfd_notify(t, sig); pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; list_add_tail(&q->list, &pending->list); sigaddset(&pending->signal, sig); complete_signal(sig, t, type); result = TRACE_SIGNAL_DELIVERED; out: trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); ret: rcu_read_unlock(); return ret; } void do_notify_pidfd(struct task_struct *task) { struct pid *pid = task_pid(task); WARN_ON(task->exit_state == 0); __wake_up(&pid->wait_pidfd, TASK_NORMAL, 0, poll_to_key(EPOLLIN | EPOLLRDNORM)); } /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. * * Returns true if our parent ignored us and so we've switched to * self-reaping. */ bool do_notify_parent(struct task_struct *tsk, int sig) { struct kernel_siginfo info; unsigned long flags; struct sighand_struct *psig; bool autoreap = false; u64 utime, stime; WARN_ON_ONCE(sig == -1); /* do_notify_parent_cldstop should have been called instead. */ WARN_ON_ONCE(task_is_stopped_or_traced(tsk)); WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); /* * tsk is a group leader and has no threads, wake up the * non-PIDFD_THREAD waiters. */ if (thread_group_empty(tsk)) do_notify_pidfd(tsk); if (sig != SIGCHLD) { /* * This is only possible if parent == real_parent. * Check if it has changed security domain. */ if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id)) sig = SIGCHLD; } clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; /* * We are under tasklist_lock here so our parent is tied to * us and cannot change. * * task_active_pid_ns will always return the same pid namespace * until a task passes through release_task. * * write_lock() currently calls preempt_disable() which is the * same as rcu_read_lock(), but according to Oleg, this is not * correct to rely on this */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent)); info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns), task_uid(tsk)); rcu_read_unlock(); task_cputime(tsk, &utime, &stime); info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime); info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) info.si_code = CLD_DUMPED; else if (tsk->exit_code & 0x7f) info.si_code = CLD_KILLED; else { info.si_code = CLD_EXITED; info.si_status = tsk->exit_code >> 8; } psig = tsk->parent->sighand; spin_lock_irqsave(&psig->siglock, flags); if (!tsk->ptrace && sig == SIGCHLD && (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { /* * We are exiting and our parent doesn't care. POSIX.1 * defines special semantics for setting SIGCHLD to SIG_IGN * or setting the SA_NOCLDWAIT flag: we should be reaped * automatically and not left for our parent's wait4 call. * Rather than having the parent do it as a magic kind of * signal handler, we just set this to tell do_exit that we * can be cleaned up without becoming a zombie. Note that * we still call __wake_up_parent in this case, because a * blocked sys_wait4 might now return -ECHILD. * * Whether we send SIGCHLD or not for SA_NOCLDWAIT * is implementation-defined: we do (if you don't want * it, just use SIG_IGN instead). */ autoreap = true; if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) sig = 0; } /* * Send with __send_signal as si_pid and si_uid are in the * parent's namespaces. */ if (valid_signal(sig) && sig) __send_signal_locked(sig, &info, tsk->parent, PIDTYPE_TGID, false); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); return autoreap; } /** * do_notify_parent_cldstop - notify parent of stopped/continued state change * @tsk: task reporting the state change * @for_ptracer: the notification is for ptracer * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report * * Notify @tsk's parent that the stopped/continued state has changed. If * @for_ptracer is %false, @tsk's group leader notifies to its real parent. * If %true, @tsk reports to @tsk->parent which should be the ptracer. * * CONTEXT: * Must be called with tasklist_lock at least read locked. */ static void do_notify_parent_cldstop(struct task_struct *tsk, bool for_ptracer, int why) { struct kernel_siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; u64 utime, stime; if (for_ptracer) { parent = tsk->parent; } else { tsk = tsk->group_leader; parent = tsk->real_parent; } clear_siginfo(&info); info.si_signo = SIGCHLD; info.si_errno = 0; /* * see comment in do_notify_parent() about the following 4 lines */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent)); info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); task_cputime(tsk, &utime, &stime); info.si_utime = nsec_to_clock_t(utime); info.si_stime = nsec_to_clock_t(stime); info.si_code = why; switch (why) { case CLD_CONTINUED: info.si_status = SIGCONT; break; case CLD_STOPPED: info.si_status = tsk->signal->group_exit_code & 0x7f; break; case CLD_TRAPPED: info.si_status = tsk->exit_code & 0x7f; break; default: BUG(); } sighand = parent->sighand; spin_lock_irqsave(&sighand->siglock, flags); if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN && !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP)) send_signal_locked(SIGCHLD, &info, parent, PIDTYPE_TGID); /* * Even if SIGCHLD is not generated, we must wake up wait4 calls. */ __wake_up_parent(tsk, parent); spin_unlock_irqrestore(&sighand->siglock, flags); } /* * This must be called with current->sighand->siglock held. * * This should be the path for all ptrace stops. * We always set current->last_siginfo while stopped here. * That makes it a way to test a stopped process for * being ptrace-stopped vs being job-control-stopped. * * Returns the signal the ptracer requested the code resume * with. If the code did not stop because the tracer is gone, * the stop signal remains unchanged unless clear_code. */ static int ptrace_stop(int exit_code, int why, unsigned long message, kernel_siginfo_t *info) __releases(¤t->sighand->siglock) __acquires(¤t->sighand->siglock) { bool gstop_done = false; if (arch_ptrace_stop_needed()) { /* * The arch code has something special to do before a * ptrace stop. This is allowed to block, e.g. for faults * on user stack pages. We can't keep the siglock while * calling arch_ptrace_stop, so we must release it now. * To preserve proper semantics, we must do this before * any signal bookkeeping like checking group_stop_count. */ spin_unlock_irq(¤t->sighand->siglock); arch_ptrace_stop(); spin_lock_irq(¤t->sighand->siglock); } /* * After this point ptrace_signal_wake_up or signal_wake_up * will clear TASK_TRACED if ptrace_unlink happens or a fatal * signal comes in. Handle previous ptrace_unlinks and fatal * signals here to prevent ptrace_stop sleeping in schedule. */ if (!current->ptrace || __fatal_signal_pending(current)) return exit_code; set_special_state(TASK_TRACED); current->jobctl |= JOBCTL_TRACED; /* * We're committing to trapping. TRACED should be visible before * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). * Also, transition to TRACED and updates to ->jobctl should be * atomic with respect to siglock and should be done after the arch * hook as siglock is released and regrabbed across it. * * TRACER TRACEE * * ptrace_attach() * [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED) * do_wait() * set_current_state() smp_wmb(); * ptrace_do_wait() * wait_task_stopped() * task_stopped_code() * [L] task_is_traced() [S] task_clear_jobctl_trapping(); */ smp_wmb(); current->ptrace_message = message; current->last_siginfo = info; current->exit_code = exit_code; /* * If @why is CLD_STOPPED, we're trapping to participate in a group * stop. Do the bookkeeping. Note that if SIGCONT was delievered * across siglock relocks since INTERRUPT was scheduled, PENDING * could be clear now. We act as if SIGCONT is received after * TASK_TRACED is entered - ignore it. */ if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING)) gstop_done = task_participate_group_stop(current); /* any trap clears pending STOP trap, STOP trap clears NOTIFY */ task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP); if (info && info->si_code >> 8 == PTRACE_EVENT_STOP) task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY); /* entering a trap, clear TRAPPING */ task_clear_jobctl_trapping(current); spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); /* * Notify parents of the stop. * * While ptraced, there are two parents - the ptracer and * the real_parent of the group_leader. The ptracer should * know about every stop while the real parent is only * interested in the completion of group stop. The states * for the two don't interact with each other. Notify * separately unless they're gonna be duplicates. */ if (current->ptrace) do_notify_parent_cldstop(current, true, why); if (gstop_done && (!current->ptrace || ptrace_reparented(current))) do_notify_parent_cldstop(current, false, why); /* * The previous do_notify_parent_cldstop() invocation woke ptracer. * One a PREEMPTION kernel this can result in preemption requirement * which will be fulfilled after read_unlock() and the ptracer will be * put on the CPU. * The ptracer is in wait_task_inactive(, __TASK_TRACED) waiting for * this task wait in schedule(). If this task gets preempted then it * remains enqueued on the runqueue. The ptracer will observe this and * then sleep for a delay of one HZ tick. In the meantime this task * gets scheduled, enters schedule() and will wait for the ptracer. * * This preemption point is not bad from a correctness point of * view but extends the runtime by one HZ tick time due to the * ptracer's sleep. The preempt-disable section ensures that there * will be no preemption between unlock and schedule() and so * improving the performance since the ptracer will observe that * the tracee is scheduled out once it gets on the CPU. * * On PREEMPT_RT locking tasklist_lock does not disable preemption. * Therefore the task can be preempted after do_notify_parent_cldstop() * before unlocking tasklist_lock so there is no benefit in doing this. * * In fact disabling preemption is harmful on PREEMPT_RT because * the spinlock_t in cgroup_enter_frozen() must not be acquired * with preemption disabled due to the 'sleeping' spinlock * substitution of RT. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); read_unlock(&tasklist_lock); cgroup_enter_frozen(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable_no_resched(); schedule(); cgroup_leave_frozen(true); /* * We are back. Now reacquire the siglock before touching * last_siginfo, so that we are sure to have synchronized with * any signal-sending on another CPU that wants to examine it. */ spin_lock_irq(¤t->sighand->siglock); exit_code = current->exit_code; current->last_siginfo = NULL; current->ptrace_message = 0; current->exit_code = 0; /* LISTENING can be set only during STOP traps, clear it */ current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN); /* * Queued signals ignored us while we were stopped for tracing. * So check for any that we should take before resuming user mode. * This sets TIF_SIGPENDING, but never clears it. */ recalc_sigpending_tsk(current); return exit_code; } static int ptrace_do_notify(int signr, int exit_code, int why, unsigned long message) { kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = signr; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); /* Let the debugger run. */ return ptrace_stop(exit_code, why, message, &info); } int ptrace_notify(int exit_code, unsigned long message) { int signr; BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); if (unlikely(task_work_pending(current))) task_work_run(); spin_lock_irq(¤t->sighand->siglock); signr = ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED, message); spin_unlock_irq(¤t->sighand->siglock); return signr; } /** * do_signal_stop - handle group stop for SIGSTOP and other stop signals * @signr: signr causing group stop if initiating * * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr * and participate in it. If already set, participate in the existing * group stop. If participated in a group stop (and thus slept), %true is * returned with siglock released. * * If ptraced, this function doesn't handle stop itself. Instead, * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock * untouched. The caller must ensure that INTERRUPT trap handling takes * places afterwards. * * CONTEXT: * Must be called with @current->sighand->siglock held, which is released * on %true return. * * RETURNS: * %false if group stop is already cancelled or ptrace trap is scheduled. * %true if participated in group stop. */ static bool do_signal_stop(int signr) __releases(¤t->sighand->siglock) { struct signal_struct *sig = current->signal; if (!(current->jobctl & JOBCTL_STOP_PENDING)) { unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; struct task_struct *t; /* signr will be recorded in task->jobctl for retries */ WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || unlikely(sig->flags & SIGNAL_GROUP_EXIT) || unlikely(sig->group_exec_task)) return false; /* * There is no group stop already in progress. We must * initiate one now. * * While ptraced, a task may be resumed while group stop is * still in effect and then receive a stop signal and * initiate another group stop. This deviates from the * usual behavior as two consecutive stop signals can't * cause two group stops when !ptraced. That is why we * also check !task_is_stopped(t) below. * * The condition can be distinguished by testing whether * SIGNAL_STOP_STOPPED is already set. Don't generate * group_exit_code in such case. * * This is not necessary for SIGNAL_STOP_CONTINUED because * an intervening stop signal is required to cause two * continued events regardless of ptrace. */ if (!(sig->flags & SIGNAL_STOP_STOPPED)) sig->group_exit_code = signr; sig->group_stop_count = 0; if (task_set_jobctl_pending(current, signr | gstop)) sig->group_stop_count++; for_other_threads(current, t) { /* * Setting state to TASK_STOPPED for a group * stop is always done with the siglock held, * so this check has no races. */ if (!task_is_stopped(t) && task_set_jobctl_pending(t, signr | gstop)) { sig->group_stop_count++; if (likely(!(t->ptrace & PT_SEIZED))) signal_wake_up(t, 0); else ptrace_trap_notify(t); } } } if (likely(!current->ptrace)) { int notify = 0; /* * If there are no other threads in the group, or if there * is a group stop in progress and we are the last to stop, * report to the parent. */ if (task_participate_group_stop(current)) notify = CLD_STOPPED; current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); /* * Notify the parent of the group stop completion. Because * we're not holding either the siglock or tasklist_lock * here, ptracer may attach inbetween; however, this is for * group stop and should always be delivered to the real * parent of the group leader. The new ptracer will get * its notification when this task transitions into * TASK_TRACED. */ if (notify) { read_lock(&tasklist_lock); do_notify_parent_cldstop(current, false, notify); read_unlock(&tasklist_lock); } /* Now we don't run again until woken by SIGCONT or SIGKILL */ cgroup_enter_frozen(); schedule(); return true; } else { /* * While ptraced, group stop is handled by STOP trap. * Schedule it and let the caller deal with it. */ task_set_jobctl_pending(current, JOBCTL_TRAP_STOP); return false; } } /** * do_jobctl_trap - take care of ptrace jobctl traps * * When PT_SEIZED, it's used for both group stop and explicit * SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with * accompanying siginfo. If stopped, lower eight bits of exit_code contain * the stop signal; otherwise, %SIGTRAP. * * When !PT_SEIZED, it's used only for group stop trap with stop signal * number as exit_code and no siginfo. * * CONTEXT: * Must be called with @current->sighand->siglock held, which may be * released and re-acquired before returning with intervening sleep. */ static void do_jobctl_trap(void) { struct signal_struct *signal = current->signal; int signr = current->jobctl & JOBCTL_STOP_SIGMASK; if (current->ptrace & PT_SEIZED) { if (!signal->group_stop_count && !(signal->flags & SIGNAL_STOP_STOPPED)) signr = SIGTRAP; WARN_ON_ONCE(!signr); ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8), CLD_STOPPED, 0); } else { WARN_ON_ONCE(!signr); ptrace_stop(signr, CLD_STOPPED, 0, NULL); } } /** * do_freezer_trap - handle the freezer jobctl trap * * Puts the task into frozen state, if only the task is not about to quit. * In this case it drops JOBCTL_TRAP_FREEZE. * * CONTEXT: * Must be called with @current->sighand->siglock held, * which is always released before returning. */ static void do_freezer_trap(void) __releases(¤t->sighand->siglock) { /* * If there are other trap bits pending except JOBCTL_TRAP_FREEZE, * let's make another loop to give it a chance to be handled. * In any case, we'll return back. */ if ((current->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) != JOBCTL_TRAP_FREEZE) { spin_unlock_irq(¤t->sighand->siglock); return; } /* * Now we're sure that there is no pending fatal signal and no * pending traps. Clear TIF_SIGPENDING to not get out of schedule() * immediately (if there is a non-fatal signal pending), and * put the task into sleep. */ __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); clear_thread_flag(TIF_SIGPENDING); spin_unlock_irq(¤t->sighand->siglock); cgroup_enter_frozen(); schedule(); /* * We could've been woken by task_work, run it to clear * TIF_NOTIFY_SIGNAL. The caller will retry if necessary. */ clear_notify_signal(); if (unlikely(task_work_pending(current))) task_work_run(); } static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type) { /* * We do not check sig_kernel_stop(signr) but set this marker * unconditionally because we do not know whether debugger will * change signr. This flag has no meaning unless we are going * to stop after return from ptrace_stop(). In this case it will * be checked in do_signal_stop(), we should only stop if it was * not cleared by SIGCONT while we were sleeping. See also the * comment in dequeue_signal(). */ current->jobctl |= JOBCTL_STOP_DEQUEUED; signr = ptrace_stop(signr, CLD_TRAPPED, 0, info); /* We're back. Did the debugger cancel the sig? */ if (signr == 0) return signr; /* * Update the siginfo structure if the signal has * changed. If the debugger wanted something * specific in the siginfo structure then it should * have updated *info via PTRACE_SETSIGINFO. */ if (signr != info->si_signo) { clear_siginfo(info); info->si_signo = signr; info->si_errno = 0; info->si_code = SI_USER; rcu_read_lock(); info->si_pid = task_pid_vnr(current->parent); info->si_uid = from_kuid_munged(current_user_ns(), task_uid(current->parent)); rcu_read_unlock(); } /* If the (new) signal is now blocked, requeue it. */ if (sigismember(¤t->blocked, signr) || fatal_signal_pending(current)) { send_signal_locked(signr, info, current, type); signr = 0; } return signr; } static void hide_si_addr_tag_bits(struct ksignal *ksig) { switch (siginfo_layout(ksig->sig, ksig->info.si_code)) { case SIL_FAULT: case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: case SIL_FAULT_PERF_EVENT: ksig->info.si_addr = arch_untagged_si_addr( ksig->info.si_addr, ksig->sig, ksig->info.si_code); break; case SIL_KILL: case SIL_TIMER: case SIL_POLL: case SIL_CHLD: case SIL_RT: case SIL_SYS: break; } } bool get_signal(struct ksignal *ksig) { struct sighand_struct *sighand = current->sighand; struct signal_struct *signal = current->signal; int signr; clear_notify_signal(); if (unlikely(task_work_pending(current))) task_work_run(); if (!task_sigpending(current)) return false; if (unlikely(uprobe_deny_signal())) return false; /* * Do this once, we can't return to user-mode if freezing() == T. * do_signal_stop() and ptrace_stop() do freezable_schedule() and * thus do not need another check after return. */ try_to_freeze(); relock: spin_lock_irq(&sighand->siglock); /* * Every stopped thread goes here after wakeup. Check to see if * we should notify the parent, prepare_signal(SIGCONT) encodes * the CLD_ si_code into SIGNAL_CLD_MASK bits. */ if (unlikely(signal->flags & SIGNAL_CLD_MASK)) { int why; if (signal->flags & SIGNAL_CLD_CONTINUED) why = CLD_CONTINUED; else why = CLD_STOPPED; signal->flags &= ~SIGNAL_CLD_MASK; spin_unlock_irq(&sighand->siglock); /* * Notify the parent that we're continuing. This event is * always per-process and doesn't make whole lot of sense * for ptracers, who shouldn't consume the state via * wait(2) either, but, for backward compatibility, notify * the ptracer of the group leader too unless it's gonna be * a duplicate. */ read_lock(&tasklist_lock); do_notify_parent_cldstop(current, false, why); if (ptrace_reparented(current->group_leader)) do_notify_parent_cldstop(current->group_leader, true, why); read_unlock(&tasklist_lock); goto relock; } for (;;) { struct k_sigaction *ka; enum pid_type type; /* Has this task already been marked for death? */ if ((signal->flags & SIGNAL_GROUP_EXIT) || signal->group_exec_task) { signr = SIGKILL; sigdelset(¤t->pending.signal, SIGKILL); trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, &sighand->action[SIGKILL-1]); recalc_sigpending(); /* * implies do_group_exit() or return to PF_USER_WORKER, * no need to initialize ksig->info/etc. */ goto fatal; } if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && do_signal_stop(0)) goto relock; if (unlikely(current->jobctl & (JOBCTL_TRAP_MASK | JOBCTL_TRAP_FREEZE))) { if (current->jobctl & JOBCTL_TRAP_MASK) { do_jobctl_trap(); spin_unlock_irq(&sighand->siglock); } else if (current->jobctl & JOBCTL_TRAP_FREEZE) do_freezer_trap(); goto relock; } /* * If the task is leaving the frozen state, let's update * cgroup counters and reset the frozen bit. */ if (unlikely(cgroup_task_frozen(current))) { spin_unlock_irq(&sighand->siglock); cgroup_leave_frozen(false); goto relock; } /* * Signals generated by the execution of an instruction * need to be delivered before any other pending signals * so that the instruction pointer in the signal stack * frame points to the faulting instruction. */ type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) signr = dequeue_signal(current, ¤t->blocked, &ksig->info, &type); if (!signr) break; /* will return 0 */ if (unlikely(current->ptrace) && (signr != SIGKILL) && !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info, type); if (!signr) continue; } ka = &sighand->action[signr-1]; /* Trace actually delivered signals. */ trace_signal_deliver(signr, &ksig->info, ka); if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ continue; if (ka->sa.sa_handler != SIG_DFL) { /* Run the handler. */ ksig->ka = *ka; if (ka->sa.sa_flags & SA_ONESHOT) ka->sa.sa_handler = SIG_DFL; break; /* will return non-zero "signr" value */ } /* * Now we are doing the default action for this signal. */ if (sig_kernel_ignore(signr)) /* Default is nothing. */ continue; /* * Global init gets no signals it doesn't want. * Container-init gets no signals it doesn't want from same * container. * * Note that if global/container-init sees a sig_kernel_only() * signal here, the signal must have been generated internally * or must have come from an ancestor namespace. In either * case, the signal cannot be dropped. */ if (unlikely(signal->flags & SIGNAL_UNKILLABLE) && !sig_kernel_only(signr)) continue; if (sig_kernel_stop(signr)) { /* * The default action is to stop all threads in * the thread group. The job control signals * do nothing in an orphaned pgrp, but SIGSTOP * always works. Note that siglock needs to be * dropped during the call to is_orphaned_pgrp() * because of lock ordering with tasklist_lock. * This allows an intervening SIGCONT to be posted. * We need to check for that and bail out if necessary. */ if (signr != SIGSTOP) { spin_unlock_irq(&sighand->siglock); /* signals can be posted during this window */ if (is_current_pgrp_orphaned()) goto relock; spin_lock_irq(&sighand->siglock); } if (likely(do_signal_stop(signr))) { /* It released the siglock. */ goto relock; } /* * We didn't actually stop, due to a race * with SIGCONT or something like that. */ continue; } fatal: spin_unlock_irq(&sighand->siglock); if (unlikely(cgroup_task_frozen(current))) cgroup_leave_frozen(true); /* * Anything else is fatal, maybe with a core dump. */ current->flags |= PF_SIGNALED; if (sig_kernel_coredump(signr)) { if (print_fatal_signals) print_fatal_signal(signr); proc_coredump_connector(current); /* * If it was able to dump core, this kills all * other threads in the group and synchronizes with * their demise. If we lost the race with another * thread getting here, it set group_exit_code * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ do_coredump(&ksig->info); } /* * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so we * cannot call do_exit() on their behalf. Note that ksig won't * be properly initialized, PF_USER_WORKER's shouldn't use it. */ if (current->flags & PF_USER_WORKER) goto out; /* * Death signals, no core dump. */ do_group_exit(signr); /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); ksig->sig = signr; if (signr && !(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) hide_si_addr_tag_bits(ksig); out: return signr > 0; } /** * signal_delivered - called after signal delivery to update blocked signals * @ksig: kernel signal struct * @stepping: nonzero if debugger single-step or block-step in use * * This function should be called when a signal has successfully been * delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask * is always blocked), and the signal itself is blocked unless %SA_NODEFER * is set in @ksig->ka.sa.sa_flags. Tracing is notified. */ static void signal_delivered(struct ksignal *ksig, int stepping) { sigset_t blocked; /* A signal was successfully delivered, and the saved sigmask was stored on the signal frame, and will be restored by sigreturn. So we can simply clear the restore sigmask flag. */ clear_restore_sigmask(); sigorsets(&blocked, ¤t->blocked, &ksig->ka.sa.sa_mask); if (!(ksig->ka.sa.sa_flags & SA_NODEFER)) sigaddset(&blocked, ksig->sig); set_current_blocked(&blocked); if (current->sas_ss_flags & SS_AUTODISARM) sas_ss_reset(current); if (stepping) ptrace_notify(SIGTRAP, 0); } void signal_setup_done(int failed, struct ksignal *ksig, int stepping) { if (failed) force_sigsegv(ksig->sig); else signal_delivered(ksig, stepping); } /* * It could be that complete_signal() picked us to notify about the * group-wide signal. Other threads should be notified now to take * the shared signals in @which since we will not. */ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) { sigset_t retarget; struct task_struct *t; sigandsets(&retarget, &tsk->signal->shared_pending.signal, which); if (sigisemptyset(&retarget)) return; for_other_threads(tsk, t) { if (t->flags & PF_EXITING) continue; if (!has_pending_signals(&retarget, &t->blocked)) continue; /* Remove the signals this thread can handle. */ sigandsets(&retarget, &retarget, &t->blocked); if (!task_sigpending(t)) signal_wake_up(t, 0); if (sigisemptyset(&retarget)) break; } } void exit_signals(struct task_struct *tsk) { int group_stop = 0; sigset_t unblocked; /* * @tsk is about to have PF_EXITING set - lock out users which * expect stable threadgroup. */ cgroup_threadgroup_change_begin(tsk); if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; } spin_lock_irq(&tsk->sighand->siglock); /* * From now this task is not visible for group-wide signals, * see wants_signal(), do_signal_stop(). */ sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); if (!task_sigpending(tsk)) goto out; unblocked = tsk->blocked; signotset(&unblocked); retarget_shared_pending(tsk, &unblocked); if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && task_participate_group_stop(tsk)) group_stop = CLD_STOPPED; out: spin_unlock_irq(&tsk->sighand->siglock); /* * If group stop has completed, deliver the notification. This * should always go to the real parent of the group leader. */ if (unlikely(group_stop)) { read_lock(&tasklist_lock); do_notify_parent_cldstop(tsk, false, group_stop); read_unlock(&tasklist_lock); } } /* * System call entry points. */ /** * sys_restart_syscall - restart a system call */ SYSCALL_DEFINE0(restart_syscall) { struct restart_block *restart = ¤t->restart_block; return restart->fn(restart); } long do_no_restart_syscall(struct restart_block *param) { return -EINTR; } static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) { if (task_sigpending(tsk) && !thread_group_empty(tsk)) { sigset_t newblocked; /* A set of now blocked but previously unblocked signals. */ sigandnsets(&newblocked, newset, ¤t->blocked); retarget_shared_pending(tsk, &newblocked); } tsk->blocked = *newset; recalc_sigpending(); } /** * set_current_blocked - change current->blocked mask * @newset: new mask * * It is wrong to change ->blocked directly, this helper should be used * to ensure the process can't miss a shared signal we are going to block. */ void set_current_blocked(sigset_t *newset) { sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP)); __set_current_blocked(newset); } void __set_current_blocked(const sigset_t *newset) { struct task_struct *tsk = current; /* * In case the signal mask hasn't changed, there is nothing we need * to do. The current->blocked shouldn't be modified by other task. */ if (sigequalsets(&tsk->blocked, newset)) return; spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, newset); spin_unlock_irq(&tsk->sighand->siglock); } /* * This is also useful for kernel threads that want to temporarily * (or permanently) block certain signals. * * NOTE! Unlike the user-mode sys_sigprocmask(), the kernel * interface happily blocks "unblockable" signals like SIGKILL * and friends. */ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) { struct task_struct *tsk = current; sigset_t newset; /* Lockless, only current can change ->blocked, never from irq */ if (oldset) *oldset = tsk->blocked; switch (how) { case SIG_BLOCK: sigorsets(&newset, &tsk->blocked, set); break; case SIG_UNBLOCK: sigandnsets(&newset, &tsk->blocked, set); break; case SIG_SETMASK: newset = *set; break; default: return -EINVAL; } __set_current_blocked(&newset); return 0; } EXPORT_SYMBOL(sigprocmask); /* * The api helps set app-provided sigmasks. * * This is useful for syscalls such as ppoll, pselect, io_pgetevents and * epoll_pwait where a new sigmask is passed from userland for the syscalls. * * Note that it does set_restore_sigmask() in advance, so it must be always * paired with restore_saved_sigmask_unless() before return from syscall. */ int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize) { sigset_t kmask; if (!umask) return 0; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&kmask, umask, sizeof(sigset_t))) return -EFAULT; set_restore_sigmask(); current->saved_sigmask = current->blocked; set_current_blocked(&kmask); return 0; } #ifdef CONFIG_COMPAT int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize) { sigset_t kmask; if (!umask) return 0; if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (get_compat_sigset(&kmask, umask)) return -EFAULT; set_restore_sigmask(); current->saved_sigmask = current->blocked; set_current_blocked(&kmask); return 0; } #endif /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals * @nset: stores pending signals * @oset: previous value of signal mask if non-null * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset, sigset_t __user *, oset, size_t, sigsetsize) { sigset_t old_set, new_set; int error; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; old_set = current->blocked; if (nset) { if (copy_from_user(&new_set, nset, sizeof(sigset_t))) return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); error = sigprocmask(how, &new_set, NULL); if (error) return error; } if (oset) { if (copy_to_user(oset, &old_set, sizeof(sigset_t))) return -EFAULT; } return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset, compat_sigset_t __user *, oset, compat_size_t, sigsetsize) { sigset_t old_set = current->blocked; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (nset) { sigset_t new_set; int error; if (get_compat_sigset(&new_set, nset)) return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); error = sigprocmask(how, &new_set, NULL); if (error) return error; } return oset ? put_compat_sigset(oset, &old_set, sizeof(*oset)) : 0; } #endif static void do_sigpending(sigset_t *set) { spin_lock_irq(¤t->sighand->siglock); sigorsets(set, ¤t->pending.signal, ¤t->signal->shared_pending.signal); spin_unlock_irq(¤t->sighand->siglock); /* Outside the lock because only this thread touches it. */ sigandsets(set, ¤t->blocked, set); } /** * sys_rt_sigpending - examine a pending signal that has been raised * while blocked * @uset: stores pending signals * @sigsetsize: size of sigset_t type or larger */ SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize) { sigset_t set; if (sigsetsize > sizeof(*uset)) return -EINVAL; do_sigpending(&set); if (copy_to_user(uset, &set, sigsetsize)) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, compat_size_t, sigsetsize) { sigset_t set; if (sigsetsize > sizeof(*uset)) return -EINVAL; do_sigpending(&set); return put_compat_sigset(uset, &set, sigsetsize); } #endif static const struct { unsigned char limit, layout; } sig_sicodes[] = { [SIGILL] = { NSIGILL, SIL_FAULT }, [SIGFPE] = { NSIGFPE, SIL_FAULT }, [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, [SIGBUS] = { NSIGBUS, SIL_FAULT }, [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, #if defined(SIGEMT) [SIGEMT] = { NSIGEMT, SIL_FAULT }, #endif [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, [SIGPOLL] = { NSIGPOLL, SIL_POLL }, [SIGSYS] = { NSIGSYS, SIL_SYS }, }; static bool known_siginfo_layout(unsigned sig, int si_code) { if (si_code == SI_KERNEL) return true; else if ((si_code > SI_USER)) { if (sig_specific_sicodes(sig)) { if (si_code <= sig_sicodes[sig].limit) return true; } else if (si_code <= NSIGPOLL) return true; } else if (si_code >= SI_DETHREAD) return true; else if (si_code == SI_ASYNCNL) return true; return false; } enum siginfo_layout siginfo_layout(unsigned sig, int si_code) { enum siginfo_layout layout = SIL_KILL; if ((si_code > SI_USER) && (si_code < SI_KERNEL)) { if ((sig < ARRAY_SIZE(sig_sicodes)) && (si_code <= sig_sicodes[sig].limit)) { layout = sig_sicodes[sig].layout; /* Handle the exceptions */ if ((sig == SIGBUS) && (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO)) layout = SIL_FAULT_MCEERR; else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR)) layout = SIL_FAULT_BNDERR; #ifdef SEGV_PKUERR else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR)) layout = SIL_FAULT_PKUERR; #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) layout = SIL_FAULT_PERF_EVENT; else if (IS_ENABLED(CONFIG_SPARC) && (sig == SIGILL) && (si_code == ILL_ILLTRP)) layout = SIL_FAULT_TRAPNO; else if (IS_ENABLED(CONFIG_ALPHA) && ((sig == SIGFPE) || ((sig == SIGTRAP) && (si_code == TRAP_UNK)))) layout = SIL_FAULT_TRAPNO; } else if (si_code <= NSIGPOLL) layout = SIL_POLL; } else { if (si_code == SI_TIMER) layout = SIL_TIMER; else if (si_code == SI_SIGIO) layout = SIL_POLL; else if (si_code < 0) layout = SIL_RT; } return layout; } static inline char __user *si_expansion(const siginfo_t __user *info) { return ((char __user *)info) + sizeof(struct kernel_siginfo); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from) { char __user *expansion = si_expansion(to); if (copy_to_user(to, from , sizeof(struct kernel_siginfo))) return -EFAULT; if (clear_user(expansion, SI_EXPANSION_SIZE)) return -EFAULT; return 0; } static int post_copy_siginfo_from_user(kernel_siginfo_t *info, const siginfo_t __user *from) { if (unlikely(!known_siginfo_layout(info->si_signo, info->si_code))) { char __user *expansion = si_expansion(from); char buf[SI_EXPANSION_SIZE]; int i; /* * An unknown si_code might need more than * sizeof(struct kernel_siginfo) bytes. Verify all of the * extra bytes are 0. This guarantees copy_siginfo_to_user * will return this data to userspace exactly. */ if (copy_from_user(&buf, expansion, SI_EXPANSION_SIZE)) return -EFAULT; for (i = 0; i < SI_EXPANSION_SIZE; i++) { if (buf[i] != 0) return -E2BIG; } } return 0; } static int __copy_siginfo_from_user(int signo, kernel_siginfo_t *to, const siginfo_t __user *from) { if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) return -EFAULT; to->si_signo = signo; return post_copy_siginfo_from_user(to, from); } int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from) { if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) return -EFAULT; return post_copy_siginfo_from_user(to, from); } #ifdef CONFIG_COMPAT /** * copy_siginfo_to_external32 - copy a kernel siginfo into a compat user siginfo * @to: compat siginfo destination * @from: kernel siginfo source * * Note: This function does not work properly for the SIGCHLD on x32, but * fortunately it doesn't have to. The only valid callers for this function are * copy_siginfo_to_user32, which is overriden for x32 and the coredump code. * The latter does not care because SIGCHLD will never cause a coredump. */ void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from) { memset(to, 0, sizeof(*to)); to->si_signo = from->si_signo; to->si_errno = from->si_errno; to->si_code = from->si_code; switch(siginfo_layout(from->si_signo, from->si_code)) { case SIL_KILL: to->si_pid = from->si_pid; to->si_uid = from->si_uid; break; case SIL_TIMER: to->si_tid = from->si_tid; to->si_overrun = from->si_overrun; to->si_int = from->si_int; break; case SIL_POLL: to->si_band = from->si_band; to->si_fd = from->si_fd; break; case SIL_FAULT: to->si_addr = ptr_to_compat(from->si_addr); break; case SIL_FAULT_TRAPNO: to->si_addr = ptr_to_compat(from->si_addr); to->si_trapno = from->si_trapno; break; case SIL_FAULT_MCEERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_lower = ptr_to_compat(from->si_lower); to->si_upper = ptr_to_compat(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_pkey = from->si_pkey; break; case SIL_FAULT_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_status = from->si_status; to->si_utime = from->si_utime; to->si_stime = from->si_stime; break; case SIL_RT: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_int = from->si_int; break; case SIL_SYS: to->si_call_addr = ptr_to_compat(from->si_call_addr); to->si_syscall = from->si_syscall; to->si_arch = from->si_arch; break; } } int __copy_siginfo_to_user32(struct compat_siginfo __user *to, const struct kernel_siginfo *from) { struct compat_siginfo new; copy_siginfo_to_external32(&new, from); if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) return -EFAULT; return 0; } static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo *from) { clear_siginfo(to); to->si_signo = from->si_signo; to->si_errno = from->si_errno; to->si_code = from->si_code; switch(siginfo_layout(from->si_signo, from->si_code)) { case SIL_KILL: to->si_pid = from->si_pid; to->si_uid = from->si_uid; break; case SIL_TIMER: to->si_tid = from->si_tid; to->si_overrun = from->si_overrun; to->si_int = from->si_int; break; case SIL_POLL: to->si_band = from->si_band; to->si_fd = from->si_fd; break; case SIL_FAULT: to->si_addr = compat_ptr(from->si_addr); break; case SIL_FAULT_TRAPNO: to->si_addr = compat_ptr(from->si_addr); to->si_trapno = from->si_trapno; break; case SIL_FAULT_MCEERR: to->si_addr = compat_ptr(from->si_addr); to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = compat_ptr(from->si_addr); to->si_lower = compat_ptr(from->si_lower); to->si_upper = compat_ptr(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = compat_ptr(from->si_addr); to->si_pkey = from->si_pkey; break; case SIL_FAULT_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_status = from->si_status; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) { to->si_utime = from->_sifields._sigchld_x32._utime; to->si_stime = from->_sifields._sigchld_x32._stime; } else #endif { to->si_utime = from->si_utime; to->si_stime = from->si_stime; } break; case SIL_RT: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_int = from->si_int; break; case SIL_SYS: to->si_call_addr = compat_ptr(from->si_call_addr); to->si_syscall = from->si_syscall; to->si_arch = from->si_arch; break; } return 0; } static int __copy_siginfo_from_user32(int signo, struct kernel_siginfo *to, const struct compat_siginfo __user *ufrom) { struct compat_siginfo from; if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) return -EFAULT; from.si_signo = signo; return post_copy_siginfo_from_user32(to, &from); } int copy_siginfo_from_user32(struct kernel_siginfo *to, const struct compat_siginfo __user *ufrom) { struct compat_siginfo from; if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) return -EFAULT; return post_copy_siginfo_from_user32(to, &from); } #endif /* CONFIG_COMPAT */ /** * do_sigtimedwait - wait for queued signals specified in @which * @which: queued signals to wait for * @info: if non-null, the signal's siginfo is returned here * @ts: upper bound on process time suspension */ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, const struct timespec64 *ts) { ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; sigset_t mask = *which; enum pid_type type; int sig, ret = 0; if (ts) { if (!timespec64_valid(ts)) return -EINVAL; timeout = timespec64_to_ktime(*ts); to = &timeout; } /* * Invert the set of allowed signals to get those we want to block. */ sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); sig = dequeue_signal(tsk, &mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested * while we are sleeping in so that we'll be awakened when * they arrive. Unblocking is always fine, we can avoid * set_current_blocked(). */ tsk->real_blocked = tsk->blocked; sigandsets(&tsk->blocked, &tsk->blocked, &mask); recalc_sigpending(); spin_unlock_irq(&tsk->sighand->siglock); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); ret = schedule_hrtimeout_range(to, tsk->timer_slack_ns, HRTIMER_MODE_REL); spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); sig = dequeue_signal(tsk, &mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); if (sig) return sig; return ret ? -EINTR : -EAGAIN; } /** * sys_rt_sigtimedwait - synchronously wait for queued signals specified * in @uthese * @uthese: queued signals to wait for * @uinfo: if non-null, the signal's siginfo is returned here * @uts: upper bound on process time suspension * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct __kernel_timespec __user *, uts, size_t, sigsetsize) { sigset_t these; struct timespec64 ts; kernel_siginfo_t info; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; if (uts) { if (get_timespec64(&ts, uts)) return -EFAULT; } ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user(uinfo, &info)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(rt_sigtimedwait_time32, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct old_timespec32 __user *, uts, size_t, sigsetsize) { sigset_t these; struct timespec64 ts; kernel_siginfo_t info; int ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; if (uts) { if (get_old_timespec32(&ts, uts)) return -EFAULT; } ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user(uinfo, &info)) ret = -EFAULT; } return ret; } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct __kernel_timespec __user *, uts, compat_size_t, sigsetsize) { sigset_t s; struct timespec64 t; kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&s, uthese)) return -EFAULT; if (uts) { if (get_timespec64(&t, uts)) return -EFAULT; } ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user32(uinfo, &info)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { sigset_t s; struct timespec64 t; kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&s, uthese)) return -EFAULT; if (uts) { if (get_old_timespec32(&t, uts)) return -EFAULT; } ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user32(uinfo, &info)) ret = -EFAULT; } return ret; } #endif #endif static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info, enum pid_type type) { clear_siginfo(info); info->si_signo = sig; info->si_errno = 0; info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER; info->si_pid = task_tgid_vnr(current); info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); } /** * sys_kill - send a signal to a process * @pid: the PID of the process * @sig: signal to be sent */ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct kernel_siginfo info; prepare_kill_siginfo(sig, &info, PIDTYPE_TGID); return kill_something_info(sig, &info, pid); } /* * Verify that the signaler and signalee either are in the same pid namespace * or that the signaler's pid namespace is an ancestor of the signalee's pid * namespace. */ static bool access_pidfd_pidns(struct pid *pid) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *p = ns_of_pid(pid); for (;;) { if (!p) return false; if (p == active) break; p = p->parent; } return true; } static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t __user *info) { #ifdef CONFIG_COMPAT /* * Avoid hooking up compat syscalls and instead handle necessary * conversions here. Note, this is a stop-gap measure and should not be * considered a generic solution. */ if (in_compat_syscall()) return copy_siginfo_from_user32( kinfo, (struct compat_siginfo __user *)info); #endif return copy_siginfo_from_user(kinfo, info); } static struct pid *pidfd_to_pid(const struct file *file) { struct pid *pid; pid = pidfd_pid(file); if (!IS_ERR(pid)) return pid; return tgid_pidfd_to_pid(file); } #define PIDFD_SEND_SIGNAL_FLAGS \ (PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \ PIDFD_SIGNAL_PROCESS_GROUP) /** * sys_pidfd_send_signal - Signal a process through a pidfd * @pidfd: file descriptor of the process * @sig: signal to send * @info: signal info * @flags: future flags * * Send the signal to the thread group or to the individual thread depending * on PIDFD_THREAD. * In the future extension to @flags may be used to override the default scope * of @pidfd. * * Return: 0 on success, negative errno on failure */ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, siginfo_t __user *, info, unsigned int, flags) { int ret; struct fd f; struct pid *pid; kernel_siginfo_t kinfo; enum pid_type type; /* Enforce flags be set to 0 until we add an extension. */ if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) return -EINVAL; /* Ensure that only a single signal scope determining flag is set. */ if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1) return -EINVAL; f = fdget(pidfd); if (!f.file) return -EBADF; /* Is this a pidfd? */ pid = pidfd_to_pid(f.file); if (IS_ERR(pid)) { ret = PTR_ERR(pid); goto err; } ret = -EINVAL; if (!access_pidfd_pidns(pid)) goto err; switch (flags) { case 0: /* Infer scope from the type of pidfd. */ if (f.file->f_flags & PIDFD_THREAD) type = PIDTYPE_PID; else type = PIDTYPE_TGID; break; case PIDFD_SIGNAL_THREAD: type = PIDTYPE_PID; break; case PIDFD_SIGNAL_THREAD_GROUP: type = PIDTYPE_TGID; break; case PIDFD_SIGNAL_PROCESS_GROUP: type = PIDTYPE_PGID; break; } if (info) { ret = copy_siginfo_from_user_any(&kinfo, info); if (unlikely(ret)) goto err; ret = -EINVAL; if (unlikely(sig != kinfo.si_signo)) goto err; /* Only allow sending arbitrary signals to yourself. */ ret = -EPERM; if ((task_pid(current) != pid || type > PIDTYPE_TGID) && (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) goto err; } else { prepare_kill_siginfo(sig, &kinfo, type); } if (type == PIDTYPE_PGID) ret = kill_pgrp_info(sig, &kinfo, pid); else ret = kill_pid_info_type(sig, &kinfo, pid, type); err: fdput(f); return ret; } static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { struct task_struct *p; int error = -ESRCH; rcu_read_lock(); p = find_task_by_vpid(pid); if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) { error = check_kill_permission(sig, info, p); /* * The null signal is a permissions and process existence * probe. No signal is actually delivered. */ if (!error && sig) { error = do_send_sig_info(sig, info, p, PIDTYPE_PID); /* * If lock_task_sighand() failed we pretend the task * dies after receiving the signal. The window is tiny, * and the signal is private anyway. */ if (unlikely(error == -ESRCH)) error = 0; } } rcu_read_unlock(); return error; } static int do_tkill(pid_t tgid, pid_t pid, int sig) { struct kernel_siginfo info; prepare_kill_siginfo(sig, &info, PIDTYPE_PID); return do_send_specific(tgid, pid, sig, &info); } /** * sys_tgkill - send signal to one specific thread * @tgid: the thread group ID of the thread * @pid: the PID of the thread * @sig: signal to be sent * * This syscall also checks the @tgid and returns -ESRCH even if the PID * exists but it's not belonging to the target process anymore. This * method solves the problem of threads exiting and PIDs getting reused. */ SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) return -EINVAL; return do_tkill(tgid, pid, sig); } /** * sys_tkill - send signal to one specific task * @pid: the PID of the task * @sig: signal to be sent * * Send a signal to only one task, even if it's a CLONE_THREAD task. */ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0) return -EINVAL; return do_tkill(0, pid, sig); } static int do_rt_sigqueueinfo(pid_t pid, int sig, kernel_siginfo_t *info) { /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ if ((info->si_code >= 0 || info->si_code == SI_TKILL) && (task_pid_vnr(current) != pid)) return -EPERM; /* POSIX.1b doesn't mention process groups. */ return kill_proc_info(sig, info, pid); } /** * sys_rt_sigqueueinfo - send signal information to a signal * @pid: the PID of the thread * @sig: signal to be sent * @uinfo: signal info to be sent */ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_sigqueueinfo(pid, sig, &info); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, compat_pid_t, pid, int, sig, struct compat_siginfo __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user32(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_sigqueueinfo(pid, sig, &info); } #endif static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, kernel_siginfo_t *info) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) return -EINVAL; /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ if ((info->si_code >= 0 || info->si_code == SI_TKILL) && (task_pid_vnr(current) != pid)) return -EPERM; return do_send_specific(tgid, pid, sig, info); } SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, compat_pid_t, tgid, compat_pid_t, pid, int, sig, struct compat_siginfo __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user32(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #endif /* * For kthreads only, must not be used if cloned with CLONE_SIGHAND */ void kernel_sigaction(int sig, __sighandler_t action) { spin_lock_irq(¤t->sighand->siglock); current->sighand->action[sig - 1].sa.sa_handler = action; if (action == SIG_IGN) { sigset_t mask; sigemptyset(&mask); sigaddset(&mask, sig); flush_sigqueue_mask(&mask, ¤t->signal->shared_pending); flush_sigqueue_mask(&mask, ¤t->pending); recalc_sigpending(); } spin_unlock_irq(¤t->sighand->siglock); } EXPORT_SYMBOL(kernel_sigaction); void __weak sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) { } int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) { struct task_struct *p = current, *t; struct k_sigaction *k; sigset_t mask; if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig))) return -EINVAL; k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); if (k->sa.sa_flags & SA_IMMUTABLE) { spin_unlock_irq(&p->sighand->siglock); return -EINVAL; } if (oact) *oact = *k; /* * Make sure that we never accidentally claim to support SA_UNSUPPORTED, * e.g. by having an architecture use the bit in their uapi. */ BUILD_BUG_ON(UAPI_SA_FLAGS & SA_UNSUPPORTED); /* * Clear unknown flag bits in order to allow userspace to detect missing * support for flag bits and to allow the kernel to use non-uapi bits * internally. */ if (act) act->sa.sa_flags &= UAPI_SA_FLAGS; if (oact) oact->sa.sa_flags &= UAPI_SA_FLAGS; sigaction_compat_abi(act, oact); if (act) { sigdelsetmask(&act->sa.sa_mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); *k = *act; /* * POSIX 3.3.1.3: * "Setting a signal action to SIG_IGN for a signal that is * pending shall cause the pending signal to be discarded, * whether or not it is blocked." * * "Setting a signal action to SIG_DFL for a signal that is * pending and whose default action is to ignore the signal * (for example, SIGCHLD), shall cause the pending signal to * be discarded, whether or not it is blocked" */ if (sig_handler_ignored(sig_handler(p, sig), sig)) { sigemptyset(&mask); sigaddset(&mask, sig); flush_sigqueue_mask(&mask, &p->signal->shared_pending); for_each_thread(p, t) flush_sigqueue_mask(&mask, &t->pending); } } spin_unlock_irq(&p->sighand->siglock); return 0; } #ifdef CONFIG_DYNAMIC_SIGFRAME static inline void sigaltstack_lock(void) __acquires(¤t->sighand->siglock) { spin_lock_irq(¤t->sighand->siglock); } static inline void sigaltstack_unlock(void) __releases(¤t->sighand->siglock) { spin_unlock_irq(¤t->sighand->siglock); } #else static inline void sigaltstack_lock(void) { } static inline void sigaltstack_unlock(void) { } #endif static int do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, size_t min_ss_size) { struct task_struct *t = current; int ret = 0; if (oss) { memset(oss, 0, sizeof(stack_t)); oss->ss_sp = (void __user *) t->sas_ss_sp; oss->ss_size = t->sas_ss_size; oss->ss_flags = sas_ss_flags(sp) | (current->sas_ss_flags & SS_FLAG_BITS); } if (ss) { void __user *ss_sp = ss->ss_sp; size_t ss_size = ss->ss_size; unsigned ss_flags = ss->ss_flags; int ss_mode; if (unlikely(on_sig_stack(sp))) return -EPERM; ss_mode = ss_flags & ~SS_FLAG_BITS; if (unlikely(ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK && ss_mode != 0)) return -EINVAL; /* * Return before taking any locks if no actual * sigaltstack changes were requested. */ if (t->sas_ss_sp == (unsigned long)ss_sp && t->sas_ss_size == ss_size && t->sas_ss_flags == ss_flags) return 0; sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; ss_sp = NULL; } else { if (unlikely(ss_size < min_ss_size)) ret = -ENOMEM; if (!sigaltstack_size_valid(ss_size)) ret = -ENOMEM; } if (!ret) { t->sas_ss_sp = (unsigned long) ss_sp; t->sas_ss_size = ss_size; t->sas_ss_flags = ss_flags; } sigaltstack_unlock(); } return ret; } SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) { stack_t new, old; int err; if (uss && copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL, current_user_stack_pointer(), MINSIGSTKSZ); if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t))) err = -EFAULT; return err; } int restore_altstack(const stack_t __user *uss) { stack_t new; if (copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; (void)do_sigaltstack(&new, NULL, current_user_stack_pointer(), MINSIGSTKSZ); /* squash all but EFAULT for now */ return 0; } int __save_altstack(stack_t __user *uss, unsigned long sp) { struct task_struct *t = current; int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); return err; } #ifdef CONFIG_COMPAT static int do_compat_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr) { stack_t uss, uoss; int ret; if (uss_ptr) { compat_stack_t uss32; if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) return -EFAULT; uss.ss_sp = compat_ptr(uss32.ss_sp); uss.ss_flags = uss32.ss_flags; uss.ss_size = uss32.ss_size; } ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, compat_user_stack_pointer(), COMPAT_MINSIGSTKSZ); if (ret >= 0 && uoss_ptr) { compat_stack_t old; memset(&old, 0, sizeof(old)); old.ss_sp = ptr_to_compat(uoss.ss_sp); old.ss_flags = uoss.ss_flags; old.ss_size = uoss.ss_size; if (copy_to_user(uoss_ptr, &old, sizeof(compat_stack_t))) ret = -EFAULT; } return ret; } COMPAT_SYSCALL_DEFINE2(sigaltstack, const compat_stack_t __user *, uss_ptr, compat_stack_t __user *, uoss_ptr) { return do_compat_sigaltstack(uss_ptr, uoss_ptr); } int compat_restore_altstack(const compat_stack_t __user *uss) { int err = do_compat_sigaltstack(uss, NULL); /* squash all but -EFAULT for now */ return err == -EFAULT ? err : 0; } int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) { int err; struct task_struct *t = current; err = __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); return err; } #endif #ifdef __ARCH_WANT_SYS_SIGPENDING /** * sys_sigpending - examine pending signals * @uset: where mask of pending signal is returned */ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, uset) { sigset_t set; if (sizeof(old_sigset_t) > sizeof(*uset)) return -EINVAL; do_sigpending(&set); if (copy_to_user(uset, &set, sizeof(old_sigset_t))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32) { sigset_t set; do_sigpending(&set); return put_user(set.sig[0], set32); } #endif #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK /** * sys_sigprocmask - examine and change blocked signals * @how: whether to add, remove, or set signals * @nset: signals to add or remove (if non-null) * @oset: previous value of signal mask if non-null * * Some platforms have their own version with special arguments; * others support only sys_rt_sigprocmask. */ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, old_sigset_t __user *, oset) { old_sigset_t old_set, new_set; sigset_t new_blocked; old_set = current->blocked.sig[0]; if (nset) { if (copy_from_user(&new_set, nset, sizeof(*nset))) return -EFAULT; new_blocked = current->blocked; switch (how) { case SIG_BLOCK: sigaddsetmask(&new_blocked, new_set); break; case SIG_UNBLOCK: sigdelsetmask(&new_blocked, new_set); break; case SIG_SETMASK: new_blocked.sig[0] = new_set; break; default: return -EINVAL; } set_current_blocked(&new_blocked); } if (oset) { if (copy_to_user(oset, &old_set, sizeof(*oset))) return -EFAULT; } return 0; } #endif /* __ARCH_WANT_SYS_SIGPROCMASK */ #ifndef CONFIG_ODD_RT_SIGACTION /** * sys_rt_sigaction - alter an action taken by a process * @sig: signal to be sent * @act: new sigaction * @oact: used to save the previous sigaction * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigaction, int, sig, const struct sigaction __user *, act, struct sigaction __user *, oact, size_t, sigsetsize) { struct k_sigaction new_sa, old_sa; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (act && copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa))) return -EFAULT; ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL); if (ret) return ret; if (oact && copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig, const struct compat_sigaction __user *, act, struct compat_sigaction __user *, oact, compat_size_t, sigsetsize) { struct k_sigaction new_ka, old_ka; #ifdef __ARCH_HAS_SA_RESTORER compat_uptr_t restorer; #endif int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (act) { compat_uptr_t handler; ret = get_user(handler, &act->sa_handler); new_ka.sa.sa_handler = compat_ptr(handler); #ifdef __ARCH_HAS_SA_RESTORER ret |= get_user(restorer, &act->sa_restorer); new_ka.sa.sa_restorer = compat_ptr(restorer); #endif ret |= get_compat_sigset(&new_ka.sa.sa_mask, &act->sa_mask); ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); if (ret) return -EFAULT; } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler); ret |= put_compat_sigset(&oact->sa_mask, &old_ka.sa.sa_mask, sizeof(oact->sa_mask)); ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags); #ifdef __ARCH_HAS_SA_RESTORER ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer); #endif } return ret; } #endif #endif /* !CONFIG_ODD_RT_SIGACTION */ #ifdef CONFIG_OLD_SIGACTION SYSCALL_DEFINE3(sigaction, int, sig, const struct old_sigaction __user *, act, struct old_sigaction __user *, oact) { struct k_sigaction new_ka, old_ka; int ret; if (act) { old_sigset_t mask; if (!access_ok(act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || __get_user(mask, &act->sa_mask)) return -EFAULT; #ifdef __ARCH_HAS_KA_RESTORER new_ka.ka_restorer = NULL; #endif siginitset(&new_ka.sa.sa_mask, mask); } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { if (!access_ok(oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; } return ret; } #endif #ifdef CONFIG_COMPAT_OLD_SIGACTION COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, const struct compat_old_sigaction __user *, act, struct compat_old_sigaction __user *, oact) { struct k_sigaction new_ka, old_ka; int ret; compat_old_sigset_t mask; compat_uptr_t handler, restorer; if (act) { if (!access_ok(act, sizeof(*act)) || __get_user(handler, &act->sa_handler) || __get_user(restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || __get_user(mask, &act->sa_mask)) return -EFAULT; #ifdef __ARCH_HAS_KA_RESTORER new_ka.ka_restorer = NULL; #endif new_ka.sa.sa_handler = compat_ptr(handler); new_ka.sa.sa_restorer = compat_ptr(restorer); siginitset(&new_ka.sa.sa_mask, mask); } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { if (!access_ok(oact, sizeof(*oact)) || __put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler) || __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer) || __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; } return ret; } #endif #ifdef CONFIG_SGETMASK_SYSCALL /* * For backwards compatibility. Functionality superseded by sigprocmask. */ SYSCALL_DEFINE0(sgetmask) { /* SMP safe */ return current->blocked.sig[0]; } SYSCALL_DEFINE1(ssetmask, int, newmask) { int old = current->blocked.sig[0]; sigset_t newset; siginitset(&newset, newmask); set_current_blocked(&newset); return old; } #endif /* CONFIG_SGETMASK_SYSCALL */ #ifdef __ARCH_WANT_SYS_SIGNAL /* * For backwards compatibility. Functionality superseded by sigaction. */ SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) { struct k_sigaction new_sa, old_sa; int ret; new_sa.sa.sa_handler = handler; new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK; sigemptyset(&new_sa.sa.sa_mask); ret = do_sigaction(sig, &new_sa, &old_sa); return ret ? ret : (unsigned long)old_sa.sa.sa_handler; } #endif /* __ARCH_WANT_SYS_SIGNAL */ #ifdef __ARCH_WANT_SYS_PAUSE SYSCALL_DEFINE0(pause) { while (!signal_pending(current)) { __set_current_state(TASK_INTERRUPTIBLE); schedule(); } return -ERESTARTNOHAND; } #endif static int sigsuspend(sigset_t *set) { current->saved_sigmask = current->blocked; set_current_blocked(set); while (!signal_pending(current)) { __set_current_state(TASK_INTERRUPTIBLE); schedule(); } set_restore_sigmask(); return -ERESTARTNOHAND; } /** * sys_rt_sigsuspend - replace the signal mask for a value with the * @unewset value until a signal is received * @unewset: new signal mask value * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) { sigset_t newset; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&newset, unewset, sizeof(newset))) return -EFAULT; return sigsuspend(&newset); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize) { sigset_t newset; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&newset, unewset)) return -EFAULT; return sigsuspend(&newset); } #endif #ifdef CONFIG_OLD_SIGSUSPEND SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) { sigset_t blocked; siginitset(&blocked, mask); return sigsuspend(&blocked); } #endif #ifdef CONFIG_OLD_SIGSUSPEND3 SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) { sigset_t blocked; siginitset(&blocked, mask); return sigsuspend(&blocked); } #endif __weak const char *arch_vma_name(struct vm_area_struct *vma) { return NULL; } static inline void siginfo_buildtime_checks(void) { BUILD_BUG_ON(sizeof(struct siginfo) != SI_MAX_SIZE); /* Verify the offsets in the two siginfos match */ #define CHECK_OFFSET(field) \ BUILD_BUG_ON(offsetof(siginfo_t, field) != offsetof(kernel_siginfo_t, field)) /* kill */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); /* timer */ CHECK_OFFSET(si_tid); CHECK_OFFSET(si_overrun); CHECK_OFFSET(si_value); /* rt */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); CHECK_OFFSET(si_value); /* sigchld */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); CHECK_OFFSET(si_status); CHECK_OFFSET(si_utime); CHECK_OFFSET(si_stime); /* sigfault */ CHECK_OFFSET(si_addr); CHECK_OFFSET(si_trapno); CHECK_OFFSET(si_addr_lsb); CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); CHECK_OFFSET(si_perf_data); CHECK_OFFSET(si_perf_type); CHECK_OFFSET(si_perf_flags); /* sigpoll */ CHECK_OFFSET(si_band); CHECK_OFFSET(si_fd); /* sigsys */ CHECK_OFFSET(si_call_addr); CHECK_OFFSET(si_syscall); CHECK_OFFSET(si_arch); #undef CHECK_OFFSET /* usb asyncio */ BUILD_BUG_ON(offsetof(struct siginfo, si_pid) != offsetof(struct siginfo, si_addr)); if (sizeof(int) == sizeof(void __user *)) { BUILD_BUG_ON(sizeof_field(struct siginfo, si_pid) != sizeof(void __user *)); } else { BUILD_BUG_ON((sizeof_field(struct siginfo, si_pid) + sizeof_field(struct siginfo, si_uid)) != sizeof(void __user *)); BUILD_BUG_ON(offsetofend(struct siginfo, si_pid) != offsetof(struct siginfo, si_uid)); } #ifdef CONFIG_COMPAT BUILD_BUG_ON(offsetof(struct compat_siginfo, si_pid) != offsetof(struct compat_siginfo, si_addr)); BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != sizeof(compat_uptr_t)); BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != sizeof_field(struct siginfo, si_pid)); #endif } #if defined(CONFIG_SYSCTL) static struct ctl_table signal_debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", .data = &show_unhandled_signals, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #endif }; static int __init init_signal_sysctls(void) { register_sysctl_init("debug", signal_debug_table); return 0; } early_initcall(init_signal_sysctls); #endif /* CONFIG_SYSCTL */ void __init signals_init(void) { siginfo_buildtime_checks(); sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC | SLAB_ACCOUNT); } #ifdef CONFIG_KGDB_KDB #include <linux/kdb.h> /* * kdb_send_sig - Allows kdb to send signals without exposing * signal internals. This function checks if the required locks are * available before calling the main signal code, to avoid kdb * deadlocks. */ void kdb_send_sig(struct task_struct *t, int sig) { static struct task_struct *kdb_prev_t; int new_t, ret; if (!spin_trylock(&t->sighand->siglock)) { kdb_printf("Can't do kill command now.\n" "The sigmask lock is held somewhere else in " "kernel, try again later\n"); return; } new_t = kdb_prev_t != t; kdb_prev_t = t; if (!task_is_running(t) && new_t) { spin_unlock(&t->sighand->siglock); kdb_printf("Process is not RUNNING, sending a signal from " "kdb risks deadlock\n" "on the run queue locks. " "The signal has _not_ been sent.\n" "Reissue the kill command if you want to risk " "the deadlock.\n"); return; } ret = send_signal_locked(sig, SEND_SIG_PRIV, t, PIDTYPE_PID); spin_unlock(&t->sighand->siglock); if (ret) kdb_printf("Fail to deliver Signal %d to process %d.\n", sig, t->pid); else kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid); } #endif /* CONFIG_KGDB_KDB */ |
| 153 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Mutexes: blocking mutual exclusion locks * * started by Ingo Molnar: * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * * This file contains the main data structure and API definitions. */ #ifndef __LINUX_MUTEX_H #define __LINUX_MUTEX_H #include <asm/current.h> #include <linux/list.h> #include <linux/spinlock_types.h> #include <linux/lockdep.h> #include <linux/atomic.h> #include <asm/processor.h> #include <linux/osq_lock.h> #include <linux/debug_locks.h> #include <linux/cleanup.h> #include <linux/mutex_types.h> struct device; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ , .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ } #else # define __DEP_MAP_MUTEX_INITIALIZER(lockname) #endif #ifdef CONFIG_DEBUG_MUTEXES # define __DEBUG_MUTEX_INITIALIZER(lockname) \ , .magic = &lockname extern void mutex_destroy(struct mutex *lock); #else # define __DEBUG_MUTEX_INITIALIZER(lockname) static inline void mutex_destroy(struct mutex *lock) {} #endif #ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized * * Initialize the mutex to unlocked state. * * It is not allowed to initialize an already locked mutex. */ #define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ \ __mutex_init((mutex), #mutex, &__key); \ } while (0) #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) extern void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); /** * mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * * Returns true if the mutex is locked, false if unlocked. */ extern bool mutex_is_locked(struct mutex *lock); #else /* !CONFIG_PREEMPT_RT */ /* * Preempt-RT variant based on rtmutexes. */ #define __MUTEX_INITIALIZER(mutexname) \ { \ .rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex) \ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ } #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) extern void __mutex_rt_init(struct mutex *lock, const char *name, struct lock_class_key *key); #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) #define __mutex_init(mutex, name, key) \ do { \ rt_mutex_base_init(&(mutex)->rtmutex); \ __mutex_rt_init((mutex), name, key); \ } while (0) #define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ \ __mutex_init((mutex), #mutex, &__key); \ } while (0) #endif /* CONFIG_PREEMPT_RT */ #ifdef CONFIG_DEBUG_MUTEXES int __devm_mutex_init(struct device *dev, struct mutex *lock); #else static inline int __devm_mutex_init(struct device *dev, struct mutex *lock) { /* * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so * no really need to register it in the devm subsystem. */ return 0; } #endif #define devm_mutex_init(dev, mutex) \ ({ \ typeof(mutex) mutex_ = (mutex); \ \ mutex_init(mutex_); \ __devm_mutex_init(dev, mutex_); \ }) /* * See kernel/locking/mutex.c for detailed documentation of these APIs. * Also see Documentation/locking/mutex-design.rst. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass); extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); extern int __must_check mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass); extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass); #define mutex_lock(lock) mutex_lock_nested(lock, 0) #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0) #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0) #define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0) #define mutex_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else extern void mutex_lock(struct mutex *lock); extern int __must_check mutex_lock_interruptible(struct mutex *lock); extern int __must_check mutex_lock_killable(struct mutex *lock); extern void mutex_lock_io(struct mutex *lock); # define mutex_lock_nested(lock, subclass) mutex_lock(lock) # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) # define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock) #endif /* * NOTE: mutex_trylock() follows the spin_trylock() convention, * not the down_trylock() convention! * * Returns 1 if the mutex has been acquired successfully, and 0 on contention. */ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T)) DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T)) DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0) #endif /* __LINUX_MUTEX_H */ |
| 295 295 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 168 168 16 16 16 16 16 16 16 16 16 16 16 16 16 16 43 162 16 16 15 162 162 162 162 43 43 43 43 43 43 168 168 168 168 168 168 168 168 149 168 127 168 168 168 168 106 116 16 162 154 168 168 168 168 162 162 162 162 162 162 162 161 162 162 162 162 14 162 162 161 162 162 162 162 162 106 154 154 154 162 162 162 162 162 162 162 162 148 109 148 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 16 16 16 16 16 16 16 16 16 28 28 28 28 28 28 16 16 16 16 16 16 162 162 162 162 162 162 162 162 162 16 16 16 16 16 16 16 18 18 18 16 16 16 16 16 16 16 16 18 162 162 162 162 162 159 159 159 159 159 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/memcontrol.h> #include <linux/llist.h> #include <linux/uio.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> #include <linux/pgtable.h> #include <linux/hugetlb.h> #include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> #include <linux/page_owner.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> #include "internal.h" #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { ioremap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; static int __init set_nohugevmalloc(char *str) { vmap_allow_huge = false; return 0; } early_param("nohugevmalloc", set_nohugevmalloc); #else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ static const bool vmap_allow_huge = false; #endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)kasan_reset_tag(x); return addr >= VMALLOC_START && addr < VMALLOC_END; } EXPORT_SYMBOL(is_vmalloc_addr); struct vfree_deferred { struct llist_head list; struct work_struct wq; }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; struct page *page; unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { if (!pte_none(ptep_get(pte))) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); dump_page(page, "remapping already mapped page"); } BUG(); } #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); if (size != PAGE_SIZE) { pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } #endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte += PFN_DOWN(size), addr += size, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PMD_SHIFT) return 0; if (!arch_vmap_pmd_supported(prot)) return 0; if ((end - addr) != PMD_SIZE) return 0; if (!IS_ALIGNED(addr, PMD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PMD_SIZE)) return 0; if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) return 0; return pmd_set_huge(pmd, phys_addr, prot); } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PMD_MODIFIED; continue; } if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PUD_SHIFT) return 0; if (!arch_vmap_pud_supported(prot)) return 0; if ((end - addr) != PUD_SIZE) return 0; if (!IS_ALIGNED(addr, PUD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PUD_SIZE)) return 0; if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) return 0; return pud_set_huge(pud, phys_addr, prot); } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PUD_MODIFIED; continue; } if (vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pud++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < P4D_SHIFT) return 0; if (!arch_vmap_p4d_supported(prot)) return 0; if ((end - addr) != P4D_SIZE) return 0; if (!IS_ALIGNED(addr, P4D_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, P4D_SIZE)) return 0; if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) return 0; return p4d_set_huge(p4d, phys_addr, prot); } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_P4D_MODIFIED; continue; } if (vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_range_noflush(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { pgd_t *pgd; unsigned long start; unsigned long next; int err; pgtbl_mod_mask mask = 0; might_sleep(); BUG_ON(addr >= end); start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask); if (err) break; } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } int vmap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { int err; err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, ioremap_max_page_shift); return err; } int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { struct vm_struct *area; area = find_vm_area((void *)addr); if (!area || !(area->flags & VM_IOREMAP)) { WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr); return -EINVAL; } if (addr != (unsigned long)area->addr || (void *)end != area->addr + get_vm_area_size(area)) { WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n", addr, end, (long)area->addr, (long)area->addr + get_vm_area_size(area)); return -ERANGE; } return vmap_page_range(addr, end, phys_addr, prot); } static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); cleared = pmd_clear_huge(pmd); if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); cleared = pud_clear_huge(pud); if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); p4d_clear_huge(p4d); if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /* * vunmap_range_noflush is similar to vunmap_range, but does not * flush caches or TLBs. * * The caller is responsible for calling flush_cache_vmap() before calling * this function, and flush_tlb_kernel_range after it has returned * successfully (and before the addresses are expected to cause a page fault * or be re-mapped for something else, if TLB flushes are being delayed or * coalesced). * * This is an internal function only. Do not use outside mm/. */ void __vunmap_range_noflush(unsigned long start, unsigned long end) { unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); } void vunmap_range_noflush(unsigned long start, unsigned long end) { kmsan_vunmap_range_noflush(start, end); __vunmap_range_noflush(start, end); } /** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap * @end: end of the VM area to unmap (non-inclusive) * * Clears any present PTEs in the virtual address range, flushes TLBs and * caches. Any subsequent access to the address before it has been re-mapped * is a kernel bug. */ void vunmap_range(unsigned long addr, unsigned long end) { flush_cache_vunmap(addr, end); vunmap_range_noflush(addr, end); flush_tlb_kernel_range(addr, end); } static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(ptep_get(pte)))) return -EBUSY; if (WARN_ON(!page)) return -ENOMEM; if (WARN_ON(!pfn_valid(page_to_pfn(page)))) return -EINVAL; set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages) { unsigned long start = addr; pgd_t *pgd; unsigned long next; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) return err; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return 0; } /* * vmap_pages_range_noflush is similar to vmap_pages_range, but does not * flush caches. * * The caller is responsible for calling flush_cache_vmap() after this * function returns successfully and before the addresses are accessed. * * This is an internal function only. Do not use outside mm/. */ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { unsigned int i, nr = (end - addr) >> PAGE_SHIFT; WARN_ON(page_shift < PAGE_SHIFT); if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || page_shift == PAGE_SHIFT) return vmap_small_pages_range_noflush(addr, end, prot, pages); for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { int err; err = vmap_range_noflush(addr, addr + (1UL << page_shift), page_to_phys(pages[i]), prot, page_shift); if (err) return err; addr += 1UL << page_shift; } return 0; } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift); if (ret) return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } /** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map * @end: end of the VM area to map (non-inclusive) * @prot: page protection flags to use * @pages: pages to map (always PAGE_SIZE pages) * @page_shift: maximum shift that the pages may be mapped with, @pages must * be aligned and contiguous up to at least this shift. * * RETURNS: * 0 on success, -errno on failure. */ static int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int err; err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift); flush_cache_vmap(addr, end); return err; } static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, unsigned long end) { might_sleep(); if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) return -EINVAL; if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) return -EINVAL; if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) return -EINVAL; if ((end - start) >> PAGE_SHIFT > totalram_pages()) return -E2BIG; if (start < (unsigned long)area->addr || (void *)end > area->addr + get_vm_area_size(area)) return -ERANGE; return 0; } /** * vm_area_map_pages - map pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area * @pages: pages to map (always PAGE_SIZE pages) */ int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages) { int err; err = check_sparse_vm_area(area, start, end); if (err) return err; return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); } /** * vm_area_unmap_pages - unmap pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area */ void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end) { if (check_sparse_vm_area(area, start, end)) return; vunmap_range(start, end); } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will * return the tail page that corresponds to the base page address, which * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd)) return NULL; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return NULL; /* XXX: no allowance for huge pgd */ if (WARN_ON_ONCE(pgd_bad(*pgd))) return NULL; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d)) return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(p4d_bad(*p4d))) return NULL; pud = pud_offset(p4d, addr); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud)) return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd)) return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; ptep = pte_offset_kernel(pmd, addr); pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte); return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define DEBUG_AUGMENT_PROPAGATE_CHECK 0 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 static DEFINE_SPINLOCK(free_vmap_area_lock); static bool vmap_initialized __read_mostly; /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block. */ static struct kmem_cache *vmap_area_cachep; /* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing. */ static LIST_HEAD(free_vmap_area_list); /* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area. */ static struct rb_root free_vmap_area_root = RB_ROOT; /* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks. */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); /* * This structure defines a single, solid model where a list and * rb-tree are part of one entity protected by the lock. Nodes are * sorted in ascending order, thus for O(1) access to left/right * neighbors a list is used as well as for sequential traversal. */ struct rb_list { struct rb_root root; struct list_head head; spinlock_t lock; }; /* * A fast size storage contains VAs up to 1M size. A pool consists * of linked between each other ready to go VAs of certain sizes. * An index in the pool-array corresponds to number of pages + 1. */ #define MAX_VA_SIZE_PAGES 256 struct vmap_pool { struct list_head head; unsigned long len; }; /* * An effective vmap-node logic. Users make use of nodes instead * of a global heap. It allows to balance an access and mitigate * contention. */ static struct vmap_node { /* Simple size segregated storage. */ struct vmap_pool pool[MAX_VA_SIZE_PAGES]; spinlock_t pool_lock; bool skip_populate; /* Bookkeeping data of this node. */ struct rb_list busy; struct rb_list lazy; /* * Ready-to-free areas. */ struct list_head purge_list; struct work_struct purge_work; unsigned long nr_purged; } single; /* * Initial setup consists of one single node, i.e. a balancing * is fully disabled. Later on, after vmap is initialized these * parameters are updated based on a system capacity. */ static struct vmap_node *vmap_nodes = &single; static __read_mostly unsigned int nr_vmap_nodes = 1; static __read_mostly unsigned int vmap_zone_size = 1; static inline unsigned int addr_to_node_id(unsigned long addr) { return (addr / vmap_zone_size) % nr_vmap_nodes; } static inline struct vmap_node * addr_to_node(unsigned long addr) { return &vmap_nodes[addr_to_node_id(addr)]; } static inline struct vmap_node * id_to_node(unsigned int id) { return &vmap_nodes[id % nr_vmap_nodes]; } /* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. * It is always greater then 0. A valid node_id which can * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id * is not valid 0 is returned. */ static unsigned int encode_vn_id(unsigned int node_id) { /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return (node_id + 1) << BITS_PER_BYTE; /* Warn and no node encoded. */ WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); return 0; } /* * Returns an encoded node-id, the valid range is within * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is * returned if extracted data is wrong. */ static unsigned int decode_vn_id(unsigned int val) { unsigned int node_id = (val >> BITS_PER_BYTE) - 1; /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return node_id; /* If it was _not_ zero, warn. */ WARN_ONCE(node_id != UINT_MAX, "Decode wrong node id (%d)\n", node_id); return nr_vmap_nodes; } static bool is_vn_id_valid(unsigned int node_id) { if (node_id < nr_vmap_nodes) return true; return false; } static __always_inline unsigned long va_size(struct vmap_area *va) { return (va->va_end - va->va_start); } static __always_inline unsigned long get_subtree_max_size(struct rb_node *node) { struct vmap_area *va; va = rb_entry_safe(node, struct vmap_area, rb_node); return va ? va->subtree_max_size : 0; } RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void reclaim_and_purge_vmap_areas(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static void drain_vmap_area_work(struct work_struct *work); static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); static atomic_long_t nr_vmalloc_pages; unsigned long vmalloc_nr_pages(void) { return atomic_long_read(&nr_vmalloc_pages); } static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) { struct vmap_area *va = NULL; struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end > addr) { va = tmp; if (tmp->va_start <= addr) break; n = n->rb_left; } else n = n->rb_right; } return va; } /* * Returns a node where a first VA, that satisfies addr < va_end, resides. * If success, a node is locked. A user is responsible to unlock it when a * VA is no longer needed to be accessed. * * Returns NULL if nothing found. */ static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { unsigned long va_start_lowest; struct vmap_node *vn; int i; repeat: for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); if (*va) if (!va_start_lowest || (*va)->va_start < va_start_lowest) va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); } /* * Check if found VA exists, it might have gone away. In this case we * repeat the search because a VA has been removed concurrently and we * need to proceed to the next one, which is a rare case. */ if (va_start_lowest) { vn = addr_to_node(va_start_lowest); spin_lock(&vn->busy.lock); *va = __find_vmap_area(va_start_lowest, &vn->busy.root); if (*va) return vn; spin_unlock(&vn->busy.lock); goto repeat; } return NULL; } /* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent) { struct vmap_area *tmp_va; struct rb_node **link; if (root) { link = &root->rb_node; if (unlikely(!*link)) { *parent = NULL; return link; } } else { link = &from; } /* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to. */ do { tmp_va = rb_entry(*link, struct vmap_area, rb_node); /* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); return NULL; } } while (*link); *parent = &tmp_va->rb_node; return link; } static __always_inline struct list_head * get_va_next_sibling(struct rb_node *parent, struct rb_node **link) { struct list_head *list; if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway. */ return NULL; list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list); } static __always_inline void __link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head, bool augment) { /* * VA is still not in the list, but we can * identify its future previous list_head node. */ if (likely(parent)) { head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link) head = head->prev; } /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on. */ rb_insert_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); va->subtree_max_size = 0; } else { rb_insert_color(&va->rb_node, root); } /* Address-sort this list */ list_add(&va->list, head); } static __always_inline void link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, false); } static __always_inline void link_va_augment(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, true); } static __always_inline void __unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, false); } static __always_inline void unlink_va_augment(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, true); } #if DEBUG_AUGMENT_PROPAGATE_CHECK /* * Gets called when remove the node and rotate. */ static __always_inline unsigned long compute_subtree_max_size(struct vmap_area *va) { return max3(va_size(va), get_subtree_max_size(va->rb_node.rb_left), get_subtree_max_size(va->rb_node.rb_right)); } static void augment_tree_propagate_check(void) { struct vmap_area *va; unsigned long computed_size; list_for_each_entry(va, &free_vmap_area_list, list) { computed_size = compute_subtree_max_size(va); if (computed_size != va->subtree_max_size) pr_emerg("tree is corrupted: %lu, %lu\n", va_size(va), va->subtree_max_size); } } #endif /* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6. */ static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one. */ free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK augment_tree_propagate_check(); #endif } static void insert_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); if (link) link_va(va, root, parent, link, head); } static void insert_vmap_area_augment(struct vmap_area *va, struct rb_node *from, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; if (from) link = find_va_links(va, NULL, from, &parent); else link = find_va_links(va, root, NULL, &parent); if (link) { link_va_augment(va, root, parent, link, head); augment_tree_propagate_from(va); } } /* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing. */ static __always_inline struct vmap_area * __merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false; /* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); if (!link) return NULL; /* * Get next node of VA to check if merging can be done. */ next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert; /* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end */ if (next != head) { sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } /* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end */ if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations. */ if (merged) __unlink_va(va, root, augment); sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } insert: if (!merged) __link_va(va, root, parent, link, head, augment); return va; } static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { return __merge_or_add_vmap_area(va, root, head, false); } static __always_inline struct vmap_area * merge_or_add_vmap_area_augment(struct vmap_area *va, struct rb_root *root, struct list_head *head) { va = __merge_or_add_vmap_area(va, root, head, true); if (va) augment_tree_propagate_from(va); return va; } static __always_inline bool is_within_this_va(struct vmap_area *va, unsigned long size, unsigned long align, unsigned long vstart) { unsigned long nva_start_addr; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr || nva_start_addr < vstart) return false; return (nva_start_addr + size <= va->va_end); } /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. Please note, with an alignment bigger than PAGE_SIZE, * a search length is adjusted to account for worst case alignment * overhead. */ static __always_inline struct vmap_area * find_vmap_lowest_match(struct rb_root *root, unsigned long size, unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ node = root->rb_node; /* Adjust the search size for alignment overhead. */ length = adjust_search_size ? size + align - 1 : size; while (node) { va = rb_entry(node, struct vmap_area, rb_node); if (get_subtree_max_size(node->rb_left) >= length && vstart < va->va_start) { node = node->rb_left; } else { if (is_within_this_va(va, size, align, vstart)) return va; /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length. */ if (get_subtree_max_size(node->rb_right) >= length) { node = node->rb_right; continue; } /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * due to "vstart" restriction or an alignment overhead * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { /* * Shift the vstart forward. Please note, we update it with * parent's start address adding "1" because we do not want * to enter same sub-tree after it has already been checked * and no suitable free block found there. */ vstart = va->va_start + 1; node = node->rb_right; break; } } } } return NULL; } #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK #include <linux/random.h> static struct vmap_area * find_vmap_lowest_linear_match(struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; list_for_each_entry(va, head, list) { if (!is_within_this_va(va, size, align, vstart)) continue; return va; } return NULL; } static void find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; unsigned int rnd; get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; va_1 = find_vmap_lowest_match(root, size, align, vstart, false); va_2 = find_vmap_lowest_linear_match(head, size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", va_1, va_2, vstart); } #endif enum fit_type { NOTHING_FIT = 0, FL_FIT_TYPE = 1, /* full fit */ LE_FIT_TYPE = 2, /* left edge fit */ RE_FIT_TYPE = 3, /* right edge fit */ NE_FIT_TYPE = 4 /* no edge fit */ }; static __always_inline enum fit_type classify_va_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { enum fit_type type; /* Check if it is within VA. */ if (nva_start_addr < va->va_start || nva_start_addr + size > va->va_end) return NOTHING_FIT; /* Now classify. */ if (va->va_start == nva_start_addr) { if (va->va_end == nva_start_addr + size) type = FL_FIT_TYPE; else type = LE_FIT_TYPE; } else if (va->va_end == nva_start_addr + size) { type = RE_FIT_TYPE; } else { type = NE_FIT_TYPE; } return type; } static __always_inline int va_clip(struct rb_root *root, struct list_head *head, struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { struct vmap_area *lva = NULL; enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------| */ unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------| */ va->va_start += size; } else if (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------| */ va->va_end = nva_start_addr; } else if (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---| */ lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -1; } /* * Build the remainder. */ lva->va_start = va->va_start; lva->va_end = nva_start_addr; /* * Shrink this VA to remaining size. */ va->va_start = nva_start_addr + size; } else { return -1; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; } static unsigned long va_alloc(struct vmap_area *va, struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; int ret; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return vend; /* Update the free vmap_area. */ ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) return vend; return nva_start_addr; } /* * Returns a start address of the newly allocated area, if success. * Otherwise a vend is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; /* * Do not adjust when: * a) align <= PAGE_SIZE, because it does not make any sense. * All blocks(their start addresses) are at least PAGE_SIZE * aligned anyway; * b) a short range where a requested size corresponds to exactly * specified [vstart:vend] interval and an alignment > PAGE_SIZE. * With adjusted search length an allocation would not succeed. */ if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) adjust_search_size = false; va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return vend; nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); if (nva_start_addr == vend) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { struct vmap_node *vn = addr_to_node(va->va_start); /* * Remove from the busy tree/list. */ spin_lock(&vn->busy.lock); unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static inline void preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) { struct vmap_area *va = NULL, *tmp; /* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. It guarantees that * a CPU that does an allocation is preloaded. * * We do it in non-atomic context, thus it allows us to use more * permissive allocation masks to be more stable under low memory * condition and high memory pressure. */ if (!this_cpu_read(ne_fit_preload_node)) va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); spin_lock(lock); tmp = NULL; if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va); } static struct vmap_pool * size_to_va_pool(struct vmap_node *vn, unsigned long size) { unsigned int idx = (size - 1) / PAGE_SIZE; if (idx < MAX_VA_SIZE_PAGES) return &vn->pool[idx]; return NULL; } static bool node_pool_add_va(struct vmap_node *n, struct vmap_area *va) { struct vmap_pool *vp; vp = size_to_va_pool(n, va_size(va)); if (!vp) return false; spin_lock(&n->pool_lock); list_add(&va->list, &vp->head); WRITE_ONCE(vp->len, vp->len + 1); spin_unlock(&n->pool_lock); return true; } static struct vmap_area * node_pool_del_va(struct vmap_node *vn, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { struct vmap_area *va = NULL; struct vmap_pool *vp; int err = 0; vp = size_to_va_pool(vn, size); if (!vp || list_empty(&vp->head)) return NULL; spin_lock(&vn->pool_lock); if (!list_empty(&vp->head)) { va = list_first_entry(&vp->head, struct vmap_area, list); if (IS_ALIGNED(va->va_start, align)) { /* * Do some sanity check and emit a warning * if one of below checks detects an error. */ err |= (va_size(va) != size); err |= (va->va_start < vstart); err |= (va->va_end > vend); if (!WARN_ON_ONCE(err)) { list_del_init(&va->list); WRITE_ONCE(vp->len, vp->len - 1); } else { va = NULL; } } else { list_move_tail(&va->list, &vp->head); va = NULL; } } spin_unlock(&vn->pool_lock); return va; } static struct vmap_area * node_alloc(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, unsigned long *addr, unsigned int *vn_id) { struct vmap_area *va; *vn_id = 0; *addr = vend; /* * Fallback to a global heap if not vmalloc or there * is only one node. */ if (vstart != VMALLOC_START || vend != VMALLOC_END || nr_vmap_nodes == 1) return NULL; *vn_id = raw_smp_processor_id() % nr_vmap_nodes; va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); *vn_id = encode_vn_id(*vn_id); if (va) *addr = va->va_start; return va; } static inline void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; } /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, unsigned long va_flags, struct vm_struct *vm) { struct vmap_node *vn; struct vmap_area *va; unsigned long freed; unsigned long addr; unsigned int vn_id; int purged = 0; int ret; if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) return ERR_PTR(-EINVAL); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); might_sleep(); /* * If a VA is obtained from a global heap(if it fails here) * it is anyway marked with this "vn_id" so it is returned * to this pool's node later. Such way gives a possibility * to populate pools based on users demand. * * On success a ready to go VA is returned. */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { gfp_mask = gfp_mask & GFP_RECLAIM_MASK; va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); } retry: if (addr == vend) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); } trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ if (unlikely(addr == vend)) goto overflow; va->va_start = addr; va->va_end = addr + size; va->vm = NULL; va->flags = (va_flags | vn_id); if (vm) { vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; va->vm = vm; } vn = addr_to_node(va->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); ret = kasan_populate_vmalloc(addr, size); if (ret) { free_vmap_area(va); return ERR_PTR(ret); } return va; overflow: if (!purged) { reclaim_and_purge_vmap_areas(); purged = 1; goto retry; } freed = 0; blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); if (freed > 0) { purged = 0; goto retry; } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", size, vstart, vend); kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } int register_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); int unregister_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); static cpumask_t purge_nodes; static void reclaim_list_global(struct list_head *head) { struct vmap_area *va, *n; if (list_empty(head)) return; spin_lock(&free_vmap_area_lock); list_for_each_entry_safe(va, n, head, list) merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static void decay_va_pool_node(struct vmap_node *vn, bool full_decay) { struct vmap_area *va, *nva; struct list_head decay_list; struct rb_root decay_root; unsigned long n_decay; int i; decay_root = RB_ROOT; INIT_LIST_HEAD(&decay_list); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { struct list_head tmp_list; if (list_empty(&vn->pool[i].head)) continue; INIT_LIST_HEAD(&tmp_list); /* Detach the pool, so no-one can access it. */ spin_lock(&vn->pool_lock); list_replace_init(&vn->pool[i].head, &tmp_list); spin_unlock(&vn->pool_lock); if (full_decay) WRITE_ONCE(vn->pool[i].len, 0); /* Decay a pool by ~25% out of left objects. */ n_decay = vn->pool[i].len >> 2; list_for_each_entry_safe(va, nva, &tmp_list, list) { list_del_init(&va->list); merge_or_add_vmap_area(va, &decay_root, &decay_list); if (!full_decay) { WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1); if (!--n_decay) break; } } /* * Attach the pool back if it has been partly decayed. * Please note, it is supposed that nobody(other contexts) * can populate the pool therefore a simple list replace * operation takes place here. */ if (!full_decay && !list_empty(&tmp_list)) { spin_lock(&vn->pool_lock); list_replace_init(&tmp_list, &vn->pool[i].head); spin_unlock(&vn->pool_lock); } } reclaim_list_global(&decay_list); } static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); struct vmap_area *va, *n_va; LIST_HEAD(local_list); vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; unsigned long orig_start = va->va_start; unsigned long orig_end = va->va_end; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); if (is_vmalloc_or_module_addr((void *)orig_start)) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) if (node_pool_add_va(vn, va)) continue; /* Go back to global. */ list_add(&va->list, &local_list); } reclaim_list_global(&local_list); } /* * Purges all lazily-freed vmap areas. */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, bool full_pool_decay) { unsigned long nr_purged_areas = 0; unsigned int nr_purge_helpers; unsigned int nr_purge_nodes; struct vmap_node *vn; int i; lockdep_assert_held(&vmap_purge_lock); /* * Use cpumask to mark which node has to be processed. */ purge_nodes = CPU_MASK_NONE; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; INIT_LIST_HEAD(&vn->purge_list); vn->skip_populate = full_pool_decay; decay_va_pool_node(vn, full_pool_decay); if (RB_EMPTY_ROOT(&vn->lazy.root)) continue; spin_lock(&vn->lazy.lock); WRITE_ONCE(vn->lazy.root.rb_node, NULL); list_replace_init(&vn->lazy.head, &vn->purge_list); spin_unlock(&vn->lazy.lock); start = min(start, list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start); end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end); cpumask_set_cpu(i, &purge_nodes); } nr_purge_nodes = cpumask_weight(&purge_nodes); if (nr_purge_nodes > 0) { flush_tlb_kernel_range(start, end); /* One extra worker is per a lazy_max_pages() full set minus one. */ nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (nr_purge_helpers > 0) { INIT_WORK(&vn->purge_work, purge_vmap_node); if (cpumask_test_cpu(i, cpu_online_mask)) schedule_work_on(i, &vn->purge_work); else schedule_work(&vn->purge_work); nr_purge_helpers--; } else { vn->purge_work.func = NULL; purge_vmap_node(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (vn->purge_work.func) { flush_work(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } } trace_purge_vmap_area_lazy(start, end, nr_purged_areas); return nr_purged_areas > 0; } /* * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list. */ static void reclaim_and_purge_vmap_areas(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); __purge_vmap_area_lazy(ULONG_MAX, 0, true); mutex_unlock(&vmap_purge_lock); } static void drain_vmap_area_work(struct work_struct *work) { mutex_lock(&vmap_purge_lock); __purge_vmap_area_lazy(ULONG_MAX, 0, false); mutex_unlock(&vmap_purge_lock); } /* * Free a vmap area, caller ensuring that the area has been unmapped, * unlinked and flush_cache_vunmap had been called for the correct * range previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy_max = lazy_max_pages(); unsigned long va_start = va->va_start; unsigned int vn_id = decode_vn_id(va->flags); struct vmap_node *vn; unsigned long nr_lazy; if (WARN_ON_ONCE(!list_empty(&va->list))) return; nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); /* * If it was request by a certain node we would like to * return it to that node, i.e. its pool for later reuse. */ vn = is_vn_id_valid(vn_id) ? id_to_node(vn_id):addr_to_node(va->va_start); spin_lock(&vn->lazy.lock); insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); spin_unlock(&vn->lazy.lock); trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); /* After this point, we may free va at any time */ if (unlikely(nr_lazy > nr_lazy_max)) schedule_work(&drain_vmap_work); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; if (unlikely(!vmap_initialized)) return NULL; /* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed * addr is not the same as va->va_start, what is not common, we * may need to scan extra nodes. See an example: * * <----va----> * -|-----|-----|-----|-----|- * 1 2 0 1 * * VA resides in node 1 whereas it spans 1, 2 an 0. If passed * addr is within 2 or 0 nodes we should do extra work. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } static struct vmap_area *find_unlink_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; /* * Check the comment in the find_vmap_area() about the loop. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); if (va) unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS \ VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) /* * Purge threshold to prevent overeager purging of fragmented blocks for * regular operations: Purge if vb->free is less than 1/4 of the capacity. */ #define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4) #define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ #define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ #define VMAP_FLAGS_MASK 0x3 struct vmap_block_queue { spinlock_t lock; struct list_head free; /* * An xarray requires an extra memory dynamically to * be allocated. If it is an issue, we can use rb-tree * instead. */ struct xarray vmap_blocks; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS); unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * In order to fast access to any "vmap_block" associated with a * specific address, we use a hash. * * A per-cpu vmap_block_queue is used in both ways, to serialize * an access to free block chains among CPUs(alloc path) and it * also acts as a vmap_block hash(alloc/free paths). It means we * overload it, since we already have the per-cpu array which is * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * * An example: * * CPU_1 CPU_2 CPU_0 * | | | * V V V * 0 10 20 30 40 50 60 * |------|------|------|------|------|------|...<vmap address space> * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 * * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; * * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; * * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. * * This technique almost always avoids lock contention on insert/remove, * however xarray spinlocks protect against any contention that remains. */ static struct xarray * addr_to_vb_xa(unsigned long addr) { int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; /* * Please note, nr_cpu_ids points on a highest set * possible bit, i.e. we never invoke cpumask_next() * if an index points on it which is nr_cpu_ids - 1. */ if (!cpu_possible(index)) index = cpumask_next(index, cpu_possible_mask); return &per_cpu(vmap_block_queue, index).vmap_blocks; } /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) { unsigned long addr; addr = va_start + (pages_off << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); return (void *)addr; } /** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno) */ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); bitmap_zero(vb->used_map, VMAP_BBMAP_BITS); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } /* * list_add_tail_rcu could happened in another core * rather than vb->cpu due to task migration, which * is safe as list_add_tail_rcu will ensure the list's * integrity together with list_for_each_rcu from read * side. */ vb->cpu = raw_smp_processor_id(); vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { struct vmap_node *vn; struct vmap_block *tmp; struct xarray *xa; xa = addr_to_vb_xa(vb->va->va_start); tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); vn = addr_to_node(vb->va->va_start); spin_lock(&vn->busy.lock); unlink_va(vb->va, &vn->busy.root); spin_unlock(&vn->busy.lock); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } static bool purge_fragmented_block(struct vmap_block *vb, struct list_head *purge_list, bool force_purge) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; /* Don't overeagerly purge usable blocks unless requested */ if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD)) return false; /* prevent further allocs after releasing lock */ WRITE_ONCE(vb->free, 0); /* prevent purging it again */ WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS); vb->dirty_min = 0; vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); list_add_tail(&vb->purge, purge_list); return true; } static void free_purged_blocks(struct list_head *purge_list) { struct vmap_block *vb, *n_vb; list_for_each_entry_safe(vb, n_vb, purge_list, purge) { list_del(&vb->purge); free_vmap_block(vb); } } static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long free = READ_ONCE(vb->free); unsigned long dirty = READ_ONCE(vb->dirty); if (free + dirty != VMAP_BBMAP_BITS || dirty == VMAP_BBMAP_BITS) continue; spin_lock(&vb->lock); purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); free_purged_blocks(&purge); } static void purge_fragmented_blocks_allcpus(void) { int cpu; for_each_possible_cpu(cpu) purge_fragmented_blocks(cpu); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; void *vaddr = NULL; unsigned int order; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); if (WARN_ON(size == 0)) { /* * Allocating 0 bytes isn't what caller wants since * get_order(0) returns funny result. Just warn and terminate * early. */ return ERR_PTR(-EINVAL); } order = get_order(size); rcu_read_lock(); vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; if (READ_ONCE(vb->free) < (1UL << order)) continue; spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); continue; } pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); WRITE_ONCE(vb->free, vb->free - (1UL << order)); bitmap_set(vb->used_map, pages_off, (1UL << order)); if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } rcu_read_unlock(); /* Allocate new block if nothing was found */ if (!vaddr) vaddr = new_vmap_block(order, gfp_mask); return vaddr; } static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; unsigned int order; struct vmap_block *vb; struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap(addr, addr + size); order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; xa = addr_to_vb_xa(addr); vb = xa_load(xa, addr_to_vb_idx(addr)); spin_lock(&vb->lock); bitmap_clear(vb->used_map, offset, (1UL << order)); spin_unlock(&vb->lock); vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); /* Expand the not yet TLB flushed dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order)); if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { LIST_HEAD(purge_list); int cpu; if (unlikely(!vmap_initialized)) return; mutex_lock(&vmap_purge_lock); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; unsigned long idx; rcu_read_lock(); xa_for_each(&vbq->vmap_blocks, idx, vb) { spin_lock(&vb->lock); /* * Try to purge a fragmented block first. If it's * not purgeable, check whether there is dirty * space to be flushed. */ if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; s = va_start + (vb->dirty_min << PAGE_SHIFT); e = va_start + (vb->dirty_max << PAGE_SHIFT); start = min(s, start); end = max(e, end); /* Prevent that this is flushed again */ vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } free_purged_blocks(&purge_list); if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int flush = 0; _vm_unmap_aliases(start, end, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)kasan_reset_tag(mem); struct vmap_area *va; might_sleep(); BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); kasan_poison_vmalloc(mem, size); if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(addr, size); return; } va = find_unlink_vmap_area(addr); if (WARN_ON_ONCE(!va)) return; debug_check_no_locks_freed((void *)va->va_start, (va->va_end - va->va_start)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM, NULL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, PAGE_SHIFT) < 0) { vm_unmap_ram(mem, count); return NULL; } /* * Mark the pages as accessible, now that they are mapped. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL); return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; static inline unsigned int vm_area_page_order(struct vm_struct *vm) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return vm->page_order; #else return 0; #endif } static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC vm->page_order = order; #else BUG_ON(order != 0); #endif } /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_add_early(struct vm_struct *vm) { struct vm_struct *tmp, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) { BUG_ON(tmp->addr < vm->addr + vm->size); break; } else BUG_ON(tmp->addr + tmp->size > vm->addr); } vm->next = *p; *p = vm; } /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { unsigned long addr = ALIGN(VMALLOC_START, align); struct vm_struct *cur, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { if ((unsigned long)cur->addr - addr >= vm->size) break; addr = ALIGN((unsigned long)cur->addr + cur->size, align); } BUG_ON(addr > VMALLOC_END - vm->size); vm->addr = (void *)addr; vm->next = *p; *p = vm; kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in show_numa_info(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; area->flags = flags; area->caller = caller; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. * For VM_ALLOC mappings, the pages are marked as accessible after * getting mapped in __vmalloc_node_range(). * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL); return area; } struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (!va) return NULL; return va->vm; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; struct vm_struct *vm; might_sleep(); if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", addr)) return NULL; va = find_unlink_vmap_area((unsigned long)addr); if (!va || !va->vm) return NULL; vm = va->vm; debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm)); debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm)); kasan_free_module_shadow(vm); kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm)); free_unmap_vmap_area(va); return vm; } static inline void set_area_direct_map(const struct vm_struct *area, int (*set_direct_map)(struct page *page)) { int i; /* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } /* * Flush the vm mapping and reset the direct map. */ static void vm_reset_perms(struct vm_struct *area) { unsigned long start = ULONG_MAX, end = 0; unsigned int page_order = vm_area_page_order(area); int flush_dmap = 0; int i; /* * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { unsigned long page_size; page_size = PAGE_SIZE << page_order; start = min(addr, start); end = max(addr + page_size, end); flush_dmap = 1; } } /* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } static void delayed_vfree_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); struct llist_node *t, *llnode; llist_for_each_safe(llnode, t, llist_del_all(&p->list)) vfree(llnode); } /** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs. */ void vfree_atomic(const void *addr) { struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); BUG_ON(in_nmi()); kmemleak_free(addr); /* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too. */ if (addr && llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } /** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { struct vm_struct *vm; int i; if (unlikely(in_interrupt())) { vfree_atomic(addr); return; } BUG_ON(in_nmi()); kmemleak_free(addr); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i]; BUG_ON(!page); mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations */ __free_page(page); cond_resched(); } atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { struct vm_struct *vm; BUG_ON(in_interrupt()); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n", addr); return; } kfree(vm); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; unsigned long addr; unsigned long size; /* In bytes */ might_sleep(); if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) return NULL; /* * Your top guard is someone else's bottom guard. Not having a top * guard compromises someone else's mappings too. */ if (WARN_ON_ONCE(flags & VM_NO_GUARD)) flags &= ~VM_NO_GUARD; if (count > totalram_pages()) return NULL; size = (unsigned long)count << PAGE_SHIFT; area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; addr = (unsigned long)area->addr; if (vmap_pages_range(addr, addr + size, pgprot_nx(prot), pages, PAGE_SHIFT) < 0) { vunmap(area->addr); return NULL; } if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; area->nr_pages = count; } return area->addr; } EXPORT_SYMBOL(vmap); #ifdef CONFIG_VMAP_PFN struct vmap_pfn_data { unsigned long *pfns; pgprot_t prot; unsigned int idx; }; static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) { struct vmap_pfn_data *data = private; unsigned long pfn = data->pfns[data->idx]; pte_t ptent; if (WARN_ON_ONCE(pfn_valid(pfn))) return -EINVAL; ptent = pte_mkspecial(pfn_pte(pfn, data->prot)); set_pte_at(&init_mm, addr, pte, ptent); data->idx++; return 0; } /** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping. */ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) { struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area; area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, __builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsigned long)area->addr, count * PAGE_SIZE, vmap_pfn_apply, &data)) { free_vm_area(area); return NULL; } flush_cache_vmap((unsigned long)area->addr, (unsigned long)area->addr + count * PAGE_SIZE); return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ static inline unsigned int vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; gfp_t alloc_gfp = gfp; bool nofail = gfp & __GFP_NOFAIL; struct page *page; int i; /* * For order-0 pages we make use of bulk allocator, if * the page array is partly or not at all populated due * to fails, fallback to a single page allocator that is * more permissive. */ if (!order) { /* bulk allocator doesn't support nofail req. officially */ gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL; while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; /* * A maximum allowed request is hard-coded and is 100 * pages per call. That is done in order to prevent a * long preemption off scenario in the bulk-allocator * so the range is [1:100]. */ nr_pages_request = min(100U, nr_pages - nr_allocated); /* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp, nr_pages_request, pages + nr_allocated); else nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid, nr_pages_request, pages + nr_allocated); nr_allocated += nr; cond_resched(); /* * If zero or pages were obtained partly, * fallback to a single page allocator. */ if (nr != nr_pages_request) break; } } else if (gfp & __GFP_NOFAIL) { /* * Higher order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!nofail && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(alloc_gfp, order); else page = alloc_pages_node_noprof(nid, alloc_gfp, order); if (unlikely(!page)) { if (!nofail) break; /* fall back to the zero order allocations */ alloc_gfp |= __GFP_NOFAIL; order = 0; continue; } /* * Higher order allocations must be able to be treated as * indepdenent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc. */ if (order) split_page(page, order); /* * Careful, we allocate and map page-order pages, but * tracking is done per PAGE_SIZE page so as to keep the * vm_struct APIs independent of the physical/mapped size. */ for (i = 0; i < (1U << order); i++) pages[nr_allocated + i] = page + i; cond_resched(); nr_allocated += 1U << order; } return nr_allocated; } static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; bool nofail = gfp_mask & __GFP_NOFAIL; unsigned long addr = (unsigned long)area->addr; unsigned long size = get_vm_area_size(area); unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; unsigned int flags; int ret; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, area->caller); } else { area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } if (!area->pages) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); free_vm_area(area); return NULL; } set_vm_area_page_order(area, page_shift - PAGE_SHIFT); page_order = vm_area_page_order(area); area->nr_pages = vm_area_alloc_pages(gfp_mask | __GFP_NOWARN, node, page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { int i; for (i = 0; i < area->nr_pages; i++) mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* * If not enough pages were obtained to accomplish an * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { /* * vm_area_alloc_pages() can fail due to insufficient memory but * also:- * * - a pending fatal signal * - insufficient huge page-order pages * * Since we always retry allocations at order-0 in the huge page * case a warning for either is spurious. */ if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocate pages", area->nr_pages * PAGE_SIZE); goto fail; } /* * page tables allocations ignore external gfp mask, enforce it * by the scope API */ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) flags = memalloc_nofs_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) flags = memalloc_noio_save(); do { ret = vmap_pages_range(addr, addr + size, prot, area->pages, page_shift); if (nofail && (ret < 0)) schedule_timeout_uninterruptible(1); } while (nofail && (ret < 0)); if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) memalloc_nofs_restore(flags); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) memalloc_noio_restore(flags); if (ret < 0) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to map pages", area->nr_pages * PAGE_SIZE); goto fail; } return area->addr; fail: vfree(area->addr); return NULL; } /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Please note that the full set of gfp * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all * supported. * Zone modifiers are not supported. From the reclaim modifiers * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported) * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and * __GFP_RETRY_MAYFAIL are not supported). * * __GFP_NOWARN can be used to suppress failures messages. * * Map them into contiguous kernel virtual space, using a pagetable * protection of @prot. * * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; void *ret; kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; unsigned long real_size = size; unsigned long real_align = align; unsigned int shift = PAGE_SHIFT; if (WARN_ON_ONCE(!size)) return NULL; if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages", real_size); return NULL; } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in * their allocations due to apply_to_page_range not * supporting them. */ size_per_node = size; if (node == NUMA_NO_NODE) size_per_node /= num_online_nodes(); if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) shift = PMD_SHIFT; else shift = arch_vmap_pte_supported_shift(size_per_node); align = max(real_align, 1UL << shift); size = ALIGN(real_size, 1UL << shift); } again: area = __get_vm_area_node(real_size, align, shift, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) { bool nofail = gfp_mask & __GFP_NOFAIL; warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, vm_struct allocation failed%s", real_size, (nofail) ? ". Retrying." : ""); if (nofail) { schedule_timeout_uninterruptible(1); goto again; } goto fail; } /* * Prepare arguments for __vmalloc_area_node() and * kasan_unpoison_vmalloc(). */ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { if (kasan_hw_tags_enabled()) { /* * Modify protection bits to allow tagging. * This must be done before mapping. */ prot = arch_vmap_pgprot_tagged(prot); /* * Skip page_alloc poisoning and zeroing for physical * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc(). */ gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; } /* Take note that the mapping is PAGE_KERNEL. */ kasan_flags |= KASAN_VMALLOC_PROT_NORMAL; } /* Allocate physical pages and map them into vmalloc space. */ ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret) goto fail; /* * Mark the pages as accessible, now that they are mapped. * The condition for setting KASAN_VMALLOC_INIT should complement the * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc(). */ kasan_flags |= KASAN_VMALLOC_VM_ALLOC; if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ area->addr = kasan_unpoison_vmalloc(area->addr, real_size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here. */ clear_vm_uninitialized_flag(area); size = PAGE_ALIGN(size); if (!(vm_flags & VM_DEFER_KMEMLEAK)) kmemleak_vmalloc(area, size, gfp_mask); return area->addr; fail: if (shift > PAGE_SHIFT) { shift = PAGE_SHIFT; align = real_align; size = real_size; goto again; } return NULL; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted * with mm people. * * Return: pointer to the allocated memory or %NULL on error */ void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_noprof); /** * vmalloc_huge - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * If @size is greater than or equal to PMD_SIZE, allow using * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(vmalloc_huge_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_node_noprof); #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_user_noprof); /* * Atomically zero bytes in the iterator. * * Returns the number of zeroed bytes. */ static size_t zero_iter(struct iov_iter *iter, size_t count) { size_t remains = count; while (remains > 0) { size_t num, copied; num = min_t(size_t, remains, PAGE_SIZE); copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); remains -= copied; if (copied < num) break; } return count - remains; } /* * small helper routine, copy contents to iter from addr. * If the page is not present, fill zero. * * Returns the number of copied bytes. */ static size_t aligned_vread_iter(struct iov_iter *iter, const char *addr, size_t count) { size_t remains = count; struct page *page; while (remains > 0) { unsigned long offset, length; size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > remains) length = remains; page = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need lock. But * adding lock here means that we need to add overhead of * vmalloc()/vfree() calls for this _debug_ interface, rarely * used. Instead of that, we'll use an local mapping via * copy_page_to_iter_nofault() and accept a small overhead in * this access function. */ if (page) copied = copy_page_to_iter_nofault(page, offset, length, iter); else copied = zero_iter(iter, length); addr += copied; remains -= copied; if (copied != length) break; } return count - remains; } /* * Read from a vm_map_ram region of memory. * * Returns the number of copied bytes. */ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, size_t count, unsigned long flags) { char *start; struct vmap_block *vb; struct xarray *xa; unsigned long offset; unsigned int rs, re; size_t remains, n; /* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here. */ if (!(flags & VMAP_BLOCK)) return aligned_vread_iter(iter, addr, count); remains = count; /* * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ xa = addr_to_vb_xa((unsigned long) addr); vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { spin_unlock(&vb->lock); goto finished_zero; } for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { size_t copied; if (remains == 0) goto finished; start = vmap_block_vaddr(vb->va->va_start, rs); if (addr < start) { size_t to_zero = min_t(size_t, start - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } /*it could start reading from the middle of used region*/ offset = offset_in_page(addr); n = ((re - rs + 1) << PAGE_SHIFT) - offset; if (n > remains) n = remains; copied = aligned_vread_iter(iter, start + offset, n); addr += copied; remains -= copied; if (copied != n) goto finished; } spin_unlock(&vb->lock); finished_zero: /* zero-fill the left dirty or free regions */ return count - remains + zero_iter(iter, remains); finished: /* We couldn't copy/zero everything */ spin_unlock(&vb->lock); return count - remains; } /** * vread_iter() - read vmalloc area in a safe way to an iterator. * @iter: the iterator to which data should be written. * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @buf. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr; size_t n, size, flags, remains; unsigned long next; addr = kasan_reset_tag(addr); /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; remains = count; vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); if (!vn) goto finished_zero; /* no intersects with alive vmap_area */ if ((unsigned long)addr + remains <= va->va_start) goto finished_zero; do { size_t copied; if (remains == 0) goto finished; vm = va->vm; flags = va->flags & VMAP_FLAGS_MASK; /* * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need * be set together with VMAP_RAM. */ WARN_ON(flags == VMAP_BLOCK); if (!vm && !flags) goto next_va; if (vm && (vm->flags & VM_UNINITIALIZED)) goto next_va; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); vaddr = (char *) va->va_start; size = vm ? get_vm_area_size(vm) : va_size(va); if (addr >= vaddr + size) goto next_va; if (addr < vaddr) { size_t to_zero = min_t(size_t, vaddr - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } n = vaddr + size - addr; if (n > remains) n = remains; if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP | SPARSE area is treated as memory hole */ copied = zero_iter(iter, n); addr += copied; remains -= copied; if (copied != n) goto finished; next_va: next = va->va_end; spin_unlock(&vn->busy.lock); } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); finished_zero: if (vn) spin_unlock(&vn->busy.lock); /* zero-fill memory holes */ return count - remains + zero_iter(iter, remains); finished: /* Nothing remains, or We couldn't copy/zero everything. */ if (vn) spin_unlock(&vn->busy.lock); return count - remains; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size) { struct vm_struct *area; unsigned long off; unsigned long end_index; if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; if (check_add_overflow(size, off, &end_index) || end_index > get_vm_area_size(area)) return -EINVAL; kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { return rb_entry_safe(n, struct vmap_area, rb_node); } /** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr. */ static struct vmap_area * pvm_find_va_enclose_addr(unsigned long addr) { struct vmap_area *va, *tmp; struct rb_node *n; n = free_vmap_area_root.rb_node; va = NULL; while (n) { tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) { va = tmp; if (tmp->va_end >= addr) break; n = n->rb_right; } else { n = n->rb_left; } } return va; } /** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * @align: alignment for required highest address * * Returns: determined end address within vmap_area */ static unsigned long pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) { unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); unsigned long addr; if (likely(*va)) { list_for_each_entry_from_reverse((*va), &free_vmap_area_list, list) { addr = min((*va)->va_end & ~(align - 1), vmalloc_end); if ((*va)->va_start < addr) return addr; } } return 0; } /** * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator * @offsets: array containing offset of each area * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to * be scattered pretty far, distance between two areas easily going up * to gigabytes. To avoid interacting with regular vmallocs, these * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { start = offsets[area]; end = start + sizes[area]; /* is everything aligned properly? */ BUG_ON(!IS_ALIGNED(offsets[area], align)); BUG_ON(!IS_ALIGNED(sizes[area], align)); /* detect the area with the highest address */ if (start > offsets[last_area]) last_area = area; for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; if (vmalloc_end - vmalloc_start < last_end) { WARN_ON(true); return NULL; } vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } retry: spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(vmalloc_end); base = pvm_determine_end_from_reverse(&va, align) - end; while (true) { /* * base might have underflowed, add last_end before * comparing. */ if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow; /* * If required width exceeds current VA block, move * base downwards and then recheck. */ if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * If this VA does not fit, move base downwards and recheck. */ if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * This area fits, move on to the previous one. If * the previous one is the terminal one, we're done. */ area = (area + nr_vms - 1) % nr_vms; if (area == term_area) break; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(base + end); } /* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret; start = base + offsets[area]; size = sizes[area]; va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; ret = va_clip(&free_vmap_area_root, &free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; /* Allocated area. */ va = vas[area]; va->va_start = start; va->va_end = start + size; } spin_unlock(&free_vmap_area_lock); /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) goto err_free_shadow; } /* insert all vm's */ for (area = 0; area < nr_vms; area++) { struct vmap_node *vn = addr_to_node(vas[area]->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); } /* * Mark allocated areas as accessible. Do it now as a best-effort * approach, as they can be mapped outside of vmalloc code. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ for (area = 0; area < nr_vms; area++) vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success. */ while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { reclaim_and_purge_vmap_areas(); purged = true; /* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue; vas[area] = kmem_cache_zalloc( vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free; } goto retry; } err_free: for (area = 0; area < nr_vms; area++) { if (vas[area]) kmem_cache_free(vmap_area_cachep, vas[area]); kfree(vms[area]); } err_free2: kfree(vas); kfree(vms); return NULL; err_free_shadow: spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case. */ for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; kfree(vms[area]); } spin_unlock(&free_vmap_area_lock); kfree(vas); kfree(vms); return NULL; } /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() * @nr_vms: the number of allocated areas * * Free vm_structs and the array allocated by pcpu_get_vm_areas(). */ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { int i; for (i = 0; i < nr_vms; i++) free_vm_area(vms[i]); kfree(vms); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { const void *caller; struct vm_struct *vm; struct vmap_area *va; struct vmap_node *vn; unsigned long addr; unsigned int nr_pages; addr = PAGE_ALIGN((unsigned long) object); vn = addr_to_node(addr); if (!spin_trylock(&vn->busy.lock)) return false; va = __find_vmap_area(addr, &vn->busy.root); if (!va || !va->vm) { spin_unlock(&vn->busy.lock); return false; } vm = va->vm; addr = (unsigned long) vm->addr; caller = vm->caller; nr_pages = vm->nr_pages; spin_unlock(&vn->busy.lock); pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", nr_pages, addr, caller); return true; } #endif #ifdef CONFIG_PROC_FS static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; unsigned int step = 1U << vm_area_page_order(v); if (!counters) return; if (v->flags & VM_UNINITIALIZED) return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr += step) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } static void show_purge_info(struct seq_file *m) { struct vmap_node *vn; struct vmap_area *va; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->lazy.lock); list_for_each_entry(va, &vn->lazy.head, list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); } spin_unlock(&vn->lazy.lock); } } static int vmalloc_info_show(struct seq_file *m, void *p) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); list_for_each_entry(va, &vn->busy.head, list) { if (!va->vm) { if (va->flags & VMAP_RAM) seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); continue; } v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_SPARSE) seq_puts(m, " sparse"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_DMA_COHERENT) seq_puts(m, " dma-coherent"); if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); } /* * As a final step, dump "unpurged" areas. */ show_purge_info(m); return 0; } static int __init proc_vmalloc_init(void) { void *priv_data = NULL; if (IS_ENABLED(CONFIG_NUMA)) priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); proc_create_single_data("vmallocinfo", 0400, NULL, vmalloc_info_show, priv_data); return 0; } module_init(proc_vmalloc_init); #endif static void __init vmap_init_free_space(void) { unsigned long vmap_start = 1; const unsigned long vmap_end = ULONG_MAX; struct vmap_area *free; struct vm_struct *busy; /* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->| */ for (busy = vmlist; busy; busy = busy->next) { if ((unsigned long) busy->addr - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = (unsigned long) busy->addr; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } vmap_start = (unsigned long) busy->addr + busy->size; } if (vmap_end - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = vmap_end; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } } static void vmap_init_nodes(void) { struct vmap_node *vn; int i, n; #if BITS_PER_LONG == 64 /* * A high threshold of max nodes is fixed and bound to 128, * thus a scale factor is 1 for systems where number of cores * are less or equal to specified threshold. * * As for NUMA-aware notes. For bigger systems, for example * NUMA with multi-sockets, where we can end-up with thousands * of cores in total, a "sub-numa-clustering" should be added. * * In this case a NUMA domain is considered as a single entity * with dedicated sub-nodes in it which describe one group or * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing. */ n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); if (n > 1) { vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); if (vn) { /* Node partition is 16 pages. */ vmap_zone_size = (1 << 4) * PAGE_SIZE; nr_vmap_nodes = n; vmap_nodes = vn; } else { pr_err("Failed to allocate an array. Disable a node layer\n"); } } #endif for (n = 0; n < nr_vmap_nodes; n++) { vn = &vmap_nodes[n]; vn->busy.root = RB_ROOT; INIT_LIST_HEAD(&vn->busy.head); spin_lock_init(&vn->busy.lock); vn->lazy.root = RB_ROOT; INIT_LIST_HEAD(&vn->lazy.head); spin_lock_init(&vn->lazy.lock); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { INIT_LIST_HEAD(&vn->pool[i].head); WRITE_ONCE(vn->pool[i].len, 0); } spin_lock_init(&vn->pool_lock); } } static unsigned long vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; struct vmap_node *vn; int i, j; for (count = 0, i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; for (j = 0; j < MAX_VA_SIZE_PAGES; j++) count += READ_ONCE(vn->pool[j].len); } return count ? count : SHRINK_EMPTY; } static unsigned long vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { int i; for (i = 0; i < nr_vmap_nodes; i++) decay_va_pool_node(&vmap_nodes[i], true); return SHRINK_STOP; } void __init vmalloc_init(void) { struct shrinker *vmap_node_shrinker; struct vmap_area *va; struct vmap_node *vn; struct vm_struct *tmp; int i; /* * Create the cache for vmap_area objects. */ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); for_each_possible_cpu(i) { struct vmap_block_queue *vbq; struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, delayed_vfree_work); xa_init(&vbq->vmap_blocks); } /* * Setup nodes before importing vmlist. */ vmap_init_nodes(); /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; vn = addr_to_node(va->va_start); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); } /* * Now we can initialize a free vmap space. */ vmap_init_free_space(); vmap_initialized = true; vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); if (!vmap_node_shrinker) { pr_err("Failed to allocate vmap-node shrinker!\n"); return; } vmap_node_shrinker->count_objects = vmap_node_shrink_count; vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; shrinker_register(vmap_node_shrinker); } |
| 3 3 3 3 3 1 1 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values seperately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; if (!interval) return 1; /* * If we contend on this state's lock then almost * by definition we are too busy to print a message, * in addition to the one that will be printed by * the entity that is holding the lock already: */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) return 0; if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, rs->missed); rs->missed = 0; } } rs->begin = jiffies; rs->printed = 0; } if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { rs->missed++; ret = 0; } raw_spin_unlock_irqrestore(&rs->lock, flags); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 78 77 48 78 78 77 78 78 78 78 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | // SPDX-License-Identifier: GPL-2.0 /* * Based on arch/arm/mm/extable.c */ #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/uaccess.h> #include <asm/asm-extable.h> #include <asm/ptrace.h> static inline unsigned long get_ex_fixup(const struct exception_table_entry *ex) { return ((unsigned long)&ex->fixup + ex->fixup); } static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex, struct pt_regs *regs) { int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data); pt_regs_write_reg(regs, reg_err, -EFAULT); pt_regs_write_reg(regs, reg_zero, 0); regs->pc = get_ex_fixup(ex); return true; } static bool ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex, struct pt_regs *regs) { int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data); int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); unsigned long data, addr, offset; addr = pt_regs_read_reg(regs, reg_addr); offset = addr & 0x7UL; addr &= ~0x7UL; data = *(unsigned long*)addr; #ifndef __AARCH64EB__ data >>= 8 * offset; #else data <<= 8 * offset; #endif pt_regs_write_reg(regs, reg_data, data); regs->pc = get_ex_fixup(ex); return true; } bool fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *ex; ex = search_exception_tables(instruction_pointer(regs)); if (!ex) return false; switch (ex->type) { case EX_TYPE_BPF: return ex_handler_bpf(ex, regs); case EX_TYPE_UACCESS_ERR_ZERO: case EX_TYPE_KACCESS_ERR_ZERO: return ex_handler_uaccess_err_zero(ex, regs); case EX_TYPE_LOAD_UNALIGNED_ZEROPAD: return ex_handler_load_unaligned_zeropad(ex, regs); } BUG(); } |
| 97 97 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. * * Each bdi_writeback that is not embedded into the backing_dev_info must hold * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; /* * Jiffies when last process was dirty throttled on this bdi. Used by * blk-wbt. */ unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif }; struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put * @nr: number of references to put */ static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { wb_put_many(wb, 1); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 159 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 - Google LLC * Author: Quentin Perret <qperret@google.com> */ #include <linux/init.h> #include <linux/kmemleak.h> #include <linux/kvm_host.h> #include <linux/memblock.h> #include <linux/mutex.h> #include <linux/sort.h> #include <asm/kvm_pkvm.h> #include "hyp_constants.h" DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory); static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr); phys_addr_t hyp_mem_base; phys_addr_t hyp_mem_size; static int cmp_hyp_memblock(const void *p1, const void *p2) { const struct memblock_region *r1 = p1; const struct memblock_region *r2 = p2; return r1->base < r2->base ? -1 : (r1->base > r2->base); } static void __init sort_memblock_regions(void) { sort(hyp_memory, *hyp_memblock_nr_ptr, sizeof(struct memblock_region), cmp_hyp_memblock, NULL); } static int __init register_memblock_regions(void) { struct memblock_region *reg; for_each_mem_region(reg) { if (*hyp_memblock_nr_ptr >= HYP_MEMBLOCK_REGIONS) return -ENOMEM; hyp_memory[*hyp_memblock_nr_ptr] = *reg; (*hyp_memblock_nr_ptr)++; } sort_memblock_regions(); return 0; } void __init kvm_hyp_reserve(void) { u64 hyp_mem_pages = 0; int ret; if (!is_hyp_mode_available() || is_kernel_in_hyp_mode()) return; if (kvm_get_mode() != KVM_MODE_PROTECTED) return; ret = register_memblock_regions(); if (ret) { *hyp_memblock_nr_ptr = 0; kvm_err("Failed to register hyp memblocks: %d\n", ret); return; } hyp_mem_pages += hyp_s1_pgtable_pages(); hyp_mem_pages += host_s2_pgtable_pages(); hyp_mem_pages += hyp_vm_table_pages(); hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE); hyp_mem_pages += hyp_ffa_proxy_pages(); /* * Try to allocate a PMD-aligned region to reduce TLB pressure once * this is unmapped from the host stage-2, and fallback to PAGE_SIZE. */ hyp_mem_size = hyp_mem_pages << PAGE_SHIFT; hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE), PMD_SIZE); if (!hyp_mem_base) hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE); else hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE); if (!hyp_mem_base) { kvm_err("Failed to reserve hyp memory\n"); return; } kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); } static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) { if (host_kvm->arch.pkvm.handle) { WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, host_kvm->arch.pkvm.handle)); } host_kvm->arch.pkvm.handle = 0; free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); } /* * Allocates and donates memory for hypervisor VM structs at EL2. * * Allocates space for the VM state, which includes the hyp vm as well as * the hyp vcpus. * * Stores an opaque handler in the kvm struct for future reference. * * Return 0 on success, negative error code on failure. */ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) { size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz; struct kvm_vcpu *host_vcpu; pkvm_handle_t handle; void *pgd, *hyp_vm; unsigned long idx; int ret; if (host_kvm->created_vcpus < 1) return -EINVAL; pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.mmu.vtcr); /* * The PGD pages will be reclaimed using a hyp_memcache which implies * page granularity. So, use alloc_pages_exact() to get individual * refcounts. */ pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT); if (!pgd) return -ENOMEM; /* Allocate memory to donate to hyp for vm and vcpu pointers. */ hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE, size_mul(sizeof(void *), host_kvm->created_vcpus))); hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vm) { ret = -ENOMEM; goto free_pgd; } /* Donate the VM memory to hyp and let hyp initialize it. */ ret = kvm_call_hyp_nvhe(__pkvm_init_vm, host_kvm, hyp_vm, pgd); if (ret < 0) goto free_vm; handle = ret; host_kvm->arch.pkvm.handle = handle; /* Donate memory for the vcpus at hyp and initialize it. */ hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); kvm_for_each_vcpu(idx, host_vcpu, host_kvm) { void *hyp_vcpu; /* Indexing of the vcpus to be sequential starting at 0. */ if (WARN_ON(host_vcpu->vcpu_idx != idx)) { ret = -EINVAL; goto destroy_vm; } hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vcpu) { ret = -ENOMEM; goto destroy_vm; } ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu, hyp_vcpu); if (ret) { free_pages_exact(hyp_vcpu, hyp_vcpu_sz); goto destroy_vm; } } return 0; destroy_vm: __pkvm_destroy_hyp_vm(host_kvm); return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); free_pgd: free_pages_exact(pgd, pgd_sz); return ret; } int pkvm_create_hyp_vm(struct kvm *host_kvm) { int ret = 0; mutex_lock(&host_kvm->arch.config_lock); if (!host_kvm->arch.pkvm.handle) ret = __pkvm_create_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); return ret; } void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { mutex_lock(&host_kvm->arch.config_lock); __pkvm_destroy_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); } int pkvm_init_host_vm(struct kvm *host_kvm) { return 0; } static void __init _kvm_host_prot_finalize(void *arg) { int *err = arg; if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize))) WRITE_ONCE(*err, -EINVAL); } static int __init pkvm_drop_host_privileges(void) { int ret = 0; /* * Flip the static key upfront as that may no longer be possible * once the host stage 2 is installed. */ static_branch_enable(&kvm_protected_mode_initialized); on_each_cpu(_kvm_host_prot_finalize, &ret, 1); return ret; } static int __init finalize_pkvm(void) { int ret; if (!is_protected_kvm_enabled() || !is_kvm_arm_initialised()) return 0; /* * Exclude HYP sections from kmemleak so that they don't get peeked * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start); kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size); ret = pkvm_drop_host_privileges(); if (ret) pr_err("Failed to finalize Hyp protection: %d\n", ret); return ret; } device_initcall_sync(finalize_pkvm); |
| 141 141 141 141 141 141 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002 ARM Limited, All Rights Reserved. */ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/irq.h> #include <linux/irqchip/arm-gic.h> #include <linux/kernel.h> #include "irq-gic-common.h" static DEFINE_RAW_SPINLOCK(irq_controller_lock); void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { if (!quirks->compatible && !quirks->property) continue; if (quirks->compatible && !of_device_is_compatible(np, quirks->compatible)) continue; if (quirks->property && !of_property_read_bool(np, quirks->property)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", quirks->desc); } } void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { if (quirks->compatible || quirks->property) continue; if (quirks->iidr != (quirks->mask & iidr)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", quirks->desc); } } int gic_configure_irq(unsigned int irq, unsigned int type, void __iomem *base) { u32 confmask = 0x2 << ((irq % 16) * 2); u32 confoff = (irq / 16) * 4; u32 val, oldval; int ret = 0; unsigned long flags; /* * Read current configuration register, and insert the config * for "irq", depending on "type". */ raw_spin_lock_irqsave(&irq_controller_lock, flags); val = oldval = readl_relaxed(base + confoff); if (type & IRQ_TYPE_LEVEL_MASK) val &= ~confmask; else if (type & IRQ_TYPE_EDGE_BOTH) val |= confmask; /* If the current configuration is the same, then we are done */ if (val == oldval) { raw_spin_unlock_irqrestore(&irq_controller_lock, flags); return 0; } /* * Write back the new configuration, and possibly re-enable * the interrupt. If we fail to write a new configuration for * an SPI then WARN and return an error. If we fail to write the * configuration for a PPI this is most likely because the GIC * does not allow us to set the configuration or we are in a * non-secure mode, and hence it may not be catastrophic. */ writel_relaxed(val, base + confoff); if (readl_relaxed(base + confoff) != val) ret = -EINVAL; raw_spin_unlock_irqrestore(&irq_controller_lock, flags); return ret; } void gic_dist_config(void __iomem *base, int gic_irqs, u8 priority) { unsigned int i; /* * Set all global interrupts to be level triggered, active low. */ for (i = 32; i < gic_irqs; i += 16) writel_relaxed(GICD_INT_ACTLOW_LVLTRIG, base + GIC_DIST_CONFIG + i / 4); /* * Set priority on all global interrupts. */ for (i = 32; i < gic_irqs; i += 4) writel_relaxed(REPEAT_BYTE_U32(priority), base + GIC_DIST_PRI + i); /* * Deactivate and disable all SPIs. Leave the PPI and SGIs * alone as they are in the redistributor registers on GICv3. */ for (i = 32; i < gic_irqs; i += 32) { writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ACTIVE_CLEAR + i / 8); writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ENABLE_CLEAR + i / 8); } } void gic_cpu_config(void __iomem *base, int nr, u8 priority) { int i; /* * Deal with the banked PPI and SGI interrupts - disable all * private interrupts. Make sure everything is deactivated. */ for (i = 0; i < nr; i += 32) { writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ACTIVE_CLEAR + i / 8); writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ENABLE_CLEAR + i / 8); } /* * Set priority on PPI and SGI interrupts */ for (i = 0; i < nr; i += 4) writel_relaxed(REPEAT_BYTE_U32(priority), base + GIC_DIST_PRI + i * 4 / 4); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queue read/write lock * * These use generic atomic and locking routines, but depend on a fair spinlock * implementation in order to be fair themselves. The implementation in * asm-generic/spinlock.h meets these requirements. * * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. * * Authors: Waiman Long <waiman.long@hp.com> */ #ifndef __ASM_GENERIC_QRWLOCK_H #define __ASM_GENERIC_QRWLOCK_H #include <linux/atomic.h> #include <asm/barrier.h> #include <asm/processor.h> #include <asm-generic/qrwlock_types.h> /* Must be included from asm/spinlock.h after defining arch_spin_is_locked. */ /* * Writer states & reader shift and bias. */ #define _QW_WAITING 0x100 /* A writer is waiting */ #define _QW_LOCKED 0x0ff /* A writer holds the lock */ #define _QW_WMASK 0x1ff /* Writer mask */ #define _QR_SHIFT 9 /* Reader count shift */ #define _QR_BIAS (1U << _QR_SHIFT) /* * External function declarations */ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** * queued_read_trylock - try to acquire read lock of a queued rwlock * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) { int cnts; cnts = atomic_read(&lock->cnts); if (likely(!(cnts & _QW_WMASK))) { cnts = (u32)atomic_add_return_acquire(_QR_BIAS, &lock->cnts); if (likely(!(cnts & _QW_WMASK))) return 1; atomic_sub(_QR_BIAS, &lock->cnts); } return 0; } /** * queued_write_trylock - try to acquire write lock of a queued rwlock * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) { int cnts; cnts = atomic_read(&lock->cnts); if (unlikely(cnts)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)); } /** * queued_read_lock - acquire read lock of a queued rwlock * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { int cnts; cnts = atomic_add_return_acquire(_QR_BIAS, &lock->cnts); if (likely(!(cnts & _QW_WMASK))) return; /* The slowpath will decrement the reader count, if necessary. */ queued_read_lock_slowpath(lock); } /** * queued_write_lock - acquire write lock of a queued rwlock * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { int cnts = 0; /* Optimize for the unfair lock case where the fair flag is 0. */ if (likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED))) return; queued_write_lock_slowpath(lock); } /** * queued_read_unlock - release read lock of a queued rwlock * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { /* * Atomically decrement the reader count */ (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts); } /** * queued_write_unlock - release write lock of a queued rwlock * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { smp_store_release(&lock->wlocked, 0); } /** * queued_rwlock_is_contended - check if the lock is contended * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) { return arch_spin_is_locked(&lock->wait_lock); } /* * Remapping rwlock architecture specific functions to the corresponding * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) #define arch_read_trylock(l) queued_read_trylock(l) #define arch_write_trylock(l) queued_write_trylock(l) #define arch_read_unlock(l) queued_read_unlock(l) #define arch_write_unlock(l) queued_write_unlock(l) #define arch_rwlock_is_contended(l) queued_rwlock_is_contended(l) #endif /* __ASM_GENERIC_QRWLOCK_H */ |
| 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ARM64_ASM_SIGNAL_H #define __ARM64_ASM_SIGNAL_H #include <asm/memory.h> #include <uapi/asm/signal.h> #include <uapi/asm/siginfo.h> static inline void __user *arch_untagged_si_addr(void __user *addr, unsigned long sig, unsigned long si_code) { /* * For historical reasons, all bits of the fault address are exposed as * address bits for watchpoint exceptions. New architectures should * handle the tag bits consistently. */ if (sig == SIGTRAP && si_code == TRAP_BRKPT) return addr; return untagged_addr(addr); } #define arch_untagged_si_addr arch_untagged_si_addr #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996 * Rewritten again by Rusty Russell, 2002 */ #ifndef _LINUX_MODULE_H #define _LINUX_MODULE_H #include <linux/list.h> #include <linux/stat.h> #include <linux/buildid.h> #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> #include <linux/error-injection.h> #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> #include <linux/dynamic_debug.h> #include <linux/percpu.h> #include <asm/module.h> #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN struct modversion_info { unsigned long crc; char name[MODULE_NAME_LEN]; }; struct module; struct exception_table_entry; struct module_kobject { struct kobject kobj; struct module *mod; struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; } __randomize_layout; struct module_attribute { struct attribute attr; ssize_t (*show)(struct module_attribute *, struct module_kobject *, char *); ssize_t (*store)(struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); void (*free)(struct module *); }; struct module_version_attribute { struct module_attribute mattr; const char *module_name; const char *version; }; extern ssize_t __modver_version_show(struct module_attribute *, struct module_kobject *, char *); extern struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); extern void cleanup_module(void); #ifndef MODULE /** * module_init() - driver initialization entry point * @x: function to be run at kernel boot time or module insertion * * module_init() will either be called during do_initcalls() (if * builtin) or at module insertion time (if a module). There can only * be one per module. */ #define module_init(x) __initcall(x); /** * module_exit() - driver exit entry point * @x: function to be run when driver is removed * * module_exit() will wrap the driver clean-up code * with cleanup_module() when used with rmmod when * the driver is a module. If the driver is statically * compiled into the kernel, module_exit() has no effect. * There can only be one per module. */ #define module_exit(x) __exitcall(x); #else /* MODULE */ /* * In most cases loadable modules do not need custom * initcall levels. There are still some valid cases where * a driver may be needed early if built in, and does not * matter when built as a loadable module. Like bus * snooping debug drivers. */ #define early_initcall(fn) module_init(fn) #define core_initcall(fn) module_init(fn) #define core_initcall_sync(fn) module_init(fn) #define postcore_initcall(fn) module_init(fn) #define postcore_initcall_sync(fn) module_init(fn) #define arch_initcall(fn) module_init(fn) #define subsys_initcall(fn) module_init(fn) #define subsys_initcall_sync(fn) module_init(fn) #define fs_initcall(fn) module_init(fn) #define fs_initcall_sync(fn) module_init(fn) #define rootfs_initcall(fn) module_init(fn) #define device_initcall(fn) module_init(fn) #define device_initcall_sync(fn) module_init(fn) #define late_initcall(fn) module_init(fn) #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ int init_module(void) __copy(initfn) \ __attribute__((alias(#initfn))); \ ___ADDRESSABLE(init_module, __initdata); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ void cleanup_module(void) __copy(exitfn) \ __attribute__((alias(#exitfn))); \ ___ADDRESSABLE(cleanup_module, __exitdata); #endif /* This means "can be init if no module support, otherwise module load may call it." */ #ifdef CONFIG_MODULES #define __init_or_module #define __initdata_or_module #define __initconst_or_module #define __INIT_OR_MODULE .text #define __INITDATA_OR_MODULE .data #define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits #else #define __init_or_module __init #define __initdata_or_module __initdata #define __initconst_or_module __initconst #define __INIT_OR_MODULE __INIT #define __INITDATA_OR_MODULE __INITDATA #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) /* Soft module dependencies. See man modprobe.d for details. * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") */ #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* * Weak module dependencies. See man modprobe.d for details. * Example: MODULE_WEAKDEP("module-foo") */ #define MODULE_WEAKDEP(_weakdep) MODULE_INFO(weakdep, _weakdep) /* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ #ifdef MODULE #define MODULE_FILE #else #define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE); #endif /* * The following license idents are currently accepted as indicating free * software modules * * "GPL" [GNU Public License v2] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MIT/GPL" [GNU Public License v2 * or MIT license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] * * The following other idents are available * * "Proprietary" [Non free products] * * Both "GPL v2" and "GPL" (the latter also in dual licensed strings) are * merely stating that the module is licensed under the GPL v2, but are not * telling whether "GPL v2 only" or "GPL v2 or later". The reason why there * are two variants is a historic and failed attempt to convey more * information in the MODULE_LICENSE string. For module loading the * "only/or later" distinction is completely irrelevant and does neither * replace the proper license identifiers in the corresponding source file * nor amends them in any way. The sole purpose is to make the * 'Proprietary' flagging work and to refuse to bind symbols which are * exported with EXPORT_SYMBOL_GPL when a non free module is loaded. * * In the same way "BSD" is not a clear license information. It merely * states, that the module is licensed under one of the compatible BSD * license variants. The detailed and correct license information is again * to be found in the corresponding source files. * * There are dual licensed components, but when running with Linux it is the * GPL that is relevant so this is a non issue. Similarly LGPL linked with GPL * is a GPL combined work. * * This exists for several reasons * 1. So modinfo can show license info for users wanting to vet their setup * is free * 2. So the community can ignore bug reports including proprietary modules * 3. So vendors can do likewise based on their own policies */ #define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license) /* * Author(s), use "Name <email>" or just "Name", for multiple * authors use multiple MODULE_AUTHOR() statements/lines. */ #define MODULE_AUTHOR(_author) MODULE_INFO(author, _author) /* What your module does. */ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ extern typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) #endif /* Version of form [<epoch>:]<version>[-<extra-version>]. * Or for CVS/RCS ID version, everything but the number is stripped. * <epoch>: A (small) unsigned integer which allows you to start versions * anew. If not mentioned, it's zero. eg. "2:1.0" is after * "1:2.0". * <version>: The <version> may contain only alphanumerics and the * character `.'. Ordered by numeric sort for numeric parts, * ascii sort for ascii parts (as per RPM or DEB algorithm). * <extraversion>: Like <version>, but inserted for local * customizations, eg "rh3" or "rusty1". * Using this automatically adds a checksum of the .c files and the * local headers in "srcversion". */ #if defined(MODULE) || !defined(CONFIG_SYSFS) #define MODULE_VERSION(_version) MODULE_INFO(version, _version) #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ static struct module_version_attribute __modver_attr \ __used __section("__modver") \ __aligned(__alignof__(struct module_version_attribute)) \ = { \ .mattr = { \ .attr = { \ .name = "version", \ .mode = S_IRUGO, \ }, \ .show = __modver_version_show, \ }, \ .module_name = KBUILD_MODNAME, \ .version = _version, \ } #endif /* Optional firmware file (or files) needed by the module * format is simply firmware file name. Multiple firmware * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) #define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) struct notifier_block; #ifdef CONFIG_MODULES extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); #define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) /* modules using other modules: kdb wants to see this. */ struct module_use { struct list_head source_list; struct list_head target_list; struct module *source, *target; }; enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ MODULE_STATE_GOING, /* Going away. */ MODULE_STATE_UNFORMED, /* Still setting it up. */ }; struct mod_tree_node { struct module *mod; struct latch_tree_node node; }; enum mod_mem_type { MOD_TEXT = 0, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, MOD_MEM_NUM_TYPES, MOD_INVALID = -1, }; #define mod_mem_type_is_init(type) \ ((type) == MOD_INIT_TEXT || \ (type) == MOD_INIT_DATA || \ (type) == MOD_INIT_RODATA) #define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) #define mod_mem_type_is_text(type) \ ((type) == MOD_TEXT || \ (type) == MOD_INIT_TEXT) #define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) #define mod_mem_type_is_core_data(type) \ (mod_mem_type_is_core(type) && \ mod_mem_type_is_data(type)) #define for_each_mod_mem_type(type) \ for (enum mod_mem_type (type) = 0; \ (type) < MOD_MEM_NUM_TYPES; (type)++) #define for_class_mod_mem_type(type, class) \ for_each_mod_mem_type(type) \ if (mod_mem_type_is_##class(type)) struct module_memory { void *base; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; #endif }; #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ #define __module_memory_align ____cacheline_aligned #else #define __module_memory_align #endif struct mod_kallsyms { Elf_Sym *symtab; unsigned int num_symtab; char *strtab; char *typetab; }; #ifdef CONFIG_LIVEPATCH /** * struct klp_modinfo - ELF information preserved from the livepatch module * * @hdr: ELF header * @sechdrs: Section header table * @secstrings: String table for the section headers * @symndx: The symbol table section index */ struct klp_modinfo { Elf_Ehdr hdr; Elf_Shdr *sechdrs; char *secstrings; unsigned int symndx; }; #endif struct module { enum module_state state; /* Member of list of modules */ struct list_head list; /* Unique handle for this module */ char name[MODULE_NAME_LEN]; #ifdef CONFIG_STACKTRACE_BUILD_ID /* Module build ID */ unsigned char build_id[BUILD_ID_SIZE_MAX]; #endif /* Sysfs stuff. */ struct module_kobject mkobj; struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; struct kobject *holders_dir; /* Exported symbols */ const struct kernel_symbol *syms; const s32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS s32 *kcfi_traps; s32 *kcfi_traps_end; #endif /* Kernel parameters. */ #ifdef CONFIG_SYSFS struct mutex param_lock; #endif struct kernel_param *kp; unsigned int num_kp; /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; const s32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; #endif bool async_probe_requested; /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; /* Startup function. */ int (*init)(void); struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; unsigned long taints; /* same bits as kernel:taint_flags */ #ifdef CONFIG_GENERIC_BUG /* Support for BUG */ unsigned num_bugs; struct list_head bug_list; struct bug_entry *bug_table; #endif #ifdef CONFIG_KALLSYMS /* Protected by RCU and/or module_mutex: use rcu_dereference() */ struct mod_kallsyms __rcu *kallsyms; struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; /* Notes attributes */ struct module_notes_attrs *notes_attrs; #endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ char *args; #ifdef CONFIG_SMP /* Per-cpu data. */ void __percpu *percpu; unsigned int percpu_size; #endif void *noinstr_text_start; unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef CONFIG_TREE_SRCU unsigned int num_srcu_structs; struct srcu_struct **srcu_struct_ptrs; #endif #ifdef CONFIG_BPF_EVENTS unsigned int num_bpf_raw_events; struct bpf_raw_event_map *bpf_raw_events; #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES unsigned int btf_data_size; unsigned int btf_base_data_size; void *btf_data; void *btf_base_data; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; #endif #ifdef CONFIG_TRACING unsigned int num_trace_bprintk_fmt; const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_eval_map **trace_evals; unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE int num_static_call_sites; struct static_call_site *static_call_sites; #endif #if IS_ENABLED(CONFIG_KUNIT) int num_kunit_init_suites; struct kunit_suite **kunit_init_suites; int num_kunit_suites; struct kunit_suite **kunit_suites; #endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ bool klp_alive; /* ELF information */ struct klp_modinfo *klp_info; #endif #ifdef CONFIG_PRINTK_INDEX unsigned int printk_index_size; struct pi_entry **printk_index_start; #endif #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; /* What modules do I depend on? */ struct list_head target_list; /* Destruction function. */ void (*exit)(void); atomic_t refcnt; #endif #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; unsigned int num_ctors; #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif #ifdef CONFIG_DYNAMIC_DEBUG_CORE struct _ddebug_info dyndbg_info; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) { return sym->st_value; } #endif /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ static inline bool module_is_live(struct module *mod) { return mod->state != MODULE_STATE_GOING; } static inline bool module_is_coming(struct module *mod) { return mod->state == MODULE_STATE_COMING; } struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline bool within_module_mem_type(unsigned long addr, const struct module *mod, enum mod_mem_type type) { unsigned long base, size; base = (unsigned long)mod->mem[type].base; size = mod->mem[type].size; return addr - base < size; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, core) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, init) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return within_module_init(addr, mod) || within_module_core(addr, mod); } /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(__stringify(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); /** * try_module_get() - take module refcount unless module is being removed * @module: the module we should check for * * Only try to get a module reference count if the module is not being removed. * This call will fail if the module is in the process of being removed. * * Care must also be taken to ensure the module exists and is alive prior to * usage of this call. This can be gauranteed through two means: * * 1) Direct protection: you know an earlier caller must have increased the * module reference through __module_get(). This can typically be achieved * by having another entity other than the module itself increment the * module reference count. * * 2) Implied protection: there is an implied protection against module * removal. An example of this is the implied protection used by kernfs / * sysfs. The sysfs store / read file operations are guaranteed to exist * through the use of kernfs's active reference (see kernfs_active()) and a * sysfs / kernfs file removal cannot happen unless the same file is not * active. Therefore, if a sysfs file is being read or written to the module * which created it must still exist. It is therefore safe to use * try_module_get() on module sysfs store / read ops. * * One of the real values to try_module_get() is the module_is_live() check * which ensures that the caller of try_module_get() can yield to userspace * module removal requests and gracefully fail if the module is on its way out. * * Returns true if the reference count was successfully incremented. */ extern bool try_module_get(struct module *module); /** * module_put() - release a reference count to a module * @module: the module we should release a reference count for * * If you successfully bump a reference count to a module with try_module_get(), * when you are finished you must call module_put() to release that reference * count. */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ static inline bool try_module_get(struct module *module) { return !module || module_is_live(module); } static inline void module_put(struct module *module) { } static inline void __module_get(struct module *module) { } #define symbol_put(x) do { } while (0) #define symbol_put_addr(p) do { } while (0) #endif /* CONFIG_MODULE_UNLOAD */ /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ ({ \ struct module *__mod = (mod); \ __mod ? __mod->name : "kernel"; \ }) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); static inline bool module_requested_async_probing(struct module *module) { return module && module->async_probe_requested; } static inline bool is_livepatch_module(struct module *mod) { #ifdef CONFIG_LIVEPATCH return mod->klp; #else return false; #endif } void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) { return NULL; } static inline struct module *__module_text_address(unsigned long addr) { return NULL; } static inline bool is_module_address(unsigned long addr) { return false; } static inline bool is_module_percpu_address(unsigned long addr) { return false; } static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { return false; } static inline bool is_module_text_address(unsigned long addr) { return false; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return false; } /* Get/put a kernel symbol (calls should be symmetric) */ #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) static inline void __module_get(struct module *module) { } static inline bool try_module_get(struct module *module) { return true; } static inline void module_put(struct module *module) { } #define module_name(mod) "kernel" static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ return 0; } static inline int unregister_module_notifier(struct notifier_block *nb) { return 0; } #define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { } static inline bool module_requested_async_probing(struct module *module) { return false; } static inline void set_module_sig_enforced(void) { } /* Dereference module function descriptor */ static inline void *dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } static inline bool module_is_coming(struct module *mod) { return false; } #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS extern struct kset *module_kset; extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) /* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */ #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_MITIGATION_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) { return true; } #endif #ifdef CONFIG_MODULE_SIG bool is_module_sig_enforced(void); static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ static inline bool is_module_sig_enforced(void) { return false; } static inline bool module_sig_ok(struct module *module) { return true; } #endif /* CONFIG_MODULE_SIG */ #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data); /* For kallsyms to ask for address resolution. namebuf should be at * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if * symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported); /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); #else /* CONFIG_MODULES && CONFIG_KALLSYMS */ static inline int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; } /* For kallsyms to ask for address resolution. NULL means not found. */ static inline int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { return 0; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { return -ERANGE; } static inline unsigned long module_kallsyms_lookup_name(const char *name) { return 0; } static inline unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) { return 0; } #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ |
| 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMER_H #define _LINUX_TIMER_H #include <linux/list.h> #include <linux/ktime.h> #include <linux/stddef.h> #include <linux/debugobjects.h> #include <linux/stringify.h> #include <linux/timer_types.h> #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting the lockdep_map key * (second argument) here is required, otherwise it could be initialised to * the copy of the lockdep_map later! We use the pointer to and the string * "<file>:<line>" as the key resp. the name of the lockdep_map. */ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(_kn, &_kn), #else #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif /* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU * eventually wakes up with a subsequent non-deferrable timer. * * @TIMER_IRQSAFE: An irqsafe timer is executed with IRQ disabled and * it's safe to wait for the completion of the running instance from * IRQ handlers, for example, by calling del_timer_sync(). * * Note: The irq disabled callback execution is a special case for * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! * * @TIMER_PINNED: A pinned timer will always expire on the CPU on which the * timer was enqueued. When a particular CPU is required, add_timer_on() * has to be used. Enqueue via mod_timer() and add_timer() is always done * on the local CPU. */ #define TIMER_CPUMASK 0x0003FFFF #define TIMER_MIGRATING 0x00040000 #define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) #define TIMER_DEFERRABLE 0x00080000 #define TIMER_PINNED 0x00100000 #define TIMER_IRQSAFE 0x00200000 #define TIMER_INIT_FLAGS (TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) #define TIMER_ARRAYSHIFT 22 #define TIMER_ARRAYMASK 0xFFC00000 #define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) #define __TIMER_INITIALIZER(_function, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ .flags = (_flags), \ __TIMER_LOCKDEP_MAP_INITIALIZER(FILE_LINE) \ } #define DEFINE_TIMER(_name, _function) \ struct timer_list _name = \ __TIMER_INITIALIZER(_function, 0) /* * LOCKDEP and DEBUG timer interfaces. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); #else static inline void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { init_timer_key(timer, func, flags, name, key); } #endif #ifdef CONFIG_LOCKDEP #define __init_timer(_timer, _fn, _flags) \ do { \ static struct lock_class_key __key; \ init_timer_key((_timer), (_fn), (_flags), #_timer, &__key);\ } while (0) #define __init_timer_on_stack(_timer, _fn, _flags) \ do { \ static struct lock_class_key __key; \ init_timer_on_stack_key((_timer), (_fn), (_flags), \ #_timer, &__key); \ } while (0) #else #define __init_timer(_timer, _fn, _flags) \ init_timer_key((_timer), (_fn), (_flags), NULL, NULL) #define __init_timer_on_stack(_timer, _fn, _flags) \ init_timer_on_stack_key((_timer), (_fn), (_flags), NULL, NULL) #endif /** * timer_setup - prepare a timer for first use * @timer: the timer in question * @callback: the function to call when timer expires * @flags: any TIMER_* flags * * Regular timer initialization should use either DEFINE_TIMER() above, * or timer_setup(). For timers on the stack, timer_setup_on_stack() must * be used and must be balanced with a call to destroy_timer_on_stack(). */ #define timer_setup(timer, callback, flags) \ __init_timer((timer), (callback), (flags)) #define timer_setup_on_stack(timer, callback, flags) \ __init_timer_on_stack((timer), (callback), (flags)) #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_timer_on_stack(struct timer_list *timer); #else static inline void destroy_timer_on_stack(struct timer_list *timer) { } #endif #define from_timer(var, callback_timer, timer_fieldname) \ container_of(callback_timer, typeof(*var), timer_fieldname) /** * timer_pending - is a timer pending? * @timer: the timer in question * * timer_pending will tell whether a given timer is currently pending, * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { return !hlist_unhashed_lockless(&timer->entry); } extern void add_timer_on(struct timer_list *timer, int cpu); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); extern int timer_reduce(struct timer_list *timer, unsigned long expires); /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: */ #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) extern void add_timer(struct timer_list *timer); extern void add_timer_local(struct timer_list *timer); extern void add_timer_global(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); extern int timer_delete_sync(struct timer_list *timer); extern int timer_delete(struct timer_list *timer); extern int timer_shutdown_sync(struct timer_list *timer); extern int timer_shutdown(struct timer_list *timer); /** * del_timer_sync - Delete a pending timer and wait for a running callback * @timer: The timer to be deleted * * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. * * Returns: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { return timer_delete_sync(timer); } /** * del_timer - Delete a pending timer * @timer: The timer to be deleted * * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. * * Returns: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { return timer_delete(timer); } extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); unsigned long round_jiffies_relative(unsigned long j); unsigned long __round_jiffies_up(unsigned long j, int cpu); unsigned long __round_jiffies_up_relative(unsigned long j, int cpu); unsigned long round_jiffies_up(unsigned long j); unsigned long round_jiffies_up_relative(unsigned long j); #ifdef CONFIG_HOTPLUG_CPU int timers_prepare_cpu(unsigned int cpu); int timers_dead_cpu(unsigned int cpu); #else #define timers_prepare_cpu NULL #define timers_dead_cpu NULL #endif #endif |
| 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 | // SPDX-License-Identifier: GPL-2.0-or-later /* auditfilter.c -- filtering of audit events * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. * Copyright 2005 IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <net/net_namespace.h> #include <net/sock.h> #include "audit.h" /* * Locking model: * * audit_filter_mutex: * Synchronizes writes and blocking reads of audit's filterlist * data. Rcu is used to traverse the filterlist and access * contents of structs audit_entry, audit_watch and opaque * LSM rules during filtering. If modified, these structures * must be copied and replace their counterparts in the filterlist. * An audit_parent struct is not accessed during filtering, so may * be written directly provided audit_filter_mutex is held. */ /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), LIST_HEAD_INIT(audit_filter_list[1]), LIST_HEAD_INIT(audit_filter_list[2]), LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), LIST_HEAD_INIT(audit_filter_list[7]), #if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[0]), LIST_HEAD_INIT(audit_rules_list[1]), LIST_HEAD_INIT(audit_rules_list[2]), LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); static void audit_free_lsm_field(struct audit_field *f) { switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: kfree(f->lsm_str); security_audit_rule_free(f->lsm_rule); } } static inline void audit_free_rule(struct audit_entry *e) { int i; struct audit_krule *erule = &e->rule; /* some rules don't have associated watches */ if (erule->watch) audit_put_watch(erule->watch); if (erule->fields) for (i = 0; i < erule->field_count; i++) audit_free_lsm_field(&erule->fields[i]); kfree(erule->fields); kfree(erule->filterkey); kfree(e); } void audit_free_rule_rcu(struct rcu_head *head) { struct audit_entry *e = container_of(head, struct audit_entry, rcu); audit_free_rule(e); } /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { struct audit_entry *entry; struct audit_field *fields; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (unlikely(!entry)) return NULL; fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); if (unlikely(!fields)) { kfree(entry); return NULL; } entry->rule.fields = fields; return entry; } /* Unpack a filter field's string representation from user-space * buffer. */ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) { char *str; if (!*bufp || (len == 0) || (len > *remain)) return ERR_PTR(-EINVAL); /* Of the currently implemented string fields, PATH_MAX * defines the longest valid length. */ if (len > PATH_MAX) return ERR_PTR(-ENAMETOOLONG); str = kmalloc(len + 1, GFP_KERNEL); if (unlikely(!str)) return ERR_PTR(-ENOMEM); memcpy(str, *bufp, len); str[len] = 0; *bufp += len; *remain -= len; return str; } /* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if ((krule->listnr != AUDIT_FILTER_EXIT && krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; return 0; } static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { unsigned n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; } p[AUDIT_WORD(n)] |= AUDIT_BIT(n); } if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { kfree(p); return -EINVAL; } classes[class] = p; return 0; } int audit_match_class(int class, unsigned syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) return 0; return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); } #ifdef CONFIG_AUDITSYSCALL static inline int audit_match_class_bits(int class, u32 *mask) { int i; if (classes[class]) { for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (mask[i] & classes[class][i]) return 0; } return 1; } static int audit_match_signal(struct audit_entry *entry) { struct audit_field *arch = entry->rule.arch_f; if (!arch) { /* When arch is unspecified, we must check both masks on biarch * as syscall number alone is ambiguous. */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask) && audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); } switch (audit_classify_arch(arch->val)) { case 0: /* native */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask)); case 1: /* 32bit on biarch */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); default: return 1; } } #endif /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; int i, err; err = -EINVAL; listnr = rule->flags & ~AUDIT_FILTER_PREPEND; switch (listnr) { default: goto exit_err; #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) goto exit_err; if (rule->field_count > AUDIT_MAX_FIELDS) goto exit_err; err = -ENOMEM; entry = audit_init_entry(rule->field_count); if (!entry) goto exit_err; entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; entry->rule.listnr = listnr; entry->rule.action = rule->action; entry->rule.field_count = rule->field_count; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; __u32 *class; if (!(*p & AUDIT_BIT(bit))) continue; *p &= ~AUDIT_BIT(bit); class = classes[i]; if (class) { int j; for (j = 0; j < AUDIT_BITMASK_SIZE; j++) entry->rule.mask[j] |= class[j]; } } return entry; exit_err: return ERR_PTR(err); } static u32 audit_ops[] = { [Audit_equal] = AUDIT_EQUAL, [Audit_not_equal] = AUDIT_NOT_EQUAL, [Audit_bitmask] = AUDIT_BIT_MASK, [Audit_bittest] = AUDIT_BIT_TEST, [Audit_lt] = AUDIT_LESS_THAN, [Audit_gt] = AUDIT_GREATER_THAN, [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, }; static u32 audit_to_op(u32 op) { u32 n; for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) ; return n; } /* check if an audit field is valid */ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch (f->type) { case AUDIT_MSGTYPE: if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; case AUDIT_FSTYPE: if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; case AUDIT_PERM: if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) return -EINVAL; break; } switch (entry->rule.listnr) { case AUDIT_FILTER_FS: switch (f->type) { case AUDIT_FSTYPE: case AUDIT_FILTERKEY: break; default: return -EINVAL; } } /* Check for valid field type and op */ switch (f->type) { case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: case AUDIT_PERS: /* <uapi/linux/personality.h> */ case AUDIT_DEVMINOR: /* all ops are valid */ break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: case AUDIT_PID: case AUDIT_MSGTYPE: case AUDIT_PPID: case AUDIT_DEVMAJOR: case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: case AUDIT_SESSIONID: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: case AUDIT_SADDR_FAM: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_WATCH: case AUDIT_DIR: case AUDIT_FILTERKEY: case AUDIT_LOGINUID_SET: case AUDIT_ARCH: case AUDIT_FSTYPE: case AUDIT_PERM: case AUDIT_FILETYPE: case AUDIT_FIELD_COMPARE: case AUDIT_EXE: /* only equal and not equal valid ops */ if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; default: /* field not recognized */ return -EINVAL; } /* Check for select valid field values */ switch (f->type) { case AUDIT_LOGINUID_SET: if ((f->val != 0) && (f->val != 1)) return -EINVAL; break; case AUDIT_PERM: if (f->val & ~15) return -EINVAL; break; case AUDIT_FILETYPE: if (f->val & ~S_IFMT) return -EINVAL; break; case AUDIT_FIELD_COMPARE: if (f->val > AUDIT_MAX_FIELD_COMPARE) return -EINVAL; break; case AUDIT_SADDR_FAM: if (f->val >= AF_MAX) return -EINVAL; break; default: break; } return 0; } /* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { int err = 0; struct audit_entry *entry; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; char *str; struct audit_fsnotify_mark *audit_mark; entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; u32 f_val; err = -EINVAL; f->op = audit_to_op(data->fieldflags[i]); if (f->op == Audit_bad) goto exit_free; f->type = data->fields[i]; f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); if (err) goto exit_free; err = -EINVAL; switch (f->type) { case AUDIT_LOGINUID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; } else if (err) goto exit_free; break; case AUDIT_WATCH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } entry->rule.buflen += f_val; break; case AUDIT_DIR: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; entry->rule.buflen += f_val; break; case AUDIT_INODE: f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; default: f->val = f_val; break; } } if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) entry->rule.inode_f = NULL; exit_nofree: return entry; exit_free: if (entry->rule.tree) audit_put_tree(entry->rule.tree); /* that's the temporary one */ if (entry->rule.exe) audit_remove_mark(entry->rule.exe); /* that's the template one */ audit_free_rule(entry); return ERR_PTR(err); } /* Pack a filter field's string representation into data block. */ static inline size_t audit_pack_string(void **bufp, const char *str) { size_t len = strlen(str); memcpy(*bufp, str, len); *bufp += len; return len; } /* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; void *bufp; int i; data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL); if (unlikely(!data)) return NULL; memset(data, 0, sizeof(*data)); data->flags = krule->flags | krule->listnr; data->action = krule->action; data->field_count = krule->field_count; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; data->fieldflags[i] = audit_ops[f->op]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->lsm_str); break; case AUDIT_WATCH: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_tree_path(krule->tree)); break; case AUDIT_FILTERKEY: data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; case AUDIT_EXE: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; data->values[i] = AUDIT_UID_UNSET; break; } fallthrough; /* if set */ default: data->values[i] = f->val; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; return data; } /* Compare two rules in kernel format. Considered success if rules * don't match. */ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) { int i; if (a->flags != b->flags || a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) return 1; for (i = 0; i < a->field_count; i++) { if (a->fields[i].type != b->fields[i].type || a->fields[i].op != b->fields[i].op) return 1; switch (a->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) return 1; break; case AUDIT_WATCH: if (strcmp(audit_watch_path(a->watch), audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: if (strcmp(audit_tree_path(a->tree), audit_tree_path(b->tree))) return 1; break; case AUDIT_FILTERKEY: /* both filterkeys exist based on above type compare */ if (strcmp(a->filterkey, b->filterkey)) return 1; break; case AUDIT_EXE: /* both paths exist based on above type compare */ if (strcmp(audit_mark_path(a->exe), audit_mark_path(b->exe))) return 1; break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) return 1; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; default: if (a->fields[i].val != b->fields[i].val) return 1; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (a->mask[i] != b->mask[i]) return 1; return 0; } /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { int ret; char *lsm_str; /* our own copy of lsm_str */ lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); if (unlikely(!lsm_str)) return -ENOMEM; df->lsm_str = lsm_str; /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", df->lsm_str); ret = 0; } return ret; } /* Duplicate an audit rule. This will be a deep copy with the exception * of the watch - that pointer is carried over. The LSM specific fields * will be updated in the copy. The point is to be able to replace the old * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ struct audit_entry *audit_dupe_rule(struct audit_krule *old) { u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; char *fk; int i, err = 0; entry = audit_init_entry(fcount); if (unlikely(!entry)) return ERR_PTR(-ENOMEM); new = &entry->rule; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->field_count = old->field_count; /* * note that we are OK with not refcounting here; audit_match_tree() * never dereferences tree and we can't get false positives there * since we'd have to have rule gone from the list *and* removed * before the chunks found by lookup had been allocated, i.e. before * the beginning of list scan. */ new->tree = old->tree; memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); /* deep copy this information, updating the lsm_rule fields, because * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_lsm_field(&new->fields[i], &old->fields[i]); break; case AUDIT_FILTERKEY: fk = kstrdup(old->filterkey, GFP_KERNEL); if (unlikely(!fk)) err = -ENOMEM; else new->filterkey = fk; break; case AUDIT_EXE: err = audit_dupe_exe(new, old); break; } if (err) { if (new->exe) audit_remove_mark(new->exe); audit_free_rule(entry); return ERR_PTR(err); } } if (old->watch) { audit_get_watch(old->watch); new->watch = old->watch; } return entry; } /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, struct list_head **p) { struct audit_entry *e, *found = NULL; struct list_head *list; int h; if (entry->rule.inode_f) { h = audit_hash_ino(entry->rule.inode_f->val); *p = list = &audit_inode_hash[h]; } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } } goto out; } else { *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } out: return found; } static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; /* Add rule to given filterlist if not a duplicate. */ static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int err = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (e) { mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) audit_put_tree(tree); return err; } if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); /* * normally audit_add_tree_rule() will free it * on failure */ if (tree) audit_put_tree(tree); return err; } } if (tree) { err = audit_add_tree_rule(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); return err; } } entry->rule.prio = ~0ULL; if (entry->rule.listnr == AUDIT_FILTER_EXIT || entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else entry->rule.prio = --prio_low; } if (entry->rule.flags & AUDIT_FILTER_PREPEND) { list_add(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { list_add_tail(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules++; if (!audit_match_signal(entry)) audit_signals++; #endif mutex_unlock(&audit_filter_mutex); return err; } /* Remove an existing rule from filterlist. */ int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (!e) { ret = -ENOENT; goto out; } if (e->rule.watch) audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); if (e->rule.exe) audit_remove_mark_rule(&e->rule); #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules--; if (!audit_match_signal(entry)) audit_signals--; #endif list_del_rcu(&e->list); list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: mutex_unlock(&audit_filter_mutex); if (tree) audit_put_tree(tree); /* that's the temporary one */ return ret; } /* List rules using struct audit_rule_data. */ static void audit_list_rules(int seq, struct sk_buff_head *q) { struct sk_buff *skb; struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1, data, struct_size(data, buf, data->buflen)); if (skb) skb_queue_tail(q, skb); kfree(data); } } skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); if (skb) skb_queue_tail(q, skb); } /* Log rule additions and removals */ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } /** * audit_rule_change - apply all rules to the specified message type * @type: audit message type * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data */ int audit_rule_change(int type, int seq, void *data, size_t datasz) { int err = 0; struct audit_entry *entry; switch (type) { case AUDIT_ADD_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: WARN_ON(1); return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); } return err; } /** * audit_list_rules_send - list the audit rules * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { struct task_struct *tsk; struct audit_netlink_list *dest; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for * auditctl to read from it... which isn't ever going to * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); put_net(dest->net); kfree(dest); return PTR_ERR(tsk); } return 0; } int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { case Audit_equal: return (left == right); case Audit_not_equal: return (left != right); case Audit_lt: return (left < right); case Audit_le: return (left <= right); case Audit_gt: return (left > right); case Audit_ge: return (left >= right); case Audit_bitmask: return (left & right); case Audit_bittest: return ((left & right) == right); default: return 0; } } int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { case Audit_equal: return uid_eq(left, right); case Audit_not_equal: return !uid_eq(left, right); case Audit_lt: return uid_lt(left, right); case Audit_le: return uid_lte(left, right); case Audit_gt: return uid_gt(left, right); case Audit_ge: return uid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) { switch (op) { case Audit_equal: return gid_eq(left, right); case Audit_not_equal: return !gid_eq(left, right); case Audit_lt: return gid_lt(left, right); case Audit_le: return gid_lte(left, right); case Audit_gt: return gid_gt(left, right); case Audit_ge: return gid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } /** * parent_len - find the length of the parent portion of a pathname * @path: pathname of which to determine length */ int parent_len(const char *path) { int plen; const char *p; plen = strlen(path); if (plen == 0) return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; /* walk backward until we find the next slash or hit beginning */ while ((*p != '/') && (p > path)) p--; /* did we find a slash? Then increment to include it in path */ if (*p == '/') p++; return p - path; } /** * audit_compare_dname_path - compare given dentry name with last component in * given path. Return of 0 indicates a match. * @dname: dentry name that we're comparing * @path: full pathname that we're comparing * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; if (pathlen - parentlen != dlen) return 1; p = path + parentlen; return strncmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) { struct audit_entry *e; int ret = 1; /* Audit by default */ rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; pid_t pid; u32 sid; switch (f->type) { case AUDIT_PID: pid = task_pid_nr(current); result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: result = audit_uid_comparator(audit_get_loginuid(current), f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { security_current_getsecid_subj(&sid); result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: result = audit_exe_compare(current, e->rule.exe); if (f->op == Audit_not_equal) result = !result; break; default: goto unlock_and_return; } if (result < 0) /* error */ goto unlock_and_return; if (!result) break; } if (result > 0) { if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } } unlock_and_return: rcu_read_unlock(); return ret; } static int update_lsm_rule(struct audit_krule *r) { struct audit_entry *entry = container_of(r, struct audit_entry, rule); struct audit_entry *nentry; int err = 0; if (!security_audit_rule_known(r)) return 0; nentry = audit_dupe_rule(r); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { /* save the first error encountered for the * return value */ err = PTR_ERR(nentry); audit_panic("error updating LSM filters"); if (r->watch) list_del(&r->rlist); list_del_rcu(&entry->list); list_del(&r->list); } else { if (r->watch || r->tree) list_replace_init(&r->rlist, &nentry->rule.rlist); list_replace_rcu(&entry->list, &nentry->list); list_replace(&r->list, &nentry->rule.list); } call_rcu(&entry->rcu, audit_free_rule_rcu); return err; } /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the * LSM field is re-initialized, and the old rule is replaced with the * updated rule. */ int audit_update_lsm_rules(void) { struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { int res = update_lsm_rule(r); if (!err) err = res; } } mutex_unlock(&audit_filter_mutex); return err; } |
| 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL static struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void __init dnotify_sysctl_init(void) { register_sysctl_init("fs", dnotify_sysctls); } #else #define dnotify_sysctl_init() do { } while (0) #endif static struct kmem_cache *dnotify_struct_cache __ro_after_init; static struct kmem_cache *dnotify_mark_cache __ro_after_init; static struct fsnotify_group *dnotify_group __ro_after_init; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = &dn->dn_filp->f_owner; send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned int arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } rcu_read_lock(); f = lookup_fdget_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); if (f) fput(f); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); return 0; } module_init(dnotify_init) |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 206 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * A 'generic' spinlock implementation that is based on MCS locks. For an * architecture that's looking for a 'generic' spinlock, please first consider * ticket-lock.h and only come looking here when you've considered all the * constraints below and can show your hardware does actually perform better * with qspinlock. * * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no * weaker than RCtso if you're power), where regular code only expects atomic_t * to be RCpc. * * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set * of atomic operations to behave well together, please audit them carefully to * ensure they all have forward progress. Many atomic operations may default to * cmpxchg() loops which will not have good forward progress properties on * LL/SC architectures. * * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) * do. Carefully read the patches that introduced * queued_fetch_set_pending_acquire(). * * qspinlock also heavily relies on mixed size atomic operations, in specific * it requires architectures to have xchg16; something which many LL/SC * architectures need to implement as a 32bit and+or in order to satisfy the * forward progress guarantees mentioned above. * * Further reading on mixed size atomics that might be relevant: * * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { int val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { int val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) 2018 - Arm Ltd */ #ifndef __ARM64_KVM_RAS_H__ #define __ARM64_KVM_RAS_H__ #include <linux/acpi.h> #include <linux/errno.h> #include <linux/types.h> #include <asm/acpi.h> /* * Was this synchronous external abort a RAS notification? * Returns '0' for errors handled by some RAS subsystem, or -ENOENT. */ static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr) { /* apei_claim_sea(NULL) expects to mask interrupts itself */ lockdep_assert_irqs_enabled(); return apei_claim_sea(NULL); } #endif /* __ARM64_KVM_RAS_H__ */ |
| 374 374 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 | /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; ino_t ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf; /* Size of read buffer. */ size_t readbuf_size; /* Buffer for writing. */ char *write_buf; /* Size of write buffer. */ size_t writebuf_size; /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** Function prototypes. **********/ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H #include <linux/bpf.h> #include <linux/bpf-cgroup-defs.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/percpu.h> #include <linux/rbtree.h> #include <net/sock.h> #include <uapi/linux/bpf.h> struct sock; struct sockaddr; struct cgroup; struct sk_buff; struct bpf_map; struct bpf_prog; struct bpf_sock_ops_kern; struct bpf_cgroup_storage; struct ctl_table; struct ctl_table_header; struct task_struct; unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, const struct bpf_insn *insn); unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, const struct bpf_insn *insn); unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, const struct bpf_insn *insn); #ifdef CONFIG_CGROUP_BPF #define CGROUP_ATYPE(type) \ case BPF_##type: return type static inline enum cgroup_bpf_attach_type to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) { switch (attach_type) { CGROUP_ATYPE(CGROUP_INET_INGRESS); CGROUP_ATYPE(CGROUP_INET_EGRESS); CGROUP_ATYPE(CGROUP_INET_SOCK_CREATE); CGROUP_ATYPE(CGROUP_SOCK_OPS); CGROUP_ATYPE(CGROUP_DEVICE); CGROUP_ATYPE(CGROUP_INET4_BIND); CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; } } #undef CGROUP_ATYPE extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype]) #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) struct bpf_cgroup_storage_map; struct bpf_storage_buffer { struct rcu_head rcu; char data[]; }; struct bpf_cgroup_storage { union { struct bpf_storage_buffer *buf; void __percpu *percpu_buf; }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list_map; struct list_head list_cg; struct rb_node node; struct rcu_head rcu; }; struct bpf_cgroup_link { struct bpf_link link; struct cgroup *cgroup; enum bpf_attach_type type; }; struct bpf_prog_list { struct hlist_node node; struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, int *optname, sockptr_t optval, int *optlen, char **kernel_optval); int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen, int max_optlen, int retval); int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, int optname, void *optval, int *optlen, int retval); static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return BPF_CGROUP_STORAGE_PERCPU; return BPF_CGROUP_STORAGE_SHARED; } struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked); struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); /* Opportunistic check to see whether we have any BPF program attached*/ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, enum cgroup_bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_prog_array *array; array = rcu_access_pointer(cgrp->bpf.effective[type]); return array != &bpf_empty_prog_array.hdr; } /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS) && sk && \ sk_fullsock(sk)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) && \ cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_SK_PROG(sk, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ __ret = __cgroup_bpf_run_filter_sk(sk, atype); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_CREATE) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_RELEASE) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET4_POST_BIND) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, NULL, NULL); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ }) /* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags * via upper bits of return code. The only flag that is supported * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ #define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ } \ __ret; \ }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(CGROUP_INET4_CONNECT) || \ cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). * * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. * Its listener-sk is not attached to the rsk_listener. * In this case, the caller holds the listener-sk (unlocked), * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with * the listener-sk such that the cgroup-bpf-progs of the * listener-sk will be run. * * Regardless of syncookie mode or not, * calling bpf_setsockopt on listener-sk will not make sense anyway, * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. */ #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ CGROUP_SOCK_OPS); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ CGROUP_SOCK_OPS); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_DEVICE)) \ __ret = __cgroup_bpf_check_dev_permission(atype, major, minor, \ access, \ CGROUP_DEVICE); \ \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ CGROUP_SYSCTL); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ kernel_optval); \ __ret; \ }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ copy_from_sockptr(&__ret, optlen, sizeof(int)); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ int __ret = retval; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ level, optname)) \ __ret = __cgroup_bpf_run_filter_getsockopt( \ sock, level, optname, optval, optlen, \ max_optlen, retval); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ optlen, retval) \ ({ \ int __ret = retval; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ }) int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { return -EINVAL; } static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EINVAL; } static inline int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value) { return 0; } static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags) { return 0; } #define cgroup_bpf_enabled(atype) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __KVM_ARM_PSCI_H__ #define __KVM_ARM_PSCI_H__ #include <linux/kvm_host.h> #include <uapi/linux/psci.h> #define KVM_ARM_PSCI_0_1 PSCI_VERSION(0, 1) #define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2) #define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0) #define KVM_ARM_PSCI_1_1 PSCI_VERSION(1, 1) #define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_1 static inline int kvm_psci_version(struct kvm_vcpu *vcpu) { /* * Our PSCI implementation stays the same across versions from * v0.2 onward, only adding the few mandatory functions (such * as FEATURES with 1.0) that are required by newer * revisions. It is thus safe to return the latest, unless * userspace has instructed us otherwise. */ if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2)) { if (vcpu->kvm->arch.psci_version) return vcpu->kvm->arch.psci_version; return KVM_ARM_PSCI_LATEST; } return KVM_ARM_PSCI_0_1; } int kvm_psci_call(struct kvm_vcpu *vcpu); #endif /* __KVM_ARM_PSCI_H__ */ |
| 252 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 292 291 292 292 292 292 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Procedures for maintaining information about logical memory blocks. * * Peter Bergner, IBM Corp. June 2001. * Copyright (C) 2001 Peter Bergner. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/poison.h> #include <linux/pfn.h> #include <linux/debugfs.h> #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 #ifndef INIT_MEMBLOCK_RESERVED_REGIONS # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif #ifndef INIT_MEMBLOCK_MEMORY_REGIONS #define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS #endif /** * DOC: memblock overview * * Memblock is a method of managing memory regions during the early * boot period when the usual kernel memory allocators are not up and * running. * * Memblock views the system memory as collections of contiguous * regions. There are several types of these collections: * * * ``memory`` - describes the physical memory available to the * kernel; this may differ from the actual physical memory installed * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated * * ``physmem`` - describes the actual physical memory available during * boot regardless of the possible restrictions and memory hot(un)plug; * the ``physmem`` type is only available on some architectures. * * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA * systems. Every memory type is described by the struct memblock_type * which contains an array of memory regions along with * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not * overlap with areas that should be reserved, for example initrd. * * The early architecture setup should tell memblock what the physical * memory layout is by using memblock_add() or memblock_add_node() * functions. The first function does not assign the region to a NUMA * node and it is appropriate for UMA systems. Yet, it is possible to * use it on NUMA systems as well and assign the region to a NUMA node * later in the setup process using memblock_set_node(). The * memblock_add_node() performs such an assignment directly. * * Once memblock is setup the memory can be allocated using one of the * API variants: * * * memblock_phys_alloc*() - these functions return the **physical** * address of the allocated memory * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. * * As the system boot progresses, the architecture specific mem_init() * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the * memblock data structures (except "physmem") will be discarded after the * system initialization completes. */ #ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP struct memblock_type physmem = { .regions = memblock_physmem_init_regions, .max = INIT_PHYSMEM_REGIONS, .name = "physmem", }; #endif /* * keep a pointer to &memblock.memory in the text section to use it in * __next_mem_range() and its helpers. * For architectures that do not keep memblock data after init, this * pointer will be reset to NULL at memblock_discard() */ static __refdata struct memblock_type *memblock_memory = &memblock.memory; #define for_each_memblock_type(i, memblock_type, rgn) \ for (i = 0, rgn = &memblock_type->regions[0]; \ i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) #define memblock_dbg(fmt, ...) \ do { \ if (memblock_debug) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock; static int memblock_reserved_in_slab __initdata_memblock; bool __init_memblock memblock_has_mirror(void) { return system_has_some_mirror; } static enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { return *size = min(*size, PHYS_ADDR_MAX - base); } /* * Address comparison utilities */ unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } bool __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { unsigned long i; memblock_cap_size(base, &size); for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) return true; return false; } /** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); cand = round_up(this_start, align); if (cand < this_end && this_end - cand >= size) return cand; } return 0; } /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_end < size) continue; cand = round_down(this_end - size, align); if (cand >= this_start) return cand; } return 0; } /** * memblock_find_in_range_node - find free area in given range and node * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, enum memblock_flags flags) { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); if (memblock_bottom_up()) return __memblock_find_range_bottom_up(start, end, size, align, nid, flags); else return __memblock_find_range_top_down(start, end, size, align, nid, flags); } /** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { phys_addr_t ret; enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; } return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; memmove(&type->regions[r], &type->regions[r + 1], (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { WARN_ON(type->total_size != 0); type->regions[0].base = 0; type->regions[0].size = 0; type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } #ifndef CONFIG_ARCH_KEEP_MEMBLOCK /** * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { phys_addr_t addr, size; if (memblock.reserved.regions != memblock_reserved_init_regions) { addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); if (memblock_reserved_in_slab) kfree(memblock.reserved.regions); else memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); if (memblock_memory_in_slab) kfree(memblock.memory.regions); else memblock_free_late(addr, size); } memblock_memory = NULL; } #endif /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled * @new_area_start: starting address of memory range to avoid overlap with * @new_area_size: size of memory range to avoid overlap with * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_start, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr, new_end; int use_slab = slab_is_available(); int *in_slab; /* We don't allow resizing until we know about the reserved regions * of memory that aren't suitable for allocation */ if (!memblock_can_resize) panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; /* * We need to allocated new one align to PAGE_SIZE, * so we can free them completely later. */ old_alloc_size = PAGE_ALIGN(old_size); new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) in_slab = &memblock_memory_in_slab; else in_slab = &memblock_reserved_in_slab; /* Try to find some space for it */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { /* only exclude range when trying to double reserved.regions */ if (type != &memblock.reserved) new_area_start = new_area_size = 0; addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", type->name, type->max, type->max * 2); return -1; } new_end = addr + new_size - 1; memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", type->name, type->max * 2, &addr, &new_end); /* * Found space, we now need to move the array over before we add the * reserved region since it may be our reserved array itself that is * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); old_array = type->regions; type->regions = new_array; type->max <<= 1; /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; return 0; } /** * memblock_merge_regions - merge neighboring compatible regions * @type: memblock type to scan * @start_rgn: start scanning from (@start_rgn - 1) * @end_rgn: end scanning at (@end_rgn - 1) * Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn) */ static void __init_memblock memblock_merge_regions(struct memblock_type *type, unsigned long start_rgn, unsigned long end_rgn) { int i = 0; if (start_rgn) i = start_rgn - 1; end_rgn = min(end_rgn, type->cnt - 1); while (i < end_rgn) { struct memblock_region *this = &type->regions[i]; struct memblock_region *next = &type->regions[i + 1]; if (this->base + this->size != next->base || memblock_get_region_node(this) != memblock_get_region_node(next) || this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; } this->size += next->size; /* move forward from next + 1, index of which is i + 2 */ memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); type->cnt--; end_rgn--; } } /** * memblock_insert_region - insert new memblock region * @type: memblock type to insert into * @idx: index for the insertion point * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region * @flags: flags of the new region * * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; BUG_ON(type->cnt >= type->max); memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); int idx, nr_new, start_rgn = -1, end_rgn; struct memblock_region *rgn; if (!size) return 0; /* special case for empty array */ if (type->regions[0].size == 0) { WARN_ON(type->cnt != 0 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; type->cnt = 1; return 0; } /* * The worst case is when new range overlaps all existing regions, * then we'll need type->cnt + 1 empty regions in @type. So if * type->cnt * 2 + 1 is less than or equal to type->max, we know * that there is enough empty regions in @type, and we can insert * regions directly. */ if (type->cnt * 2 + 1 <= type->max) insert = true; repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; /* * @rgn overlaps. If it separates the lower part of new * area, insert that portion. */ if (rbase > base) { #ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } } /* area below @rend is dealt with, forget about it */ base = min(rend, end); } /* insert the remaining portion */ if (base < end) { nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx, base, end - base, nid, flags); } } if (!nr_new) return 0; /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. */ if (!insert) { while (type->cnt + nr_new > type->max) if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; } else { memblock_merge_regions(type, start_rgn, end_rgn); return 0; } } /** * memblock_add_node - add new memblock region within a NUMA node * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, &base, &end, nid, flags, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** * memblock_add - add new memblock region * @base: base address of the new region * @size: size of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold * @threshold_bytes: maximal number of pages that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. * Check if amount of such memory is below @threshold_bytes. * * Return: true on success, false on failure. */ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) { unsigned long nr_pages = 0; unsigned long start_pfn, end_pfn, mem_size_mb; int nid, i; /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); return false; } return true; } /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate * @size: size of range to isolate * @start_rgn: out parameter for the start of isolated region * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and the index of the * first region after the range is returned in *@end_rgn. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); int idx; struct memblock_region *rgn; *start_rgn = *end_rgn = 0; if (!size) return 0; /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; if (rbase < base) { /* * @rgn intersects from below. Split and continue * to process the next region - the new top half. */ rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the * current region - the new bottom half. */ rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) *start_rgn = idx; *end_rgn = idx + 1; } } return 0; } static int __init_memblock memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = end_rgn - 1; i >= start_rgn; i--) memblock_remove_region(type, i); return 0; } int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_remove_range(&memblock.memory, base, size); } /** * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); } /** * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif /** * memblock_setclr_flag - set or clear flag for a memory region * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int set, int flag) { int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) { struct memblock_region *r = &type->regions[i]; if (set) r->flags |= flag; else r->flags &= ~flag; } memblock_merge_regions(type, start_rgn, end_rgn); return 0; } /** * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { if (!mirrored_kernelcore) return 0; system_has_some_mirror = true; return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. * @base: the base phys addr of the region * @size: the size of the region * * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the * direct mapping of the physical memory. These regions will still be * covered by the memory map. The struct page representing NOMAP memory * frames in the memory map will be PageReserved() * * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from * memblock, the caller must inform kmemleak to ignore that memory * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); } /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized * for this region. * @base: the base phys addr of the region * @size: the size of the region * * struct pages will not be initialized for reserved memory regions marked with * %MEMBLOCK_RSRV_NOINIT. * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.reserved, base, size, 1, MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; } /** * __next_mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of * *@idx contains index into type_a and the upper 32bit indexes the * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) * * The upper 32bit indexes the following regions. * * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) * * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b < type_b->cnt + 1; idx_b++) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; /* * The region which ends first is * advanced for the next iteration. */ if (m_end <= r_end) idx_a++; else idx_b++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Finds the next range from type_a which is not marked as unsuitable * in type_b. * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) idx_b = type_b->cnt; else idx_b = 0; } for (; idx_a >= 0; idx_a--) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b >= 0; idx_b--) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ if (m_end > r_start) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; if (m_start >= r_start) idx_a--; else idx_b--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /* * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid) { struct memblock_type *type = &memblock.memory; struct memblock_region *r; int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { *idx = -1; return; } if (out_start_pfn) *out_start_pfn = PFN_UP(r->base); if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) *out_nid = r_nid; } /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for * @type: memblock type to set node ID for * @nid: node ID to set * * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { #ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type, start_rgn, end_rgn); #endif return 0; } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() * * @idx: pointer to u64 loop variable * @zone: zone in which all of the memory blocks reside * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL * * This function is meant to be a zone/pfn specific wrapper for the * for_each_mem_range type iterators. Specifically they are used in the * deferred memory init routines and as such we were duplicating much of * this logic throughout the code. So instead of having it in multiple * locations it seemed like it would make more sense to centralize this to * one new iterator that does everything they need. */ void __init_memblock __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn) { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); unsigned long spfn = PFN_UP(spa); /* * Verify the end is at least past the start of the zone and * that we have at least one PFN to initialize. */ if (zone->zone_start_pfn < epfn && spfn < epfn) { /* if we went too far just stop searching */ if (zone_end_pfn(zone) <= spfn) { *idx = U64_MAX; break; } if (out_spfn) *out_spfn = max(zone->zone_start_pfn, spfn); if (out_epfn) *out_epfn = min(zone_end_pfn(zone), epfn); return; } __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); } /* signal end of iteration */ if (out_spfn) *out_spfn = ULONG_MAX; if (out_epfn) *out_epfn = 0; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** * memblock_alloc_range_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * * If the specified node can not hold the requested memory and @exact_nid * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any * memory region. * * In addition, function using kmemleak_alloc_phys for allocated boot * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) { void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid); return vaddr ? virt_to_phys(vaddr) : 0; } if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); align = SMP_CACHE_BYTES; } again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) goto done; if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (found && !memblock_reserve(found, size)) goto done; } if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } return 0; done: /* * Skip kmemleak for those places like kasan_init() and * early_pgtable_alloc() due to high volume. */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * Memblock allocated blocks are never reported as * leaks. This is because many of these blocks are * only referred via the physical address which is * not looked up by kmemleak. */ kmemleak_alloc_phys(found, size, 0); /* * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, * require memory to be accepted before it can be used by the * guest. * * Accept the memory of the allocated buffer. */ accept_memory(found, found + size); return found; } /** * memblock_phys_alloc_range - allocate a memory block inside specified range * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (physical address) * @end: the upper bound of the memory region to allocate (physical address) * * Allocate @size bytes in the between @start and @end. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end) { memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, &start, &end, (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Allocates memory block from the specified NUMA node. If the node * has no available memory, attempts to allocated from any node in the * system. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. * * The @min_addr limit is dropped if it can not be satisfied and the allocation * will fall back to memory below @min_addr. Other constraints, such * as node and mirrored memory will be handled again in * memblock_alloc_range_nid(). * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid, bool exact_nid) { phys_addr_t alloc; if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, exact_nid); if (!alloc) return NULL; return phys_to_virt(alloc); } /** * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node * without zeroing memory * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_exact_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, true); } /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); } /** * memblock_alloc_try_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { void *ptr; memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); return ptr; } /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * This is only useful when the memblock allocator has already been torn * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } /* * Remaining API functions */ phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } phys_addr_t __init_memblock memblock_reserved_size(void) { return memblock.reserved.total_size; } /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { return memblock.memory.regions[0].base; } phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = PHYS_ADDR_MAX; struct memblock_region *r; /* * translate the memory @limit size into the max address within one of * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; } limit -= r->size; } return max_addr; } void __init memblock_enforce_memory_limit(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, PHYS_ADDR_MAX); memblock_remove_range(&memblock.reserved, max_addr, PHYS_ADDR_MAX); } void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; if (!size) return; if (!memblock_memory->total_size) { pr_warn("%s: No memory registered yet\n", __func__); return; } ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) return; /* remove all the MAP regions */ for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); for (i = start_rgn - 1; i >= 0; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); /* truncate the reserved regions */ memblock_remove_range(&memblock.reserved, 0, base); memblock_remove_range(&memblock.reserved, base + size, PHYS_ADDR_MAX); } void __init memblock_mem_limit_remove_map(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; memblock_cap_memory_range(0, max_addr); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; do { unsigned int mid = (right + left) / 2; if (addr < type->regions[mid].base) right = mid; else if (addr >= (type->regions[mid].base + type->regions[mid].size)) left = mid + 1; else return mid; } while (left < right); return -1; } bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); if (i == -1) return false; return !memblock_is_nomap(&memblock.memory.regions[i]); } int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return memblock_get_region_node(&type->regions[mid]); } /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) is a subset of a memory block. * * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } /** * memblock_is_region_reserved - check if a region intersects reserved memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) intersects a reserved * memory block. * * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { return memblock_overlaps_region(&memblock.reserved, base, size); } void __init_memblock memblock_trim_memory(phys_addr_t align) { phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); if (start == orig_start && end == orig_end) continue; if (start < end) { r->base = start; r->size = end - start; } else { memblock_remove_region(&memblock.memory, r - memblock.memory.regions); r--; } } } void __init_memblock memblock_set_current_limit(phys_addr_t limit) { memblock.current_limit = limit; } phys_addr_t __init_memblock memblock_get_current_limit(void) { return memblock.current_limit; } static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; enum memblock_flags flags; int idx; struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(idx, type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", &memblock.memory.total_size, &memblock.reserved.total_size); memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP memblock_dump(&physmem); #endif } void __init_memblock memblock_dump_all(void) { if (memblock_debug) __memblock_dump_all(); } void __init memblock_allow_resize(void) { memblock_can_resize = 1; } static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) memblock_debug = 1; return 0; } early_param("memblock", early_memblock); static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) { struct page *start_pg, *end_pg; phys_addr_t pg, pgend; /* * Convert start_pfn/end_pfn to a struct page pointer. */ start_pg = pfn_to_page(start_pfn - 1) + 1; end_pg = pfn_to_page(end_pfn - 1) + 1; /* * Convert to physical addresses, and round start upwards and end * downwards. */ pg = PAGE_ALIGN(__pa(start_pg)); pgend = PAGE_ALIGN_DOWN(__pa(end_pg)); /* * If there are free pages between these, free the section of the * memmap array. */ if (pg < pgend) memblock_phys_free(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ static void __init free_unused_memmap(void) { unsigned long start, end, prev_end = 0; int i; if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) return; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); #endif /* * Align down here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ start = pageblock_start_pfn(start); /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ if (prev_end && prev_end < start) free_memmap(prev_end, start); /* * Align up here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ prev_end = pageblock_align(end); } #ifdef CONFIG_SPARSEMEM if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { prev_end = pageblock_align(end); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); } #endif } static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; while (start < end) { /* * Free the pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for * the case. */ if (start) order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } } static unsigned long __init __free_memory_core(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = min_t(unsigned long, PFN_DOWN(end), max_low_pfn); if (start_pfn >= end_pfn) return 0; __free_pages_memory(start_pfn, end_pfn); return end_pfn - start_pfn; } static void __init memmap_init_reserved_pages(void) { struct memblock_region *region; phys_addr_t start, end; int nid; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); memblock_set_node(start, end, &memblock.reserved, nid); } /* * initialize struct pages for reserved regions that don't have * the MEMBLOCK_RSRV_NOINIT flag set */ for_each_reserved_mem_region(region) { if (!memblock_is_reserved_noinit(region)) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); } } } static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end; u64 i; memblock_clear_hotplug(0, -1); memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); return count; } static int reset_managed_pages_done __initdata; static void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) atomic_long_set(&z->managed_pages, 0); } void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; if (reset_managed_pages_done) return; for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); reset_managed_pages_done = 1; } /** * memblock_free_all - release free pages to the buddy allocator */ void __init memblock_free_all(void) { unsigned long pages; free_unused_memmap(); reset_all_zones_managed_pages(); pages = free_low_memory_core_early(); totalram_pages_add(pages); } /* Keep a table to reserve named memory */ #define RESERVE_MEM_MAX_ENTRIES 8 #define RESERVE_MEM_NAME_SIZE 16 struct reserve_mem_table { char name[RESERVE_MEM_NAME_SIZE]; phys_addr_t start; phys_addr_t size; }; static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES]; static int reserved_mem_count; /* Add wildcard region with a lookup name */ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size, const char *name) { struct reserve_mem_table *map; map = &reserved_mem_table[reserved_mem_count++]; map->start = start; map->size = size; strscpy(map->name, name); } /** * reserve_mem_find_by_name - Find reserved memory region with a given name * @name: The name that is attached to a reserved memory region * @start: If found, holds the start address * @size: If found, holds the size of the address. * * @start and @size are only updated if @name is found. * * Returns: 1 if found or 0 if not found. */ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size) { struct reserve_mem_table *map; int i; for (i = 0; i < reserved_mem_count; i++) { map = &reserved_mem_table[i]; if (!map->size) continue; if (strcmp(name, map->name) == 0) { *start = map->start; *size = map->size; return 1; } } return 0; } EXPORT_SYMBOL_GPL(reserve_mem_find_by_name); /* * Parse reserve_mem=nn:align:name */ static int __init reserve_mem(char *p) { phys_addr_t start, size, align, tmp; char *name; char *oldp; int len; if (!p) return -EINVAL; /* Check if there's room for more reserved memory */ if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES) return -EBUSY; oldp = p; size = memparse(p, &p); if (!size || p == oldp) return -EINVAL; if (*p != ':') return -EINVAL; align = memparse(p+1, &p); if (*p != ':') return -EINVAL; /* * memblock_phys_alloc() doesn't like a zero size align, * but it is OK for this command to have it. */ if (align < SMP_CACHE_BYTES) align = SMP_CACHE_BYTES; name = p + 1; len = strlen(name); /* name needs to have length but not too big */ if (!len || len >= RESERVE_MEM_NAME_SIZE) return -EINVAL; /* Make sure that name has text */ for (p = name; *p; p++) { if (!isspace(*p)) break; } if (!*p) return -EINVAL; /* Make sure the name is not already used */ if (reserve_mem_find_by_name(name, &start, &tmp)) return -EBUSY; start = memblock_phys_alloc(size, align); if (!start) return -ENOMEM; reserved_mem_add(start, size, name); return 1; } __setup("reserve_mem=", reserve_mem); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) static const char * const flagname[] = { [ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG", [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) { struct memblock_type *type = m->private; struct memblock_region *reg; int i, j, nid; unsigned int count = ARRAY_SIZE(flagname); phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; end = reg->base + reg->size - 1; nid = memblock_get_region_node(reg); seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); if (reg->flags) { for (j = 0; j < count; j++) { if (reg->flags & (1U << j)) { seq_printf(m, "%s\n", flagname[j]); break; } } if (j == count) seq_printf(m, "%s\n", "UNKNOWN"); } else { seq_printf(m, "%s\n", "NONE"); } } return 0; } DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP debugfs_create_file("physmem", 0444, root, &physmem, &memblock_debug_fops); #endif return 0; } __initcall(memblock_init_debugfs); #endif /* CONFIG_DEBUG_FS */ |
| 3 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/rcupdate.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) #define INIT_PASID 0 struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * The mapcount field must not be used for own purposes. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and counters. * That requires that freelist & counters in struct slab be adjacent and * double-word aligned. Because struct slab currently just reinterprets the * bits of struct page, we align all struct pages to double-word boundaries, * and ensure that 'freelist' is aligned within struct slab. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) #else #define _struct_page_alignment __aligned(sizeof(unsigned long)) #endif struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. * WARNING: bit 0 of the first word is used for PageTail(). That * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ union { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ union { struct list_head lru; /* Or, for the Unevictable "LRU list" slot */ struct { /* Always even, to negate PageTail */ void *__filler; /* Count page's or folio's mlocks */ unsigned int mlock_count; }; /* Or, free page */ struct list_head buddy_list; struct list_head pcp_list; }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; union { pgoff_t index; /* Our offset within mapping. */ unsigned long share; /* share count for fsdax */ }; /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if PageSwapCache. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; }; struct { /* page_pool used by netstack */ /** * @pp_magic: magic value to avoid recycling non * page_pool allocated pages. */ unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being * mapped so the next 3 words hold the mapping, index, * and private fields from the source anonymous or * page cache page while the page is migrated to device * private memory. * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also * use the mapping, index, and private fields when * pmem backed DAX files are mapped. */ }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; }; union { /* This union is 4 bytes in size. */ /* * For head pages of typed folios, the value stored here * allows for determining what this page is used for. The * tail pages of typed folios will not store a type * (page_type == _mapcount == -1). * * See page-flags.h for a list of page types which are currently * stored here. * * Owners of typed folios may reuse the lower 16 bit of the * head page page_type field after setting the page type, * but must reset these 16 bit to -1 before clearing the * page type. */ unsigned int page_type; /* * For pages that are part of non-typed folios for which mappings * are tracked via the RMAP, encodes the number of times this page * is directly referenced by a page table. * * Note that the mapcount is always initialized to -1, so that * transitions both from it and to it can be tracked, using * atomic_inc_and_test() and atomic_add_negative(-1). */ atomic_t _mapcount; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_MEMCG unsigned long memcg_data; #elif defined(CONFIG_SLAB_OBJ_EXT) unsigned long _unused_slab_obj_exts; #endif /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with * highmem some memory is mapped into kernel virtual memory * dynamically, so we need a place to store that address. * Note that this field could be 16 bits on x86 ... ;) * * Architectures with slow multiplication can define * WANT_PAGE_VIRTUAL in asm/page.h */ #if defined(WANT_PAGE_VIRTUAL) void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif #ifdef CONFIG_KMSAN /* * KMSAN metadata for this page: * - shadow page: every bit indicates whether the corresponding * bit of the original page is initialized (0) or not (1); * - origin page: every 4 bytes contain an id of the stack trace * where the uninitialized value was created. */ struct page *kmsan_shadow; struct page *kmsan_origin; #endif } _struct_page_alignment; /* * struct encoded_page - a nonexistent type marking this pointer * * An 'encoded_page' pointer is a pointer to a regular 'struct page', but * with the low bits of the pointer indicating extra context-dependent * information. Only used in mmu_gather handling, and this acts as a type * system check on that use. * * We only really have two guaranteed bits in general, although you could * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE) * for more. * * Use the supplied helper functions to endcode/decode the pointer and bits. */ struct encoded_page; #define ENCODED_PAGE_BITS 3ul /* Perform rmap removal after we have flushed the TLB. */ #define ENCODED_PAGE_BIT_DELAY_RMAP 1ul /* * The next item in an encoded_page array is the "nr_pages" argument, specifying * the number of consecutive pages starting from this page, that all belong to * the same folio. For example, "nr_pages" corresponds to the number of folio * references that must be dropped. If this bit is not set, "nr_pages" is * implicitly 1. */ #define ENCODED_PAGE_BIT_NR_PAGES_NEXT 2ul static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags) { BUILD_BUG_ON(flags > ENCODED_PAGE_BITS); return (struct encoded_page *)(flags | (unsigned long)page); } static inline unsigned long encoded_page_flags(struct encoded_page *page) { return ENCODED_PAGE_BITS & (unsigned long)page; } static inline struct page *encoded_page_ptr(struct encoded_page *page) { return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page); } static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr) { VM_WARN_ON_ONCE((nr << 2) >> 2 != nr); return (struct encoded_page *)(nr << 2); } static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page) { return ((unsigned long)page) >> 2; } /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ typedef struct { unsigned long val; } swp_entry_t; /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, * this is the index from the beginning of the mmap. * @private: Filesystem per-folio data (see folio_attach_private()). * @swap: Used for swp_entry_t if folio_test_swapcache(). * @_mapcount: Do not access this member directly. Use folio_mapcount() to * find out how many times this folio is mapped by userspace. * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_large_mapcount: Do not use directly, call folio_mapcount(). * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head(). * @_deferred_list: Folios to be split under memory pressure. * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab. * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that * same power-of-two. It is at least as large as %PAGE_SIZE. If it is * in the page cache, it is at a file offset which is a multiple of that * power-of-two. It may be mapped into userspace at an address which is * at an arbitrary page offset, but its kernel virtual address is aligned * to its size. */ struct folio { /* private: don't document the anon union */ union { struct { /* public: */ unsigned long flags; union { struct list_head lru; /* private: avoid cluttering the output */ struct { void *__filler; /* public: */ unsigned int mlock_count; /* private: */ }; /* public: */ }; struct address_space *mapping; pgoff_t index; union { void *private; swp_entry_t swap; }; atomic_t _mapcount; atomic_t _refcount; #ifdef CONFIG_MEMCG unsigned long memcg_data; #elif defined(CONFIG_SLAB_OBJ_EXT) unsigned long _unused_slab_obj_exts; #endif #if defined(WANT_PAGE_VIRTUAL) void *virtual; #endif #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif /* private: the union with struct page is transitional */ }; struct page page; }; union { struct { unsigned long _flags_1; unsigned long _head_1; /* public: */ atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; #endif /* private: the union with struct page is transitional */ }; struct page __page_1; }; union { struct { unsigned long _flags_2; unsigned long _head_2; /* public: */ void *_hugetlb_subpool; void *_hugetlb_cgroup; void *_hugetlb_cgroup_rsvd; void *_hugetlb_hwpoison; /* private: the union with struct page is transitional */ }; struct { unsigned long _flags_2a; unsigned long _head_2a; /* public: */ struct list_head _deferred_list; /* private: the union with struct page is transitional */ }; struct page __page_2; }; }; #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); FOLIO_MATCH(_mapcount, _mapcount); FOLIO_MATCH(_refcount, _refcount); #ifdef CONFIG_MEMCG FOLIO_MATCH(memcg_data, memcg_data); #endif #if defined(WANT_PAGE_VIRTUAL) FOLIO_MATCH(virtual, virtual); #endif #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS FOLIO_MATCH(_last_cpupid, _last_cpupid); #endif #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ offsetof(struct page, pg) + sizeof(struct page)) FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ offsetof(struct page, pg) + 2 * sizeof(struct page)) FOLIO_MATCH(flags, _flags_2); FOLIO_MATCH(compound_head, _head_2); FOLIO_MATCH(flags, _flags_2a); FOLIO_MATCH(compound_head, _head_2a); #undef FOLIO_MATCH /** * struct ptdesc - Memory descriptor for page tables. * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. * @pt_list: List of used page tables. Used for s390 and x86. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. * @__page_refcount: Same as page refcount. * @pt_memcg_data: Memcg data. Tracked for page tables here. * * This struct overlays struct page for now. Do not modify without a good * understanding of the issues. */ struct ptdesc { unsigned long __page_flags; union { struct rcu_head pt_rcu_head; struct list_head pt_list; struct { unsigned long _pt_pad_1; pgtable_t pmd_huge_pte; }; }; unsigned long __page_mapping; union { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; }; union { unsigned long _pt_pad_2; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; #endif }; unsigned int __page_type; atomic_t __page_refcount; #ifdef CONFIG_MEMCG unsigned long pt_memcg_data; #endif }; #define TABLE_MATCH(pg, pt) \ static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt)) TABLE_MATCH(flags, __page_flags); TABLE_MATCH(compound_head, pt_list); TABLE_MATCH(compound_head, _pt_pad_1); TABLE_MATCH(mapping, __page_mapping); TABLE_MATCH(index, pt_index); TABLE_MATCH(rcu_head, pt_rcu_head); TABLE_MATCH(page_type, __page_type); TABLE_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG TABLE_MATCH(memcg_data, pt_memcg_data); #endif #undef TABLE_MATCH static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); #define ptdesc_page(pt) (_Generic((pt), \ const struct ptdesc *: (const struct page *)(pt), \ struct ptdesc *: (struct page *)(pt))) #define ptdesc_folio(pt) (_Generic((pt), \ const struct ptdesc *: (const struct folio *)(pt), \ struct ptdesc *: (struct folio *)(pt))) #define page_ptdesc(p) (_Generic((p), \ const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages * should be used for data that's ancillary to the head page (eg attaching * buffer heads to tail pages after attaching buffer heads to the head page) */ #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) { page->private = private; } static inline void *folio_get_private(struct folio *folio) { return folio->private; } struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) __u16 offset; __u16 size; #else __u32 offset; #endif /* we maintain a pagecount bias, so that we dont dirty cache line * containing page->_refcount every time we allocate a fragment. */ unsigned int pagecnt_bias; bool pfmemalloc; }; typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { struct rb_node vm_rb; /* link in global region tree */ vm_flags_t vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for * this region */ }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) struct vm_userfaultfd_ctx { struct userfaultfd_ctx *ctx; }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ struct anon_vma_name { struct kref kref; /* The name needs to be at the end because it is dynamically sized. */ char name[]; }; #ifdef CONFIG_ANON_VMA_NAME /* * mmap_lock should be read-locked when calling anon_vma_name(). Caller should * either keep holding the lock while using the returned pointer or it should * raise anon_vma_name refcount before releasing the lock. */ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); struct anon_vma_name *anon_vma_name_alloc(const char *name); void anon_vma_name_free(struct kref *kref); #else /* CONFIG_ANON_VMA_NAME */ static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { return NULL; } static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) { return NULL; } #endif struct vma_lock { struct rw_semaphore lock; }; struct vma_numab_state { /* * Initialised as time in 'jiffies' after which VMA * should be scanned. Delays first scan of new VMA by at * least sysctl_numa_balancing_scan_delay: */ unsigned long next_scan; /* * Time in jiffies when pids_active[] is reset to * detect phase change behaviour: */ unsigned long pids_active_reset; /* * Approximate tracking of PIDs that trapped a NUMA hinting * fault. May produce false positives due to hash collisions. * * [0] Previous PID tracking * [1] Current PID tracking * * Window moves after next_pid_reset has expired approximately * every VMA_PID_RESET_PERIOD jiffies: */ unsigned long pids_active[2]; /* MM scan sequence ID when scan first started after VMA creation */ int start_scan_seq; /* * MM scan sequence ID when the VMA was last completely scanned. * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq */ int prev_scan_seq; }; /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ union { struct { /* VMA covers [vm_start; vm_end) addresses within mm */ unsigned long vm_start; unsigned long vm_end; }; #ifdef CONFIG_PER_VMA_LOCK struct rcu_head vm_rcu; /* Used for deferred freeing. */ #endif }; struct mm_struct *vm_mm; /* The address space we belong to. */ pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. * To modify use vm_flags_{init|reset|set|clear|mod} functions. */ union { const vm_flags_t vm_flags; vm_flags_t __private __vm_flags; }; #ifdef CONFIG_PER_VMA_LOCK /* Flag to indicate areas detached from the mm->mm_mt tree */ bool detached; /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) * - vm_lock->lock (in write mode) * Can be read reliably while holding one of: * - mmap_lock (in read or write mode) * - vm_lock->lock (in read or write mode) * Can be read unreliably (using READ_ONCE()) for pessimistic bailout * while holding nothing (except RCU to keep the VMA struct allocated). * * This sequence counter is explicitly allowed to overflow; sequence * counter reuse can only lead to occasional unnecessary use of the * slowpath. */ int vm_lock_seq; struct vma_lock *vm_lock; #endif /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. * */ struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_ANON_VMA_NAME /* * For private and shared anonymous mappings, a pointer to a null * terminated string containing the name given to the vma, or NULL if * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. */ struct anon_vma_name *anon_name; #endif #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif #ifdef CONFIG_NUMA_BALANCING struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; #ifdef CONFIG_NUMA #define vma_policy(vma) ((vma)->vm_policy) #else #define vma_policy(vma) NULL #endif #ifdef CONFIG_SCHED_MM_CID struct mm_cid { u64 time; int cid; }; #endif struct kioctx_table; struct iommu_mm_data; struct mm_struct { struct { /* * Fields which are often written to are placed in a separate * cache line. */ struct { /** * @mm_count: The number of references to &struct * mm_struct (@mm_users count as 1). * * Use mmgrab()/mmdrop() to modify. When this drops to * 0, the &struct mm_struct is freed. */ atomic_t mm_count; } ____cacheline_aligned_in_smp; struct maple_tree mm_mt; unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* Base addresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER /** * @membarrier_state: Flags controlling membarrier behavior. * * This field is close to @pgd to hopefully fit in the same * cache-line, which needs to be touched by switch_mm(). */ atomic_t membarrier_state; #endif /** * @mm_users: The number of users including userspace. * * Use mmget()/mmget_not_zero()/mmput() to modify. When this * drops to 0 (i.e. when the task exits and there are no other * temporary reference holders), we also release a reference on * @mm_count (which may then free the &struct mm_struct if * @mm_count also drops to 0). */ atomic_t mm_users; #ifdef CONFIG_SCHED_MM_CID /** * @pcpu_cid: Per-cpu current cid. * * Keep track of the currently allocated mm_cid for each cpu. * The per-cpu mm_cid values are serialized by their respective * runqueue locks. */ struct mm_cid __percpu *pcpu_cid; /* * @mm_cid_next_scan: Next mm_cid scan (in jiffies). * * When the next mm_cid scan is due (in jiffies). */ unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ #endif int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some * counters */ /* * With some kernel config, the current mmap_lock's offset * inside 'mm_struct' is at 0x120, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * * So please be careful with adding new fields before * mmap_lock, which can easily push the 2 fields into one * cacheline. */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off * init_mm.mmlist, and are protected * by mmlist_lock */ #ifdef CONFIG_PER_VMA_LOCK /* * This field has lock-like semantics, meaning it is sometimes * accessed with ACQUIRE/RELEASE semantics. * Roughly speaking, incrementing the sequence number is * equivalent to releasing locks on VMAs; reading the sequence * number can be part of taking a read lock on a VMA. * * Can be modified under write mmap_lock using RELEASE * semantics. * Can be read with no other protection when holding write * mmap_lock. * Can be read with ACQUIRE semantics if not holding write * mmap_lock. */ int mm_lock_seq; #endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ atomic64_t pinned_vm; /* Refcount permanently increased */ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; /** * @write_protect_seq: Locked when any thread is write * protecting pages mapped by this mm to enforce a later COW, * for instance during page table copying for fork(). */ seqcount_t write_protect_seq; spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ struct percpu_counter rss_stat[NR_MM_COUNTERS]; struct linux_binfmt *binfmt; /* Architecture-specific MM context */ mm_context_t context; unsigned long flags; /* Must use atomic bitops to access */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */ struct task_struct __rcu *owner; #endif struct user_namespace *user_ns; /* store ref to file /proc/<pid>/exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING /* * numa_next_scan is the next time that PTEs will be remapped * PROT_NONE to trigger NUMA hinting faults; such faults gather * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT struct rcu_head delayed_drop; #endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; #ifdef CONFIG_IOMMU_MM_DATA struct iommu_mm_data *iommu_mm; #endif #ifdef CONFIG_KSM /* * Represent how many pages of this process are involved in KSM * merging (not including ksm_zero_pages). */ unsigned long ksm_merging_pages; /* * Represent how many pages are checked for ksm merging * including merged and not merged. */ unsigned long ksm_rmap_items; /* * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { /* this mm_struct is on lru_gen_mm_list */ struct list_head list; /* * Set when switching to this mm_struct, as a hint of * whether it has been used since the last time per-node * page table walkers cleared the corresponding bits. */ unsigned long bitmap; #ifdef CONFIG_MEMCG /* points to the memcg of "owner" above */ struct mem_cgroup *memcg; #endif } lru_gen; #endif /* CONFIG_LRU_GEN_WALKS_MMU */ } __randomize_layout; /* * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ unsigned long cpu_bitmap[]; }; #define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { return (struct cpumask *)&mm->cpu_bitmap; } #ifdef CONFIG_LRU_GEN struct lru_gen_mm_list { /* mm_struct list for page table walkers */ struct list_head fifo; /* protects the list above */ spinlock_t lock; }; #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_LRU_GEN_WALKS_MMU void lru_gen_add_mm(struct mm_struct *mm); void lru_gen_del_mm(struct mm_struct *mm); void lru_gen_migrate_mm(struct mm_struct *mm); static inline void lru_gen_init_mm(struct mm_struct *mm) { INIT_LIST_HEAD(&mm->lru_gen.list); mm->lru_gen.bitmap = 0; #ifdef CONFIG_MEMCG mm->lru_gen.memcg = NULL; #endif } static inline void lru_gen_use_mm(struct mm_struct *mm) { /* * When the bitmap is set, page reclaim knows this mm_struct has been * used since the last time it cleared the bitmap. So it might be worth * walking the page tables of this mm_struct to clear the accessed bit. */ WRITE_ONCE(mm->lru_gen.bitmap, -1); } #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static inline void lru_gen_add_mm(struct mm_struct *mm) { } static inline void lru_gen_del_mm(struct mm_struct *mm) { } static inline void lru_gen_migrate_mm(struct mm_struct *mm) { } static inline void lru_gen_init_mm(struct mm_struct *mm) { } static inline void lru_gen_use_mm(struct mm_struct *mm) { } #endif /* CONFIG_LRU_GEN_WALKS_MMU */ struct vma_iterator { struct ma_state mas; }; #define VMA_ITERATOR(name, __mm, __addr) \ struct vma_iterator name = { \ .mas = { \ .tree = &(__mm)->mm_mt, \ .index = __addr, \ .node = NULL, \ .status = ma_start, \ }, \ } static inline void vma_iter_init(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long addr) { mas_init(&vmi->mas, &mm->mm_mt, addr); } #ifdef CONFIG_SCHED_MM_CID enum mm_cid_state { MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ MM_CID_LAZY_PUT = (1U << 31), }; static inline bool mm_cid_is_unset(int cid) { return cid == MM_CID_UNSET; } static inline bool mm_cid_is_lazy_put(int cid) { return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); } static inline bool mm_cid_is_valid(int cid) { return !(cid & MM_CID_LAZY_PUT); } static inline int mm_cid_set_lazy_put(int cid) { return cid | MM_CID_LAZY_PUT; } static inline int mm_cid_clear_lazy_put(int cid) { return cid & ~MM_CID_LAZY_PUT; } /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { unsigned long cid_bitmap = (unsigned long)mm; cid_bitmap += offsetof(struct mm_struct, cpu_bitmap); /* Skip cpu_bitmap */ cid_bitmap += cpumask_size(); return (struct cpumask *)cid_bitmap; } static inline void mm_init_cid(struct mm_struct *mm) { int i; for_each_possible_cpu(i) { struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); pcpu_cid->cid = MM_CID_UNSET; pcpu_cid->time = 0; } cpumask_clear(mm_cidmask(mm)); } static inline int mm_alloc_cid_noprof(struct mm_struct *mm) { mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm); return 0; } #define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { free_percpu(mm->pcpu_cid); mm->pcpu_cid = NULL; } static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ typedef __bitwise unsigned int vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100, VM_FAULT_LOCKED = (__force vm_fault_t)0x000200, VM_FAULT_RETRY = (__force vm_fault_t)0x000400, VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) #define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ { VM_FAULT_COMPLETED, "COMPLETED" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ /* * If .fault is not provided, this points to a * NULL-terminated array of pages that back the special mapping. * * This must not be NULL unless .fault is provided. */ struct page **pages; /* * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ vm_fault_t (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; /** * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to break COW in a * COW mapping, making sure that an exclusive anon page is * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. * * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when * applied to mappings that are not COW mappings. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, FAULT_FLAG_MKWRITE = 1 << 1, FAULT_FLAG_ALLOW_RETRY = 1 << 2, FAULT_FLAG_RETRY_NOWAIT = 1 << 3, FAULT_FLAG_KILLABLE = 1 << 4, FAULT_FLAG_TRIED = 1 << 5, FAULT_FLAG_USER = 1 << 6, FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; /* Flags for clear_young_dirty_ptes(). */ typedef int __bitwise cydp_t; /* Clear the access bit */ #define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) /* Clear the dirty bit */ #define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ enum { /* check pte is writable */ FOLL_WRITE = 1 << 0, /* do get_page on page */ FOLL_GET = 1 << 1, /* give error on hole if it would be zero */ FOLL_DUMP = 1 << 2, /* get_user_pages read/write w/o permission */ FOLL_FORCE = 1 << 3, /* * if a disk transfer is needed, start the IO and return without waiting * upon it */ FOLL_NOWAIT = 1 << 4, /* do not fault in pages */ FOLL_NOFAULT = 1 << 5, /* check page is hwpoisoned */ FOLL_HWPOISON = 1 << 6, /* don't do file mappings */ FOLL_ANON = 1 << 7, /* * FOLL_LONGTERM indicates that the page will be held for an indefinite * time period _often_ under userspace control. This is in contrast to * iov_iter_get_pages(), whose usages are transient. */ FOLL_LONGTERM = 1 << 8, /* split huge pmd before returning */ FOLL_SPLIT_PMD = 1 << 9, /* allow returning PCI P2PDMA pages */ FOLL_PCI_P2PDMA = 1 << 10, /* allow interrupts from generic signals */ FOLL_INTERRUPTIBLE = 1 << 11, /* * Always honor (trigger) NUMA hinting faults. * * FOLL_WRITE implicitly honors NUMA hinting faults because a * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE * apply). get_user_pages_fast_only() always implicitly honors NUMA * hinting faults. */ FOLL_HONOR_NUMA_FAULT = 1 << 12, /* See also internal only FOLL flags in mm/internal.h */ }; #endif /* _LINUX_MM_TYPES_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG #define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); struct file *needs_masking; /* * 'mask' is zero for an out-of-bounds fd, all ones for ok. * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. * * Accessing fdt->fd[0] is ok, but needs masking of the result. */ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } struct file *lookup_fdget_rcu(unsigned int fd); struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); } struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 157 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/interval_tree.h> #include <linux/interval_tree_generic.h> #include <linux/compiler.h> #include <linux/export.h> #define START(node) ((node)->start) #define LAST(node) ((node)->last) INTERVAL_TREE_DEFINE(struct interval_tree_node, rb, unsigned long, __subtree_last, START, LAST,, interval_tree) EXPORT_SYMBOL_GPL(interval_tree_insert); EXPORT_SYMBOL_GPL(interval_tree_remove); EXPORT_SYMBOL_GPL(interval_tree_iter_first); EXPORT_SYMBOL_GPL(interval_tree_iter_next); #ifdef CONFIG_INTERVAL_TREE_SPAN_ITER /* * Roll nodes[1] into nodes[0] by advancing nodes[1] to the end of a contiguous * span of nodes. This makes nodes[0]->last the end of that contiguous used span * indexes that started at the original nodes[1]->start. nodes[1] is now the * first node starting the next used span. A hole span is between nodes[0]->last * and nodes[1]->start. nodes[1] must be !NULL. */ static void interval_tree_span_iter_next_gap(struct interval_tree_span_iter *state) { struct interval_tree_node *cur = state->nodes[1]; state->nodes[0] = cur; do { if (cur->last > state->nodes[0]->last) state->nodes[0] = cur; cur = interval_tree_iter_next(cur, state->first_index, state->last_index); } while (cur && (state->nodes[0]->last >= cur->start || state->nodes[0]->last + 1 == cur->start)); state->nodes[1] = cur; } void interval_tree_span_iter_first(struct interval_tree_span_iter *iter, struct rb_root_cached *itree, unsigned long first_index, unsigned long last_index) { iter->first_index = first_index; iter->last_index = last_index; iter->nodes[0] = NULL; iter->nodes[1] = interval_tree_iter_first(itree, first_index, last_index); if (!iter->nodes[1]) { /* No nodes intersect the span, whole span is hole */ iter->start_hole = first_index; iter->last_hole = last_index; iter->is_hole = 1; return; } if (iter->nodes[1]->start > first_index) { /* Leading hole on first iteration */ iter->start_hole = first_index; iter->last_hole = iter->nodes[1]->start - 1; iter->is_hole = 1; interval_tree_span_iter_next_gap(iter); return; } /* Starting inside a used */ iter->start_used = first_index; iter->is_hole = 0; interval_tree_span_iter_next_gap(iter); iter->last_used = iter->nodes[0]->last; if (iter->last_used >= last_index) { iter->last_used = last_index; iter->nodes[0] = NULL; iter->nodes[1] = NULL; } } EXPORT_SYMBOL_GPL(interval_tree_span_iter_first); void interval_tree_span_iter_next(struct interval_tree_span_iter *iter) { if (!iter->nodes[0] && !iter->nodes[1]) { iter->is_hole = -1; return; } if (iter->is_hole) { iter->start_used = iter->last_hole + 1; iter->last_used = iter->nodes[0]->last; if (iter->last_used >= iter->last_index) { iter->last_used = iter->last_index; iter->nodes[0] = NULL; iter->nodes[1] = NULL; } iter->is_hole = 0; return; } if (!iter->nodes[1]) { /* Trailing hole */ iter->start_hole = iter->nodes[0]->last + 1; iter->last_hole = iter->last_index; iter->nodes[0] = NULL; iter->is_hole = 1; return; } /* must have both nodes[0] and [1], interior hole */ iter->start_hole = iter->nodes[0]->last + 1; iter->last_hole = iter->nodes[1]->start - 1; iter->is_hole = 1; interval_tree_span_iter_next_gap(iter); } EXPORT_SYMBOL_GPL(interval_tree_span_iter_next); /* * Advance the iterator index to a specific position. The returned used/hole is * updated to start at new_index. This is faster than calling * interval_tree_span_iter_first() as it can avoid full searches in several * cases where the iterator is already set. */ void interval_tree_span_iter_advance(struct interval_tree_span_iter *iter, struct rb_root_cached *itree, unsigned long new_index) { if (iter->is_hole == -1) return; iter->first_index = new_index; if (new_index > iter->last_index) { iter->is_hole = -1; return; } /* Rely on the union aliasing hole/used */ if (iter->start_hole <= new_index && new_index <= iter->last_hole) { iter->start_hole = new_index; return; } if (new_index == iter->last_hole + 1) interval_tree_span_iter_next(iter); else interval_tree_span_iter_first(iter, itree, new_index, iter->last_index); } EXPORT_SYMBOL_GPL(interval_tree_span_iter_advance); #endif |
| 18 | 1 2 3 4 5 6 7 8 9 10 11 12 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <asm/kvm_hyp.h> void __kvm_timer_set_cntvoff(u64 cntvoff) { write_sysreg(cntvoff, cntvoff_el2); } |
| 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ #include "internal.h" static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT), PAGE_KERNEL, pages, PAGE_SHIFT); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); if (tcpu == cpu) break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the * region back to vmalloc() which will lazily flush the tlb. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } /** * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim * @chunk: chunk of interest * * This is the entry point for percpu reclaim. If a chunk qualifies, it is then * isolated and managed in separate lists at the back of pcpu_slot: sidelined * and to_depopulate respectively. The to_depopulate list holds chunks slated * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once * they are on this list. Once depopulated, they are moved onto the sidelined * list which enables them to be pulled back in for allocation if no other chunk * can suffice the allocation. */ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) { /* do not reclaim either the first chunk or reserved chunk */ if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) return false; /* * If it is isolated, it may be on the sidelined list so move it back to * the to_depopulate list. If we hit at least 1/4 pages empty pages AND * there is no system-wide shortage of empty pages aside from this * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || (pcpu_nr_empty_pop_pages > (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } |
| 226 224 226 226 224 115 234 300 300 235 235 300 7 115 234 235 235 235 234 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, NR_MEMMAP, /* page metadata allocated through buddy allocator */ NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable pages are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the * eviction. The first check takes care of the accessed bit set on the initial * fault; the second check makes sure this page hasn't been used since then. * This process, AKA second chance, requires a minimum of two generations, * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive * LRU, e.g., /proc/vmstat, these two generations are considered active; the * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * * PG_active is always cleared while a page is on one of lrugen->folios[] so * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A page accessed N times * through file descriptors is in tier order_base_2(N). A page in the first tier * (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A page in any other tier (N>1) is marked by * PG_referenced and PG_workingset. This implies a minimum of two tiers is * supported without using additional bits in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the * rest infer whether pages accessed multiple times through file descriptors * are statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H struct lruvec; struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types as clean file pages * can be evicted regardless of swap constraints. * * Normally anon and file min_seq are in sync. But if swapping is constrained, * e.g., out of swap space, file min_seq is allowed to advance and leave anon * min_seq behind. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* the first tier doesn't need protection, hence the minus one */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; bool can_swap; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return a->pgmap == b->pgmap; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!z->zone) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 41 159 159 159 16 40 40 45 40 45 30 41 41 41 6 41 41 41 41 40 40 40 41 41 41 41 41 41 41 41 41 40 40 41 41 40 41 41 41 41 41 41 30 41 41 41 41 41 40 41 41 41 41 41 60 60 60 1 1 1 1 1 20 59 59 59 59 58 40 40 20 20 59 59 59 59 59 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 16 16 16 6 6 6 6 6 16 16 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */ static cpumask_var_t wq_online_cpumask; /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1 << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); while (true) { int old, tmp; old = atomic_read(&nna->nr); if (old >= max) return false; tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1); if (tmp == old) return true; } } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) kick_pool(pwq->pool); } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data = *work_data_bits(work); debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be deleted directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Move the linked * barrier work items to the worklist when deleting the grabbed * item. Also keep WORK_STRUCT_INACTIVE in work_data, so that * it doesn't participate in nr_active management in later * pwq_dec_nr_in_flight(). */ if (work_data & WORK_STRUCT_INACTIVE) move_linked_works(work, &pwq->pool->worklist, NULL); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack_noalloc(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq)))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. * * For ordered workqueue, work items must be queued on the newest pwq * for accurate order management. Guaranteed order also guarantees * non-reentrancy. See the comments above unplug_oldest_pwq(). */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void detach_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); unbind_worker(worker); list_del(&worker->node); worker->pool = NULL; } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); detach_worker(worker); mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void detach_dying_workers(struct list_head *cull_list) { struct worker *worker; list_for_each_entry(worker, cull_list, entry) detach_worker(worker); } static void reap_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); kthread_stop_put(worker->task); kfree(worker); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); /* get an extra task struct reference for later kthread_stop_put() */ get_task_struct(worker->task); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_unbound_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong set_pf_worker() in its self-destruct path. * This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before detach_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); pwq->stats[PWQ_STAT_COMPLETED]++; lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(&pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->watchdog_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); ida_free(&pool->worker_ida, worker->id); WARN_ON_ONCE(!list_empty(&worker->entry)); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) pwq->stats[PWQ_STAT_RESCUED]++; } if (!list_empty(&rescuer->scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; unsigned long data; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ data = *work_data_bits(work); if (from_cancel && !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted soft * interrupt processing or prevents ksoftirqd from running by * keeping flipping BH. If the BH work item runs on a different * CPU then this has no effect other than doing the BH * disable/enable dance for nothing. This is copied from * kernel/softirq.c::tasklet_unlock_spin_wait(). */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { local_bh_disable(); local_bh_enable(); } else { cpu_relax(); } } } else { wait_for_completion(&barr.done); } destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); /* shut down the timers */ del_timer_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } kfree_rcu(pwq, rcu); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } static void apply_wqattrs_lock(void) { mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * * Calculate the cpumask a workqueue with @attrs should use on @pod. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* calculate possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); /* does @pod have any online CPUs @attrs wants? */ if (!cpumask_intersects(attrs->__pod_cpumask, wq_online_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); /* rescuer needs to respect wq cpumask changes */ if (ctx->wq->rescuer) set_cpus_allowed_ptr(ctx->wq->rescuer->task, unbound_effective_cpumask(ctx->wq)); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update the pwq slot for * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is in the same pod of the CPU being hot[un]plugged. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu) { struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = unbound_wq_update_pwq_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; lockdep_assert_held(&wq_pool_mutex); wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { struct worker_pool __percpu *pools; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool *pool; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) kmem_cache_free(pwq_cache, pwq); } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; if (wq->flags & WQ_UNBOUND) kthread_bind_mask(rescuer->task, unbound_effective_cpumask(wq)); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { va_list args; struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } va_start(args, max_active); name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_unreg_lockdep; } /* * wq_pool_mutex protects the workqueues list, allocations of PWQs, * and the global freeze state. */ apply_wqattrs_lock(); if (alloc_and_link_pwqs(wq) < 0) goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); if (wq_online && init_rescuer(wq) < 0) goto err_unlock_destroy; apply_wqattrs_unlock(); if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; return wq; err_unlock_free_node_nr_active: apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() * completes before calling kfree(wq). */ if (wq->flags & WQ_UNBOUND) { kthread_flush_worker(pwq_release_worker); free_node_nr_active(wq->node_nr_active); } err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_unlock_destroy: apply_wqattrs_unlock(); err_destroy: destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(alloc_workqueue); static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & WQ_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); cpumask_set_cpu(cpu, wq_online_cpumask); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); /** * work_on_cpu_safe_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * @key: The lock class key for lock debugging purposes * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) ret = work_on_cpu_key(cpu, fn, arg, key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * * This function can be called from cpuset code to provide a set of isolated * CPUs that should be excluded from wq_unbound_cpumask. */ int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; mutex_lock(&wq_pool_mutex); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); /* Save the current isolated cpumask & export it via sysfs */ if (!ret) cpumask_copy(wq_isolated_cpumask, exclude_cpumask); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { int i; for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) return i; } return -EINVAL; } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { ret = 0; apply_wqattrs_lock(); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); if (!ret) cpumask_copy(wq_requested_unbound_cpumask, cpumask); apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active breaks ordering guarantee. Disallow exposing * ordered workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; /* * Show workers that might prevent the processing of pending work items. * The only candidates are CPU-bound workers in the running state. * Pending work items should be handled by another idle worker * in all other situations. */ static void show_cpu_pool_hog(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (task_is_running(worker->task)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_hogs(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_hog(pool); } rcu_read_unlock(); } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_hogs(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_online_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_online_cpumask, cpu_online_mask); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!unbound_wq_update_pwq_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call unbound_wq_update_pwq() on all workqueue * and CPU combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup); |
| 248 248 75 76 76 51 51 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2010 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm_main.c * implements evm_inode_setxattr, evm_inode_post_setxattr, * evm_inode_removexattr, evm_verifyxattr, and evm_inode_set_acl. */ #define pr_fmt(fmt) "EVM: "fmt #include <linux/init.h> #include <linux/audit.h> #include <linux/xattr.h> #include <linux/integrity.h> #include <linux/evm.h> #include <linux/magic.h> #include <linux/posix_acl_xattr.h> #include <linux/lsm_hooks.h> #include <crypto/hash.h> #include <crypto/hash_info.h> #include <crypto/utils.h> #include "evm.h" int evm_initialized; static const char * const integrity_status_msg[] = { "pass", "pass_immutable", "fail", "fail_immutable", "no_label", "no_xattrs", "unknown" }; int evm_hmac_attrs; static struct xattr_list evm_config_default_xattrnames[] = { { .name = XATTR_NAME_SELINUX, .enabled = IS_ENABLED(CONFIG_SECURITY_SELINUX) }, { .name = XATTR_NAME_SMACK, .enabled = IS_ENABLED(CONFIG_SECURITY_SMACK) }, { .name = XATTR_NAME_SMACKEXEC, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKTRANSMUTE, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKMMAP, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_APPARMOR, .enabled = IS_ENABLED(CONFIG_SECURITY_APPARMOR) }, { .name = XATTR_NAME_IMA, .enabled = IS_ENABLED(CONFIG_IMA_APPRAISE) }, { .name = XATTR_NAME_CAPS, .enabled = true }, }; LIST_HEAD(evm_config_xattrnames); static int evm_fixmode __ro_after_init; static int __init evm_set_fixmode(char *str) { if (strncmp(str, "fix", 3) == 0) evm_fixmode = 1; else pr_err("invalid \"%s\" mode", str); return 1; } __setup("evm=", evm_set_fixmode); static void __init evm_init_config(void) { int i, xattrs; xattrs = ARRAY_SIZE(evm_config_default_xattrnames); pr_info("Initialising EVM extended attributes:\n"); for (i = 0; i < xattrs; i++) { pr_info("%s%s\n", evm_config_default_xattrnames[i].name, !evm_config_default_xattrnames[i].enabled ? " (disabled)" : ""); list_add_tail(&evm_config_default_xattrnames[i].list, &evm_config_xattrnames); } #ifdef CONFIG_EVM_ATTR_FSUUID evm_hmac_attrs |= EVM_ATTR_FSUUID; #endif pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs); } static bool evm_key_loaded(void) { return (bool)(evm_initialized & EVM_KEY_MASK); } /* * This function determines whether or not it is safe to ignore verification * errors, based on the ability of EVM to calculate HMACs. If the HMAC key * is not loaded, and it cannot be loaded in the future due to the * EVM_SETUP_COMPLETE initialization flag, allowing an operation despite the * attrs/xattrs being found invalid will not make them valid. */ static bool evm_hmac_disabled(void) { if (evm_initialized & EVM_INIT_HMAC) return false; if (!(evm_initialized & EVM_SETUP_COMPLETE)) return false; return true; } static int evm_find_protected_xattrs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct xattr_list *xattr; int error; int count = 0; if (!(inode->i_opflags & IOP_XATTR)) return -EOPNOTSUPP; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0); if (error < 0) { if (error == -ENODATA) continue; return error; } count++; } return count; } static int is_unsupported_hmac_fs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (inode->i_sb->s_iflags & SB_I_EVM_HMAC_UNSUPPORTED) { pr_info_once("%s not supported\n", inode->i_sb->s_type->name); return 1; } return 0; } /* * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr * * Compute the HMAC on the dentry's protected set of extended attributes * and compare it against the stored security.evm xattr. * * For performance: * - use the previoulsy retrieved xattr value and length to calculate the * HMAC.) * - cache the verification result in the iint, when available. * * Returns integrity status */ static enum integrity_status evm_verify_hmac(struct dentry *dentry, const char *xattr_name, char *xattr_value, size_t xattr_value_len) { struct evm_ima_xattr_data *xattr_data = NULL; struct signature_v2_hdr *hdr; enum integrity_status evm_status = INTEGRITY_PASS; struct evm_digest digest; struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); int rc, xattr_len, evm_immutable = 0; if (iint && (iint->evm_status == INTEGRITY_PASS || iint->evm_status == INTEGRITY_PASS_IMMUTABLE)) return iint->evm_status; /* * On unsupported filesystems without EVM_INIT_X509 enabled, skip * signature verification. */ if (!(evm_initialized & EVM_INIT_X509) && is_unsupported_hmac_fs(dentry)) return INTEGRITY_UNKNOWN; /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; if (rc == -ENODATA) { rc = evm_find_protected_xattrs(dentry); if (rc > 0) evm_status = INTEGRITY_NOLABEL; else if (rc == 0) evm_status = INTEGRITY_NOXATTRS; /* new file */ } else if (rc == -EOPNOTSUPP) { evm_status = INTEGRITY_UNKNOWN; } goto out; } xattr_len = rc; /* check value type */ switch (xattr_data->type) { case EVM_XATTR_HMAC: if (xattr_len != sizeof(struct evm_xattr)) { evm_status = INTEGRITY_FAIL; goto out; } digest.hdr.algo = HASH_ALGO_SHA1; rc = evm_calc_hmac(dentry, xattr_name, xattr_value, xattr_value_len, &digest, iint); if (rc) break; rc = crypto_memneq(xattr_data->data, digest.digest, SHA1_DIGEST_SIZE); if (rc) rc = -EINVAL; break; case EVM_XATTR_PORTABLE_DIGSIG: evm_immutable = 1; fallthrough; case EVM_IMA_XATTR_DIGSIG: /* accept xattr with non-empty signature field */ if (xattr_len <= sizeof(struct signature_v2_hdr)) { evm_status = INTEGRITY_FAIL; goto out; } hdr = (struct signature_v2_hdr *)xattr_data; digest.hdr.algo = hdr->hash_algo; rc = evm_calc_hash(dentry, xattr_name, xattr_value, xattr_value_len, xattr_data->type, &digest, iint); if (rc) break; rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM, (const char *)xattr_data, xattr_len, digest.digest, digest.hdr.length); if (!rc) { if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG) { if (iint) iint->flags |= EVM_IMMUTABLE_DIGSIG; evm_status = INTEGRITY_PASS_IMMUTABLE; } else if (!IS_RDONLY(inode) && !(inode->i_sb->s_readonly_remount) && !IS_IMMUTABLE(inode) && !is_unsupported_hmac_fs(dentry)) { evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } } break; default: rc = -EINVAL; break; } if (rc) { if (rc == -ENODATA) evm_status = INTEGRITY_NOXATTRS; else if (evm_immutable) evm_status = INTEGRITY_FAIL_IMMUTABLE; else evm_status = INTEGRITY_FAIL; } pr_debug("digest: (%d) [%*phN]\n", digest.hdr.length, digest.hdr.length, digest.digest); out: if (iint) iint->evm_status = evm_status; kfree(xattr_data); return evm_status; } static int evm_protected_xattr_common(const char *req_xattr_name, bool all_xattrs) { int namelen; int found = 0; struct xattr_list *xattr; namelen = strlen(req_xattr_name); list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { if (!all_xattrs && !xattr->enabled) continue; if ((strlen(xattr->name) == namelen) && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) { found = 1; break; } if (strncmp(req_xattr_name, xattr->name + XATTR_SECURITY_PREFIX_LEN, strlen(req_xattr_name)) == 0) { found = 1; break; } } return found; } int evm_protected_xattr(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, false); } int evm_protected_xattr_if_enabled(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, true); } /** * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values * @dentry: dentry of the read xattrs * @buffer: buffer xattr names, lengths or values are copied to * @buffer_size: size of buffer * @type: n: names, l: lengths, v: values * @canonical_fmt: data format (true: little endian, false: native format) * * Read protected xattr names (separated by |), lengths (u32) or values for a * given dentry and return the total size of copied data. If buffer is NULL, * just return the total size. * * Returns the total size on success, a negative value on error. */ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt) { struct xattr_list *xattr; int rc, size, total_size = 0; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, NULL, 0); if (rc < 0 && rc == -ENODATA) continue; else if (rc < 0) return rc; switch (type) { case 'n': size = strlen(xattr->name) + 1; if (buffer) { if (total_size) *(buffer + total_size - 1) = '|'; memcpy(buffer + total_size, xattr->name, size); } break; case 'l': size = sizeof(u32); if (buffer) { if (canonical_fmt) rc = (__force int)cpu_to_le32(rc); *(u32 *)(buffer + total_size) = rc; } break; case 'v': size = rc; if (buffer) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, buffer + total_size, buffer_size - total_size); if (rc < 0) return rc; } break; default: return -EINVAL; } total_size += size; } return total_size; } /** * evm_verifyxattr - verify the integrity of the requested xattr * @dentry: object of the verify xattr * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Calculate the HMAC for the given dentry and verify it against the stored * security.evm xattr. For performance, use the xattr value and length * previously retrieved to calculate the HMAC. * * Returns the xattr integrity status. * * This function requires the caller to lock the inode's i_mutex before it * is executed. */ enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, size_t xattr_value_len) { if (!evm_key_loaded() || !evm_protected_xattr(xattr_name)) return INTEGRITY_UNKNOWN; return evm_verify_hmac(dentry, xattr_name, xattr_value, xattr_value_len); } EXPORT_SYMBOL_GPL(evm_verifyxattr); /* * evm_verify_current_integrity - verify the dentry's metadata integrity * @dentry: pointer to the affected dentry * * Verify and return the dentry's metadata integrity. The exceptions are * before EVM is initialized or in 'fix' mode. */ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode) return INTEGRITY_PASS; return evm_verify_hmac(dentry, NULL, NULL, 0); } /* * evm_xattr_change - check if passed xattr value differs from current value * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Check if passed xattr value differs from current value. * * Returns 1 if passed xattr value differs from current value, 0 otherwise. */ static int evm_xattr_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { char *xattr_data = NULL; int rc = 0; rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data, 0, GFP_NOFS); if (rc < 0) { rc = 1; goto out; } if (rc == xattr_value_len) rc = !!memcmp(xattr_value, xattr_data, rc); else rc = 1; out: kfree(xattr_data); return rc; } /* * evm_protect_xattr - protect the EVM extended attribute * * Prevent security.evm from being modified or removed without the * necessary permissions or when the existing value is invalid. * * The posix xattr acls are 'system' prefixed, which normally would not * affect security.evm. An interesting side affect of writing posix xattr * acls is their modifying of the i_mode, which is included in security.evm. * For posix xattr acls only, permit security.evm, even if it currently * doesn't exist, to be updated unless the EVM signature is immutable. */ static int evm_protect_xattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { enum integrity_status evm_status; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (is_unsupported_hmac_fs(dentry)) return -EPERM; } else if (!evm_protected_xattr(xattr_name)) { if (!posix_xattr_acl(xattr_name)) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; goto out; } else if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if (evm_status == INTEGRITY_NOXATTRS) { struct evm_iint_cache *iint; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled()) return 0; iint = evm_iint_inode(d_backing_inode(dentry)); if (iint && (iint->flags & EVM_NEW_FILE)) return 0; /* exception for pseudo filesystems */ if (dentry->d_sb->s_magic == TMPFS_MAGIC || dentry->d_sb->s_magic == SYSFS_MAGIC) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, dentry->d_name.name, "update_metadata", integrity_status_msg[evm_status], -EPERM, 0); } out: /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_xattr_change(idmap, dentry, xattr_name, xattr_value, xattr_value_len)) return 0; if (evm_status != INTEGRITY_PASS && evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return evm_status == INTEGRITY_PASS ? 0 : -EPERM; } /** * evm_inode_setxattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Before allowing the 'security.evm' protected xattr to be updated, * verify the existing value is valid. As only the kernel should have * access to the EVM encrypted key needed to calculate the HMAC, prevent * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xattr_data = xattr_value; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!xattr_value_len) return -EINVAL; if (xattr_data->type != EVM_IMA_XATTR_DIGSIG && xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) return -EPERM; } return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_removexattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0); } #ifdef CONFIG_FS_POSIX_ACL static int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { int rc; umode_t mode; struct inode *inode = d_backing_inode(dentry); if (!kacl) return 1; rc = posix_acl_update_mode(idmap, inode, &mode, &kacl); if (rc || (inode->i_mode != mode)) return 1; return 0; } #else static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { return 0; } #endif /** * evm_inode_set_acl - protect the EVM extended attribute from posix acls * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Prevent modifying posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl)) return 0; if (evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Prevent removing posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static void evm_reset_status(struct inode *inode) { struct evm_iint_cache *iint; iint = evm_iint_inode(inode); if (iint) iint->evm_status = INTEGRITY_UNKNOWN; } /** * evm_metadata_changed: Detect changes to the metadata * @inode: a file's inode * @metadata_inode: metadata inode * * On a stacked filesystem detect whether the metadata has changed. If this is * the case reset the evm_status associated with the inode that represents the * file. */ bool evm_metadata_changed(struct inode *inode, struct inode *metadata_inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); bool ret = false; if (iint) { ret = (!IS_I_VERSION(metadata_inode) || integrity_inode_attrs_changed(&iint->metadata_inode, metadata_inode)); if (ret) iint->evm_status = INTEGRITY_UNKNOWN; } return ret; } /** * evm_revalidate_status - report whether EVM status re-validation is necessary * @xattr_name: pointer to the affected extended attribute name * * Report whether callers of evm_verifyxattr() should re-validate the * EVM status. * * Return true if re-validation is necessary, false otherwise. */ bool evm_revalidate_status(const char *xattr_name) { if (!evm_key_loaded()) return false; /* evm_inode_post_setattr() passes NULL */ if (!xattr_name) return true; if (!evm_protected_xattr(xattr_name) && !posix_xattr_acl(xattr_name) && strcmp(xattr_name, XATTR_NAME_EVM)) return false; return true; } /** * evm_inode_post_setxattr - update 'security.evm' to reflect the changes * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Update the HMAC stored in 'security.evm' to reflect the change. * * No need to take the i_mutex lock here, as this function is called from * __vfs_setxattr_noperm(). The caller of which has taken the inode's * i_mutex lock. */ static void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting * posix acls. */ static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); } /** * evm_inode_post_removexattr - update 'security.evm' after removing the xattr * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Update the HMAC stored in 'security.evm' to reflect removal of the xattr. * * No need to take the i_mutex lock here, as this function is called from * vfs_removexattr() which takes the i_mutex. */ static void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; evm_update_evmxattr(dentry, xattr_name, NULL, 0); } /** * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after * removing posix acls. */ static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = attr->ia_valid; if (!i_uid_needs_update(idmap, attr, inode) && !i_gid_needs_update(idmap, attr, inode) && (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode)) return 0; return 1; } /** * evm_inode_setattr - prevent updating an invalid EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; enum integrity_status evm_status; /* Policy permits modification of the protected attrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) return 0; evm_status = evm_verify_current_integrity(dentry); /* * Writing attrs is safe for portable signatures, as portable signatures * are immutable and can never be updated. */ if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS) || (evm_status == INTEGRITY_FAIL_IMMUTABLE) || (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN))) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_attr_change(idmap, dentry, attr)) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_post_setattr - update 'security.evm' after modifying metadata * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * For now, update the HMAC stored in 'security.evm' to reflect UID/GID * changes. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (!evm_revalidate_status(NULL)) return; evm_reset_status(dentry->d_inode); if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) evm_update_evmxattr(dentry, NULL, NULL, 0); } static int evm_inode_copy_up_xattr(struct dentry *src, const char *name) { struct evm_ima_xattr_data *xattr_data = NULL; int rc; if (strcmp(name, XATTR_NAME_EVM) != 0) return -EOPNOTSUPP; /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, src, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) return -EPERM; if (rc < offsetof(struct evm_ima_xattr_data, type) + sizeof(xattr_data->type)) return -EPERM; switch (xattr_data->type) { case EVM_XATTR_PORTABLE_DIGSIG: rc = 0; /* allow copy-up */ break; case EVM_XATTR_HMAC: case EVM_IMA_XATTR_DIGSIG: default: rc = 1; /* discard */ } kfree(xattr_data); return rc; } /* * evm_inode_init_security - initializes security.evm HMAC value */ int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { struct evm_xattr *xattr_data; struct xattr *xattr, *evm_xattr; bool evm_protected_xattrs = false; int rc; if (!(evm_initialized & EVM_INIT_HMAC) || !xattrs) return 0; /* * security_inode_init_security() makes sure that the xattrs array is * contiguous, there is enough space for security.evm, and that there is * a terminator at the end of the array. */ for (xattr = xattrs; xattr->name; xattr++) { if (evm_protected_xattr(xattr->name)) evm_protected_xattrs = true; } /* EVM xattr not needed. */ if (!evm_protected_xattrs) return 0; evm_xattr = lsm_get_xattr_slot(xattrs, xattr_count); /* * Array terminator (xattr name = NULL) must be the first non-filled * xattr slot. */ WARN_ONCE(evm_xattr != xattr, "%s: xattrs terminator is not the first non-filled slot\n", __func__); xattr_data = kzalloc(sizeof(*xattr_data), GFP_NOFS); if (!xattr_data) return -ENOMEM; xattr_data->data.type = EVM_XATTR_HMAC; rc = evm_init_hmac(inode, xattrs, xattr_data->digest); if (rc < 0) goto out; evm_xattr->value = xattr_data; evm_xattr->value_len = sizeof(*xattr_data); evm_xattr->name = XATTR_EVM_SUFFIX; return 0; out: kfree(xattr_data); return rc; } EXPORT_SYMBOL_GPL(evm_inode_init_security); static int evm_inode_alloc_security(struct inode *inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); /* Called by security_inode_alloc(), it cannot be NULL. */ iint->flags = 0UL; iint->evm_status = INTEGRITY_UNKNOWN; return 0; } static void evm_file_release(struct file *file) { struct inode *inode = file_inode(file); struct evm_iint_cache *iint = evm_iint_inode(inode); fmode_t mode = file->f_mode; if (!S_ISREG(inode->i_mode) || !(mode & FMODE_WRITE)) return; if (iint && atomic_read(&inode->i_writecount) == 1) iint->flags &= ~EVM_NEW_FILE; } static void evm_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); if (!S_ISREG(inode->i_mode)) return; if (iint) iint->flags |= EVM_NEW_FILE; } #ifdef CONFIG_EVM_LOAD_X509 void __init evm_load_x509(void) { int rc; rc = integrity_load_x509(INTEGRITY_KEYRING_EVM, CONFIG_EVM_X509_PATH); if (!rc) evm_initialized |= EVM_INIT_X509; } #endif static int __init init_evm(void) { int error; struct list_head *pos, *q; evm_init_config(); error = integrity_init_keyring(INTEGRITY_KEYRING_EVM); if (error) goto error; error = evm_init_secfs(); if (error < 0) { pr_info("Error registering secfs\n"); goto error; } error: if (error != 0) { if (!list_empty(&evm_config_xattrnames)) { list_for_each_safe(pos, q, &evm_config_xattrnames) list_del(pos); } } return error; } static struct security_hook_list evm_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_setattr, evm_inode_setattr), LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr), LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr), LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr), LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl), LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl), LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl), LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl), LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr), LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr), LSM_HOOK_INIT(inode_init_security, evm_inode_init_security), LSM_HOOK_INIT(inode_alloc_security, evm_inode_alloc_security), LSM_HOOK_INIT(file_release, evm_file_release), LSM_HOOK_INIT(path_post_mknod, evm_post_path_mknod), }; static const struct lsm_id evm_lsmid = { .name = "evm", .id = LSM_ID_EVM, }; static int __init init_evm_lsm(void) { security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid); return 0; } struct lsm_blob_sizes evm_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct evm_iint_cache), .lbs_xattr_count = 1, }; DEFINE_LSM(evm) = { .name = "evm", .init = init_evm_lsm, .order = LSM_ORDER_LAST, .blobs = &evm_blob_sizes, }; late_initcall(init_evm); |
| 159 159 159 159 159 166 161 166 166 166 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return true; return false; } EXPORT_SYMBOL(__bitmap_intersects); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_subset); #define BITMAP_WEIGHT(FETCH, bits) \ ({ \ unsigned int __bits = (bits), idx, w = 0; \ \ for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ w += hweight_long(FETCH); \ \ if (__bits % BITS_PER_LONG) \ w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ \ w; \ }) unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_and); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_andnot); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return bitmap_weight(buf, pos); } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); #ifdef CONFIG_NUMA /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) { return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags, node); } EXPORT_SYMBOL(bitmap_alloc_node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) { return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(bitmap_zalloc_node); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif #if BITS_PER_LONG == 32 /** * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u64 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits) { int n; for (n = nbits; n > 0; n -= 64) { u64 val = *buf++; *bitmap++ = val; if (n > 32) *bitmap++ = val >> 32; } /* * Clear tail bits in the last word beyond nbits. * * Negative index is OK because here we point to the word next * to the last word of the bitmap, except for nbits == 0, which * is tested implicitly. */ if (nbits % BITS_PER_LONG) bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr64); /** * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits * @buf: array of u64 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) { const unsigned long *end = bitmap + BITS_TO_LONGS(nbits); while (bitmap < end) { *buf = *bitmap++; if (bitmap < end) *buf |= (u64)(*bitmap++) << 32; buf++; } /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif |
| 160 175 160 160 160 160 103 147 20 160 103 160 160 160 20 20 175 20 160 160 160 160 160 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate hardware time stamp based on cycles if supported */ SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) { return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page = netmem_to_page(netmem); __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline void skb_reset_mac_len(struct sk_buff *skb) { skb->mac_len = skb->network_header - skb->mac_header; } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { skb->inner_network_header = skb->data - skb->head; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { skb->inner_mac_header = skb->data - skb->head; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { skb->transport_header = skb->data - skb->head; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { skb->network_header = skb->data - skb->head; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data - skb->head; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull(skb, skb_network_offset(skb) + len); } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Returns the &struct page associated with @frag. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { return netmem_to_page(frag->netmem); } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { void *ptr = page_address(skb_frag_page(frag)); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 2 2 2 3 3 3 3 3 3 2 3 3 3 3 3 1 1 1 1 6 6 6 6 6 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 1 1 3 4 1 1 1 4 10 10 3 2 2 2 1 5 1 1 1 3 1 1 1 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 | // SPDX-License-Identifier: GPL-2.0-only /* * GICv3 ITS emulation * * Copyright (C) 2015,2016 ARM Ltd. * Author: Andre Przywara <andre.przywara@arm.com> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/list_sort.h> #include <linux/irqchip/arm-gic-v3.h> #include <asm/kvm_emulate.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include "vgic.h" #include "vgic-mmio.h" static struct kvm_device_ops kvm_arm_vgic_its_ops; static int vgic_its_save_tables_v0(struct vgic_its *its); static int vgic_its_restore_tables_v0(struct vgic_its *its); static int vgic_its_commit_v0(struct vgic_its *its); static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv); /* * Creates a new (reference to a) struct vgic_irq for a given LPI. * If this LPI is already mapped on another ITS, we increase its refcount * and return a pointer to the existing structure. * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq. * This function returns a pointer to the _unlocked_ structure. */ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, struct kvm_vcpu *vcpu) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ if (irq) return irq; irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!irq) return ERR_PTR(-ENOMEM); ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); } INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; kref_init(&irq->refcount); irq->intid = intid; irq->target_vcpu = vcpu; irq->group = 1; xa_lock_irqsave(&dist->lpi_xa, flags); /* * There could be a race with another vgic_add_lpi(), so we need to * check that we don't add a second list entry with the same LPI. */ oldirq = xa_load(&dist->lpi_xa, intid); if (vgic_try_get_irq_kref(oldirq)) { /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; goto out_unlock; } ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); if (ret) { xa_release(&dist->lpi_xa, intid); kfree(irq); } out_unlock: xa_unlock_irqrestore(&dist->lpi_xa, flags); if (ret) return ERR_PTR(ret); /* * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. * * Should any of these fail, behave as if we couldn't create the LPI * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } return irq; } struct its_device { struct list_head dev_list; /* the head for the list of ITTEs */ struct list_head itt_head; u32 num_eventid_bits; gpa_t itt_addr; u32 device_id; }; #define COLLECTION_NOT_MAPPED ((u32)~0) struct its_collection { struct list_head coll_list; u32 collection_id; u32 target_addr; }; #define its_is_collection_mapped(coll) ((coll) && \ ((coll)->target_addr != COLLECTION_NOT_MAPPED)) struct its_ite { struct list_head ite_list; struct vgic_irq *irq; struct its_collection *collection; u32 event_id; }; /** * struct vgic_its_abi - ITS abi ops and settings * @cte_esz: collection table entry size * @dte_esz: device table entry size * @ite_esz: interrupt translation table entry size * @save_tables: save the ITS tables into guest RAM * @restore_tables: restore the ITS internal structs from tables * stored in guest RAM * @commit: initialize the registers which expose the ABI settings, * especially the entry sizes */ struct vgic_its_abi { int cte_esz; int dte_esz; int ite_esz; int (*save_tables)(struct vgic_its *its); int (*restore_tables)(struct vgic_its *its); int (*commit)(struct vgic_its *its); }; #define ABI_0_ESZ 8 #define ESZ_MAX ABI_0_ESZ static const struct vgic_its_abi its_table_abi_versions[] = { [0] = { .cte_esz = ABI_0_ESZ, .dte_esz = ABI_0_ESZ, .ite_esz = ABI_0_ESZ, .save_tables = vgic_its_save_tables_v0, .restore_tables = vgic_its_restore_tables_v0, .commit = vgic_its_commit_v0, }, }; #define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions) inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its) { return &its_table_abi_versions[its->abi_rev]; } static int vgic_its_set_abi(struct vgic_its *its, u32 rev) { const struct vgic_its_abi *abi; its->abi_rev = rev; abi = vgic_its_get_abi(its); return abi->commit(its); } /* * Find and returns a device in the device table for an ITS. * Must be called with the its_lock mutex held. */ static struct its_device *find_its_device(struct vgic_its *its, u32 device_id) { struct its_device *device; list_for_each_entry(device, &its->device_list, dev_list) if (device_id == device->device_id) return device; return NULL; } /* * Find and returns an interrupt translation table entry (ITTE) for a given * Device ID/Event ID pair on an ITS. * Must be called with the its_lock mutex held. */ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, u32 event_id) { struct its_device *device; struct its_ite *ite; device = find_its_device(its, device_id); if (device == NULL) return NULL; list_for_each_entry(ite, &device->itt_head, ite_list) if (ite->event_id == event_id) return ite; return NULL; } /* To be used as an iterator this macro misses the enclosing parentheses */ #define for_each_lpi_its(dev, ite, its) \ list_for_each_entry(dev, &(its)->device_list, dev_list) \ list_for_each_entry(ite, &(dev)->itt_head, ite_list) #define GIC_LPI_OFFSET 8192 #define VITS_TYPER_IDBITS 16 #define VITS_MAX_EVENTID (BIT(VITS_TYPER_IDBITS) - 1) #define VITS_TYPER_DEVBITS 16 #define VITS_MAX_DEVID (BIT(VITS_TYPER_DEVBITS) - 1) #define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1) #define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1) /* * Finds and returns a collection in the ITS collection table. * Must be called with the its_lock mutex held. */ static struct its_collection *find_collection(struct vgic_its *its, int coll_id) { struct its_collection *collection; list_for_each_entry(collection, &its->collection_list, coll_list) { if (coll_id == collection->collection_id) return collection; } return NULL; } #define LPI_PROP_ENABLE_BIT(p) ((p) & LPI_PROP_ENABLED) #define LPI_PROP_PRIORITY(p) ((p) & 0xfc) /* * Reads the configuration data for a given LPI from guest memory and * updates the fields in struct vgic_irq. * If filter_vcpu is not NULL, applies only if the IRQ is targeting this * VCPU. Unconditionally applies if filter_vcpu is NULL. */ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv) { u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser); u8 prop; int ret; unsigned long flags; ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, &prop, 1); if (ret) return ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { irq->priority = LPI_PROP_PRIORITY(prop); irq->enabled = LPI_PROP_ENABLE_BIT(prop); if (!irq->hw) { vgic_queue_irq_unlock(kvm, irq, flags); return 0; } } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); return 0; } static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; unsigned long flags; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; ret = its_get_vlpi(irq->host_irq, &map); if (ret) return ret; if (map.vpe) atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } return ret; } static struct kvm_vcpu *collection_to_vcpu(struct kvm *kvm, struct its_collection *col) { return kvm_get_vcpu_by_id(kvm, col->target_addr); } /* * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI * is targeting) to the VGIC's view, which deals with target VCPUs. * Needs to be called whenever either the collection for a LPIs has * changed or the collection itself got retargeted. */ static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite) { struct kvm_vcpu *vcpu; if (!its_is_collection_mapped(ite->collection)) return; vcpu = collection_to_vcpu(kvm, ite->collection); update_affinity(ite->irq, vcpu); } /* * Updates the target VCPU for every LPI targeting this collection. * Must be called with the its_lock mutex held. */ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its, struct its_collection *coll) { struct its_device *device; struct its_ite *ite; for_each_lpi_its(device, ite, its) { if (ite->collection != coll) continue; update_affinity_ite(kvm, ite); } } static u32 max_lpis_propbaser(u64 propbaser) { int nr_idbits = (propbaser & 0x1f) + 1; return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS); } /* * Sync the pending table pending bit of LPIs targeting @vcpu * with our own data structures. This relies on the LPI being * mapped before. */ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) { gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); struct vgic_dist *dist = &vcpu->kvm->arch.vgic; unsigned long intid, flags; struct vgic_irq *irq; int last_byte_offset = -1; int ret = 0; u8 pendmask; xa_for_each(&dist->lpi_xa, intid, irq) { int byte_offset, bit_nr; byte_offset = intid / BITS_PER_BYTE; bit_nr = intid % BITS_PER_BYTE; /* * For contiguously allocated LPIs chances are we just read * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { ret = kvm_read_guest_lock(vcpu->kvm, pendbase + byte_offset, &pendmask, 1); if (ret) return ret; last_byte_offset = byte_offset; } irq = vgic_get_irq(vcpu->kvm, NULL, intid); if (!irq) continue; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu == vcpu) irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return ret; } static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 reg = GITS_TYPER_PLPIS; /* * We use linear CPU numbers for redistributor addressing, * so GITS_TYPER.PTA is 0. * Also we force all PROPBASER registers to be the same, so * CommonLPIAff is 0 as well. * To avoid memory waste in the guest, we keep the number of IDBits and * DevBits low - as least for the time being. */ reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT; reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT; reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT; return extract_bytes(reg, addr & 7, len); } static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 val; val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK; val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM; return val; } static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 rev = GITS_IIDR_REV(val); if (rev >= NR_ITS_ABIS) return -EINVAL; return vgic_its_set_abi(its, rev); } static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { switch (addr & 0xffff) { case GITS_PIDR0: return 0x92; /* part number, bits[7:0] */ case GITS_PIDR1: return 0xb4; /* part number, bits[11:8] */ case GITS_PIDR2: return GIC_PIDR2_ARCH_GICv3 | 0x0b; case GITS_PIDR4: return 0x40; /* This is a 64K software visible page */ /* The following are the ID registers for (any) GIC. */ case GITS_CIDR0: return 0x0d; case GITS_CIDR1: return 0xf0; case GITS_CIDR2: return 0x05; case GITS_CIDR3: return 0xb1; } return 0; } static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db) { struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db); if (!kvm_io_dev) return ERR_PTR(-EINVAL); if (kvm_io_dev->ops != &kvm_io_gic_ops) return ERR_PTR(-EINVAL); iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); if (iodev->iodev_type != IODEV_ITS) return ERR_PTR(-EINVAL); return iodev->its; } static unsigned long vgic_its_cache_key(u32 devid, u32 eventid) { return (((unsigned long)devid) << VITS_TYPER_IDBITS) | eventid; } static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, u32 devid, u32 eventid) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_its *its; struct vgic_irq *irq; if (devid > VITS_MAX_DEVID || eventid > VITS_MAX_EVENTID) return NULL; its = __vgic_doorbell_to_its(kvm, db); if (IS_ERR(its)) return NULL; rcu_read_lock(); irq = xa_load(&its->translation_cache, cache_key); if (!vgic_try_get_irq_kref(irq)) irq = NULL; rcu_read_unlock(); return irq; } static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq *irq) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_irq *old; /* Do not cache a directly injected interrupt */ if (irq->hw) return; /* * The irq refcount is guaranteed to be nonzero while holding the * its_lock, as the ITE (and the reference it holds) cannot be freed. */ lockdep_assert_held(&its->its_lock); vgic_get_irq_kref(irq); /* * We could have raced with another CPU caching the same * translation behind our back, ensure we don't leak a * reference if that is the case. */ old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); if (old) vgic_put_irq(kvm, old); } static void vgic_its_invalidate_cache(struct vgic_its *its) { struct kvm *kvm = its->dev->kvm; struct vgic_irq *irq; unsigned long idx; xa_for_each(&its->translation_cache, idx, irq) { xa_erase(&its->translation_cache, idx); vgic_put_irq(kvm, irq); } } void vgic_its_invalidate_all_caches(struct kvm *kvm) { struct kvm_device *dev; struct vgic_its *its; rcu_read_lock(); list_for_each_entry_rcu(dev, &kvm->devices, vm_node) { if (dev->ops != &kvm_arm_vgic_its_ops) continue; its = dev->private; vgic_its_invalidate_cache(its); } rcu_read_unlock(); } int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq) { struct kvm_vcpu *vcpu; struct its_ite *ite; if (!its->enabled) return -EBUSY; ite = find_ite(its, devid, eventid); if (!ite || !its_is_collection_mapped(ite->collection)) return E_ITS_INT_UNMAPPED_INTERRUPT; vcpu = collection_to_vcpu(kvm, ite->collection); if (!vcpu) return E_ITS_INT_UNMAPPED_INTERRUPT; if (!vgic_lpis_enabled(vcpu)) return -EBUSY; vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); *irq = ite->irq; return 0; } struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi) { u64 address; if (!vgic_has_its(kvm)) return ERR_PTR(-ENODEV); if (!(msi->flags & KVM_MSI_VALID_DEVID)) return ERR_PTR(-EINVAL); address = (u64)msi->address_hi << 32 | msi->address_lo; return __vgic_doorbell_to_its(kvm, address); } /* * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. * Returns 0 on success, a positive error value for any ITS mapping * related errors and negative error values for generic errors. */ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid) { struct vgic_irq *irq = NULL; unsigned long flags; int err; err = vgic_its_resolve_lpi(kvm, its, devid, eventid, &irq); if (err) return err; if (irq->hw) return irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); return 0; } int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_irq *irq; unsigned long flags; phys_addr_t db; db = (u64)msi->address_hi << 32 | msi->address_lo; irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); if (!irq) return -EWOULDBLOCK; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); vgic_put_irq(kvm, irq); return 0; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_its *its; int ret; if (!vgic_its_inject_cached_translation(kvm, msi)) return 1; its = vgic_msi_to_its(kvm, msi); if (IS_ERR(its)) return PTR_ERR(its); mutex_lock(&its->its_lock); ret = vgic_its_trigger_msi(kvm, its, msi->devid, msi->data); mutex_unlock(&its->its_lock); if (ret < 0) return ret; /* * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 * if the guest has blocked the MSI. So we map any LPI mapping * related error to that. */ if (ret) return 0; else return 1; } /* Requires the its_lock to be held. */ static void its_free_ite(struct kvm *kvm, struct its_ite *ite) { list_del(&ite->ite_list); /* This put matches the get in vgic_add_lpi. */ if (ite->irq) { if (ite->irq->hw) WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); vgic_put_irq(kvm, ite->irq); } kfree(ite); } static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size) { return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1); } #define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8) #define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32) #define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1) #define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32) #define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32) #define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16) #define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8) #define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32) #define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1) /* * The DISCARD command frees an Interrupt Translation Table Entry (ITTE). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (ite && its_is_collection_mapped(ite->collection)) { /* * Though the spec talks about removing the pending state, we * don't bother here since we clear the ITTE anyway and the * pending state is a property of the ITTE struct. */ vgic_its_invalidate_cache(its); its_free_ite(kvm, ite); return 0; } return E_ITS_DISCARD_UNMAPPED_INTERRUPT; } /* * The MOVI command moves an ITTE to a different collection. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct kvm_vcpu *vcpu; struct its_ite *ite; struct its_collection *collection; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_MOVI_UNMAPPED_INTERRUPT; if (!its_is_collection_mapped(ite->collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; ite->collection = collection; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invalidate_cache(its); return update_affinity(ite->irq, vcpu); } static bool __is_visible_gfn_locked(struct vgic_its *its, gpa_t gpa) { gfn_t gfn = gpa >> PAGE_SHIFT; int idx; bool ret; idx = srcu_read_lock(&its->dev->kvm->srcu); ret = kvm_is_visible_gfn(its->dev->kvm, gfn); srcu_read_unlock(&its->dev->kvm->srcu, idx); return ret; } /* * Check whether an ID can be stored into the corresponding guest table. * For a direct table this is pretty easy, but gets a bit nasty for * indirect tables. We check whether the resulting guest physical address * is actually valid (covered by a memslot and guest accessible). * For this we have to read the respective first level entry. */ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, gpa_t *eaddr) { int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; u64 indirect_ptr, type = GITS_BASER_TYPE(baser); phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); int index; switch (type) { case GITS_BASER_TYPE_DEVICE: if (id > VITS_MAX_DEVID) return false; break; case GITS_BASER_TYPE_COLLECTION: /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */ if (id >= BIT_ULL(16)) return false; break; default: return false; } if (!(baser & GITS_BASER_INDIRECT)) { phys_addr_t addr; if (id >= (l1_tbl_size / esz)) return false; addr = base + id * esz; if (eaddr) *eaddr = addr; return __is_visible_gfn_locked(its, addr); } /* calculate and check the index into the 1st level */ index = id / (SZ_64K / esz); if (index >= (l1_tbl_size / sizeof(u64))) return false; /* Each 1st level entry is represented by a 64-bit value. */ if (kvm_read_guest_lock(its->dev->kvm, base + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; indirect_ptr = le64_to_cpu(indirect_ptr); /* check the valid bit of the first level entry */ if (!(indirect_ptr & BIT_ULL(63))) return false; /* Mask the guest physical address and calculate the frame number. */ indirect_ptr &= GENMASK_ULL(51, 16); /* Find the address of the actual entry */ index = id % (SZ_64K / esz); indirect_ptr += index * esz; if (eaddr) *eaddr = indirect_ptr; return __is_visible_gfn_locked(its, indirect_ptr); } /* * Check whether an event ID can be stored in the corresponding Interrupt * Translation Table, which starts at device->itt_addr. */ static bool vgic_its_check_event_id(struct vgic_its *its, struct its_device *device, u32 event_id) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ite_esz = abi->ite_esz; gpa_t gpa; /* max table size is: BIT_ULL(device->num_eventid_bits) * ite_esz */ if (event_id >= BIT_ULL(device->num_eventid_bits)) return false; gpa = device->itt_addr + event_id * ite_esz; return __is_visible_gfn_locked(its, gpa); } /* * Add a new collection into the ITS collection table. * Returns 0 on success, and a negative error value for generic errors. */ static int vgic_its_alloc_collection(struct vgic_its *its, struct its_collection **colp, u32 coll_id) { struct its_collection *collection; collection = kzalloc(sizeof(*collection), GFP_KERNEL_ACCOUNT); if (!collection) return -ENOMEM; collection->collection_id = coll_id; collection->target_addr = COLLECTION_NOT_MAPPED; list_add_tail(&collection->coll_list, &its->collection_list); *colp = collection; return 0; } static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id) { struct its_collection *collection; struct its_device *device; struct its_ite *ite; /* * Clearing the mapping for that collection ID removes the * entry from the list. If there wasn't any before, we can * go home early. */ collection = find_collection(its, coll_id); if (!collection) return; for_each_lpi_its(device, ite, its) if (ite->collection && ite->collection->collection_id == coll_id) ite->collection = NULL; list_del(&collection->coll_list); kfree(collection); } /* Must be called with its_lock mutex held */ static struct its_ite *vgic_its_alloc_ite(struct its_device *device, struct its_collection *collection, u32 event_id) { struct its_ite *ite; ite = kzalloc(sizeof(*ite), GFP_KERNEL_ACCOUNT); if (!ite) return ERR_PTR(-ENOMEM); ite->event_id = event_id; ite->collection = collection; list_add_tail(&ite->ite_list, &device->itt_head); return ite; } /* * The MAPTI and MAPI commands map LPIs to ITTEs. * Must be called with its_lock mutex held. */ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct its_ite *ite; struct kvm_vcpu *vcpu = NULL; struct its_device *device; struct its_collection *collection, *new_coll = NULL; struct vgic_irq *irq; int lpi_nr; device = find_its_device(its, device_id); if (!device) return E_ITS_MAPTI_UNMAPPED_DEVICE; if (!vgic_its_check_event_id(its, device, event_id)) return E_ITS_MAPTI_ID_OOR; if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) lpi_nr = its_cmd_get_physical_id(its_cmd); else lpi_nr = event_id; if (lpi_nr < GIC_LPI_OFFSET || lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; /* If there is an existing mapping, behavior is UNPREDICTABLE. */ if (find_ite(its, device_id, event_id)) return 0; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; new_coll = collection; } ite = vgic_its_alloc_ite(device, collection, event_id); if (IS_ERR(ite)) { if (new_coll) vgic_its_free_collection(its, coll_id); return PTR_ERR(ite); } if (its_is_collection_mapped(collection)) vcpu = collection_to_vcpu(kvm, collection); irq = vgic_add_lpi(kvm, lpi_nr, vcpu); if (IS_ERR(irq)) { if (new_coll) vgic_its_free_collection(its, coll_id); its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return 0; } /* Requires the its_lock to be held. */ static void vgic_its_free_device(struct kvm *kvm, struct vgic_its *its, struct its_device *device) { struct its_ite *ite, *temp; /* * The spec says that unmapping a device with still valid * ITTEs associated is UNPREDICTABLE. We remove all ITTEs, * since we cannot leave the memory unreferenced. */ list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list) its_free_ite(kvm, ite); vgic_its_invalidate_cache(its); list_del(&device->dev_list); kfree(device); } /* its lock must be held */ static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its) { struct its_device *cur, *temp; list_for_each_entry_safe(cur, temp, &its->device_list, dev_list) vgic_its_free_device(kvm, its, cur); } /* its lock must be held */ static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its) { struct its_collection *cur, *temp; list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list) vgic_its_free_collection(its, cur->collection_id); } /* Must be called with its_lock mutex held */ static struct its_device *vgic_its_alloc_device(struct vgic_its *its, u32 device_id, gpa_t itt_addr, u8 num_eventid_bits) { struct its_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL_ACCOUNT); if (!device) return ERR_PTR(-ENOMEM); device->device_id = device_id; device->itt_addr = itt_addr; device->num_eventid_bits = num_eventid_bits; INIT_LIST_HEAD(&device->itt_head); list_add_tail(&device->dev_list, &its->device_list); return device; } /* * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); bool valid = its_cmd_get_validbit(its_cmd); u8 num_eventid_bits = its_cmd_get_size(its_cmd); gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd); struct its_device *device; if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL)) return E_ITS_MAPD_DEVICE_OOR; if (valid && num_eventid_bits > VITS_TYPER_IDBITS) return E_ITS_MAPD_ITTSIZE_OOR; device = find_its_device(its, device_id); /* * The spec says that calling MAPD on an already mapped device * invalidates all cached data for this device. We implement this * by removing the mapping and re-establishing it. */ if (device) vgic_its_free_device(kvm, its, device); /* * The spec does not say whether unmapping a not-mapped device * is an error, so we are done in any case. */ if (!valid) return 0; device = vgic_its_alloc_device(its, device_id, itt_addr, num_eventid_bits); return PTR_ERR_OR_ZERO(device); } /* * The MAPC command maps collection IDs to redistributors. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u16 coll_id; struct its_collection *collection; bool valid; valid = its_cmd_get_validbit(its_cmd); coll_id = its_cmd_get_collection(its_cmd); if (!valid) { vgic_its_free_collection(its, coll_id); vgic_its_invalidate_cache(its); } else { struct kvm_vcpu *vcpu; vcpu = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); if (!vcpu) return E_ITS_MAPC_PROCNUM_OOR; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = vcpu->vcpu_id; } else { collection->target_addr = vcpu->vcpu_id; update_affinity_collection(kvm, its, collection); } } return 0; } /* * The CLEAR command removes the pending state for a particular LPI. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_CLEAR_UNMAPPED_INTERRUPT; ite->irq->pending_latch = false; if (ite->irq->hw) return irq_set_irqchip_state(ite->irq->host_irq, IRQCHIP_STATE_PENDING, false); return 0; } int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq) { return update_lpi_config(kvm, irq, NULL, true); } /* * The INV command syncs the configuration bits from the memory table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_INV_UNMAPPED_INTERRUPT; return vgic_its_inv_lpi(kvm, ite->irq); } /** * vgic_its_invall - invalidate all LPIs targeting a given vcpu * @vcpu: the vcpu for which the RD is targeted by an invalidation * * Contrary to the INVALL command, this targets a RD instead of a * collection, and we don't need to hold the its_lock, since no ITS is * involved here. */ int vgic_its_invall(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, NULL, intid); if (!irq) continue; update_lpi_config(kvm, irq, vcpu, false); vgic_put_irq(kvm, irq); } if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); return 0; } /* * The INVALL command requests flushing of all IRQ data in this collection. * Find the VCPU mapped to that collection, then iterate over the VM's list * of mapped LPIs and update the configuration for each IRQ which targets * the specified vcpu. The configuration will be read from the in-memory * configuration table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 coll_id = its_cmd_get_collection(its_cmd); struct its_collection *collection; struct kvm_vcpu *vcpu; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_INVALL_UNMAPPED_COLLECTION; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invall(vcpu); return 0; } /* * The MOVALL command moves the pending state of all IRQs targeting one * redistributor to another. We don't hold the pending state in the VCPUs, * but in the IRQs instead, so there is really not much to do for us here. * However the spec says that no IRQ must target the old redistributor * afterwards, so we make sure that no LPI is using the associated target_vcpu. * This command affects all LPIs in the system that target that redistributor. */ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu1, *vcpu2; struct vgic_irq *irq; unsigned long intid; /* We advertise GITS_TYPER.PTA==0, making the address the vcpu ID */ vcpu1 = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); vcpu2 = kvm_get_vcpu_by_id(kvm, its_cmd_mask_field(its_cmd, 3, 16, 32)); if (!vcpu1 || !vcpu2) return E_ITS_MOVALL_PROCNUM_OOR; if (vcpu1 == vcpu2) return 0; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, NULL, intid); if (!irq) continue; update_affinity(irq, vcpu2); vgic_put_irq(kvm, irq); } vgic_its_invalidate_cache(its); return 0; } /* * The INT command injects the LPI associated with that DevID/EvID pair. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* * This function is called with the its_cmd lock held, but the ITS data * structure lock dropped. */ static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { int ret = -ENODEV; mutex_lock(&its->its_lock); switch (its_cmd_get_command(its_cmd)) { case GITS_CMD_MAPD: ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd); break; case GITS_CMD_MAPC: ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd); break; case GITS_CMD_MAPI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MAPTI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MOVI: ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd); break; case GITS_CMD_DISCARD: ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd); break; case GITS_CMD_CLEAR: ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd); break; case GITS_CMD_MOVALL: ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd); break; case GITS_CMD_INT: ret = vgic_its_cmd_handle_int(kvm, its, its_cmd); break; case GITS_CMD_INV: ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd); break; case GITS_CMD_INVALL: ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd); break; case GITS_CMD_SYNC: /* we ignore this command: we are in sync all of the time */ ret = 0; break; } mutex_unlock(&its->its_lock); return ret; } static u64 vgic_sanitise_its_baser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK, GITS_BASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK, GITS_BASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK, GITS_BASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* We support only one (ITS) page size: 64K */ reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; return reg; } static u64 vgic_sanitise_its_cbaser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK, GITS_CBASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK, GITS_CBASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK, GITS_CBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* Sanitise the physical address to be 64k aligned. */ reg &= ~GENMASK_ULL(15, 12); return reg; } static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cbaser, addr & 7, len); } static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* When GITS_CTLR.Enable is 1, this register is RO. */ if (its->enabled) return; mutex_lock(&its->cmd_lock); its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val); its->cbaser = vgic_sanitise_its_cbaser(its->cbaser); its->creadr = 0; /* * CWRITER is architecturally UNKNOWN on reset, but we need to reset * it to CREADR to make sure we start with an empty command buffer. */ its->cwriter = its->creadr; mutex_unlock(&its->cmd_lock); } #define ITS_CMD_BUFFER_SIZE(baser) ((((baser) & 0xff) + 1) << 12) #define ITS_CMD_SIZE 32 #define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) /* Must be called with the cmd_lock held. */ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) { gpa_t cbaser; u64 cmd_buf[4]; /* Commands are only processed when the ITS is enabled. */ if (!its->enabled) return; cbaser = GITS_CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going * wrong from which we cannot easily recover. * According to section 6.3.2 in the GICv3 spec we can just * ignore that command then. */ if (!ret) vgic_its_handle_command(kvm, its, cmd_buf); its->creadr += ITS_CMD_SIZE; if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) its->creadr = 0; } } /* * By writing to CWRITER the guest announces new commands to be processed. * To avoid any races in the first place, we take the its_cmd lock, which * protects our ring buffer variables, so that there is only one user * per ITS handling commands at a given time. */ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u64 reg; if (!its) return; mutex_lock(&its->cmd_lock); reg = update_64bit_reg(its->cwriter, addr & 7, len, val); reg = ITS_CMD_OFFSET(reg); if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { mutex_unlock(&its->cmd_lock); return; } its->cwriter = reg; vgic_its_process_commands(kvm, its); mutex_unlock(&its->cmd_lock); } static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cwriter, addr & 0x7, len); } static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->creadr, addr & 0x7, len); } static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 cmd_offset; int ret = 0; mutex_lock(&its->cmd_lock); if (its->enabled) { ret = -EBUSY; goto out; } cmd_offset = ITS_CMD_OFFSET(val); if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { ret = -EINVAL; goto out; } its->creadr = cmd_offset; out: mutex_unlock(&its->cmd_lock); return ret; } #define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7) static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u64 reg; switch (BASER_INDEX(addr)) { case 0: reg = its->baser_device_table; break; case 1: reg = its->baser_coll_table; break; default: reg = 0; break; } return extract_bytes(reg, addr & 7, len); } #define GITS_BASER_RO_MASK (GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56)) static void vgic_mmio_write_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 entry_size, table_type; u64 reg, *regptr, clearbits = 0; /* When GITS_CTLR.Enable is 1, we ignore write accesses. */ if (its->enabled) return; switch (BASER_INDEX(addr)) { case 0: regptr = &its->baser_device_table; entry_size = abi->dte_esz; table_type = GITS_BASER_TYPE_DEVICE; break; case 1: regptr = &its->baser_coll_table; entry_size = abi->cte_esz; table_type = GITS_BASER_TYPE_COLLECTION; clearbits = GITS_BASER_INDIRECT; break; default: return; } reg = update_64bit_reg(*regptr, addr & 7, len, val); reg &= ~GITS_BASER_RO_MASK; reg &= ~clearbits; reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT; reg |= table_type << GITS_BASER_TYPE_SHIFT; reg = vgic_sanitise_its_baser(reg); *regptr = reg; if (!(reg & GITS_BASER_VALID)) { /* Take the its_lock to prevent a race with a save/restore */ mutex_lock(&its->its_lock); switch (table_type) { case GITS_BASER_TYPE_DEVICE: vgic_its_free_device_list(kvm, its); break; case GITS_BASER_TYPE_COLLECTION: vgic_its_free_collection_list(kvm, its); break; } mutex_unlock(&its->its_lock); } } static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 reg = 0; mutex_lock(&its->cmd_lock); if (its->creadr == its->cwriter) reg |= GITS_CTLR_QUIESCENT; if (its->enabled) reg |= GITS_CTLR_ENABLE; mutex_unlock(&its->cmd_lock); return reg; } static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { mutex_lock(&its->cmd_lock); /* * It is UNPREDICTABLE to enable the ITS if any of the CBASER or * device/collection BASER are invalid */ if (!its->enabled && (val & GITS_CTLR_ENABLE) && (!(its->baser_device_table & GITS_BASER_VALID) || !(its->baser_coll_table & GITS_BASER_VALID) || !(its->cbaser & GITS_CBASER_VALID))) goto out; its->enabled = !!(val & GITS_CTLR_ENABLE); if (!its->enabled) vgic_its_invalidate_cache(its); /* * Try to process any pending commands. This function bails out early * if the ITS is disabled or no commands have been queued. */ vgic_its_process_commands(kvm, its); out: mutex_unlock(&its->cmd_lock); } #define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ } #define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ .uaccess_its_write = uwr, \ } static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } static struct vgic_register_region its_registers[] = { REGISTER_ITS_DESC(GITS_CTLR, vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_IIDR, vgic_mmio_read_its_iidr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_iidr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_TYPER, vgic_mmio_read_its_typer, its_mmio_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CBASER, vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CWRITER, vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_CREADR, vgic_mmio_read_its_creadr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_creadr, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_BASER, vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_IDREGS_BASE, vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30, VGIC_ACCESS_32bit), }; /* This is called on setting the LPI enable bit in the redistributor. */ void vgic_enable_lpis(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ)) its_sync_lpi_pending_table(vcpu); } static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its, u64 addr) { struct vgic_io_device *iodev = &its->iodev; int ret; mutex_lock(&kvm->slots_lock); if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -EBUSY; goto out; } its->vgic_its_base = addr; iodev->regions = its_registers; iodev->nr_regions = ARRAY_SIZE(its_registers); kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops); iodev->base_addr = its->vgic_its_base; iodev->iodev_type = IODEV_ITS; iodev->its = its; ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr, KVM_VGIC_V3_ITS_SIZE, &iodev->dev); out: mutex_unlock(&kvm->slots_lock); return ret; } #define INITIAL_BASER_VALUE \ (GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \ GITS_BASER_PAGE_SIZE_64K) #define INITIAL_PROPBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)) static int vgic_its_create(struct kvm_device *dev, u32 type) { int ret; struct vgic_its *its; if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) return -ENODEV; its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL_ACCOUNT); if (!its) return -ENOMEM; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_initialized(dev->kvm)) { ret = vgic_v4_init(dev->kvm); if (ret < 0) { mutex_unlock(&dev->kvm->arch.config_lock); kfree(its); return ret; } } mutex_init(&its->its_lock); mutex_init(&its->cmd_lock); /* Yep, even more trickery for lock ordering... */ #ifdef CONFIG_LOCKDEP mutex_lock(&its->cmd_lock); mutex_lock(&its->its_lock); mutex_unlock(&its->its_lock); mutex_unlock(&its->cmd_lock); #endif its->vgic_its_base = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&its->device_list); INIT_LIST_HEAD(&its->collection_list); xa_init(&its->translation_cache); dev->kvm->arch.vgic.msis_require_devid = true; dev->kvm->arch.vgic.has_its = true; its->enabled = false; its->dev = dev; its->baser_device_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT); its->baser_coll_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT); dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE; dev->private = its; ret = vgic_its_set_abi(its, NR_ITS_ABIS - 1); mutex_unlock(&dev->kvm->arch.config_lock); return ret; } static void vgic_its_destroy(struct kvm_device *kvm_dev) { struct kvm *kvm = kvm_dev->kvm; struct vgic_its *its = kvm_dev->private; mutex_lock(&its->its_lock); vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); vgic_its_invalidate_cache(its); xa_destroy(&its->translation_cache); mutex_unlock(&its->its_lock); kfree(its); kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */ } static int vgic_its_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) { const struct vgic_register_region *region; gpa_t offset = attr->attr; int align; align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7; if (offset & align) return -EINVAL; region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) return -ENXIO; return 0; } static int vgic_its_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, u64 *reg, bool is_write) { const struct vgic_register_region *region; struct vgic_its *its; gpa_t addr, offset; unsigned int len; int align, ret = 0; its = dev->private; offset = attr->attr; /* * Although the spec supports upper/lower 32-bit accesses to * 64-bit ITS registers, the userspace ABI requires 64-bit * accesses to all 64-bit wide registers. We therefore only * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID * registers */ if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4)) align = 0x3; else align = 0x7; if (offset & align) return -EINVAL; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -ENXIO; goto out; } region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) { ret = -ENXIO; goto out; } addr = its->vgic_its_base + offset; len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; if (is_write) { if (region->uaccess_its_write) ret = region->uaccess_its_write(dev->kvm, its, addr, len, *reg); else region->its_write(dev->kvm, its, addr, len, *reg); } else { *reg = region->its_read(dev->kvm, its, addr, len); } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return ret; } static u32 compute_next_devid_offset(struct list_head *h, struct its_device *dev) { struct its_device *next; u32 next_offset; if (list_is_last(&dev->dev_list, h)) return 0; next = list_next_entry(dev, dev_list); next_offset = next->device_id - dev->device_id; return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET); } static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite) { struct its_ite *next; u32 next_offset; if (list_is_last(&ite->ite_list, h)) return 0; next = list_next_entry(ite, ite_list); next_offset = next->event_id - ite->event_id; return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET); } /** * typedef entry_fn_t - Callback called on a table entry restore path * @its: its handle * @id: id of the entry * @entry: pointer to the entry * @opaque: pointer to an opaque data * * Return: < 0 on error, 0 if last element was identified, id offset to next * element otherwise */ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, void *opaque); /** * scan_its_table - Scan a contiguous table in guest RAM and applies a function * to each entry * * @its: its handle * @base: base gpa of the table * @size: size of the table in bytes * @esz: entry size in bytes * @start_id: the ID of the first entry in the table * (non zero for 2d level tables) * @fn: function to apply on each entry * @opaque: pointer to opaque data * * Return: < 0 on error, 0 if last element was identified, 1 otherwise * (the last element may not be found on second level tables) */ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, int start_id, entry_fn_t fn, void *opaque) { struct kvm *kvm = its->dev->kvm; unsigned long len = size; int id = start_id; gpa_t gpa = base; char entry[ESZ_MAX]; int ret; memset(entry, 0, esz); while (true) { int next_offset; size_t byte_offset; ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; next_offset = fn(its, id, entry, opaque); if (next_offset <= 0) return next_offset; byte_offset = next_offset * esz; if (byte_offset >= len) break; id += next_offset; gpa += byte_offset; len -= byte_offset; } return 1; } /* * vgic_its_save_ite - Save an interrupt translation entry at @gpa */ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, struct its_ite *ite, gpa_t gpa, int ite_esz) { struct kvm *kvm = its->dev->kvm; u32 next_offset; u64 val; next_offset = compute_next_eventid_offset(&dev->itt_head, ite); val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) | ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); return vgic_write_guest_lock(kvm, gpa, &val, ite_esz); } /** * vgic_its_restore_ite - restore an interrupt translation entry * * @its: its handle * @event_id: id used for indexing * @ptr: pointer to the ITE entry * @opaque: pointer to the its_device */ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; u64 val; u64 *p = (u64 *)ptr; struct vgic_irq *irq; u32 coll_id, lpi_id; struct its_ite *ite; u32 offset; val = *p; val = le64_to_cpu(val); coll_id = val & KVM_ITS_ITE_ICID_MASK; lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT; if (!lpi_id) return 1; /* invalid entry, no choice but to scan next entry */ if (lpi_id < VGIC_MIN_LPI) return -EINVAL; offset = val >> KVM_ITS_ITE_NEXT_SHIFT; if (event_id + offset >= BIT_ULL(dev->num_eventid_bits)) return -EINVAL; collection = find_collection(its, coll_id); if (!collection) return -EINVAL; if (!vgic_its_check_event_id(its, dev, event_id)) return -EINVAL; ite = vgic_its_alloc_ite(dev, collection, event_id); if (IS_ERR(ite)) return PTR_ERR(ite); if (its_is_collection_mapped(collection)) vcpu = kvm_get_vcpu_by_id(kvm, collection->target_addr); irq = vgic_add_lpi(kvm, lpi_id, vcpu); if (IS_ERR(irq)) { its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return offset; } static int vgic_its_ite_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_ite *itea = container_of(a, struct its_ite, ite_list); struct its_ite *iteb = container_of(b, struct its_ite, ite_list); if (itea->event_id < iteb->event_id) return -1; else return 1; } static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = device->itt_addr; struct its_ite *ite; int ret; int ite_esz = abi->ite_esz; list_sort(NULL, &device->itt_head, vgic_its_ite_cmp); list_for_each_entry(ite, &device->itt_head, ite_list) { gpa_t gpa = base + ite->event_id * ite_esz; /* * If an LPI carries the HW bit, this means that this * interrupt is controlled by GICv4, and we do not * have direct access to that state without GICv4.1. * Let's simply fail the save operation... */ if (ite->irq->hw && !kvm_vgic_global_state.has_gicv4_1) return -EACCES; ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz); if (ret) return ret; } return 0; } /** * vgic_its_restore_itt - restore the ITT of a device * * @its: its handle * @dev: device handle * * Return 0 on success, < 0 on error */ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = dev->itt_addr; int ret; int ite_esz = abi->ite_esz; size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz; ret = scan_its_table(its, base, max_size, ite_esz, 0, vgic_its_restore_ite, dev); /* scan_its_table returns +1 if all ITEs are invalid */ if (ret > 0) ret = 0; return ret; } /** * vgic_its_save_dte - Save a device table entry at a given GPA * * @its: ITS handle * @dev: ITS device * @ptr: GPA * @dte_esz: device table entry size */ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, gpa_t ptr, int dte_esz) { struct kvm *kvm = its->dev->kvm; u64 val, itt_addr_field; u32 next_offset; itt_addr_field = dev->itt_addr >> 8; next_offset = compute_next_devid_offset(&its->device_list, dev); val = (1ULL << KVM_ITS_DTE_VALID_SHIFT | ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) | (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); return vgic_write_guest_lock(kvm, ptr, &val, dte_esz); } /** * vgic_its_restore_dte - restore a device table entry * * @its: its handle * @id: device id the DTE corresponds to * @ptr: kernel VA where the 8 byte DTE is located * @opaque: unused * * Return: < 0 on error, 0 if the dte is the last one, id offset to the * next dte otherwise */ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, void *ptr, void *opaque) { struct its_device *dev; u64 baser = its->baser_device_table; gpa_t itt_addr; u8 num_eventid_bits; u64 entry = *(u64 *)ptr; bool valid; u32 offset; int ret; entry = le64_to_cpu(entry); valid = entry >> KVM_ITS_DTE_VALID_SHIFT; num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1; itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK) >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8; if (!valid) return 1; /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; if (!vgic_its_check_id(its, baser, id, NULL)) return -EINVAL; dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); if (IS_ERR(dev)) return PTR_ERR(dev); ret = vgic_its_restore_itt(its, dev); if (ret) { vgic_its_free_device(its->dev->kvm, its, dev); return ret; } return offset; } static int vgic_its_device_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_device *deva = container_of(a, struct its_device, dev_list); struct its_device *devb = container_of(b, struct its_device, dev_list); if (deva->device_id < devb->device_id) return -1; else return 1; } /* * vgic_its_save_device_tables - Save the device table and all ITT * into guest RAM * * L1/L2 handling is hidden by vgic_its_check_id() helper which directly * returns the GPA of the device entry */ static int vgic_its_save_device_tables(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_device_table; struct its_device *dev; int dte_esz = abi->dte_esz; if (!(baser & GITS_BASER_VALID)) return 0; list_sort(NULL, &its->device_list, vgic_its_device_cmp); list_for_each_entry(dev, &its->device_list, dev_list) { int ret; gpa_t eaddr; if (!vgic_its_check_id(its, baser, dev->device_id, &eaddr)) return -EINVAL; ret = vgic_its_save_itt(its, dev); if (ret) return ret; ret = vgic_its_save_dte(its, dev, eaddr, dte_esz); if (ret) return ret; } return 0; } /** * handle_l1_dte - callback used for L1 device table entries (2 stage case) * * @its: its handle * @id: index of the entry in the L1 table * @addr: kernel VA * @opaque: unused * * L1 table entries are scanned by steps of 1 entry * Return < 0 if error, 0 if last dte was found when scanning the L2 * table, +1 otherwise (meaning next L1 entry must be scanned) */ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, void *opaque) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int l2_start_id = id * (SZ_64K / abi->dte_esz); u64 entry = *(u64 *)addr; int dte_esz = abi->dte_esz; gpa_t gpa; int ret; entry = le64_to_cpu(entry); if (!(entry & KVM_ITS_L1E_VALID_MASK)) return 1; gpa = entry & KVM_ITS_L1E_ADDR_MASK; ret = scan_its_table(its, gpa, SZ_64K, dte_esz, l2_start_id, vgic_its_restore_dte, NULL); return ret; } /* * vgic_its_restore_device_tables - Restore the device table and all ITT * from guest RAM to internal data structs */ static int vgic_its_restore_device_tables(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_device_table; int l1_esz, ret; int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; gpa_t l1_gpa; if (!(baser & GITS_BASER_VALID)) return 0; l1_gpa = GITS_BASER_ADDR_48_to_52(baser); if (baser & GITS_BASER_INDIRECT) { l1_esz = GITS_LVL1_ENTRY_SIZE; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, handle_l1_dte, NULL); } else { l1_esz = abi->dte_esz; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, vgic_its_restore_dte, NULL); } /* scan_its_table returns +1 if all entries are invalid */ if (ret > 0) ret = 0; if (ret < 0) vgic_its_free_device_list(its->dev->kvm, its); return ret; } static int vgic_its_save_cte(struct vgic_its *its, struct its_collection *collection, gpa_t gpa, int esz) { u64 val; val = (1ULL << KVM_ITS_CTE_VALID_SHIFT | ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz); } /* * Restore a collection entry into the ITS collection table. * Return +1 on success, 0 if the entry was invalid (which should be * interpreted as end-of-table), and a negative error value for generic errors. */ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) { struct its_collection *collection; struct kvm *kvm = its->dev->kvm; u32 target_addr, coll_id; u64 val; int ret; BUG_ON(esz > sizeof(val)); ret = kvm_read_guest_lock(kvm, gpa, &val, esz); if (ret) return ret; val = le64_to_cpu(val); if (!(val & KVM_ITS_CTE_VALID_MASK)) return 0; target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); coll_id = val & KVM_ITS_CTE_ICID_MASK; if (target_addr != COLLECTION_NOT_MAPPED && !kvm_get_vcpu_by_id(kvm, target_addr)) return -EINVAL; collection = find_collection(its, coll_id); if (collection) return -EEXIST; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return -EINVAL; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = target_addr; return 1; } /* * vgic_its_save_collection_table - Save the collection table into * guest RAM */ static int vgic_its_save_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); struct its_collection *collection; u64 val; size_t max_size, filled = 0; int ret, cte_esz = abi->cte_esz; if (!(baser & GITS_BASER_VALID)) return 0; max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; list_for_each_entry(collection, &its->collection_list, coll_list) { ret = vgic_its_save_cte(its, collection, gpa, cte_esz); if (ret) return ret; gpa += cte_esz; filled += cte_esz; } if (filled == max_size) return 0; /* * table is not fully filled, add a last dummy element * with valid bit unset */ val = 0; BUG_ON(cte_esz > sizeof(val)); ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } /* * vgic_its_restore_collection_table - reads the collection table * in guest memory and restores the ITS internal state. Requires the * BASER registers to be restored before. */ static int vgic_its_restore_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; int cte_esz = abi->cte_esz; size_t max_size, read = 0; gpa_t gpa; int ret; if (!(baser & GITS_BASER_VALID)) return 0; gpa = GITS_BASER_ADDR_48_to_52(baser); max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; while (read < max_size) { ret = vgic_its_restore_cte(its, gpa, cte_esz); if (ret <= 0) break; gpa += cte_esz; read += cte_esz; } if (ret > 0) return 0; if (ret < 0) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } /* * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM * according to v0 ABI */ static int vgic_its_save_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_save_device_tables(its); if (ret) return ret; return vgic_its_save_collection_table(its); } /* * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM * to internal data structs according to V0 ABI * */ static int vgic_its_restore_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_restore_collection_table(its); if (ret) return ret; ret = vgic_its_restore_device_tables(its); if (ret) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } static int vgic_its_commit_v0(struct vgic_its *its) { const struct vgic_its_abi *abi; abi = vgic_its_get_abi(its); its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); return 0; } static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its) { /* We need to keep the ABI specific field values */ its->baser_coll_table &= ~GITS_BASER_VALID; its->baser_device_table &= ~GITS_BASER_VALID; its->cbaser = 0; its->creadr = 0; its->cwriter = 0; its->enabled = 0; vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); } static int vgic_its_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_ITS_ADDR_TYPE: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_ITS_CTRL_RESET: return 0; case KVM_DEV_ARM_ITS_SAVE_TABLES: return 0; case KVM_DEV_ARM_ITS_RESTORE_TABLES: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: return vgic_its_has_attr_regs(dev, attr); } return -ENXIO; } static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ return 0; mutex_lock(&kvm->lock); if (!lock_all_vcpus(kvm)) { mutex_unlock(&kvm->lock); return -EBUSY; } mutex_lock(&kvm->arch.config_lock); mutex_lock(&its->its_lock); switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: ret = abi->save_tables(its); break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); break; } mutex_unlock(&its->its_lock); mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); mutex_unlock(&kvm->lock); return ret; } /* * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory * without the running VCPU when dirty ring is enabled. * * The running VCPU is required to track dirty guest pages when dirty ring * is enabled. Otherwise, the backup bitmap should be used to track the * dirty guest pages. When vgic/its tables are being saved, the backup * bitmap is used to track the dirty guest pages due to the missed running * VCPU in the period. */ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { struct vgic_its *its = dev->private; int ret; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; u64 addr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; ret = vgic_check_iorange(dev->kvm, its->vgic_its_base, addr, SZ_64K, KVM_VGIC_V3_ITS_SIZE); if (ret) return ret; return vgic_register_its_iodev(dev->kvm, its, addr); } case KVM_DEV_ARM_VGIC_GRP_CTRL: return vgic_its_ctrl(dev->kvm, its, attr->attr); case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; if (get_user(reg, uaddr)) return -EFAULT; return vgic_its_attr_regs_access(dev, attr, ®, true); } } return -ENXIO; } static int vgic_its_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { struct vgic_its *its = dev->private; u64 addr = its->vgic_its_base; u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_to_user(uaddr, &addr, sizeof(addr))) return -EFAULT; break; } case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; int ret; ret = vgic_its_attr_regs_access(dev, attr, ®, false); if (ret) return ret; return put_user(reg, uaddr); } default: return -ENXIO; } return 0; } static struct kvm_device_ops kvm_arm_vgic_its_ops = { .name = "kvm-arm-vgic-its", .create = vgic_its_create, .destroy = vgic_its_destroy, .set_attr = vgic_its_set_attr, .get_attr = vgic_its_get_attr, .has_attr = vgic_its_has_attr, }; int kvm_vgic_register_its_device(void) { return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } |
| 321 348 78 77 77 77 77 2 45 107 176 153 176 176 268 108 162 108 231 52 229 231 231 231 162 231 37 134 254 255 321 321 348 348 348 347 348 348 348 348 348 115 51 51 24 14 76 4 4 133 108 3 100 58 107 230 76 24 24 14 14 14 14 21 24 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H #include <asm/bug.h> #include <asm/proc-fns.h> #include <asm/memory.h> #include <asm/mte.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable-prot.h> #include <asm/tlbflush.h> /* * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) #if VA_BITS == VA_BITS_MIN #define VMALLOC_END (VMEMMAP_START - SZ_8M) #else #define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) #define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) #endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #ifndef __ASSEMBLY__ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE /* Set stride and tlb_level in flush_*_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2) #define flush_pud_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page * fault on one CPU which has been handled concurrently by another CPU * does not need to perform additional invalidation. */ #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) /* * Macros to convert between a physical address and its placement in a * page table entry, taking care of 52-bit addresses. */ #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif #define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) \ __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) #define __pte_clear(mm, addr, ptep) \ __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ #define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) #define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_tagged(pte) ((pte_val(pte) & PTE_ATTRINDX_MASK) == \ PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pte_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pmd_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_present_invalid(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. */ #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) /* * Returns true if the pte is valid and has the contiguous bit set. */ #define pte_valid_cont(pte) (pte_valid(pte) && pte_cont(pte)) /* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. * Note that we can't make any assumptions based on the state of the access * flag, since __ptep_clear_flush_young() elides a DSB when invalidating the * TLB. */ #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ #define pte_access_permitted(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ (pte_access_permitted(pud_pte(pud), (write))) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) &= ~pgprot_val(prot); return pte; } static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) |= pgprot_val(prot); return pte; } static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) &= ~pgprot_val(prot); return pmd; } static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) |= pgprot_val(prot); return pmd; } static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkclean(pte_t pte) { pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkdirty(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); if (pte_write(pte)) pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_wrprotect(pte_t pte) { /* * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline pte_t pte_mkcont(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_CONT)); return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mkpresent(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } static inline pte_t pte_mkinvalid(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); return pte; } static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } static inline pte_t pte_mkdevmap(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_UFFD_WP); } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void __set_pte(pte_t *ptep, pte_t pte) { __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ if (pte_valid_not_user(pte)) { dsb(ishst); isb(); } } static inline pte_t __ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } extern void __sync_icache_dcache(pte_t pteval); bool pgattr_change_is_safe(u64 old, u64 new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management * (PTE_WRITE == PTE_DBM): * * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) * 0 0 | 1 0 0 * 0 1 | 1 1 0 * 1 0 | 1 0 1 * 1 1 | 0 1 x * * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, pte_t pte) { pte_t old_pte; if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; old_pte = __ptep_get(ptep); if (!pte_valid(old_pte) || !pte_valid(pte)) return; if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1) return; /* * Check for potential race with hardware updates of the pte * (__ptep_set_access_flags safely changes valid ptes without going * through an invalid entry). */ VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)), "%s: unsafe attribute change: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); } static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although * pte_access_permitted() returns false for exec only mappings, they * don't expose tags (instruction fetches don't check tags). */ if (system_supports_mte() && pte_access_permitted(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } /* * Select all bits except the pfn */ static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); } #define pte_advance_pfn pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); } static inline void __set_ptes(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); __sync_cache_and_tags(pte, nr); for (;;) { __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_advance_pfn(pte, 1); } } /* * Huge pte definitions. */ #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* * Hugetlb definitions. */ #define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) static inline pte_t pgd_pte(pgd_t pgd) { return __pte(pgd_val(pgd)); } static inline pte_t p4d_pte(p4d_t p4d) { return __pte(p4d_val(p4d)); } static inline pte_t pud_pte(pud_t pud) { return __pte(pud_val(pud)); } static inline pud_t pte_pud(pte_t pte) { return __pud(pte_val(pte)); } static inline pmd_t pud_pmd(pud_t pud) { return __pmd(pud_val(pud)); } static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); } static inline pmd_t pte_pmd(pte_t pte) { return __pmd(pte_val(pte)); } static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); } static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & PTE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } static inline int pte_swp_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_SWP_UFFD_WP); } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { /* * pte_present_invalid() tells us that the pte is invalid from HW * perspective but present from SW perspective, so the fields are to be * interpretted as per the HW layout. The second 2 checks are the unique * encoding that we use for PROT_NONE. It is insufficient to only use * the first check because we share the same encoding scheme with pmds * which support pmd_mkinvalid(), so can be present-invalid without * being PROT_NONE. */ return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); } static inline int pmd_protnone(pmd_t pmd) { return pte_protnone(pmd_pte(pmd)); } #endif #define pmd_present(pmd) pte_present(pmd_pte(pmd)) /* * THP definitions. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) #define pmd_user(pmd) pte_user(pmd_pte(pmd)) #define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) #define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) #define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) #define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) #define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) #define pmd_swp_clear_uffd_wp(pmd) \ pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) #endif static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); } #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pud_young(pud) pte_young(pud_pte(pud)) #define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) #define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) static inline void __set_pte_at(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { __sync_cache_and_tags(pte, nr); __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), PMD_SIZE >> PAGE_SHIFT); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), PUD_SIZE >> PAGE_SHIFT); } #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) #define __pgd_to_phys(pgd) __pte_to_phys(pgd_pte(pgd)) #define __phys_to_pgd_val(phys) __phys_to_pte_val(phys) #define __pgprot_modify(prot,mask,bits) \ __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_device(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define pgprot_tagged(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pgprot_mhp pgprot_tagged /* * DMA allocations for non-coherent devices use what the Arm architecture calls * "Normal non-cacheable" memory, which permits speculation, unaligned accesses * and merging of writes. This is different from "Device-nGnR[nE]" memory which * is intended for MMIO and thus forbids speculation, preserves access size, * requires strict alignment and can also force write responses to come from the * endpoint. */ #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) #define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) #define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) #define pud_table(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_TABLE) #endif extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; extern pgd_t swapper_pg_dir[]; extern pgd_t idmap_pg_dir[]; extern pgd_t tramp_pg_dir[]; extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); static inline bool in_swapper_pgdir(void *addr) { return ((unsigned long)addr & PAGE_MASK) == ((unsigned long)swapper_pg_dir & PAGE_MASK); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { #ifdef __PAGETABLE_PMD_FOLDED if (in_swapper_pgdir(pmdp)) { set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd))); return; } #endif /* __PAGETABLE_PMD_FOLDED */ WRITE_ONCE(*pmdp, pmd); if (pmd_valid(pmd)) { dsb(ishst); isb(); } } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } static inline phys_addr_t pmd_page_paddr(pmd_t pmd) { return __pmd_to_phys(pmd); } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_page_paddr(pmd)); } /* Find an entry in the third-level page table. */ #define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) #define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) #define pte_clear_fixmap() clear_fixmap(FIX_PTE) #define pmd_page(pmd) phys_to_page(__pmd_to_phys(pmd)) /* use ONLY for statically allocated translation tables */ #define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ #define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) #if CONFIG_PGTABLE_LEVELS > 2 #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) #ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #else #define pud_leaf(pud) false #endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline bool pgtable_l4_enabled(void); static inline void set_pud(pud_t *pudp, pud_t pud) { if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } WRITE_ONCE(*pudp, pud); if (pud_valid(pud)) { dsb(ishst); isb(); } } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); } static inline phys_addr_t pud_page_paddr(pud_t pud) { return __pud_to_phys(pud); } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_page_paddr(pud)); } /* Find an entry in the second-level page table. */ #define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) #define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) #define pmd_clear_fixmap() clear_fixmap(FIX_PMD) #define pud_page(pud) phys_to_page(__pud_to_phys(pud)) /* use ONLY for statically allocated translation tables */ #define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr)))) #else #define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL #define pmd_set_fixmap_offset(pudp, addr) ((pmd_t *)pudp) #define pmd_clear_fixmap() #define pmd_offset_kimg(dir,addr) ((pmd_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static __always_inline bool pgtable_l4_enabled(void) { if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) return true; if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_pud_folded(const struct mm_struct *mm) { return !pgtable_l4_enabled(); } #define mm_pud_folded mm_pud_folded #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) #define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { if (in_swapper_pgdir(p4dp)) { set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d))); return; } WRITE_ONCE(*p4dp, p4d); dsb(ishst); isb(); } static inline void p4d_clear(p4d_t *p4dp) { if (pgtable_l4_enabled()) set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) { return __p4d_to_phys(p4d); } #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) { return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) { BUG_ON(!pgtable_l4_enabled()); return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); } static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); } #define pud_offset_lockless pud_offset_lockless static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) { return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); } #define pud_offset pud_offset static inline pud_t *pud_set_fixmap(unsigned long addr) { if (!pgtable_l4_enabled()) return NULL; return (pud_t *)set_fixmap_offset(FIX_PUD, addr); } static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return pud_set_fixmap(pud_offset_phys(p4dp, addr)); } static inline void pud_clear_fixmap(void) { if (pgtable_l4_enabled()) clear_fixmap(FIX_PUD); } /* use ONLY for statically allocated translation tables */ static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); } #define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else static inline bool pgtable_l4_enabled(void) { return false; } #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL #define pud_set_fixmap_offset(pgdp, addr) ((pud_t *)pgdp) #define pud_clear_fixmap() #define pud_offset_kimg(dir,addr) ((pud_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static __always_inline bool pgtable_l5_enabled(void) { if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_p4d_folded(const struct mm_struct *mm) { return !pgtable_l5_enabled(); } #define mm_p4d_folded mm_p4d_folded #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) #define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { if (in_swapper_pgdir(pgdp)) { set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); return; } WRITE_ONCE(*pgdp, pgd); dsb(ishst); isb(); } static inline void pgd_clear(pgd_t *pgdp) { if (pgtable_l5_enabled()) set_pgd(pgdp, __pgd(0)); } static inline phys_addr_t pgd_page_paddr(pgd_t pgd) { return __pgd_to_phys(pgd); } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) { return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); } static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) { BUG_ON(!pgtable_l5_enabled()); return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); } static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); } #define p4d_offset_lockless p4d_offset_lockless static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) { return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); } static inline p4d_t *p4d_set_fixmap(unsigned long addr) { if (!pgtable_l5_enabled()) return NULL; return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); } static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); } static inline void p4d_clear_fixmap(void) { if (pgtable_l5_enabled()) clear_fixmap(FIX_P4D); } /* use ONLY for statically allocated translation tables */ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); } #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) #else static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ #define p4d_set_fixmap(addr) NULL #define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) #define p4d_clear_fixmap() #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) static inline p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { /* * With runtime folding of the pud, pud_offset_lockless() passes * the 'pgd_t *' we return here to p4d_to_folded_pud(), which * will offset the pointer assuming that it points into * a page-table page. However, the fast GUP path passes us a * pgd_t allocated on the stack and so we must use the original * pointer in 'pgdp' to construct the p4d pointer instead of * using the generic p4d_offset_lockless() implementation. * * Note: reusing the original pointer means that we may * dereference the same (live) page-table entry multiple times. * This is safe because it is still only loaded once in the * context of each level and the CPU guarantees same-address * read-after-read ordering. */ return p4d_offset(pgdp, addr); } #define p4d_offset_lockless p4d_offset_lockless_folded #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) #define pgd_set_fixmap(addr) ((pgd_t *)set_fixmap_offset(FIX_PGD, addr)) #define pgd_clear_fixmap() clear_fixmap(FIX_PGD) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* * Normal and Normal-Tagged are two different memory types and indices * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | PTE_GP | PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); /* * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware * dirtiness again. */ if (pte_sw_dirty(pte)) pte = pte_mkdirty(pte); return pte; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } extern int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif /* * Atomic pte/pmd modifications. */ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; pte = __ptep_get(ptep); do { old_pte = pte; pte = pte_mkold(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); return pte_young(pte); } static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* * We can elide the trailing DSB here since the worst that can * happen is that a CPU continues to use the young entry in its * TLB and we mistakenly reclaim the associated page. The * window for such an event is bounded by the next * context-switch, which provides a DSB to complete the TLB * invalidation. */ flush_tlb_page_nosync(vma, address); } return young; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); page_table_check_pte_clear(mm, pte); return pte; } static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { __ptep_get_and_clear(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = __ptep_get_and_clear(mm, addr, ptep); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { pte_t old_pte; do { old_pte = pte; pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } /* * __ptep_set_wrprotect - mark read-only while trasferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { ___ptep_set_wrprotect(mm, address, ptep, __ptep_get(ptep)); } static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, pte_t *ptep, unsigned int nr) { unsigned int i; for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++) __ptep_set_wrprotect(mm, address, ptep); } static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, cydp_t flags) { pte_t old_pte; do { old_pte = pte; if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { pte = __ptep_get(ptep); if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) __set_pte(ptep, pte_mkclean(pte_mkold(pte))); else __clear_young_dirty_pte(vma, addr, ptep, pte, flags); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { __ptep_set_wrprotect(mm, address, (pte_t *)pmdp); } #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) * bits 2: remember PG_anon_exclusive * bit 3: remember uffd-wp state * bits 6-10: swap type * bit 11: PTE_PRESENT_INVALID (must be zero) * bits 12-61: swap offset */ #define __SWP_TYPE_SHIFT 6 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT 12 #define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) #define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(swp) __pmd((swp).val) #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ /* * Ensure that there are not more swap files than can be encoded in the kernel * PTEs. */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { if (system_supports_mte()) mte_invalidate_tags(type, offset); } static inline void arch_swap_invalidate_area(int type) { if (system_supports_mte()) mte_invalidate_tags_area(type); } #define __HAVE_ARCH_SWAP_RESTORE extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ /* * On AArch64, the cache coherency is handled via the __set_ptes() function. */ static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * We don't do anything here, so there's a very small chance of * us retaking a user fault which we just fixed up. The alternative * is doing a dsb(ishst), but that penalises the fastpath. */ } #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif /* * On arm64 without hardware Access Flag, copying from user will fail because * the pte is old and cannot be marked young. So we always end up with zeroed * page after fork() + CoW for pfn mappings. We don't always have a * hardware-managed access flag on arm64. */ #define arch_has_hw_pte_young cpu_has_hw_af /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION #define ptep_modify_prot_start ptep_modify_prot_start extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define ptep_modify_prot_commit ptep_modify_prot_commit extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); #ifdef CONFIG_ARM64_CONTPTE /* * The contpte APIs are used to transparently manage the contiguous bit in ptes * where it is possible and makes sense to do so. The PTE_CONT bit is considered * a private implementation detail of the public ptep API (see below). */ extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte); extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep); extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr); extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * Only bother trying if both the virtual and physical addresses are * aligned and correspond to the last entry in a contig range. The core * code mostly modifies ranges from low to high, so this is the likely * the last modification in the contig range, so a good time to fold. * We can't fold special mappings, because there is no associated folio. */ const unsigned long contmask = CONT_PTES - 1; bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask; if (unlikely(valign)) { bool palign = (pte_pfn(pte) & contmask) == contmask; if (unlikely(palign && pte_valid(pte) && !pte_cont(pte) && !pte_special(pte))) __contpte_try_fold(mm, addr, ptep, pte); } } static __always_inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (unlikely(pte_valid_cont(pte))) __contpte_try_unfold(mm, addr, ptep, pte); } #define pte_batch_hint pte_batch_hint static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { if (!pte_valid_cont(pte)) return 1; return CONT_PTES - (((unsigned long)ptep >> 3) & (CONT_PTES - 1)); } /* * The below functions constitute the public API that arm64 presents to the * core-mm to manipulate PTE entries within their page tables (or at least this * is the subset of the API that arm64 needs to implement). These public * versions will automatically and transparently apply the contiguous bit where * it makes sense to do so. Therefore any users that are contig-aware (e.g. * hugetlb, kernel mapper) should NOT use these APIs, but instead use the * private versions, which are prefixed with double underscore. All of these * APIs except for ptep_get_lockless() are expected to be called with the PTL * held. Although the contiguous bit is considered private to the * implementation, it is deliberately allowed to leak through the getters (e.g. * ptep_get()), back to core code. This is required so that pte_leaf_size() can * provide an accurate size for perf_get_pgtable_size(). But this leakage means * its possible a pte will be passed to a setter with the contiguous bit set, so * we explicitly clear the contiguous bit in those cases to prevent accidentally * setting it in the pgtable. */ #define ptep_get ptep_get static inline pte_t ptep_get(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get(ptep, pte); } #define ptep_get_lockless ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get_lockless(ptep); } static inline void set_pte(pte_t *ptep, pte_t pte) { /* * We don't have the mm or vaddr so cannot unfold contig entries (since * it requires tlb maintenance). set_pte() is not used in core code, so * this should never even be called. Regardless do our best to service * any call and emit a warning if there is any attempt to set a pte on * top of an existing contig range. */ pte_t orig_pte = __ptep_get(ptep); WARN_ON_ONCE(pte_valid_cont(orig_pte)); __set_pte(ptep, pte_mknoncont(pte)); } #define set_ptes set_ptes static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { pte = pte_mknoncont(pte); if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __set_ptes(mm, addr, ptep, pte, 1); contpte_try_fold(mm, addr, ptep, pte); } else { contpte_set_ptes(mm, addr, ptep, pte, nr); } } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __pte_clear(mm, addr, ptep); } #define clear_full_ptes clear_full_ptes static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __clear_full_ptes(mm, addr, ptep, nr, full); } else { contpte_clear_full_ptes(mm, addr, ptep, nr, full); } } #define get_and_clear_full_ptes get_and_clear_full_ptes static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte; if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } else { pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full); } return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); return __ptep_get_and_clear(mm, addr, ptep); } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); return contpte_ptep_test_and_clear_young(vma, addr, ptep); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); return contpte_ptep_clear_flush_young(vma, addr, ptep); } #define wrprotect_ptes wrprotect_ptes static __always_inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1)) { /* * Optimization: wrprotect_ptes() can only be called for present * ptes so we only need to check contig bit as condition for * unfold, and we can remove the contig bit from the pte we read * to avoid re-reading. This speeds up fork() which is sensitive * for order-0 folios. Equivalent to contpte_try_unfold(). */ pte_t orig_pte = __ptep_get(ptep); if (unlikely(pte_cont(orig_pte))) { __contpte_try_unfold(mm, addr, ptep, orig_pte); orig_pte = pte_mknoncont(orig_pte); } ___ptep_set_wrprotect(mm, addr, ptep, orig_pte); } else { contpte_wrprotect_ptes(mm, addr, ptep, nr); } } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { wrprotect_ptes(mm, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS static inline int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { pte_t orig_pte = __ptep_get(ptep); entry = pte_mknoncont(entry); if (likely(!pte_valid_cont(orig_pte))) return __ptep_set_access_flags(vma, addr, ptep, entry, dirty); return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } #define clear_young_dirty_ptes clear_young_dirty_ptes static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); else contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); } #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get #define set_pte __set_pte #define set_ptes __set_ptes #define pte_clear __pte_clear #define clear_full_ptes __clear_full_ptes #define get_and_clear_full_ptes __get_and_clear_full_ptes #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define ptep_get_and_clear __ptep_get_and_clear #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young __ptep_test_and_clear_young #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young __ptep_clear_flush_young #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define ptep_set_wrprotect __ptep_set_wrprotect #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags #define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ |
| 159 156 26 8 8 8 7 7 7 26 7 26 7 26 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2020 Google LLC * Author: Will Deacon <will@kernel.org> */ #ifndef __ARM64_KVM_PGTABLE_H__ #define __ARM64_KVM_PGTABLE_H__ #include <linux/bits.h> #include <linux/kvm_host.h> #include <linux/types.h> #define KVM_PGTABLE_FIRST_LEVEL -1 #define KVM_PGTABLE_LAST_LEVEL 3 /* * The largest supported block sizes for KVM (no 52-bit PA support): * - 4K (level 1): 1GB * - 16K (level 2): 32MB * - 64K (level 2): 512MB */ #ifdef CONFIG_ARM64_4K_PAGES #define KVM_PGTABLE_MIN_BLOCK_LEVEL 1 #else #define KVM_PGTABLE_MIN_BLOCK_LEVEL 2 #endif #define kvm_lpa2_is_enabled() system_supports_lpa2() static inline u64 kvm_get_parange_max(void) { if (kvm_lpa2_is_enabled() || (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16)) return ID_AA64MMFR0_EL1_PARANGE_52; else return ID_AA64MMFR0_EL1_PARANGE_48; } static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange_max = kvm_get_parange_max(); u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); if (parange > parange_max) parange = parange_max; return parange; } typedef u64 kvm_pte_t; #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) #define KVM_PTE_ADDR_51_48 GENMASK(15, 12) #define KVM_PTE_ADDR_MASK_LPA2 GENMASK(49, PAGE_SHIFT) #define KVM_PTE_ADDR_51_50_LPA2 GENMASK(9, 8) #define KVM_PHYS_INVALID (-1ULL) static inline bool kvm_pte_valid(kvm_pte_t pte) { return pte & KVM_PTE_VALID; } static inline u64 kvm_pte_to_phys(kvm_pte_t pte) { u64 pa; if (kvm_lpa2_is_enabled()) { pa = pte & KVM_PTE_ADDR_MASK_LPA2; pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50; } else { pa = pte & KVM_PTE_ADDR_MASK; if (PAGE_SHIFT == 16) pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48; } return pa; } static inline kvm_pte_t kvm_phys_to_pte(u64 pa) { kvm_pte_t pte; if (kvm_lpa2_is_enabled()) { pte = pa & KVM_PTE_ADDR_MASK_LPA2; pa &= GENMASK(51, 50); pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50); } else { pte = pa & KVM_PTE_ADDR_MASK; if (PAGE_SHIFT == 16) { pa &= GENMASK(51, 48); pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48); } } return pte; } static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte) { return __phys_to_pfn(kvm_pte_to_phys(pte)); } static inline u64 kvm_granule_shift(s8 level) { /* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */ return ARM64_HW_PGTABLE_LEVEL_SHIFT(level); } static inline u64 kvm_granule_size(s8 level) { return BIT(kvm_granule_shift(level)); } static inline bool kvm_level_supports_block_mapping(s8 level) { return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } static inline u32 kvm_supported_block_sizes(void) { s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL; u32 r = 0; for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) r |= BIT(kvm_granule_shift(level)); return r; } static inline bool kvm_is_block_size_supported(u64 size) { bool is_power_of_two = IS_ALIGNED(size, size); return is_power_of_two && (size & kvm_supported_block_sizes()); } /** * struct kvm_pgtable_mm_ops - Memory management callbacks. * @zalloc_page: Allocate a single zeroed memory page. * The @arg parameter can be used by the walker * to pass a memcache. The initial refcount of * the page is 1. * @zalloc_pages_exact: Allocate an exact number of zeroed memory pages. * The @size parameter is in bytes, and is rounded * up to the next page boundary. The resulting * allocation is physically contiguous. * @free_pages_exact: Free an exact number of memory pages previously * allocated by zalloc_pages_exact. * @free_unlinked_table: Free an unlinked paging structure by unlinking and * dropping references. * @get_page: Increment the refcount on a page. * @put_page: Decrement the refcount on a page. When the * refcount reaches 0 the page is automatically * freed. * @page_count: Return the refcount of a page. * @phys_to_virt: Convert a physical address into a virtual * address mapped in the current context. * @virt_to_phys: Convert a virtual address mapped in the current * context into a physical address. * @dcache_clean_inval_poc: Clean and invalidate the data cache to the PoC * for the specified memory address range. * @icache_inval_pou: Invalidate the instruction cache to the PoU * for the specified memory address range. */ struct kvm_pgtable_mm_ops { void* (*zalloc_page)(void *arg); void* (*zalloc_pages_exact)(size_t size); void (*free_pages_exact)(void *addr, size_t size); void (*free_unlinked_table)(void *addr, s8 level); void (*get_page)(void *addr); void (*put_page)(void *addr); int (*page_count)(void *addr); void* (*phys_to_virt)(phys_addr_t phys); phys_addr_t (*virt_to_phys)(void *addr); void (*dcache_clean_inval_poc)(void *addr, size_t size); void (*icache_inval_pou)(void *addr, size_t size); }; /** * enum kvm_pgtable_stage2_flags - Stage-2 page-table flags. * @KVM_PGTABLE_S2_NOFWB: Don't enforce Normal-WB even if the CPUs have * ARM64_HAS_STAGE2_FWB. * @KVM_PGTABLE_S2_IDMAP: Only use identity mappings. */ enum kvm_pgtable_stage2_flags { KVM_PGTABLE_S2_NOFWB = BIT(0), KVM_PGTABLE_S2_IDMAP = BIT(1), }; /** * enum kvm_pgtable_prot - Page-table permissions and attributes. * @KVM_PGTABLE_PROT_X: Execute permission. * @KVM_PGTABLE_PROT_W: Write permission. * @KVM_PGTABLE_PROT_R: Read permission. * @KVM_PGTABLE_PROT_DEVICE: Device attributes. * @KVM_PGTABLE_PROT_NORMAL_NC: Normal noncacheable attributes. * @KVM_PGTABLE_PROT_SW0: Software bit 0. * @KVM_PGTABLE_PROT_SW1: Software bit 1. * @KVM_PGTABLE_PROT_SW2: Software bit 2. * @KVM_PGTABLE_PROT_SW3: Software bit 3. */ enum kvm_pgtable_prot { KVM_PGTABLE_PROT_X = BIT(0), KVM_PGTABLE_PROT_W = BIT(1), KVM_PGTABLE_PROT_R = BIT(2), KVM_PGTABLE_PROT_DEVICE = BIT(3), KVM_PGTABLE_PROT_NORMAL_NC = BIT(4), KVM_PGTABLE_PROT_SW0 = BIT(55), KVM_PGTABLE_PROT_SW1 = BIT(56), KVM_PGTABLE_PROT_SW2 = BIT(57), KVM_PGTABLE_PROT_SW3 = BIT(58), }; #define KVM_PGTABLE_PROT_RW (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W) #define KVM_PGTABLE_PROT_RWX (KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X) #define PKVM_HOST_MEM_PROT KVM_PGTABLE_PROT_RWX #define PKVM_HOST_MMIO_PROT KVM_PGTABLE_PROT_RW #define PAGE_HYP KVM_PGTABLE_PROT_RW #define PAGE_HYP_EXEC (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X) #define PAGE_HYP_RO (KVM_PGTABLE_PROT_R) #define PAGE_HYP_DEVICE (PAGE_HYP | KVM_PGTABLE_PROT_DEVICE) typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, enum kvm_pgtable_prot prot); /** * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk. * @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid * entries. * @KVM_PGTABLE_WALK_TABLE_PRE: Visit table entries before their * children. * @KVM_PGTABLE_WALK_TABLE_POST: Visit table entries after their * children. * @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared * with other software walkers. * @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was * invoked from a fault handler. * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI: Visit and update table entries * without Break-before-make's * TLB invalidation. * @KVM_PGTABLE_WALK_SKIP_CMO: Visit and update table entries * without Cache maintenance * operations required. */ enum kvm_pgtable_walk_flags { KVM_PGTABLE_WALK_LEAF = BIT(0), KVM_PGTABLE_WALK_TABLE_PRE = BIT(1), KVM_PGTABLE_WALK_TABLE_POST = BIT(2), KVM_PGTABLE_WALK_SHARED = BIT(3), KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4), KVM_PGTABLE_WALK_SKIP_BBM_TLBI = BIT(5), KVM_PGTABLE_WALK_SKIP_CMO = BIT(6), }; struct kvm_pgtable_visit_ctx { kvm_pte_t *ptep; kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; u64 start; u64 addr; u64 end; s8 level; enum kvm_pgtable_walk_flags flags; }; typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit); static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx) { return ctx->flags & KVM_PGTABLE_WALK_SHARED; } /** * struct kvm_pgtable_walker - Hook into a page-table walk. * @cb: Callback function to invoke during the walk. * @arg: Argument passed to the callback function. * @flags: Bitwise-OR of flags to identify the entry types on which to * invoke the callback function. */ struct kvm_pgtable_walker { const kvm_pgtable_visitor_fn_t cb; void * const arg; const enum kvm_pgtable_walk_flags flags; }; /* * RCU cannot be used in a non-kernel context such as the hyp. As such, page * table walkers used in hyp do not call into RCU and instead use other * synchronization mechanisms (such as a spinlock). */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) typedef kvm_pte_t *kvm_pteref_t; static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, kvm_pteref_t pteref) { return pteref; } static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { /* * Due to the lack of RCU (or a similar protection scheme), only * non-shared table walkers are allowed in the hypervisor. */ if (walker->flags & KVM_PGTABLE_WALK_SHARED) return -EPERM; return 0; } static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {} static inline bool kvm_pgtable_walk_lock_held(void) { return true; } #else typedef kvm_pte_t __rcu *kvm_pteref_t; static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, kvm_pteref_t pteref) { return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_lock(); return 0; } static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_unlock(); } static inline bool kvm_pgtable_walk_lock_held(void) { return rcu_read_lock_held(); } #endif /** * struct kvm_pgtable - KVM page-table. * @ia_bits: Maximum input address size, in bits. * @start_level: Level at which the page-table walk starts. * @pgd: Pointer to the first top-level entry of the page-table. * @mm_ops: Memory management callbacks. * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. * @flags: Stage-2 page-table flags. * @force_pte_cb: Function that returns true if page level mappings must * be used instead of block mappings. */ struct kvm_pgtable { u32 ia_bits; s8 start_level; kvm_pteref_t pgd; struct kvm_pgtable_mm_ops *mm_ops; /* Stage-2 only */ struct kvm_s2_mmu *mmu; enum kvm_pgtable_stage2_flags flags; kvm_pgtable_force_pte_cb_t force_pte_cb; }; /** * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table. * @pgt: Uninitialised page-table structure to initialise. * @va_bits: Maximum virtual address bits. * @mm_ops: Memory management callbacks. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops); /** * kvm_pgtable_hyp_destroy() - Destroy an unused hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * * The page-table is assumed to be unreachable by any hardware walkers prior * to freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt); /** * kvm_pgtable_hyp_map() - Install a mapping in a hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * @addr: Virtual address at which to place the mapping. * @size: Size of the mapping. * @phys: Physical address of the memory to map. * @prot: Permissions and attributes for the mapping. * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. Attempts to install a new mapping * for a virtual address that is already mapped will be rejected with an * error and a WARN(). * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot); /** * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * @addr: Virtual address from which to remove the mapping. * @size: Size of the mapping. * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * TLB invalidation is performed for each page-table entry cleared during the * unmapping operation and the reference count for the page-table page * containing the cleared entry is decremented, with unreferenced pages being * freed. The unmapping operation will stop early if it encounters either an * invalid page-table entry or a valid block mapping which maps beyond the range * being unmapped. * * Return: Number of bytes unmapped, which may be 0. */ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_get_vtcr() - Helper to construct VTCR_EL2 * @mmfr0: Sanitized value of SYS_ID_AA64MMFR0_EL1 register. * @mmfr1: Sanitized value of SYS_ID_AA64MMFR1_EL1 register. * @phys_shfit: Value to set in VTCR_EL2.T0SZ. * * The VTCR value is common across all the physical CPUs on the system. * We use system wide sanitised values to fill in different fields, * except for Hardware Management of Access Flags. HA Flag is set * unconditionally on all CPUs, as it is safe to run with or without * the feature and the bit is RES0 on CPUs that don't support it. * * Return: VTCR_EL2 value */ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); /** * kvm_pgtable_stage2_pgd_size() - Helper to compute size of a stage-2 PGD * @vtcr: Content of the VTCR register. * * Return: the size (in bytes) of the stage-2 PGD */ size_t kvm_pgtable_stage2_pgd_size(u64 vtcr); /** * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table. * @pgt: Uninitialised page-table structure to initialise. * @mmu: S2 MMU context for this S2 translation * @mm_ops: Memory management callbacks. * @flags: Stage-2 configuration flags. * @force_pte_cb: Function that returns true if page level mappings must * be used instead of block mappings. * * Return: 0 on success, negative error code on failure. */ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb); #define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \ __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL) /** * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * * The page-table is assumed to be unreachable by any hardware walkers prior * to freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); /** * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure. * @mm_ops: Memory management callbacks. * @pgtable: Unlinked stage-2 paging structure to be freed. * @level: Level of the stage-2 paging structure to be freed. * * The page-table is assumed to be unreachable by any hardware walkers prior to * freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level); /** * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @phys: Physical address of the memory to map. * @level: Starting level of the stage-2 paging structure to be created. * @prot: Permissions and attributes for the mapping. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @force_pte: Force mappings to PAGE_SIZE granularity. * * Returns an unlinked page-table tree. This new page-table tree is * not reachable (i.e., it is unlinked) from the root pgd and it's * therefore unreachableby the hardware page-table walker. No TLB * invalidation or CMOs are performed. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. * * Return: The fully populated (unlinked) stage-2 paging structure, or * an ERR_PTR(error) on failure. */ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte); /** * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address at which to place the mapping. * @size: Size of the mapping. * @phys: Physical address of the memory to map. * @prot: Permissions and attributes for the mapping. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @flags: Flags to control the page-table walk (ex. a shared walk) * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. * * Note that the update of a valid leaf PTE in this function will be aborted, * if it's trying to recreate the exact same mapping or only change the access * permissions. Instead, the vCPU will exit one more time from guest if still * needed and then go through the path of relaxing permissions. * * Note that this function will both coalesce existing table entries and split * existing block mappings, relying on page-faults to fault back areas outside * of the new mapping lazily. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags); /** * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to * track ownership. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Base intermediate physical address to annotate. * @size: Size of the annotated range. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @owner_id: Unique identifier for the owner of the page. * * By default, all page-tables are owned by identifier 0. This function can be * used to mark portions of the IPA space as owned by other entities. When a * stage 2 is used with identity-mappings, these annotations allow to use the * page-table data structure as a simple rmap. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc, u8 owner_id); /** * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to remove the mapping. * @size: Size of the mapping. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * TLB invalidation is performed for each page-table entry cleared during the * unmapping operation and the reference count for the page-table page * containing the cleared entry is decremented, with unreferenced pages being * freed. Unmapping a cacheable page will ensure that it is clean to the PoC if * FWB is not supported by the CPU. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_wrprotect() - Write-protect guest stage-2 address range * without TLB invalidation. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to write-protect, * @size: Size of the range. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * Note that it is the caller's responsibility to invalidate the TLB after * calling this function to ensure that the updated permissions are visible * to the CPUs. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * * The offset of @addr within a page is ignored. * * If there is a valid, leaf page-table entry used to translate @addr, then * set the access flag in that entry. * * Return: The old page-table entry prior to setting the flag, 0 on failure. */ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr); /** * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access * flag in a page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * @size: Size of the address range to visit. * @mkold: True if the access flag should be cleared. * * The offset of @addr within a page is ignored. * * Tests and conditionally clears the access flag for every valid, leaf * page-table entry used to translate the range [@addr, @addr + @size). * * Note that it is the caller's responsibility to invalidate the TLB after * calling this function to ensure that the updated permissions are visible * to the CPUs. * * Return: True if any of the visited PTEs had the access flag set. */ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold); /** * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a * page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * @prot: Additional permissions to grant for the mapping. * * The offset of @addr within a page is ignored. * * If there is a valid, leaf page-table entry used to translate @addr, then * relax the permissions in that entry according to the read, write and * execute permissions specified by @prot. No permissions are removed, and * TLB invalidation is performed after updating the entry. Software bits cannot * be set or cleared using kvm_pgtable_stage2_relax_perms(). * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot); /** * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point * of Coherency for guest stage-2 address * range. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to flush. * @size: Size of the range. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing * to PAGE_SIZE guest pages. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init(). * @addr: Intermediate physical address from which to split. * @size: Size of the range. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * * The function tries to split any level 1 or 2 entry that overlaps * with the input range (given by @addr and @size). * * Return: 0 on success, negative error code on failure. Note that * kvm_pgtable_stage2_split() is best effort: it tries to break as many * blocks in the input range as allowed by @mc_capacity. */ int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc); /** * kvm_pgtable_walk() - Walk a page-table. * @pgt: Page-table structure initialised by kvm_pgtable_*_init(). * @addr: Input address for the start of the walk. * @size: Size of the range to walk. * @walker: Walker callback description. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * The walker will walk the page-table entries corresponding to the input * address range specified, visiting entries according to the walker flags. * Invalid entries are treated as leaf entries. The visited page table entry is * reloaded after invoking the walker callback, allowing the walker to descend * into a newly installed table. * * Returning a negative error code from the walker callback function will * terminate the walk immediately with the same error code. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker); /** * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry * with its level. * @pgt: Page-table structure initialised by kvm_pgtable_*_init() * or a similar initialiser. * @addr: Input address for the start of the walk. * @ptep: Pointer to storage for the retrieved PTE. * @level: Pointer to storage for the level of the retrieved PTE. * * The offset of @addr within a page is ignored. * * The walker will walk the page-table entries corresponding to the input * address specified, retrieving the leaf corresponding to this address. * Invalid entries are treated as leaf entries. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, kvm_pte_t *ptep, s8 *level); /** * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a * stage-2 Page-Table Entry. * @pte: Page-table entry * * Return: protection attributes of the page-table entry in the enum * kvm_pgtable_prot format. */ enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte); /** * kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1 * Page-Table Entry. * @pte: Page-table entry * * Return: protection attributes of the page-table entry in the enum * kvm_pgtable_prot format. */ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte); /** * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries * * @mmu: Stage-2 KVM MMU struct * @addr: The base Intermediate physical address from which to invalidate * @size: Size of the range from the base to invalidate */ void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, size_t size); #endif /* __ARM64_KVM_PGTABLE_H__ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __bitmask(target_cpus, nr_cpumask_bits) __field(const char *, reason) ), TP_fast_assign( __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015 Linaro Ltd. * Author: Shannon Zhao <shannon.zhao@linaro.org> */ #ifndef __ASM_ARM_KVM_PMU_H #define __ASM_ARM_KVM_PMU_H #include <linux/perf_event.h> #include <linux/perf/arm_pmuv3.h> #define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1) #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM) struct kvm_pmc { u8 idx; /* index into the pmu->pmc array */ struct perf_event *perf_event; }; struct kvm_pmu_events { u32 events_host; u32 events_guest; }; struct kvm_pmu { struct irq_work overflow_work; struct kvm_pmu_events events; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; int irq_num; bool created; bool irq_level; }; struct arm_pmu_entry { struct list_head entry; struct arm_pmu *arm_pmu; }; DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static __always_inline bool kvm_arm_support_pmu_v3(void) { return static_branch_likely(&kvm_arm_pmu_available); } #define kvm_arm_pmu_irq_initialized(v) ((v)->arch.pmu.irq_num >= VGIC_NR_SGIS) u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx); void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val); u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu); u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1); void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu); bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu); void kvm_pmu_update_run(struct kvm_vcpu *vcpu); void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx); void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu); int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); struct kvm_pmu_events *kvm_get_pmu_events(void); void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); void kvm_vcpu_pmu_resync_el0(void); #define kvm_vcpu_has_pmu(vcpu) \ (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PMU_V3)) /* * Updates the vcpu's view of the pmu events for this cpu. * Must be called before every vcpu run after disabling interrupts, to ensure * that an interrupt cannot fire and update the structure. */ #define kvm_pmu_update_vcpu_events(vcpu) \ do { \ if (!has_vhe() && kvm_arm_support_pmu_v3()) \ vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) u8 kvm_arm_pmu_get_pmuver_limit(void); u64 kvm_pmu_evtyper_mask(struct kvm *kvm); int kvm_arm_set_default_pmu(struct kvm *kvm); u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm); u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu); #else struct kvm_pmu { }; static inline bool kvm_arm_support_pmu_v3(void) { return false; } #define kvm_arm_pmu_irq_initialized(v) (false) static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { return 0; } static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) {} static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { return 0; } static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {} static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) { return false; } static inline void kvm_pmu_update_run(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) {} static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { return 0; } static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { return 0; } #define kvm_vcpu_has_pmu(vcpu) ({ false; }) static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) {} static inline u8 kvm_arm_pmu_get_pmuver_limit(void) { return 0; } static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm) { return 0; } static inline void kvm_vcpu_pmu_resync_el0(void) {} static inline int kvm_arm_set_default_pmu(struct kvm *kvm) { return -ENODEV; } static inline u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { return 0; } static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { return 0; } #endif #endif |
| 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/sched/isolation.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the folio has dirty or writeback buffers. If all the buffers * are unlocked and clean then the folio_test_dirty information is stale. If * any of the buffers are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; if (folio_test_writeback(folio)) *writeback = true; bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); put_bh(bh); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * i_private_lock. * * Hack idea: for the blockdev mapping, i_private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take i_private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct folio *folio; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = ((loff_t)block << blkbits) / PAGE_SIZE; folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio)) goto out; spin_lock(&bd_mapping->i_private_lock); head = folio_buffers(folio); if (!head) goto out_unlock; bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << blkbits); } out_unlock: spin_unlock(&bd_mapping->i_private_lock); folio_put(folio); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_read(folio, folio_uptodate); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } struct postprocess_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void verify_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; bool valid; valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, valid); kfree(ctx); } static bool need_fsverity(struct buffer_head *bh) { struct folio *folio = bh->b_folio; struct inode *inode = folio->mapping->host; return fsverity_active(inode) && /* needed by ext4 */ folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); } static void decrypt_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); if (err == 0 && need_fsverity(bh)) { /* * We use different work queues for decryption and for verity * because verity may require reading metadata pages that need * decryption, and we shouldn't recurse to the same workqueue. */ INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); return; } end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { struct inode *inode = bh->b_folio->mapping->host; bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); bool verify = need_fsverity(bh); /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ if (uptodate && (decrypt || verify)) { struct postprocess_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { ctx->bh = bh; if (decrypt) { INIT_WORK(&ctx->work, decrypt_bh); fscrypt_enqueue_decrypt_work(&ctx->work); } else { INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); } return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_folio() - folios which are unlocked * during I/O, and which have the writeback flag cleared upon I/O completion. */ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; BUG_ON(!buffer_async_write(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_writeback(folio); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, * mapping->i_private_list will always be protected by the backing blockdev's * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->i_private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->i_private_list via these * utility functions are free to use i_private_lock and i_private_list for * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.i_private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer * as you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->i_private_data; if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) return 0; return fsync_buffers_list(&buffer_mapping->i_private_lock, &mapping->i_private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /** * generic_buffers_fsync_noflush - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(generic_buffers_fsync_noflush); /** * generic_buffers_fsync - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. This also makes sure that * a device cache flush operation is called at the end. */ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); if (!ret) ret = blkdev_issue_flush(inode->i_sb->s_bdev); return ret; } EXPORT_SYMBOL(generic_buffers_fsync); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) write_dirty_buffer(bh, 0); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); if (!mapping->i_private_data) { mapping->i_private_data = buffer_mapping; } else { BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /** * block_dirty_folio - Mark a folio as dirty. * @mapping: The address space containing this folio. * @folio: The folio to mark dirty. * * Filesystems which use buffer_heads can use this function as their * ->dirty_folio implementation. Some filesystems need to do a little * work before calling this function. Filesystems which do not use * buffer_heads should call filemap_dirty_folio() instead. * * If the folio has buffers, the uptodate buffers are set dirty, to * preserve dirty-state coherency between the folio and the buffers. * Buffers added to a dirty folio are created dirty. * * The buffers are dirtied before the folio is dirtied. There's a small * race window in which writeback may see the folio cleanness but not the * buffer dirtiness. That's fine. If this code were to set the folio * dirty before the buffers, writeback could clear the folio dirty flag, * see a bunch of clean buffers and we'd end up with dirty buffers/clean * folio on the dirty folio list. * * We use i_private_lock to lock against try_to_free_buffers() while * using the folio's buffer list. This also prevents clean buffers * being added to the folio after it was set dirty. * * Context: May only be called from process context. Does not sleep. * Caller must ensure that @folio cannot be truncated during this call, * typically by holding the folio lock or having a page in the folio * mapped and holding the page table lock. * * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { struct buffer_head *head; bool newly_dirty; spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ folio_memcg_lock(folio); newly_dirty = !folio_test_set_dirty(folio); spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); folio_memcg_unlock(folio); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(block_dirty_folio); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->i_private_lock); } return ret; } /* * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp) { struct buffer_head *bh, *head; long offset; struct mem_cgroup *memcg, *old_memcg; /* The folio lock pins the memcg */ memcg = folio_memcg(folio); old_memcg = set_active_memcg(memcg); head = NULL; offset = folio_size(folio); while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its folio */ folio_set_bh(bh, folio, offset); } out: set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(folio_alloc_buffers); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; if (retry) gfp |= __GFP_NOFAIL; return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct folio *folio, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; folio_attach_private(folio, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev folio's buffers. */ static sector_t folio_init_buffers(struct folio *folio, struct block_device *bdev, unsigned size) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh = head; bool uptodate = folio_test_uptodate(folio); sector_t block = div_u64(folio_pos(folio), size); sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. * * Returns false if we have a failure which cannot be cured by retrying * without sleeping. Returns true if we succeeded, or the caller should retry. */ static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { struct address_space *mapping = bdev->bd_mapping; struct folio *folio; struct buffer_head *bh; sector_t end_block = 0; folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return false; bh = folio_buffers(folio); if (bh) { if (bh->b_size == size) { end_block = folio_init_buffers(folio, bdev, size); goto unlock; } /* * Retrying may succeed; for example the folio may finish * writeback, or buffers may be cleaned. This should not * happen very often; maybe we have old buffers attached to * this blockdev's page cache and we're trying to change * the block size? */ if (!try_to_free_buffers(folio)) { end_block = ~0ULL; goto unlock; } } bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); if (!bh) goto unlock; /* * Link the folio to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ spin_lock(&mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, size); spin_unlock(&mapping->i_private_lock); unlock: folio_unlock(folio); folio_put(folio); return block < end_block; } /* * Create buffers for the specified block device block's folio. If * that folio was dirty, the buffers are set dirty also. Returns false * if we've hit a permanent error. */ static bool grow_buffers(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { loff_t pos; /* * Check for a block which lies outside our maximum possible * pagecache index. */ if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) { printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n", __func__, (unsigned long long)block, bdev); return false; } /* Create a folio with the proper size buffers */ return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; bh = __find_get_block(bdev, block, size); if (bh) return bh; if (!grow_buffers(bdev, block, size, gfp)) return NULL; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_folio() against that folio will discover all the uptodate * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; folio_memcg_lock(folio); if (!folio_test_set_dirty(folio)) { mapping = folio->mapping; if (mapping) __folio_mark_dirty(folio, mapping, 0); } folio_memcg_unlock(folio); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); if (bh->b_assoc_map) { mapping_set_error(bh->b_assoc_map, -EIO); errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO); } } EXPORT_SYMBOL(mark_buffer_write_io_error); /** * __brelse - Release a buffer. * @bh: The buffer to release. * * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ void __brelse(struct buffer_head *bh) { if (atomic_read(&bh->b_count)) { put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /** * __bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * This variant of bforget() can be called if @bh is guaranteed to not * be NULL. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_folio->mapping; spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); if (cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return NULL; } for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } EXPORT_SYMBOL(__find_get_block); /** * bdev_getblk - Get a buffer_head in a block device's buffer cache. * @bdev: The block device. * @block: The block number. * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * * The returned buffer head has its reference count incremented, but is * not locked. The caller should call brelse() when it has finished * with the buffer. The buffer may not be uptodate. If needed, the * caller can bring it uptodate either by reading it or overwriting it. * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_alloc(gfp); if (bh) return bh; return __getblk_slow(bdev, block, size, gfp); } EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = bdev_getblk(bdev, block, size, GFP_NOWAIT | __GFP_MOVABLE); if (likely(bh)) { bh_readahead(bh, REQ_RAHEAD); brelse(bh); } } EXPORT_SYMBOL(__breadahead); /** * __bread_gfp() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * @gfp: Not page allocation flags; see below. * * You are not expected to call this function. You should use one of * sb_bread(), sb_bread_unmovable() or __bread(). * * Read a specified block, and return the buffer head that refers to it. * If @gfp is 0, the memory will be allocated using the block device's * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be * allocated from a movable area. Do not pass in a complete set of * GFP flags. * * The returned buffer head has its refcount increased. The caller should * call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); /* * Prefer looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp |= __GFP_NOFAIL; bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset) { bh->b_folio = folio; BUG_ON(offset >= folio_size(folio)); if (folio_test_highmem(folio)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = folio_address(folio) + offset; } EXPORT_SYMBOL(folio_set_bh); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = READ_ONCE(bh->b_state); do { } while (!try_cmpxchg(&bh->b_state, &b_state, b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } /** * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * * block_invalidate_folio() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; size_t curr_off = 0; size_t stop = length + offset; BUG_ON(!folio_test_locked(folio)); /* * Check for overflow */ BUG_ON(stop > folio_size(folio) || stop < length); head = folio_buffers(folio); if (!head) return; bh = head; do { size_t next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire folio is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == folio_size(folio)) filemap_release_folio(folio, 0); out: return; } EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { if (folio_test_dirty(folio)) set_buffer_dirty(bh); if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } folio_attach_private(folio, head); spin_unlock(&folio->mapping->i_private_lock); return head; } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct folio_batch fbatch; pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; folio_batch_init(&fbatch); while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { count = folio_batch_count(&fbatch); for (i = 0; i < count; i++) { struct folio *folio = fbatch.folios[i]; if (!folio_buffers(folio)) continue; /* * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ folio_lock(folio); /* Recheck when the folio is locked which pins bhs */ head = folio_buffers(folio); if (!head) goto unlock_page; bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); static struct buffer_head *folio_create_buffers(struct folio *folio, struct inode *inode, unsigned int b_state) { struct buffer_head *bh; BUG_ON(!folio_test_locked(folio)); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, 1 << READ_ONCE(inode->i_blkbits), b_state); return bh; } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_folio() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; size_t blocksize; int nr_underway = 0; blk_opf_t write_flags = wbc_to_write_flags(wbc); head = folio_create_buffers(folio, inode, (1 << BH_Dirty) | (1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from block_dirty_folio * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the folio stays dirty. * * Buffers outside i_size may be dirtied by block_dirty_folio; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; block = div_u64(folio_pos(folio), blocksize); last_block = div_u64(i_size_read(inode) - 1, blocksize); /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this folio can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_folio() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the folio. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { folio_redirty_for_writepage(wbc, folio); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The folio and its buffers are protected by the writeback flag, * so we can drop the bh refcounts early. */ BUG_ON(folio_test_writeback(folio)); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); err = 0; done: if (nr_underway == 0) { /* * The folio was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * write_dirty_buffer/submit_bh. A rare case. */ folio_end_writeback(folio); /* * The folio and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The folio is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { /* * The buffer may have been set dirty during * attachment to a dirty folio. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); BUG_ON(folio_test_writeback(folio)); mapping_set_error(folio->mapping, err); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); goto done; } EXPORT_SYMBOL(__block_write_full_folio); /* * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { size_t start, xend; start = max(from, block_start); xend = min(to, block_end); folio_zero_segment(folio, start, xend); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(folio_zero_new_buffers); static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = (loff_t)block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ if (offset >= iomap->offset + iomap->length) return -EIO; switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) { /* * This can happen if truncating the block device races * with the check in the caller as i_size updates on * block devices aren't synchronized by i_rwsem for * block devices. */ if (S_ISBLK(inode->i_mode)) return -EIO; set_buffer_new(bh); } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); return 0; default: WARN_ON_ONCE(1); return -EIO; } } int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { size_t from = offset_in_folio(folio, pos); size_t to = from + len; struct inode *inode = folio->mapping->host; size_t block_start, block_end; sector_t block; int err = 0; size_t blocksize; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!folio_test_locked(folio)); BUG_ON(to > folio_size(folio)); BUG_ON(from > to); head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; block = div_u64(folio_pos(folio), blocksize); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) err = get_block(inode, block, bh, 1); else err = iomap_to_bh(inode, block, bh, iomap); if (err) break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (folio_test_uptodate(folio)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) folio_zero_segments(folio, to, block_end, block_start, from); continue; } } if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) folio_zero_new_buffers(folio, from, to); return err; } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(page_folio(page), pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); static void __block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; unsigned blocksize; struct buffer_head *bh, *head; bh = head = folio_buffers(folio); if (!bh) return; blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the folio went * uptodate as a result of this (potentially partial) write. */ if (!partial) folio_mark_uptodate(folio); } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; } *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct folio *folio = page_folio(page); size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so * we don't have to worry about a read_folio reading them * and overwriting a partial write. However if we have * encountered a short write and only partially written * into a buffer, it will not be marked uptodate, so a * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate folio as a zero-length write, and force the * caller to redo the whole thing. */ if (!folio_test_uptodate(folio)) copied = 0; folio_zero_new_buffers(folio, start+copied, start+len); } flush_dcache_folio(folio); /* This could be a short (even 0-length) commit */ __block_commit_write(folio, start, start + copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * * Returns true if all buffers which correspond to the specified part * of the folio are uptodate. */ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; bool ret = true; head = folio_buffers(folio); if (!head) return false; blocksize = head->b_size; to = min_t(unsigned, folio_size(folio) - from, count); to = from + to; if (from < blocksize && to > folio_size(folio) - blocksize) return false; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = false; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * folio once IO has completed. */ int block_read_full_folio(struct folio *folio, get_block_t *get_block) { struct inode *inode = folio->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; size_t blocksize; int nr, i; int fully_mapped = 1; bool page_error = false; loff_t limit = i_size_read(inode); /* This is needed for ext4. */ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) limit = inode->i_sb->s_maxbytes; VM_BUG_ON_FOLIO(folio_test_large(folio), folio); head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; iblock = div_u64(folio_pos(folio), blocksize); lblock = div_u64(limit + blocksize - 1, blocksize); bh = head; nr = 0; i = 0; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) page_error = true; } if (!buffer_mapped(bh)) { folio_zero_range(folio, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } arr[nr++] = bh; } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) folio_set_mappedtodisk(folio); if (!nr) { /* * All buffers are uptodate or get_block() returned an * error when trying to map them - we can finish the read. */ folio_end_read(folio, !page_error); return 0; } /* Stage two: lock the buffers */ for (i = 0; i < nr; i++) { bh = arr[i]; lock_buffer(bh); mark_buffer_async_read(bh); } /* * Stage 3: start the IO. Check for uptodateness * inside the buffer lock in case another process reading * the underlying blockdev brought it uptodate (the sct fix). */ for (i = 0; i < nr; i++) { bh = arr[i]; if (buffer_uptodate(bh)) end_buffer_async_read(bh, 1); else submit_bh(REQ_OP_READ, bh); } return 0; } EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; struct page *page; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata); if (err) goto out; err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = aops->write_begin(file, mapping, curpos, len, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = aops->write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = aops->write_begin(file, mapping, curpos, len, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = aops->write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); void block_commit_write(struct page *page, unsigned from, unsigned to) { struct folio *folio = page_folio(page); __block_commit_write(folio, from, to); } EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; folio_lock(folio); size = i_size_read(inode); if ((folio->mapping != inode->i_mapping) || (folio_pos(folio) >= size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } end = folio_size(folio); /* folio is wholly or partially inside EOF */ if (folio_pos(folio) + end > size) end = size - folio_pos(folio); ret = __block_write_begin_int(folio, 0, end, get_block, NULL); if (unlikely(ret)) goto out_unlock; __block_commit_write(folio, 0, end); folio_mark_dirty(folio); folio_wait_stable(folio); return 0; out_unlock: folio_unlock(folio); return ret; } EXPORT_SYMBOL(block_page_mkwrite); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned blocksize; sector_t iblock; size_t offset, length, pos; struct inode *inode = mapping->host; struct folio *folio; struct buffer_head *bh; int err = 0; blocksize = i_blocksize(inode); length = from & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = bh_read(bh, 0); /* Uhhuh. Read error. Complain and punt. */ if (err < 0) goto unlock; } folio_zero_range(folio, offset, length); mark_buffer_dirty(bh); unlock: folio_unlock(folio); folio_put(folio); return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) { struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); /* Is the folio fully inside i_size? */ if (folio_pos(folio) + folio_size(folio) <= i_size) return __block_write_full_folio(inode, folio, get_block, wbc); /* Is the folio fully outside i_size? (truncate in progress) */ if (folio_pos(folio) >= i_size) { folio_unlock(folio); return 0; /* don't care */ } /* * The folio straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); return __block_write_full_folio(inode, folio, get_block, wbc); } sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { const enum req_op op = opf & REQ_OP_MASK; struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); if (buffer_meta(bh)) opf |= REQ_META; if (buffer_prio(bh)) opf |= REQ_PRIO; bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_write_hint = write_hint; __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); } void submit_bh(blk_opf_t opf, struct buffer_head *bh) { submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL); } EXPORT_SYMBOL(submit_bh); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | op_flags, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) return -EIO; } else { unlock_buffer(bh); } return 0; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static bool drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; folio_detach_private(folio); return true; failed: return false; } /** * try_to_free_buffers - Release buffers attached to this folio. * @folio: The folio. * * If any buffers are in use (dirty, under writeback, elevated refcount), * no buffers will be freed. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * i_private_lock. * * Exclusion against try_to_free_buffers may be obtained by either * locking the folio or by holding its mapping's i_private_lock. * * Context: Process context. @folio must be locked. Will not sleep. * Return: true if all buffers attached to this folio were freed. */ bool try_to_free_buffers(struct folio *folio) { struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; bool ret = 0; BUG_ON(!folio_test_locked(folio)); if (folio_test_writeback(folio)) return false; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(folio, &buffers_to_free); goto out; } spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty folio. We * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the folio's buffers clean. We discover that here and clean * the folio also. * * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @wait: wait until reading finish * * Returns zero on success or don't wait, and -EIO on error. */ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { int ret = 0; BUG_ON(!buffer_locked(bh)); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ | op_flags, bh); if (wait) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } return ret; } EXPORT_SYMBOL(__bh_read); /** * __bh_read_batch - Submit read for a batch of unlocked buffers * @nr: entry number of the buffer batch * @bhs: a batch of struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @force_lock: force to get a lock on the buffer if set, otherwise drops any * buffer that cannot lock. * * Returns zero on success or don't wait, and -EIO on error. */ void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (buffer_uptodate(bh)) continue; if (force_lock) lock_buffer(bh); else if (!trylock_buffer(bh)) continue; if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } } EXPORT_SYMBOL(__bh_read_batch); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = KMEM_CACHE(buffer_head, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 256 253 253 252 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 302 177 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) #endif /* _LINUX_TOPOLOGY_H */ |
| 17 17 17 17 8 17 17 17 17 17 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 | // SPDX-License-Identifier: GPL-2.0 /* * VMID allocator. * * Based on Arm64 ASID allocator algorithm. * Please refer arch/arm64/mm/context.c for detailed * comments on algorithm. * * Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved. * Copyright (C) 2012 ARM Ltd. */ #include <linux/bitfield.h> #include <linux/bitops.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> unsigned int __ro_after_init kvm_arm_vmid_bits; static DEFINE_RAW_SPINLOCK(cpu_vmid_lock); static atomic64_t vmid_generation; static unsigned long *vmid_map; static DEFINE_PER_CPU(atomic64_t, active_vmids); static DEFINE_PER_CPU(u64, reserved_vmids); #define VMID_MASK (~GENMASK(kvm_arm_vmid_bits - 1, 0)) #define VMID_FIRST_VERSION (1UL << kvm_arm_vmid_bits) #define NUM_USER_VMIDS VMID_FIRST_VERSION #define vmid2idx(vmid) ((vmid) & ~VMID_MASK) #define idx2vmid(idx) vmid2idx(idx) /* * As vmid #0 is always reserved, we will never allocate one * as below and can be treated as invalid. This is used to * set the active_vmids on vCPU schedule out. */ #define VMID_ACTIVE_INVALID VMID_FIRST_VERSION #define vmid_gen_match(vmid) \ (!(((vmid) ^ atomic64_read(&vmid_generation)) >> kvm_arm_vmid_bits)) static void flush_context(void) { int cpu; u64 vmid; bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); /* Preserve reserved VMID */ if (vmid == 0) vmid = per_cpu(reserved_vmids, cpu); __set_bit(vmid2idx(vmid), vmid_map); per_cpu(reserved_vmids, cpu) = vmid; } /* * Unlike ASID allocator, we expect less frequent rollover in * case of VMIDs. Hence, instead of marking the CPU as * flush_pending and issuing a local context invalidation on * the next context-switch, we broadcast TLB flush + I-cache * invalidation over the inner shareable domain on rollover. */ kvm_call_hyp(__kvm_flush_vm_context); } static bool check_update_reserved_vmid(u64 vmid, u64 newvmid) { int cpu; bool hit = false; /* * Iterate over the set of reserved VMIDs looking for a match * and update to use newvmid (i.e. the same VMID in the current * generation). */ for_each_possible_cpu(cpu) { if (per_cpu(reserved_vmids, cpu) == vmid) { hit = true; per_cpu(reserved_vmids, cpu) = newvmid; } } return hit; } static u64 new_vmid(struct kvm_vmid *kvm_vmid) { static u32 cur_idx = 1; u64 vmid = atomic64_read(&kvm_vmid->id); u64 generation = atomic64_read(&vmid_generation); if (vmid != 0) { u64 newvmid = generation | (vmid & ~VMID_MASK); if (check_update_reserved_vmid(vmid, newvmid)) { atomic64_set(&kvm_vmid->id, newvmid); return newvmid; } if (!__test_and_set_bit(vmid2idx(vmid), vmid_map)) { atomic64_set(&kvm_vmid->id, newvmid); return newvmid; } } vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, cur_idx); if (vmid != NUM_USER_VMIDS) goto set_vmid; /* We're out of VMIDs, so increment the global generation count */ generation = atomic64_add_return_relaxed(VMID_FIRST_VERSION, &vmid_generation); flush_context(); /* We have more VMIDs than CPUs, so this will always succeed */ vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, 1); set_vmid: __set_bit(vmid, vmid_map); cur_idx = vmid; vmid = idx2vmid(vmid) | generation; atomic64_set(&kvm_vmid->id, vmid); return vmid; } /* Called from vCPU sched out with preemption disabled */ void kvm_arm_vmid_clear_active(void) { atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID); } bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) { unsigned long flags; u64 vmid, old_active_vmid; bool updated = false; vmid = atomic64_read(&kvm_vmid->id); /* * Please refer comments in check_and_switch_context() in * arch/arm64/mm/context.c. * * Unlike ASID allocator, we set the active_vmids to * VMID_ACTIVE_INVALID on vCPU schedule out to avoid * reserving the VMID space needlessly on rollover. * Hence explicitly check here for a "!= 0" to * handle the sync with a concurrent rollover. */ old_active_vmid = atomic64_read(this_cpu_ptr(&active_vmids)); if (old_active_vmid != 0 && vmid_gen_match(vmid) && 0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids), old_active_vmid, vmid)) return false; raw_spin_lock_irqsave(&cpu_vmid_lock, flags); /* Check that our VMID belongs to the current generation. */ vmid = atomic64_read(&kvm_vmid->id); if (!vmid_gen_match(vmid)) { vmid = new_vmid(kvm_vmid); updated = true; } atomic64_set(this_cpu_ptr(&active_vmids), vmid); raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags); return updated; } /* * Initialize the VMID allocator */ int __init kvm_arm_vmid_alloc_init(void) { kvm_arm_vmid_bits = kvm_get_vmid_bits(); /* * Expect allocation after rollover to fail if we don't have * at least one more VMID than CPUs. VMID #0 is always reserved. */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; return 0; } void __init kvm_arm_vmid_alloc_free(void) { bitmap_free(vmid_map); } |
| 11 11 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 1 1 1 1 1 1 1 1 1 1 1 1 1 1 11 1 1 10 10 17 11 11 11 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 | // SPDX-License-Identifier: GPL-2.0-only /* * Fault injection for both 32 and 64bit guests. * * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Based on arch/arm/kvm/emulate.c * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <hyp/adjust_pc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! #endif static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) { u64 val; if (unlikely(vcpu_has_nv(vcpu))) return vcpu_read_sys_reg(vcpu, reg); else if (__vcpu_read_sys_reg_from_cpu(reg, &val)) return val; return __vcpu_sys_reg(vcpu, reg); } static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) { if (unlikely(vcpu_has_nv(vcpu))) vcpu_write_sys_reg(vcpu, val, reg); else if (!__vcpu_write_sys_reg_to_cpu(val, reg)) __vcpu_sys_reg(vcpu, reg) = val; } static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode, u64 val) { if (unlikely(vcpu_has_nv(vcpu))) { if (target_mode == PSR_MODE_EL1h) vcpu_write_sys_reg(vcpu, val, SPSR_EL1); else vcpu_write_sys_reg(vcpu, val, SPSR_EL2); } else if (has_vhe()) { write_sysreg_el1(val, SYS_SPSR); } else { __vcpu_sys_reg(vcpu, SPSR_EL1) = val; } } static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) { if (has_vhe()) write_sysreg(val, spsr_abt); else vcpu->arch.ctxt.spsr_abt = val; } static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val) { if (has_vhe()) write_sysreg(val, spsr_und); else vcpu->arch.ctxt.spsr_und = val; } /* * This performs the exception entry at a given EL (@target_mode), stashing PC * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE. * The EL passed to this function *must* be a non-secure, privileged mode with * bit 0 being set (PSTATE.SP == 1). * * When an exception is taken, most PSTATE fields are left unchanged in the * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0. * * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429. * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426. * * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from * MSB to LSB. */ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, enum exception_type type) { unsigned long sctlr, vbar, old, new, mode; u64 exc_offset; mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); if (mode == target_mode) exc_offset = CURRENT_EL_SP_ELx_VECTOR; else if ((mode | PSR_MODE_THREAD_BIT) == target_mode) exc_offset = CURRENT_EL_SP_EL0_VECTOR; else if (!(mode & PSR_MODE32_BIT)) exc_offset = LOWER_EL_AArch64_VECTOR; else exc_offset = LOWER_EL_AArch32_VECTOR; switch (target_mode) { case PSR_MODE_EL1h: vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL1); sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); break; case PSR_MODE_EL2h: vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2); sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2); break; default: /* Don't do that */ BUG(); } *vcpu_pc(vcpu) = vbar + exc_offset + type; old = *vcpu_cpsr(vcpu); new = 0; new |= (old & PSR_N_BIT); new |= (old & PSR_Z_BIT); new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); // PSTATE.UAO is set to zero upon any exception to AArch64 // See ARM DDI 0487E.a, page D5-2579. // PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0 // SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented // See ARM DDI 0487E.a, page D5-2578. new |= (old & PSR_PAN_BIT); if (!(sctlr & SCTLR_EL1_SPAN)) new |= PSR_PAN_BIT; // PSTATE.SS is set to zero upon any exception to AArch64 // See ARM DDI 0487E.a, page D2-2452. // PSTATE.IL is set to zero upon any exception to AArch64 // See ARM DDI 0487E.a, page D1-2306. // PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64 // See ARM DDI 0487E.a, page D13-3258 if (sctlr & SCTLR_ELx_DSSBS) new |= PSR_SSBS_BIT; // PSTATE.BTYPE is set to zero upon any exception to AArch64 // See ARM DDI 0487E.a, pages D1-2293 to D1-2294. new |= PSR_D_BIT; new |= PSR_A_BIT; new |= PSR_I_BIT; new |= PSR_F_BIT; new |= target_mode; *vcpu_cpsr(vcpu) = new; __vcpu_write_spsr(vcpu, target_mode, old); } /* * When an exception is taken, most CPSR fields are left unchanged in the * handler. However, some are explicitly overridden (e.g. M[4:0]). * * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was * obsoleted by the ARMv7 virtualization extensions and is RES0. * * For the SPSR layout seen from AArch32, see: * - ARM DDI 0406C.d, page B1-1148 * - ARM DDI 0487E.a, page G8-6264 * * For the SPSR_ELx layout for AArch32 seen from AArch64, see: * - ARM DDI 0487E.a, page C5-426 * * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from * MSB to LSB. */ static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) { u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); unsigned long old, new; old = *vcpu_cpsr(vcpu); new = 0; new |= (old & PSR_AA32_N_BIT); new |= (old & PSR_AA32_Z_BIT); new |= (old & PSR_AA32_C_BIT); new |= (old & PSR_AA32_V_BIT); new |= (old & PSR_AA32_Q_BIT); // CPSR.IT[7:0] are set to zero upon any exception // See ARM DDI 0487E.a, section G1.12.3 // See ARM DDI 0406C.d, section B1.8.3 new |= (old & PSR_AA32_DIT_BIT); // CPSR.SSBS is set to SCTLR.DSSBS upon any exception // See ARM DDI 0487E.a, page G8-6244 if (sctlr & BIT(31)) new |= PSR_AA32_SSBS_BIT; // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented // See ARM DDI 0487E.a, page G8-6246 new |= (old & PSR_AA32_PAN_BIT); if (!(sctlr & BIT(23))) new |= PSR_AA32_PAN_BIT; // SS does not exist in AArch32, so ignore // CPSR.IL is set to zero upon any exception // See ARM DDI 0487E.a, page G1-5527 new |= (old & PSR_AA32_GE_MASK); // CPSR.IT[7:0] are set to zero upon any exception // See prior comment above // CPSR.E is set to SCTLR.EE upon any exception // See ARM DDI 0487E.a, page G8-6245 // See ARM DDI 0406C.d, page B4-1701 if (sctlr & BIT(25)) new |= PSR_AA32_E_BIT; // CPSR.A is unchanged upon an exception to Undefined, Supervisor // CPSR.A is set upon an exception to other modes // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 // See ARM DDI 0406C.d, page B1-1182 new |= (old & PSR_AA32_A_BIT); if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) new |= PSR_AA32_A_BIT; // CPSR.I is set upon any exception // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 // See ARM DDI 0406C.d, page B1-1182 new |= PSR_AA32_I_BIT; // CPSR.F is set upon an exception to FIQ // CPSR.F is unchanged upon an exception to other modes // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 // See ARM DDI 0406C.d, page B1-1182 new |= (old & PSR_AA32_F_BIT); if (mode == PSR_AA32_MODE_FIQ) new |= PSR_AA32_F_BIT; // CPSR.T is set to SCTLR.TE upon any exception // See ARM DDI 0487E.a, page G8-5514 // See ARM DDI 0406C.d, page B1-1181 if (sctlr & BIT(30)) new |= PSR_AA32_T_BIT; new |= mode; return new; } /* * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. */ static const u8 return_offsets[8][2] = { [0] = { 0, 0 }, /* Reset, unused */ [1] = { 4, 2 }, /* Undefined */ [2] = { 0, 0 }, /* SVC, unused */ [3] = { 4, 4 }, /* Prefetch abort */ [4] = { 8, 8 }, /* Data abort */ [5] = { 0, 0 }, /* HVC, unused */ [6] = { 4, 4 }, /* IRQ, unused */ [7] = { 4, 4 }, /* FIQ, unused */ }; static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) { unsigned long spsr = *vcpu_cpsr(vcpu); bool is_thumb = (spsr & PSR_AA32_T_BIT); u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); u32 return_address; *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); return_address = *vcpu_pc(vcpu); return_address += return_offsets[vect_offset >> 2][is_thumb]; /* KVM only enters the ABT and UND modes, so only deal with those */ switch(mode) { case PSR_AA32_MODE_ABT: __vcpu_write_spsr_abt(vcpu, host_spsr_to_spsr32(spsr)); vcpu_gp_regs(vcpu)->compat_lr_abt = return_address; break; case PSR_AA32_MODE_UND: __vcpu_write_spsr_und(vcpu, host_spsr_to_spsr32(spsr)); vcpu_gp_regs(vcpu)->compat_lr_und = return_address; break; } /* Branch to exception vector */ if (sctlr & (1 << 13)) vect_offset += 0xffff0000; else /* always have security exceptions */ vect_offset += __vcpu_read_sys_reg(vcpu, VBAR_EL1); *vcpu_pc(vcpu) = vect_offset; } static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { case unpack_vcpu_flag(EXCEPT_AA32_UND): enter_exception32(vcpu, PSR_AA32_MODE_UND, 4); break; case unpack_vcpu_flag(EXCEPT_AA32_IABT): enter_exception32(vcpu, PSR_AA32_MODE_ABT, 12); break; case unpack_vcpu_flag(EXCEPT_AA32_DABT): enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16); break; default: /* Err... */ break; } } else { switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); break; case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync); break; case unpack_vcpu_flag(EXCEPT_AA64_EL2_IRQ): enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq); break; default: /* * Only EL1_SYNC and EL2_{SYNC,IRQ} makes * sense so far. Everything else gets silently * ignored. */ break; } } } /* * Adjust the guest PC (and potentially exception state) depending on * flags provided by the emulation code. */ void __kvm_adjust_pc(struct kvm_vcpu *vcpu) { if (vcpu_get_flag(vcpu, PENDING_EXCEPTION)) { kvm_inject_exception(vcpu); vcpu_clear_flag(vcpu, PENDING_EXCEPTION); vcpu_clear_flag(vcpu, EXCEPT_MASK); } else if (vcpu_get_flag(vcpu, INCREMENT_PC)) { kvm_skip_instr(vcpu); vcpu_clear_flag(vcpu, INCREMENT_PC); } } |
| 50 170 356 50 49 50 113 114 114 114 113 114 114 114 114 114 114 114 114 14 14 9 9 9 4 4 4 114 114 114 114 14 13 9 4 4 4 170 170 170 170 170 4 170 170 170 4 4 4 4 4 217 217 217 193 193 50 50 50 49 50 300 216 217 300 349 349 349 349 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> #include <linux/nospec.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __ro_after_init; static unsigned int m_hash_shift __ro_after_init; static unsigned int mp_hash_mask __ro_after_init; static unsigned int mp_hash_shift __ro_after_init; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ #define MNT_UNIQUE_ID_OFFSET (1ULL << 31) static atomic64_t mnt_id_ctr = ATOMIC64_INIT(MNT_UNIQUE_ID_OFFSET); static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ static DEFINE_RWLOCK(mnt_ns_tree_lock); static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */ struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; unsigned int propagation; unsigned int lookup_flags; bool recurse; struct user_namespace *mnt_userns; struct mnt_idmap *mnt_idmap; }; /* /sys/fs */ struct kobject *fs_kobj __ro_after_init; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static int mnt_ns_cmp(u64 seq, const struct mnt_namespace *ns) { u64 seq_b = ns->seq; if (seq < seq_b) return -1; if (seq > seq_b) return 1; return 0; } static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) { if (!node) return NULL; return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node); } static bool mnt_ns_less(struct rb_node *a, const struct rb_node *b) { struct mnt_namespace *ns_a = node_to_mnt_ns(a); struct mnt_namespace *ns_b = node_to_mnt_ns(b); u64 seq_a = ns_a->seq; return mnt_ns_cmp(seq_a, ns_b) < 0; } static void mnt_ns_tree_add(struct mnt_namespace *ns) { guard(write_lock)(&mnt_ns_tree_lock); rb_add(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_less); } static void mnt_ns_release(struct mnt_namespace *ns) { lockdep_assert_not_held(&mnt_ns_tree_lock); /* keep alive for {list,stat}mount() */ if (refcount_dec_and_test(&ns->passive)) { put_user_ns(ns->user_ns); kfree(ns); } } DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) static void mnt_ns_tree_remove(struct mnt_namespace *ns) { /* remove from global mount namespace list */ if (!is_anon_ns(ns)) { guard(write_lock)(&mnt_ns_tree_lock); rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree); } mnt_ns_release(ns); } /* * Returns the mount namespace which either has the specified id, or has the * next smallest id afer the specified one. */ static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) { struct rb_node *node = mnt_ns_tree.rb_node; struct mnt_namespace *ret = NULL; lockdep_assert_held(&mnt_ns_tree_lock); while (node) { struct mnt_namespace *n = node_to_mnt_ns(node); if (mnt_ns_id <= n->seq) { ret = node_to_mnt_ns(node); if (mnt_ns_id == n->seq) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } /* * Lookup a mount namespace by id and take a passive reference count. Taking a * passive reference means the mount namespace can be emptied if e.g., the last * task holding an active reference exits. To access the mounts of the * namespace the @namespace_sem must first be acquired. If the namespace has * already shut down before acquiring @namespace_sem, {list,stat}mount() will * see that the mount rbtree of the namespace is empty. */ static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id) { struct mnt_namespace *ns; guard(read_lock)(&mnt_ns_tree_lock); ns = mnt_ns_find_id_at(mnt_ns_id); if (!ns || ns->seq != mnt_ns_id) return NULL; refcount_inc(&ns->passive); return ns; } static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (READ_ONCE(mnt->mnt_sb->s_readonly_remount)) return 1; /* * The barrier pairs with the barrier in sb_start_ro_state_change() * making sure if we don't see s_readonly_remount set yet, we also will * not see any superblock / mount flag changes done by remount. * It also pairs with the barrier in sb_end_ro_state_change() * assuring that if we see s_readonly_remount already cleared, we will * see the values of superblock / mount flags updated by remount. */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); might_lock(&mount_lock.lock); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { cpu_relax(); } else { /* * This prevents priority inversion, if the task * setting MNT_WRITE_HOLD got preempted on a remote * CPU, and it prevents life lock if the task setting * MNT_WRITE_HOLD has a lower priority and is bound to * the same CPU as the task that is spinning here. */ preempt_enable(); lock_mount_hash(); unlock_mount_hash(); preempt_disable(); } } /* * The barrier pairs with the barrier sb_start_ro_state_change() making * sure that if we see MNT_WRITE_HOLD cleared, we will also see * s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in * mnt_is_readonly() and bail in case we are racing with remount * read-only. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be * paired with mnt_put_write_access_file. */ int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* * Superblock may have become readonly while there are still * writable fd's, e.g. due to a fs error with errors=remount-ro */ if (__mnt_is_readonly(file->f_path.mnt)) return -EROFS; return 0; } return mnt_get_write_access(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the freeze protection and the check for emergency r/o * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * mnt_get_write_access() call above. */ void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); /** * mnt_hold_writers - prevent write access to the given mount * @mnt: mnt to prevent write access to * * Prevents write access to @mnt if there are no active writers for @mnt. * This function needs to be called and return successfully before changing * properties of @mnt that need to remain stable for callers with write access * to @mnt. * * After this functions has been called successfully callers must pair it with * a call to mnt_unhold_writers() in order to stop preventing write access to * @mnt. * * Context: This function expects lock_mount_hash() to be held serializing * setting MNT_WRITE_HOLD. * Return: On success 0 is returned. * On error, -EBUSY is returned. */ static inline int mnt_hold_writers(struct mount *mnt) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) return -EBUSY; return 0; } /** * mnt_unhold_writers - stop preventing write access to the given mount * @mnt: mnt to stop preventing write access to * * Stop preventing write access to @mnt allowing callers to gain write access * to @mnt again. * * This function can only be called after a successful call to * mnt_hold_writers(). * * Context: This function expects lock_mount_hash() to be held. */ static inline void mnt_unhold_writers(struct mount *mnt) { /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } static int mnt_make_readonly(struct mount *mnt) { int ret; ret = mnt_hold_writers(mnt); if (!ret) mnt->mnt.mnt_flags |= MNT_READONLY; mnt_unhold_writers(mnt); return ret; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { err = mnt_hold_writers(mnt); if (err) break; } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) sb_start_ro_state_change(sb); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { mnt_idmap_put(mnt_idmap(&mnt->mnt)); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /** * __lookup_mnt - find first child mount * @mnt: parent mount * @dentry: mountpoint * * If @mnt has a child mount @c mounted @dentry find and return it. * * Note that the child mount @c need not be unique. There are cases * where shadow mounts are created. For example, during mount * propagation when a source mount @mnt whose root got overmounted by a * mount @o after path lookup but before @namespace_sem could be * acquired gets copied and propagated. So @mnt gets copied including * @o. When @mnt is propagated to a destination mount @d that already * has another mount @n mounted at the same mountpoint then the source * mount @mnt will be tucked beneath @n, i.e., @n will be mounted on * @mnt and @mnt mounted on @d. Now both @n and @o are mounted at @mnt * on @dentry. * * Return: The first child of @mnt mounted @dentry or NULL. */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt, *n; bool is_covered = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } /** * mnt_set_mountpoint_beneath - mount a mount beneath another one * * @new_parent: the source mount * @top_mnt: the mount beneath which @new_parent is mounted * @new_mp: the new mountpoint of @top_mnt on @new_parent * * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and * parent @top_mnt->mnt_parent and mount it on top of @new_parent at * @new_mp. And mount @new_parent on the old parent and old * mountpoint of @top_mnt. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void mnt_set_mountpoint_beneath(struct mount *new_parent, struct mount *top_mnt, struct mountpoint *new_mp) { struct mount *old_top_parent = top_mnt->mnt_parent; struct mountpoint *old_top_mp = top_mnt->mnt_mp; mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent); mnt_change_mountpoint(new_parent, new_mp, top_mnt); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /** * attach_mnt - mount a mount, attach to @mount_hashtable and parent's * list of child mounts * @parent: the parent * @mnt: the new mount * @mp: the new mountpoint * @beneath: whether to mount @mnt beneath or on top of @parent * * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt * to @parent's child mount list and to @mount_hashtable. * * If @beneath is true, remove @mnt from its current parent and * mountpoint and mount it on @mp on @parent, and mount @parent on the * old parent and old mountpoint of @mnt. Finally, attach @parent to * @mnt_hashtable and @parent->mnt_parent->mnt_mounts. * * Note, when __attach_mnt() is called @mnt->mnt_parent already points * to the correct parent. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp, bool beneath) { if (beneath) mnt_set_mountpoint_beneath(mnt, parent, mp); else mnt_set_mountpoint(parent, mp, mnt); /* * Note, @mnt->mnt_parent has to be used. If @mnt was mounted * beneath @parent then @mnt will need to be attached to * @parent's old parent, not @parent. IOW, @mnt->mnt_parent * isn't the same mount as @parent. */ __attach_mnt(mnt, mnt->mnt_parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp, false); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } static inline struct mount *node_to_mount(struct rb_node *node) { return node ? rb_entry(node, struct mount, mnt_node) : NULL; } static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); mnt->mnt_ns = ns; while (*link) { parent = *link; if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); mnt->mnt.mnt_flags |= MNT_ONRB; } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); while (!list_empty(&head)) { m = list_first_entry(&head, typeof(*m), mnt_list); list_del(&m->mnt_list); mnt_add_to_ns(n, m); } n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* * Make a mount point inaccessible to new lookups. * Because there may still be current users, the caller MUST WAIT * for an RCU grace period before destroying the mount point. */ void mnt_make_shortterm(struct vfsmount *mnt) { if (mnt) real_mount(mnt)->mnt_ns = NULL; } /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } /* * Returns the mount which either has the specified mnt_id, or has the next * smallest id afer the specified one. */ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id <= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } /* * Returns the mount which either has the specified mnt_id, or has the next * greater id before the specified one. */ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id >= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_right; } else { node = node->rb_left; } } return ret; } #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; down_read(&namespace_sem); return mnt_find_id_at(p->ns, *pos); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct mount *next = NULL, *mnt = v; struct rb_node *node = rb_next(&mnt->mnt_node); ++*pos; if (node) { next = node_to_mount(node); *pos = next->mnt_id_unique; } return next; } static void m_stop(struct seq_file *m, void *v) { up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @m: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; if (p->mnt.mnt_flags & MNT_ONRB) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->nr_mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } static void warn_mandlock(void) { pr_warn_once("=======================================================\n" "WARNING: The mand mount option has been deprecated and\n" " and is ignored by this kernel. Remove the mand\n" " option from the mount to silence this warning.\n" "=======================================================\n"); } static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); if (!may_mount()) return -EPERM; if (!path_mounted(path)) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *src_root, struct dentry *dentry, int flag) { struct mount *res, *src_parent, *src_root_child, *src_mnt, *dst_parent, *dst_mnt; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_root)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = dst_mnt = clone_mnt(src_root, dentry, flag); if (IS_ERR(dst_mnt)) return dst_mnt; src_parent = src_root; dst_mnt->mnt_mountpoint = src_root->mnt_mountpoint; list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) { if (!is_subdir(src_root_child->mnt_mountpoint, dentry)) continue; for (src_mnt = src_root_child; src_mnt; src_mnt = next_mnt(src_mnt, src_root_child)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_mnt)) { if (src_mnt->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ dst_mnt = ERR_PTR(-EPERM); goto out; } else { src_mnt = skip_mnt_tree(src_mnt); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(src_mnt->mnt.mnt_root)) { src_mnt = skip_mnt_tree(src_mnt); continue; } while (src_parent != src_mnt->mnt_parent) { src_parent = src_parent->mnt_parent; dst_mnt = dst_mnt->mnt_parent; } src_parent = src_mnt; dst_parent = dst_mnt; dst_mnt = clone_mnt(src_mnt, src_mnt->mnt.mnt_root, flag); if (IS_ERR(dst_mnt)) goto out; lock_mount_hash(); list_add_tail(&dst_mnt->mnt_list, &res->mnt_list); attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp, false); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return dst_mnt; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * @path: path to clone * * This creates a new vfsmount, which will be the clone of @path. The new mount * will not be attached anywhere in the namespace and will be private (i.e. * changes to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0; struct mount *p; if (ns->nr_mounts >= max) return -ENOSPC; max -= ns->nr_mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; if (mounts > max) return -ENOSPC; ns->pending_mounts += mounts; return 0; } enum mnt_tree_flags_t { MNT_TREE_MOVE = BIT(0), MNT_TREE_BENEATH = BIT(1), }; /** * attach_recursive_mnt - attach a source mount tree * @source_mnt: mount tree to be attached * @top_mnt: mount that @source_mnt will be mounted on or mounted beneath * @dest_mp: the mountpoint @source_mnt will be mounted at * @flags: modify how @source_mnt is supposed to be attached * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. * * Context: The function expects namespace_lock() to be held. * Return: If @source_mnt was successfully attached 0 is returned. * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *top_mnt, struct mountpoint *dest_mp, enum mnt_tree_flags_t flags) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = top_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *dest_mnt, *p; struct hlist_node *n; int err = 0; bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH; /* * Preallocate a mountpoint in case the new mounts need to be * mounted beneath mounts on the same mountpoint. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (beneath) dest_mnt = top_mnt->mnt_parent; else dest_mnt = top_mnt; if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); } lock_mount_hash(); if (err) goto out_cleanup_ids; if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } if (moving) { if (beneath) dest_mp = smp; unhash_mnt(source_mnt); attach_mnt(source_mnt, top_mnt, dest_mp, beneath); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { LIST_HEAD(head); /* move from anon - the caller will destroy */ for (p = source_mnt; p; p = next_mnt(p, source_mnt)) move_from_ns(p, &head); list_del_init(&head); } if (beneath) mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); else mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } /** * do_lock_mount - lock mount and mountpoint * @path: target path * @beneath: whether the intention is to mount beneath @path * * Follow the mount stack on @path until the top mount @mnt is found. If * the initial @path->{mnt,dentry} is a mountpoint lookup the first * mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root} * until nothing is stacked on top of it anymore. * * Acquire the inode_lock() on the top mount's ->mnt_root to protect * against concurrent removal of the new mountpoint from another mount * namespace. * * If @beneath is requested, acquire inode_lock() on @mnt's mountpoint * @mp on @mnt->mnt_parent must be acquired. This protects against a * concurrent unlink of @mp->mnt_dentry from another mount namespace * where @mnt doesn't have a child mount mounted @mp. A concurrent * removal of @mnt->mnt_root doesn't matter as nothing will be mounted * on top of it for @beneath. * * In addition, @beneath needs to make sure that @mnt hasn't been * unmounted or moved from its current mountpoint in between dropping * @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt * being unmounted would be detected later by e.g., calling * check_mnt(mnt) in the function it's called from. For the @beneath * case however, it's useful to detect it directly in do_lock_mount(). * If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points * to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will * point to @mnt->mnt_root and @mnt->mnt_mp will be NULL. * * Return: Either the target mountpoint on the top mount or the top * mount's mountpoint. */ static struct mountpoint *do_lock_mount(struct path *path, bool beneath) { struct vfsmount *mnt = path->mnt; struct dentry *dentry; struct mountpoint *mp = ERR_PTR(-ENOENT); for (;;) { struct mount *m; if (beneath) { m = real_mount(mnt); read_seqlock_excl(&mount_lock); dentry = dget(m->mnt_mountpoint); read_sequnlock_excl(&mount_lock); } else { dentry = path->dentry; } inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); goto out; } namespace_lock(); if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) { namespace_unlock(); inode_unlock(dentry->d_inode); goto out; } mnt = lookup_mnt(path); if (likely(!mnt)) break; namespace_unlock(); inode_unlock(dentry->d_inode); if (beneath) dput(dentry); path_put(path); path->mnt = mnt; path->dentry = dget(mnt->mnt_root); } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); } out: if (beneath) dput(dentry); return mp; } static inline struct mountpoint *lock_mount(struct path *path) { return do_lock_mount(path, false); } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, 0); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (!path_mounted(path)) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { mnt_add_to_ns(ns, p); ns->nr_mounts++; } ns->root = mnt; mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); mnt->mnt.mnt_flags &= ~MNT_READONLY; return 0; } static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf = (char *)__get_free_page(GFP_KERNEL); char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; /* * We're only checking whether the superblock is read-only not * changing it, so only take down_read(&sb->s_umount). */ down_read(&sb->s_umount); lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) { lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); } } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = -EINVAL; /* To and From must be mounted */ if (!is_mounted(&from->mnt)) goto out; if (!is_mounted(&to->mnt)) goto out; err = -EPERM; /* We should be allowed to modify mount namespaces of both mounts */ if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (!path_mounted(from_path)) goto out; if (!path_mounted(to_path)) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } /** * path_overmounted - check if path is overmounted * @path: path to check * * Check if path is overmounted, i.e., if there's a mount on top of * @path->mnt with @path->dentry as mountpoint. * * Context: This function expects namespace_lock() to be held. * Return: If path is overmounted true is returned, false if not. */ static inline bool path_overmounted(const struct path *path) { rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, path->dentry))) { rcu_read_unlock(); return true; } rcu_read_unlock(); return false; } /** * can_move_mount_beneath - check that we can mount beneath the top mount * @from: mount to mount beneath * @to: mount under which to mount * @mp: mountpoint of @to * * - Make sure that @to->dentry is actually the root of a mount under * which we can mount another mount. * - Make sure that nothing can be mounted beneath the caller's current * root or the rootfs of the namespace. * - Make sure that the caller can unmount the topmost mount ensuring * that the caller could reveal the underlying mountpoint. * - Ensure that nothing has been mounted on top of @from before we * grabbed @namespace_sem to avoid creating pointless shadow mounts. * - Prevent mounting beneath a mount if the propagation relationship * between the source mount, parent mount, and top mount would lead to * nonsensical mount trees. * * Context: This function expects namespace_lock() to be held. * Return: On success 0, and on error a negative error code is returned. */ static int can_move_mount_beneath(const struct path *from, const struct path *to, const struct mountpoint *mp) { struct mount *mnt_from = real_mount(from->mnt), *mnt_to = real_mount(to->mnt), *parent_mnt_to = mnt_to->mnt_parent; if (!mnt_has_parent(mnt_to)) return -EINVAL; if (!path_mounted(to)) return -EINVAL; if (IS_MNT_LOCKED(mnt_to)) return -EINVAL; /* Avoid creating shadow mounts during mount propagation. */ if (path_overmounted(from)) return -EINVAL; /* * Mounting beneath the rootfs only makes sense when the * semantics of pivot_root(".", ".") are used. */ if (&mnt_to->mnt == current->fs->root.mnt) return -EINVAL; if (parent_mnt_to == current->nsproxy->mnt_ns->root) return -EINVAL; for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent) if (p == mnt_to) return -EINVAL; /* * If the parent mount propagates to the child mount this would * mean mounting @mnt_from on @mnt_to->mnt_parent and then * propagating a copy @c of @mnt_from on top of @mnt_to. This * defeats the whole purpose of mounting beneath another mount. */ if (propagation_would_overmount(parent_mnt_to, mnt_to, mp)) return -EINVAL; /* * If @mnt_to->mnt_parent propagates to @mnt_from this would * mean propagating a copy @c of @mnt_from on top of @mnt_from. * Afterwards @mnt_from would be mounted on top of * @mnt_to->mnt_parent and @mnt_to would be unmounted from * @mnt->mnt_parent and remounted on @mnt_from. But since @c is * already mounted on @mnt_from, @mnt_to would ultimately be * remounted on top of @c. Afterwards, @mnt_from would be * covered by a copy @c of @mnt_from and @c would be covered by * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) return -EINVAL; return 0; } static int do_move_mount(struct path *old_path, struct path *new_path, bool beneath) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; enum mnt_tree_flags_t flags = 0; mp = do_lock_mount(new_path, beneath); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); if (attached) flags |= MNT_TREE_MOVE; old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (!path_mounted(old_path)) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; if (beneath) { err = can_move_mount_beneath(old_path, new_path, mp); if (err) goto out; err = -EINVAL; p = p->mnt_parent; flags |= MNT_TREE_BENEATH; } /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path, false); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, const struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path_mounted(path)) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, const struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } if (path_overmounted(path)) { err = 0; goto discard_locked; } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if (flags & SB_MANDLOCK) warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); mnt_ns_tree_remove(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); refcount_set(&new_ns->ns.count, 1); refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node); init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { mnt_add_to_ns(new_ns, q); new_ns->nr_mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; // an mntns binding we'd skipped? while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } mnt_ns_tree_add(new_ns); namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } ns->root = mnt; ns->nr_mounts++; mnt_add_to_ns(ns, mnt); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } #define FSMOUNT_VALID_FLAGS \ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); ns->root = mnt; ns->nr_mounts = 1; mnt_add_to_ns(ns, mnt); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path, (flags & MOVE_MOUNT_BENEATH)); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (!path_mounted(&root)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (!path_mounted(&new)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp, false); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp, false); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) { unsigned int flags = mnt->mnt.mnt_flags; /* flags to clear */ flags &= ~kattr->attr_clr; /* flags to raise */ flags |= kattr->attr_set; return flags; } static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_idmap) return 0; /* * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ if (kattr->mnt_userns == m->mnt_sb->s_user_ns) return -EINVAL; /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. */ if (is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ if (!is_anon_ns(mnt->mnt_ns)) return -EINVAL; return 0; } /** * mnt_allow_writers() - check whether the attribute change allows writers * @kattr: the new mount attributes * @mnt: the mount to which @kattr will be applied * * Check whether thew new mount attributes in @kattr allow concurrent writers. * * Return: true if writers need to be held, false if not */ static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { return (!(kattr->attr_set & MNT_READONLY) || (mnt->mnt.mnt_flags & MNT_READONLY)) && !kattr->mnt_idmap; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; int err; for (m = mnt; m; m = next_mnt(m, mnt)) { if (!can_change_locked_flags(m, recalc_flags(kattr, m))) { err = -EPERM; break; } err = can_idmap_mount(kattr, m); if (err) break; if (!mnt_allow_writers(kattr, m)) { err = mnt_hold_writers(m); if (err) break; } if (!kattr->recurse) return 0; } if (err) { struct mount *p; /* * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all * mounts and needs to take care to include the first mount. */ for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); /* * We're done once the first mount we changed got * MNT_WRITE_HOLD unset. */ if (p == m) break; } } return err; } static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { if (!kattr->mnt_idmap) return; /* * Pairs with smp_load_acquire() in mnt_idmap(). * * Since we only allow a mount to change the idmapping once and * verified this in can_idmap_mount() we know that the mount has * @nop_mnt_idmap attached to it. So there's no need to drop any * references. */ smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap)); } static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; for (m = mnt; m; m = next_mnt(m, mnt)) { unsigned int flags; do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); /* If we had to hold writers unblock them. */ if (m->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(m); if (kattr->propagation) change_mnt_propagation(m, kattr->propagation); if (!kattr->recurse) break; } touch_mnt_namespace(mnt->mnt_ns); } static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) { struct mount *mnt = real_mount(path->mnt); int err = 0; if (!path_mounted(path)) return -EINVAL; if (kattr->mnt_userns) { struct mnt_idmap *mnt_idmap; mnt_idmap = alloc_mnt_idmap(kattr->mnt_userns); if (IS_ERR(mnt_idmap)) return PTR_ERR(mnt_idmap); kattr->mnt_idmap = mnt_idmap; } if (kattr->propagation) { /* * Only take namespace_lock() if we're actually changing * propagation. */ namespace_lock(); if (kattr->propagation == MS_SHARED) { err = invent_group_ids(mnt, kattr->recurse); if (err) { namespace_unlock(); return err; } } } err = -EINVAL; lock_mount_hash(); /* Ensure that this isn't anything purely vfs internal. */ if (!is_mounted(&mnt->mnt)) goto out; /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. * * If this mount doesn't have a parent it's most often simply a * detached mount with an anonymous mount namespace. IOW, something * that's simply not attached yet. But there are apparently also users * that do change mount properties on the rootfs itself. That obviously * neither has a parent nor is it a detached mount so we cannot * unconditionally check for detached mounts. */ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* * First, we get the mount tree in a shape where we can change mount * properties without failure. If we succeeded to do so we commit all * changes and if we failed we clean up. */ err = mount_setattr_prepare(kattr, mnt); if (!err) mount_setattr_commit(kattr, mnt); out: unlock_mount_hash(); if (kattr->propagation) { if (err) cleanup_group_ids(mnt, NULL); namespace_unlock(); } return err; } static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { int err = 0; struct ns_common *ns; struct user_namespace *mnt_userns; struct fd f; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; /* * We currently do not support clearing an idmapped mount. If this ever * is a use-case we can revisit this but for now let's keep it simple * and not allow it. */ if (attr->attr_clr & MOUNT_ATTR_IDMAP) return -EINVAL; if (attr->userns_fd > INT_MAX) return -EINVAL; f = fdget(attr->userns_fd); if (!f.file) return -EBADF; if (!proc_ns_file(f.file)) { err = -EINVAL; goto out_fput; } ns = get_proc_ns(file_inode(f.file)); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; } /* * The initial idmapping cannot be used to create an idmapped * mount. We use the initial idmapping as an indicator of a mount * that is not idmapped. It can simply be passed into helpers that * are aware of idmapped mounts as a convenient shortcut. A user * can just create a dedicated identity mapping to achieve the same * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); if (mnt_userns == &init_user_ns) { err = -EPERM; goto out_fput; } /* We're not controlling the target namespace. */ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { err = -EPERM; goto out_fput; } kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: fdput(f); return err; } static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; *kattr = (struct mount_kattr) { .lookup_flags = lookup_flags, .recurse = !!(flags & AT_RECURSIVE), }; if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) return -EINVAL; if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) return -EINVAL; kattr->propagation = attr->propagation; if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); /* * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, * users wanting to transition to a different atime setting cannot * simply specify the atime setting in @attr_set, but must also * specify MOUNT_ATTR__ATIME in the @attr_clr field. * So ensure that MOUNT_ATTR__ATIME can't be partially set in * @attr_clr and that @attr_set can't have any atime bits set if * MOUNT_ATTR__ATIME isn't set in @attr_clr. */ if (attr->attr_clr & MOUNT_ATTR__ATIME) { if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) return -EINVAL; /* * Clear all previous time settings as they are mutually * exclusive. */ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; switch (attr->attr_set & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_RELATIME: kattr->attr_set |= MNT_RELATIME; break; case MOUNT_ATTR_NOATIME: kattr->attr_set |= MNT_NOATIME; break; case MOUNT_ATTR_STRICTATIME: break; default: return -EINVAL; } } else { if (attr->attr_set & MOUNT_ATTR__ATIME) return -EINVAL; } return build_mount_idmapped(attr, usize, kattr, flags); } static void finish_mount_kattr(struct mount_kattr *kattr) { put_user_ns(kattr->mnt_userns); kattr->mnt_userns = NULL; if (kattr->mnt_idmap) mnt_idmap_put(kattr->mnt_idmap); } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, unsigned int, flags, struct mount_attr __user *, uattr, size_t, usize) { int err; struct path target; struct mount_attr attr; struct mount_kattr kattr; BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); if (flags & ~(AT_EMPTY_PATH | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) return -EINVAL; if (!may_mount()) return -EPERM; err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); if (err) return err; /* Don't bother walking through the mounts if this is a nop. */ if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) return 0; err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); if (!err) { err = do_mount_setattr(&target, &kattr); path_put(&target); } finish_mount_kattr(&kattr); return err; } int show_path(struct seq_file *m, struct dentry *root) { if (root->d_sb->s_op->show_path) return root->d_sb->s_op->show_path(m, root); seq_dentry(m, root, " \t\n\\"); return 0; } static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) { struct mount *mnt = mnt_find_id_at(ns, id); if (!mnt || mnt->mnt_id_unique != id) return NULL; return &mnt->mnt; } struct kstatmount { struct statmount __user *buf; size_t bufsize; struct vfsmount *mnt; u64 mask; struct path root; struct statmount sm; struct seq_file seq; }; static u64 mnt_to_attr_flags(struct vfsmount *mnt) { unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); u64 attr_flags = 0; if (mnt_flags & MNT_READONLY) attr_flags |= MOUNT_ATTR_RDONLY; if (mnt_flags & MNT_NOSUID) attr_flags |= MOUNT_ATTR_NOSUID; if (mnt_flags & MNT_NODEV) attr_flags |= MOUNT_ATTR_NODEV; if (mnt_flags & MNT_NOEXEC) attr_flags |= MOUNT_ATTR_NOEXEC; if (mnt_flags & MNT_NODIRATIME) attr_flags |= MOUNT_ATTR_NODIRATIME; if (mnt_flags & MNT_NOSYMFOLLOW) attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; if (mnt_flags & MNT_NOATIME) attr_flags |= MOUNT_ATTR_NOATIME; else if (mnt_flags & MNT_RELATIME) attr_flags |= MOUNT_ATTR_RELATIME; else attr_flags |= MOUNT_ATTR_STRICTATIME; if (is_idmapped_mnt(mnt)) attr_flags |= MOUNT_ATTR_IDMAP; return attr_flags; } static u64 mnt_to_propagation_flags(struct mount *m) { u64 propagation = 0; if (IS_MNT_SHARED(m)) propagation |= MS_SHARED; if (IS_MNT_SLAVE(m)) propagation |= MS_SLAVE; if (IS_MNT_UNBINDABLE(m)) propagation |= MS_UNBINDABLE; if (!propagation) propagation |= MS_PRIVATE; return propagation; } static void statmount_sb_basic(struct kstatmount *s) { struct super_block *sb = s->mnt->mnt_sb; s->sm.mask |= STATMOUNT_SB_BASIC; s->sm.sb_dev_major = MAJOR(sb->s_dev); s->sm.sb_dev_minor = MINOR(sb->s_dev); s->sm.sb_magic = sb->s_magic; s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); } static void statmount_mnt_basic(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_MNT_BASIC; s->sm.mnt_id = m->mnt_id_unique; s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; s->sm.mnt_id_old = m->mnt_id; s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); s->sm.mnt_propagation = mnt_to_propagation_flags(m); s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0; s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; } static void statmount_propagate_from(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_PROPAGATE_FROM; if (IS_MNT_SLAVE(m)) s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); } static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq) { int ret; size_t start = seq->count; ret = show_path(seq, s->mnt->mnt_root); if (ret) return ret; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; /* * Unescape the result. It would be better if supplied string was not * escaped in the first place, but that's a pretty invasive change. */ seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); return 0; } static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; int err; err = seq_path_root(seq, &mnt_path, &s->root, ""); return err == SEQ_SKIP ? 0 : err; } static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; seq_puts(seq, sb->s_type->name); return 0; } static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns) { s->sm.mask |= STATMOUNT_MNT_NS_ID; s->sm.mnt_ns_id = ns->seq; } static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; int err; if (sb->s_op->show_options) { size_t start = seq->count; err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (seq->count == start) return 0; /* skip leading comma */ memmove(seq->buf + start, seq->buf + start + 1, seq->count - start - 1); seq->count--; } return 0; } static int statmount_string(struct kstatmount *s, u64 flag) { int ret; size_t kbufsize; struct seq_file *seq = &s->seq; struct statmount *sm = &s->sm; switch (flag) { case STATMOUNT_FS_TYPE: sm->fs_type = seq->count; ret = statmount_fs_type(s, seq); break; case STATMOUNT_MNT_ROOT: sm->mnt_root = seq->count; ret = statmount_mnt_root(s, seq); break; case STATMOUNT_MNT_POINT: sm->mnt_point = seq->count; ret = statmount_mnt_point(s, seq); break; case STATMOUNT_MNT_OPTS: sm->mnt_opts = seq->count; ret = statmount_mnt_opts(s, seq); break; default: WARN_ON_ONCE(true); return -EINVAL; } if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize))) return -EOVERFLOW; if (kbufsize >= s->bufsize) return -EOVERFLOW; /* signal a retry */ if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (ret) return ret; seq->buf[seq->count++] = '\0'; sm->mask |= flag; return 0; } static int copy_statmount_to_user(struct kstatmount *s) { struct statmount *sm = &s->sm; struct seq_file *seq = &s->seq; char __user *str = ((char __user *)s->buf) + sizeof(*sm); size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); if (seq->count && copy_to_user(str, seq->buf, seq->count)) return -EFAULT; /* Return the number of bytes copied to the buffer */ sm->size = copysize + seq->count; if (copy_to_user(s->buf, sm, copysize)) return -EFAULT; return 0; } static struct mount *listmnt_next(struct mount *curr, bool reverse) { struct rb_node *node; if (reverse) node = rb_prev(&curr->mnt_node); else node = rb_next(&curr->mnt_node); return node_to_mount(node); } static int grab_requested_root(struct mnt_namespace *ns, struct path *root) { struct mount *first, *child; rwsem_assert_held(&namespace_sem); /* We're looking at our own ns, just use get_fs_root. */ if (ns == current->nsproxy->mnt_ns) { get_fs_root(current->fs, root); return 0; } /* * We have to find the first mount in our ns and use that, however it * may not exist, so handle that properly. */ if (RB_EMPTY_ROOT(&ns->mounts)) return -ENOENT; first = child = ns->root; for (;;) { child = listmnt_next(child, false); if (!child) return -ENOENT; if (child->mnt_parent == first) break; } root->mnt = mntget(&child->mnt); root->dentry = dget(root->mnt->mnt_root); return 0; } static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, struct mnt_namespace *ns) { struct path root __free(path_put) = {}; struct mount *m; int err; /* Has the namespace already been emptied? */ if (mnt_ns_id && RB_EMPTY_ROOT(&ns->mounts)) return -ENOENT; s->mnt = lookup_mnt_in_ns(mnt_id, ns); if (!s->mnt) return -ENOENT; err = grab_requested_root(ns, &root); if (err) return err; /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ m = real_mount(s->mnt); if (!is_path_reachable(m, m->mnt.mnt_root, &root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; err = security_sb_statfs(s->mnt->mnt_root); if (err) return err; s->root = root; if (s->mask & STATMOUNT_SB_BASIC) statmount_sb_basic(s); if (s->mask & STATMOUNT_MNT_BASIC) statmount_mnt_basic(s); if (s->mask & STATMOUNT_PROPAGATE_FROM) statmount_propagate_from(s); if (s->mask & STATMOUNT_FS_TYPE) err = statmount_string(s, STATMOUNT_FS_TYPE); if (!err && s->mask & STATMOUNT_MNT_ROOT) err = statmount_string(s, STATMOUNT_MNT_ROOT); if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); if (!err && s->mask & STATMOUNT_MNT_OPTS) err = statmount_string(s, STATMOUNT_MNT_OPTS); if (!err && s->mask & STATMOUNT_MNT_NS_ID) statmount_mnt_ns_id(s, ns); if (err) return err; return 0; } static inline bool retry_statmount(const long ret, size_t *seq_size) { if (likely(ret != -EAGAIN)) return false; if (unlikely(check_mul_overflow(*seq_size, 2, seq_size))) return false; if (unlikely(*seq_size > MAX_RW_COUNT)) return false; return true; } #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \ STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS) static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, size_t seq_size) { if (!access_ok(buf, bufsize)) return -EFAULT; memset(ks, 0, sizeof(*ks)); ks->mask = kreq->param; ks->buf = buf; ks->bufsize = bufsize; if (ks->mask & STATMOUNT_STRING_REQ) { if (bufsize == sizeof(ks->sm)) return -EOVERFLOW; ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT); if (!ks->seq.buf) return -ENOMEM; ks->seq.size = seq_size; } return 0; } static int copy_mnt_id_req(const struct mnt_id_req __user *req, struct mnt_id_req *kreq) { int ret; size_t usize; BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1); ret = get_user(usize, &req->size); if (ret) return -EFAULT; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) return -EINVAL; memset(kreq, 0, sizeof(*kreq)); ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; if (kreq->spare != 0) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; return 0; } /* * If the user requested a specific mount namespace id, look that up and return * that, or if not simply grab a passive reference on our mount namespace and * return that. */ static struct mnt_namespace *grab_requested_mnt_ns(u64 mnt_ns_id) { if (mnt_ns_id) return lookup_mnt_ns(mnt_ns_id); refcount_inc(¤t->nsproxy->mnt_ns->passive); return current->nsproxy->mnt_ns; } SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) { struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct kstatmount *ks __free(kfree) = NULL; struct mnt_id_req kreq; /* We currently support retrieval of 3 strings. */ size_t seq_size = 3 * PATH_MAX; int ret; if (flags) return -EINVAL; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; ns = grab_requested_mnt_ns(kreq.mnt_ns_id); if (!ns) return -ENOENT; if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT); if (!ks) return -ENOMEM; retry: ret = prepare_kstatmount(ks, &kreq, buf, bufsize, seq_size); if (ret) return ret; scoped_guard(rwsem_read, &namespace_sem) ret = do_statmount(ks, kreq.mnt_id, kreq.mnt_ns_id, ns); if (!ret) ret = copy_statmount_to_user(ks); kvfree(ks->seq.buf); if (retry_statmount(ret, &seq_size)) goto retry; return ret; } static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids, bool reverse) { struct path root __free(path_put) = {}; struct path orig; struct mount *r, *first; ssize_t ret; rwsem_assert_held(&namespace_sem); ret = grab_requested_root(ns, &root); if (ret) return ret; if (mnt_parent_id == LSMT_ROOT) { orig = root; } else { orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns); if (!orig.mnt) return -ENOENT; orig.dentry = orig.mnt->mnt_root; } /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; ret = security_sb_statfs(orig.dentry); if (ret) return ret; if (!last_mnt_id) { if (reverse) first = node_to_mount(rb_last(&ns->mounts)); else first = node_to_mount(rb_first(&ns->mounts)); } else { if (reverse) first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); else first = mnt_find_id_at(ns, last_mnt_id + 1); } for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, &orig)) continue; *mnt_ids = r->mnt_id_unique; mnt_ids++; nr_mnt_ids--; ret++; } return ret; } SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags) { u64 *kmnt_ids __free(kvfree) = NULL; const size_t maxcount = 1000000; struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct mnt_id_req kreq; u64 last_mnt_id; ssize_t ret; if (flags & ~LISTMOUNT_REVERSE) return -EINVAL; /* * If the mount namespace really has more than 1 million mounts the * caller must iterate over the mount namespace (and reconsider their * system design...). */ if (unlikely(nr_mnt_ids > maxcount)) return -EOVERFLOW; if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids))) return -EFAULT; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; last_mnt_id = kreq.param; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kmnt_ids), GFP_KERNEL_ACCOUNT); if (!kmnt_ids) return -ENOMEM; ns = grab_requested_mnt_ns(kreq.mnt_ns_id); if (!ns) return -ENOENT; if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; scoped_guard(rwsem_read, &namespace_sem) ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids, nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (ret <= 0) return ret; if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) return -EFAULT; return ret; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); ns->root = m; ns->nr_mounts = 1; mnt_add_to_ns(ns, m); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); mnt_ns_tree_add(ns); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!refcount_dec_and_test(&ns->ns.count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR(mnt)) { mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt, *n; bool visible = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { struct mount *child; int mnt_flags; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; #ifdef CONFIG_SYSCTL static struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, }; static int __init init_fs_namespace_sysctls(void) { register_sysctl_init("fs", fs_namespace_sysctls); return 0; } fs_initcall(init_fs_namespace_sysctls); #endif /* CONFIG_SYSCTL */ |
| 177 177 177 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/cgroup.h> #include <linux/wait.h> #include <linux/workqueue.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* * There could be abnormal cpuset configurations for cpu or memory * node binding, add this key to provide a quick low-cost judgment * of the situation. */ DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; /* * Invalid partition error code */ enum prs_errcode { PERR_NONE = 0, PERR_INVCPUS, PERR_INVPARENT, PERR_NOTPART, PERR_NOTEXCL, PERR_NOCPUS, PERR_HOTPLUG, PERR_CPUSEMPTY, PERR_HKEEPING, }; static const char * const perr_strings[] = { [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus.exclusive", [PERR_INVPARENT] = "Parent is an invalid partition root", [PERR_NOTPART] = "Parent is not a partition root", [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive", [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", [PERR_HOTPLUG] = "No cpu available due to hotplug", [PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty", [PERR_HKEEPING] = "partition config conflicts with housekeeping setup", }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierarchy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * Exclusive CPUs dedicated to current cgroup (default hierarchy only) * * The effective_cpus of a valid partition root comes solely from its * effective_xcpus and some of the effective_xcpus may be distributed * to sub-partitions below & hence excluded from its effective_cpus. * For a valid partition root, its effective_cpus have no relationship * with cpus_allowed unless its exclusive_cpus isn't set. * * This value will only be set if either exclusive_cpus is set or * when this cpuset becomes a local partition root. */ cpumask_var_t effective_xcpus; /* * Exclusive CPUs as requested by the user (default hierarchy only) * * Its value is independent of cpus_allowed and designates the set of * CPUs that can be granted to the current cpuset or its children when * it becomes a valid partition root. The effective set of exclusive * CPUs granted (effective_xcpus) depends on whether those exclusive * CPUs are passed down by its ancestors and not yet taken up by * another sibling partition root along the way. * * If its value isn't set, it defaults to cpus_allowed. */ cpumask_var_t exclusive_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of valid local child partitions */ int nr_subparts; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; /* * number of SCHED_DEADLINE tasks attached to this cpuset, so that we * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; /* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; /* Remote partition silbling list anchored at remote_children */ struct list_head remote_sibling; }; /* * Legacy hierarchy call to cgroup_transfer_tasks() is handled asynchrously */ struct cpuset_remove_tasks_struct { struct work_struct work; struct cpuset *cs; }; /* * Exclusive CPUs distributed out to sub-partitions of top_cpuset */ static cpumask_var_t subpartitions_cpus; /* * Exclusive CPUs in isolated partitions */ static cpumask_var_t isolated_cpus; /* List of remote partition root children */ static struct list_head remote_children; /* * Partition root states: * * 0 - member (not a partition root) * 1 - partition root * 2 - partition root without load balancing (isolated) * -1 - invalid partition root * -2 - invalid isolated partition root * * There are 2 types of partitions - local or remote. Local partitions are * those whose parents are partition root themselves. Setting of * cpuset.cpus.exclusive are optional in setting up local partitions. * Remote partitions are those whose parents are not partition roots. Passing * down exclusive CPUs by setting cpuset.cpus.exclusive along its ancestor * nodes are mandatory in creating a remote partition. * * For simplicity, a local partition can be created under a local or remote * partition but a remote partition cannot have any partition root in its * ancestor chain except the cgroup root. */ #define PRS_MEMBER 0 #define PRS_ROOT 1 #define PRS_ISOLATED 2 #define PRS_INVALID_ROOT -1 #define PRS_INVALID_ISOLATED -2 static inline bool is_prs_invalid(int prs_state) { return prs_state < 0; } /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks++; } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks--; } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_valid(const struct cpuset *cs) { return cs->partition_root_state > 0; } static inline int is_partition_invalid(const struct cpuset *cs) { return cs->partition_root_state < 0; } /* * Callers should hold callback_lock to modify partition_root_state. */ static inline void make_partition_invalid(struct cpuset *cs) { if (cs->partition_root_state > 0) cs->partition_root_state = -cs->partition_root_state; } /* * Send notification event of whenever partition_root_state changes. */ static inline void notify_partition_change(struct cpuset *cs, int old_prs) { if (old_prs == cs->partition_root_state) return; cgroup_file_notify(&cs->partition_file); /* Reset prs_err if not invalid */ if (is_partition_valid(cs)) WRITE_ONCE(cs->prs_err, PERR_NONE); } static struct cpuset top_cpuset = { .flags = BIT(CS_ONLINE) | BIT(CS_CPU_EXCLUSIVE) | BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE), .partition_root_state = PRS_ROOT, .relax_domain_level = -1, .remote_sibling = LIST_HEAD_INIT(top_cpuset.remote_sibling), }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, it blocks others, ensuring that it is the only task able to * also acquire callback_lock and be able to modify cpusets. It can perform * various checks on the cpuset structure first, knowing nothing will change. * It can also allocate memory while just holding cpuset_mutex. While it is * performing these checks, various callback routines can briefly acquire * callback_lock to query cpusets. Once it is ready to make the changes, it * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_seq_show() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); static inline void check_insane_mems_config(nodemask_t *nodes) { if (!cpusets_insane_config() && movable_only_nodes(nodes)) { static_branch_enable(&cpusets_insane_config_key); pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" "Cpuset allocations might fail even with a lot of memory available.\n", nodemask_pr_args(nodes)); } } /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /** * partition_is_populated - check if partition has tasks * @cs: partition root to be checked * @excluded_child: a child cpuset to be excluded in task checking * Return: true if there are tasks, false otherwise * * It is assumed that @cs is a valid partition root. @excluded_child should * be non-NULL when this cpuset is going to become a partition itself. */ static inline bool partition_is_populated(struct cpuset *cs, struct cpuset *excluded_child) { struct cgroup_subsys_state *css; struct cpuset *child; if (cs->css.cgroup->nr_populated_csets) return true; if (!excluded_child && !cs->nr_subparts) return cgroup_is_populated(cs->css.cgroup); rcu_read_lock(); cpuset_for_each_child(child, css, cs) { if (child == excluded_child) continue; if (is_partition_valid(child)) continue; if (cgroup_is_populated(child->css.cgroup)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /* * Return in pmask the portion of a task's cpusets's cpus_allowed that * are online and are capable of running the task. If none are found, * walk up the cpuset hierarchy until we find one that does have some * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); struct cpuset *cs; if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) cpumask_copy(pmask, cpu_online_mask); rcu_read_lock(); cs = task_cs(tsk); while (!cpumask_intersects(cs->effective_cpus, pmask)) cs = parent_cs(cs); cpumask_and(pmask, pmask, cs->effective_cpus); rcu_read_unlock(); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flags(struct cpuset *cs, struct task_struct *tsk) { if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) return; if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3, *pmask4; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->effective_xcpus; pmask4 = &cs->exclusive_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; pmask4 = NULL; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; if (pmask4 && !zalloc_cpumask_var(pmask4, GFP_KERNEL)) goto free_three; return 0; free_three: free_cpumask_var(*pmask3); free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->effective_xcpus); free_cpumask_var(cs->exclusive_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->effective_cpus, cs->effective_cpus); cpumask_copy(trial->effective_xcpus, cs->effective_xcpus); cpumask_copy(trial->exclusive_cpus, cs->exclusive_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* Return user specified exclusive CPUs */ static inline struct cpumask *user_xcpus(struct cpuset *cs) { return cpumask_empty(cs->exclusive_cpus) ? cs->cpus_allowed : cs->exclusive_cpus; } static inline bool xcpus_empty(struct cpuset *cs) { return cpumask_empty(cs->cpus_allowed) && cpumask_empty(cs->exclusive_cpus); } static inline struct cpumask *fetch_xcpus(struct cpuset *cs) { return !cpumask_empty(cs->exclusive_cpus) ? cs->exclusive_cpus : cpumask_empty(cs->effective_xcpus) ? cs->cpus_allowed : cs->effective_xcpus; } /* * cpusets_are_exclusive() - check if two cpusets are exclusive * * Return true if exclusive, false if not */ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2) { struct cpumask *xcpus1 = fetch_xcpus(cs1); struct cpumask *xcpus2 = fetch_xcpus(cs2); if (cpumask_intersects(xcpus1, xcpus2)) return false; return true; } /* * validate_change_legacy() - Validate conditions specific to legacy (v1) * behavior. */ static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; WARN_ON_ONCE(!rcu_read_lock_held()); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* On legacy hierarchy, we must be a subset of our parent cpuset. */ ret = -EACCES; par = parent_cs(cur); if (par && !is_cpuset_subset(trial, par)) goto out; ret = 0; out: return ret; } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret = 0; rcu_read_lock(); if (!is_in_v2_mode()) ret = validate_change_legacy(cur, trial); if (ret) goto out; /* Remaining checks don't apply to root cpuset */ if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap. exclusive_cpus cannot overlap with each other if set. */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { bool txset, cxset; /* Are exclusive_cpus set? */ if (c == cur) continue; txset = !cpumask_empty(trial->exclusive_cpus); cxset = !cpumask_empty(c->exclusive_cpus); if (is_cpu_exclusive(trial) || is_cpu_exclusive(c) || (txset && cxset)) { if (!cpusets_are_exclusive(trial, c)) goto out; } else if (txset || cxset) { struct cpumask *xcpus, *acpus; /* * When just one of the exclusive_cpus's is set, * cpus_allowed of the other cpuset, if set, cannot be * a subset of it or none of those CPUs will be * available if these exclusive CPUs are activated. */ if (txset) { xcpus = trial->exclusive_cpus; acpus = c->cpus_allowed; } else { xcpus = c->exclusive_cpus; acpus = trial->cpus_allowed; } if (!cpumask_empty(acpus) && cpumask_subset(acpus, xcpus)) goto out; } if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); bool cgrpv2 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && cpumask_empty(subpartitions_cpus)) { single_root_domain: ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; if (cgrpv2) goto v2; /* * v1: * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_TYPE_DOMAIN)))) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree */ pos_css = css_rightmost_descendant(pos_css); continue; v2: /* * Only valid partition roots that are not isolated and with * non-empty effective_cpus will be saved into csn[]. */ if ((cp->partition_root_state == PRS_ROOT) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* * Skip @cp's subtree if not a partition root and has no * exclusive CPUs to be granted to child cpusets. */ if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); /* * If there are only isolated partitions underneath the cgroup root, * we can optimize out unneeded sched domains scanning. */ if (root_load_balance && (csn == 1)) goto single_root_domain; for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); /* * Cgroup v2 doesn't support domain attributes, just set all of them * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a * subset of HK_TYPE_DOMAIN housekeeping CPUs. */ if (cgrpv2) { for (i = 0; i < ndoms; i++) { cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) dattr[i] = SD_ATTR_INIT; } goto done; } for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (cs->nr_deadline_tasks == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_handle_hotplug() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (cpumask_empty(subpartitions_cpus) && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (!cpumask_empty(subpartitions_cpus)) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_valid(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ static void rebuild_sched_domains_cpuslocked(void) { mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); } void rebuild_sched_domains(void) { cpus_read_lock(); rebuild_sched_domains_cpuslocked(); cpus_read_unlock(); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask() * is used instead of effective_cpus to make sure all offline CPUs are also * included as hotplug code won't update cpumasks for tasks in top_cpuset. */ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { const struct cpumask *possible_mask = task_cpu_possible_mask(task); if (top_cs) { /* * Percpu kthreads in top_cpuset are ignored */ if (kthread_is_per_cpu(task)) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { cpumask_and(new_cpus, possible_mask, cs->effective_cpus); } set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * The result is valid only if the given cpuset isn't a partition root. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); } /* * Commands for update_parent_effective_cpumask */ enum partition_cmd { partcmd_enable, /* Enable partition root */ partcmd_enablei, /* Enable isolated partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's effective_cpus */ partcmd_invalidate, /* Make partition invalid */ }; static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on); static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp); /* * Update partition exclusive flag * * Return: 0 if successful, an error code otherwise */ static int update_partition_exclusive(struct cpuset *cs, int new_prs) { bool exclusive = (new_prs > PRS_MEMBER); if (exclusive && !is_cpu_exclusive(cs)) { if (update_flag(CS_CPU_EXCLUSIVE, cs, 1)) return PERR_NOTEXCL; } else if (!exclusive && is_cpu_exclusive(cs)) { /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } return 0; } /* * Update partition load balance flag and/or rebuild sched domain * * Changing load balance flag will automatically call * rebuild_sched_domains_locked(). * This function is for cgroup v2 only. */ static void update_partition_sd_lb(struct cpuset *cs, int old_prs) { int new_prs = cs->partition_root_state; bool rebuild_domains = (new_prs > 0) || (old_prs > 0); bool new_lb; /* * If cs is not a valid partition root, the load balance state * will follow its parent. */ if (new_prs > 0) { new_lb = (new_prs != PRS_ISOLATED); } else { new_lb = is_sched_load_balance(parent_cs(cs)); } if (new_lb != !!is_sched_load_balance(cs)) { rebuild_domains = true; if (new_lb) set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); else clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } if (rebuild_domains) rebuild_sched_domains_locked(); } /* * tasks_nocpu_error - Return true if tasks will have no effective_cpus */ static bool tasks_nocpu_error(struct cpuset *parent, struct cpuset *cs, struct cpumask *xcpus) { /* * A populated partition (cs or parent) can't have empty effective_cpus */ return (cpumask_subset(parent->effective_cpus, xcpus) && partition_is_populated(parent, cs)) || (!cpumask_intersects(xcpus, cpu_active_mask) && partition_is_populated(cs, NULL)); } static void reset_partition_data(struct cpuset *cs) { struct cpuset *parent = parent_cs(cs); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) return; lockdep_assert_held(&callback_lock); cs->nr_subparts = 0; if (cpumask_empty(cs->exclusive_cpus)) { cpumask_clear(cs->effective_xcpus); if (is_cpu_exclusive(cs)) clear_bit(CS_CPU_EXCLUSIVE, &cs->flags); } if (!cpumask_and(cs->effective_cpus, parent->effective_cpus, cs->cpus_allowed)) { cs->use_parent_ecpus = true; parent->child_ecpus_count++; cpumask_copy(cs->effective_cpus, parent->effective_cpus); } } /* * partition_xcpus_newstate - Exclusive CPUs state change * @old_prs: old partition_root_state * @new_prs: new partition_root_state * @xcpus: exclusive CPUs with state change */ static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs == new_prs); if (new_prs == PRS_ISOLATED) cpumask_or(isolated_cpus, isolated_cpus, xcpus); else cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); } /* * partition_xcpus_add - Add new exclusive CPUs to partition * @new_prs: new partition_root_state * @parent: parent cpuset * @xcpus: exclusive CPUs to be added * Return: true if isolated_cpus modified, false otherwise * * Remote partition if parent == NULL */ static bool partition_xcpus_add(int new_prs, struct cpuset *parent, struct cpumask *xcpus) { bool isolcpus_updated; WARN_ON_ONCE(new_prs < 0); lockdep_assert_held(&callback_lock); if (!parent) parent = &top_cpuset; if (parent == &top_cpuset) cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus); isolcpus_updated = (new_prs != parent->partition_root_state); if (isolcpus_updated) partition_xcpus_newstate(parent->partition_root_state, new_prs, xcpus); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus); return isolcpus_updated; } /* * partition_xcpus_del - Remove exclusive CPUs from partition * @old_prs: old partition_root_state * @parent: parent cpuset * @xcpus: exclusive CPUs to be removed * Return: true if isolated_cpus modified, false otherwise * * Remote partition if parent == NULL */ static bool partition_xcpus_del(int old_prs, struct cpuset *parent, struct cpumask *xcpus) { bool isolcpus_updated; WARN_ON_ONCE(old_prs < 0); lockdep_assert_held(&callback_lock); if (!parent) parent = &top_cpuset; if (parent == &top_cpuset) cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus); isolcpus_updated = (old_prs != parent->partition_root_state); if (isolcpus_updated) partition_xcpus_newstate(old_prs, parent->partition_root_state, xcpus); cpumask_and(xcpus, xcpus, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); return isolcpus_updated; } static void update_unbound_workqueue_cpumask(bool isolcpus_updated) { int ret; lockdep_assert_cpus_held(); if (!isolcpus_updated) return; ret = workqueue_unbound_exclude_cpumask(isolated_cpus); WARN_ON_ONCE(ret < 0); } /** * cpuset_cpu_is_isolated - Check if the given CPU is isolated * @cpu: the CPU number to be checked * Return: true if CPU is used in an isolated partition, false otherwise */ bool cpuset_cpu_is_isolated(int cpu) { return cpumask_test_cpu(cpu, isolated_cpus); } EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated); /* * compute_effective_exclusive_cpumask - compute effective exclusive CPUs * @cs: cpuset * @xcpus: effective exclusive CPUs value to be set * Return: true if xcpus is not empty, false otherwise. * * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set), * it must be a subset of parent's effective_xcpus. */ static bool compute_effective_exclusive_cpumask(struct cpuset *cs, struct cpumask *xcpus) { struct cpuset *parent = parent_cs(cs); if (!xcpus) xcpus = cs->effective_xcpus; return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus); } static inline bool is_remote_partition(struct cpuset *cs) { return !list_empty(&cs->remote_sibling); } static inline bool is_local_partition(struct cpuset *cs) { return is_partition_valid(cs) && !is_remote_partition(cs); } /* * remote_partition_enable - Enable current cpuset as a remote partition root * @cs: the cpuset to update * @new_prs: new partition_root_state * @tmp: temparary masks * Return: 1 if successful, 0 if error * * Enable the current cpuset to become a remote partition root taking CPUs * directly from the top cpuset. cpuset_mutex must be held by the caller. */ static int remote_partition_enable(struct cpuset *cs, int new_prs, struct tmpmasks *tmp) { bool isolcpus_updated; /* * The user must have sysadmin privilege. */ if (!capable(CAP_SYS_ADMIN)) return 0; /* * The requested exclusive_cpus must not be allocated to other * partitions and it can't use up all the root's effective_cpus. * * Note that if there is any local partition root above it or * remote partition root underneath it, its exclusive_cpus must * have overlapped with subpartitions_cpus. */ compute_effective_exclusive_cpumask(cs, tmp->new_cpus); if (cpumask_empty(tmp->new_cpus) || cpumask_intersects(tmp->new_cpus, subpartitions_cpus) || cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus)) return 0; spin_lock_irq(&callback_lock); isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus); list_add(&cs->remote_sibling, &remote_children); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } spin_unlock_irq(&callback_lock); update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. */ update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); return 1; } /* * remote_partition_disable - Remove current cpuset from remote partition list * @cs: the cpuset to update * @tmp: temparary masks * * The effective_cpus is also updated. * * cpuset_mutex must be held by the caller. */ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) { bool isolcpus_updated; compute_effective_exclusive_cpumask(cs, tmp->new_cpus); WARN_ON_ONCE(!is_remote_partition(cs)); WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus)); spin_lock_irq(&callback_lock); list_del_init(&cs->remote_sibling); isolcpus_updated = partition_xcpus_del(cs->partition_root_state, NULL, tmp->new_cpus); cs->partition_root_state = -cs->partition_root_state; if (!cs->prs_err) cs->prs_err = PERR_INVCPUS; reset_partition_data(cs); spin_unlock_irq(&callback_lock); update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. */ update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); } /* * remote_cpus_update - cpus_exclusive change of remote partition * @cs: the cpuset to be updated * @newmask: the new effective_xcpus mask * @tmp: temparary masks * * top_cpuset and subpartitions_cpus will be updated or partition can be * invalidated. */ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask, struct tmpmasks *tmp) { bool adding, deleting; int prs = cs->partition_root_state; int isolcpus_updated = 0; if (WARN_ON_ONCE(!is_remote_partition(cs))) return; WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus)); if (cpumask_empty(newmask)) goto invalidate; adding = cpumask_andnot(tmp->addmask, newmask, cs->effective_xcpus); deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, newmask); /* * Additions of remote CPUs is only allowed if those CPUs are * not allocated to other partitions and there are effective_cpus * left in the top cpuset. */ if (adding && (!capable(CAP_SYS_ADMIN) || cpumask_intersects(tmp->addmask, subpartitions_cpus) || cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))) goto invalidate; spin_lock_irq(&callback_lock); if (adding) isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask); if (deleting) isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask); spin_unlock_irq(&callback_lock); update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. */ update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); return; invalidate: remote_partition_disable(cs, tmp); } /* * remote_partition_check - check if a child remote partition needs update * @cs: the cpuset to be updated * @newmask: the new effective_xcpus mask * @delmask: temporary mask for deletion (not in tmp) * @tmp: temparary masks * * This should be called before the given cs has updated its cpus_allowed * and/or effective_xcpus. */ static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask, struct cpumask *delmask, struct tmpmasks *tmp) { struct cpuset *child, *next; int disable_cnt = 0; /* * Compute the effective exclusive CPUs that will be deleted. */ if (!cpumask_andnot(delmask, cs->effective_xcpus, newmask) || !cpumask_intersects(delmask, subpartitions_cpus)) return; /* No deletion of exclusive CPUs in partitions */ /* * Searching the remote children list to look for those that will * be impacted by the deletion of exclusive CPUs. * * Since a cpuset must be removed from the remote children list * before it can go offline and holding cpuset_mutex will prevent * any change in cpuset status. RCU read lock isn't needed. */ lockdep_assert_held(&cpuset_mutex); list_for_each_entry_safe(child, next, &remote_children, remote_sibling) if (cpumask_intersects(child->effective_cpus, delmask)) { remote_partition_disable(child, tmp); disable_cnt++; } if (disable_cnt) rebuild_sched_domains_locked(); } /* * prstate_housekeeping_conflict - check for partition & housekeeping conflicts * @prstate: partition root state to be checked * @new_cpus: cpu mask * Return: true if there is conflict, false otherwise * * CPUs outside of housekeeping_cpumask(HK_TYPE_DOMAIN) can only be used in * an isolated partition. */ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) { const struct cpumask *hk_domain = housekeeping_cpumask(HK_TYPE_DOMAIN); bool all_in_hk = cpumask_subset(new_cpus, hk_domain); if (!all_in_hk && (prstate != PRS_ISOLATED)) return true; return false; } /** * update_parent_effective_cpumask - update effective_cpus mask of parent cpuset * @cs: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0 or a partition root state error code * * For partcmd_enable*, the cpuset is being transformed from a non-partition * root to a partition root. The effective_xcpus (cpus_allowed if * effective_xcpus not set) mask of the given cpuset will be taken away from * parent's effective_cpus. The function will return 0 if all the CPUs listed * in effective_xcpus can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transformed from a partition * root back to a non-partition root. Any CPUs in effective_xcpus will be * given back to parent's effective_cpus. 0 will always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu list is * to be changed from effective_xcpus to newmask. Otherwise, effective_xcpus is * assumed to remain the same. The cpuset should either be a valid or invalid * partition root. The partition root state may change from valid to invalid * or vice versa. An error code will be returned if transitioning from * invalid to valid violates the exclusivity rule. * * For partcmd_invalidate, the current partition will be made invalid. * * The partcmd_enable* and partcmd_disable commands are used by * update_prstate(). An error code may be returned and the caller will check * for error. * * The partcmd_update command is used by update_cpumasks_hier() with newmask * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used * by update_cpumask() with NULL newmask. In both cases, the callers won't * check for error and so partition_root_state and prs_error will be updated * directly. */ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cs); int adding; /* Adding cpus to parent's effective_cpus */ int deleting; /* Deleting cpus from parent's effective_cpus */ int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */ int subparts_delta = 0; struct cpumask *xcpus; /* cs effective_xcpus */ int isolcpus_updated = 0; bool nocpu; lockdep_assert_held(&cpuset_mutex); /* * new_prs will only be changed for the partcmd_update and * partcmd_invalidate commands. */ adding = deleting = false; old_prs = new_prs = cs->partition_root_state; xcpus = user_xcpus(cs); if (cmd == partcmd_invalidate) { if (is_prs_invalid(old_prs)) return 0; /* * Make the current partition invalid. */ if (is_partition_valid(parent)) adding = cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); if (old_prs > 0) { new_prs = -old_prs; subparts_delta--; } goto write_error; } /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_valid(parent)) { return is_partition_invalid(parent) ? PERR_INVPARENT : PERR_NOTPART; } if (!newmask && xcpus_empty(cs)) return PERR_CPUSEMPTY; nocpu = tasks_nocpu_error(parent, cs, xcpus); if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) { /* * Enabling partition root is not allowed if its * effective_xcpus is empty or doesn't overlap with * parent's effective_xcpus. */ if (cpumask_empty(xcpus) || !cpumask_intersects(xcpus, parent->effective_xcpus)) return PERR_INVCPUS; if (prstate_housekeeping_conflict(new_prs, xcpus)) return PERR_HKEEPING; /* * A parent can be left with no CPU as long as there is no * task directly associated with the parent partition. */ if (nocpu) return PERR_NOCPUS; cpumask_copy(tmp->delmask, xcpus); deleting = true; subparts_delta++; new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED; } else if (cmd == partcmd_disable) { /* * May need to add cpus to parent's effective_cpus for * valid partition root. */ adding = !is_prs_invalid(old_prs) && cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); if (adding) subparts_delta--; new_prs = PRS_MEMBER; } else if (newmask) { /* * Empty cpumask is not allowed */ if (cpumask_empty(newmask)) { part_error = PERR_CPUSEMPTY; goto write_error; } /* * partcmd_update with newmask: * * Compute add/delete mask to/from effective_cpus * * For valid partition: * addmask = exclusive_cpus & ~newmask * & parent->effective_xcpus * delmask = newmask & ~exclusive_cpus * & parent->effective_xcpus * * For invalid partition: * delmask = newmask & parent->effective_xcpus */ if (is_prs_invalid(old_prs)) { adding = false; deleting = cpumask_and(tmp->delmask, newmask, parent->effective_xcpus); } else { cpumask_andnot(tmp->addmask, xcpus, newmask); adding = cpumask_and(tmp->addmask, tmp->addmask, parent->effective_xcpus); cpumask_andnot(tmp->delmask, newmask, xcpus); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->effective_xcpus); } /* * Make partition invalid if parent's effective_cpus could * become empty and there are tasks in the parent. */ if (nocpu && (!adding || !cpumask_intersects(tmp->addmask, cpu_active_mask))) { part_error = PERR_NOCPUS; deleting = false; adding = cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); } } else { /* * partcmd_update w/o newmask * * delmask = effective_xcpus & parent->effective_cpus * * This can be called from: * 1) update_cpumasks_hier() * 2) cpuset_hotplug_update_tasks() * * Check to see if it can be transitioned from valid to * invalid partition or vice versa. * * A partition error happens when parent has tasks and all * its effective CPUs will have to be distributed out. */ WARN_ON_ONCE(!is_partition_valid(parent)); if (nocpu) { part_error = PERR_NOCPUS; if (is_partition_valid(cs)) adding = cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); } else if (is_partition_invalid(cs) && cpumask_subset(xcpus, parent->effective_xcpus)) { struct cgroup_subsys_state *css; struct cpuset *child; bool exclusive = true; /* * Convert invalid partition to valid has to * pass the cpu exclusivity test. */ rcu_read_lock(); cpuset_for_each_child(child, css, parent) { if (child == cs) continue; if (!cpusets_are_exclusive(cs, child)) { exclusive = false; break; } } rcu_read_unlock(); if (exclusive) deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_cpus); else part_error = PERR_NOTEXCL; } } write_error: if (part_error) WRITE_ONCE(cs->prs_err, part_error); if (cmd == partcmd_update) { /* * Check for possible transition between valid and invalid * partition root. */ switch (cs->partition_root_state) { case PRS_ROOT: case PRS_ISOLATED: if (part_error) { new_prs = -old_prs; subparts_delta--; } break; case PRS_INVALID_ROOT: case PRS_INVALID_ISOLATED: if (!part_error) { new_prs = -old_prs; subparts_delta++; } break; } } if (!adding && !deleting && (new_prs == old_prs)) return 0; /* * Transitioning between invalid to valid or vice versa may require * changing CS_CPU_EXCLUSIVE. In the case of partcmd_update, * validate_change() has already been successfully called and * CPU lists in cs haven't been updated yet. So defer it to later. */ if ((old_prs != new_prs) && (cmd != partcmd_update)) { int err = update_partition_exclusive(cs, new_prs); if (err) return err; } /* * Change the parent's effective_cpus & effective_xcpus (top cpuset * only). * * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (old_prs != new_prs) { cs->partition_root_state = new_prs; if (new_prs <= 0) cs->nr_subparts = 0; } /* * Adding to parent's effective_cpus means deletion CPUs from cs * and vice versa. */ if (adding) isolcpus_updated += partition_xcpus_del(old_prs, parent, tmp->addmask); if (deleting) isolcpus_updated += partition_xcpus_add(new_prs, parent, tmp->delmask); if (is_partition_valid(parent)) { parent->nr_subparts += subparts_delta; WARN_ON_ONCE(parent->nr_subparts < 0); } spin_unlock_irq(&callback_lock); update_unbound_workqueue_cpumask(isolcpus_updated); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive(cs, new_prs); if (adding || deleting) { update_tasks_cpumask(parent, tmp->addmask); update_sibling_cpumasks(parent, cs, tmp); } /* * For partcmd_update without newmask, it is being called from * cpuset_handle_hotplug(). Update the load balance flag and * scheduling domain accordingly. */ if ((cmd == partcmd_update) && !newmask) update_partition_sd_lb(cs, old_prs); notify_partition_change(cs, old_prs); return 0; } /** * compute_partition_effective_cpumask - compute effective_cpus for partition * @cs: partition root cpuset * @new_ecpus: previously computed effective_cpus to be updated * * Compute the effective_cpus of a partition root by scanning effective_xcpus * of child partition roots and excluding their effective_xcpus. * * This has the side effect of invalidating valid child partition roots, * if necessary. Since it is called from either cpuset_hotplug_update_tasks() * or update_cpumasks_hier() where parent and children are modified * successively, we don't need to call update_parent_effective_cpumask() * and the child's effective_cpus will be updated in later iterations. * * Note that rcu_read_lock() is assumed to be held. */ static void compute_partition_effective_cpumask(struct cpuset *cs, struct cpumask *new_ecpus) { struct cgroup_subsys_state *css; struct cpuset *child; bool populated = partition_is_populated(cs, NULL); /* * Check child partition roots to see if they should be * invalidated when * 1) child effective_xcpus not a subset of new * excluisve_cpus * 2) All the effective_cpus will be used up and cp * has tasks */ compute_effective_exclusive_cpumask(cs, new_ecpus); cpumask_and(new_ecpus, new_ecpus, cpu_active_mask); rcu_read_lock(); cpuset_for_each_child(child, css, cs) { if (!is_partition_valid(child)) continue; child->prs_err = 0; if (!cpumask_subset(child->effective_xcpus, cs->effective_xcpus)) child->prs_err = PERR_INVCPUS; else if (populated && cpumask_subset(new_ecpus, child->effective_xcpus)) child->prs_err = PERR_NOCPUS; if (child->prs_err) { int old_prs = child->partition_root_state; /* * Invalidate child partition */ spin_lock_irq(&callback_lock); make_partition_invalid(child); cs->nr_subparts--; child->nr_subparts = 0; spin_unlock_irq(&callback_lock); notify_partition_change(child, old_prs); continue; } cpumask_andnot(new_ecpus, new_ecpus, child->effective_xcpus); } rcu_read_unlock(); } /* * update_cpumasks_hier() flags */ #define HIER_CHECKALL 0x01 /* Check all cpusets with no skipping */ #define HIER_NO_SD_REBUILD 0x02 /* Don't rebuild sched domains */ /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * @force: don't skip any descendant cpusets if set * * When configured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, int flags) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; int old_prs, new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); bool remote = is_remote_partition(cp); bool update_parent = false; /* * Skip descendent remote partition that acquires CPUs * directly from top cpuset unless it is cs. */ if (remote && (cp != cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * Update effective_xcpus if exclusive_cpus set. * The case when exclusive_cpus isn't set is handled later. */ if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs)) { spin_lock_irq(&callback_lock); compute_effective_exclusive_cpumask(cp, NULL); spin_unlock_irq(&callback_lock); } old_prs = new_prs = cp->partition_root_state; if (remote || (is_partition_valid(parent) && is_partition_valid(cp))) compute_partition_effective_cpumask(cp, tmp->new_cpus); else compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * A partition with no effective_cpus is allowed as long as * there is no task associated with it. Call * update_parent_effective_cpumask() to check it. */ if (is_partition_valid(cp) && cpumask_empty(tmp->new_cpus)) { update_parent = true; goto update_parent_effective; } /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs unless * it is a partition root that has explicitly distributed * out all its CPUs. */ if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } if (remote) goto get_css; /* * Skip the whole subtree if * 1) the cpumask remains the same, * 2) has no partition root state, * 3) HIER_CHECKALL flag not set, and * 4) for v2 load balance state same as its parent. */ if (!cp->partition_root_state && !(flags & HIER_CHECKALL) && cpumask_equal(tmp->new_cpus, cp->effective_cpus) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (is_sched_load_balance(parent) == is_sched_load_balance(cp)))) { pos_css = css_rightmost_descendant(pos_css); continue; } update_parent_effective: /* * update_parent_effective_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's effective_cpus changes. */ if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_ROOT: case PRS_ISOLATED: update_parent = true; break; default: /* * When parent is not a partition root or is * invalid, child partition roots become * invalid too. */ if (is_partition_valid(cp)) new_prs = -cp->partition_root_state; WRITE_ONCE(cp->prs_err, is_partition_invalid(parent) ? PERR_INVPARENT : PERR_NOTPART); break; } } get_css: if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); if (update_parent) { update_parent_effective_cpumask(cp, partcmd_update, NULL, tmp); /* * The cpuset partition_root_state may become * invalid. Capture it. */ new_prs = cp->partition_root_state; } spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); cp->partition_root_state = new_prs; /* * Make sure effective_xcpus is properly set for a valid * partition root. */ if ((new_prs > 0) && cpumask_empty(cp->exclusive_cpus)) cpumask_and(cp->effective_xcpus, cp->cpus_allowed, parent->effective_xcpus); else if (new_prs < 0) reset_partition_data(cp); spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp, cp->effective_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE * from parent if current cpuset isn't a valid partition root * and their load balance states differ. */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && !is_partition_valid(cp) && (is_sched_load_balance(parent) != is_sched_load_balance(cp))) { if (is_sched_load_balance(parent)) set_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); else clear_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); } /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_valid(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD)) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() * if their effective_cpus will need to be changed. * * With the addition of effective_xcpus which is a subset of * cpus_allowed. It is possible a change in parent's effective_cpus * due to a change in a child partition's effective_xcpus will impact * its siblings even if they do not inherit parent's effective_cpus * directly. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. HIER_NO_SD_REBUILD * flag is used to suppress rebuild of sched domains as the callers * will take care of that. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus && !is_partition_valid(sibling)) { compute_effective_cpumask(tmp->new_cpus, sibling, parent); if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus)) continue; } if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp, HIER_NO_SD_REBUILD); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; struct cpuset *parent = parent_cs(cs); bool invalidate = false; int hier_flags = 0; int old_prs = cs->partition_root_state; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); cpumask_clear(trialcs->effective_xcpus); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; if (!cpumask_subset(trialcs->cpus_allowed, top_cpuset.cpus_allowed)) return -EINVAL; /* * When exclusive_cpus isn't explicitly set, it is constrainted * by cpus_allowed and parent's effective_xcpus. Otherwise, * trialcs->effective_xcpus is used as a temporary cpumask * for checking validity of the partition root. */ if (!cpumask_empty(trialcs->exclusive_cpus) || is_partition_valid(cs)) compute_effective_exclusive_cpumask(trialcs, NULL); } /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; if (alloc_cpumasks(NULL, &tmp)) return -ENOMEM; if (old_prs) { if (is_partition_valid(cs) && cpumask_empty(trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_INVCPUS; } else if (prstate_housekeeping_conflict(old_prs, trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_HKEEPING; } else if (tasks_nocpu_error(parent, cs, trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_NOCPUS; } } /* * Check all the descendants in update_cpumasks_hier() if * effective_xcpus is to be changed. */ if (!cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus)) hier_flags = HIER_CHECKALL; retval = validate_change(cs, trialcs); if ((retval == -EINVAL) && cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) { struct cgroup_subsys_state *css; struct cpuset *cp; /* * The -EINVAL error code indicates that partition sibling * CPU exclusivity rule has been violated. We still allow * the cpumask change to proceed while invalidating the * partition. However, any conflicting sibling partitions * have to be marked as invalid too. */ invalidate = true; rcu_read_lock(); cpuset_for_each_child(cp, css, parent) { struct cpumask *xcpus = fetch_xcpus(trialcs); if (is_partition_valid(cp) && cpumask_intersects(xcpus, cp->effective_xcpus)) { rcu_read_unlock(); update_parent_effective_cpumask(cp, partcmd_invalidate, NULL, &tmp); rcu_read_lock(); } } rcu_read_unlock(); retval = 0; } if (retval < 0) goto out_free; if (is_partition_valid(cs) || (is_partition_invalid(cs) && !invalidate)) { struct cpumask *xcpus = trialcs->effective_xcpus; if (cpumask_empty(xcpus) && is_partition_invalid(cs)) xcpus = trialcs->cpus_allowed; /* * Call remote_cpus_update() to handle valid remote partition */ if (is_remote_partition(cs)) remote_cpus_update(cs, xcpus, &tmp); else if (invalidate) update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, &tmp); else update_parent_effective_cpumask(cs, partcmd_update, xcpus, &tmp); } else if (!cpumask_empty(cs->exclusive_cpus)) { /* * Use trialcs->effective_cpus as a temp cpumask */ remote_partition_check(cs, trialcs->effective_xcpus, trialcs->effective_cpus, &tmp); } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus); if ((old_prs > 0) && !is_partition_valid(cs)) reset_partition_data(cs); spin_unlock_irq(&callback_lock); /* effective_cpus/effective_xcpus will be updated here */ update_cpumasks_hier(cs, &tmp, hier_flags); /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */ if (cs->partition_root_state) update_partition_sd_lb(cs, old_prs); out_free: free_cpumasks(NULL, &tmp); return retval; } /** * update_exclusive_cpumask - update the exclusive_cpus mask of a cpuset * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset * * The tasks' cpumask will be updated if cs is a valid partition root. */ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; struct cpuset *parent = parent_cs(cs); bool invalidate = false; int hier_flags = 0; int old_prs = cs->partition_root_state; if (!*buf) { cpumask_clear(trialcs->exclusive_cpus); cpumask_clear(trialcs->effective_xcpus); } else { retval = cpulist_parse(buf, trialcs->exclusive_cpus); if (retval < 0) return retval; } /* Nothing to do if the CPUs didn't change */ if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus)) return 0; if (*buf) compute_effective_exclusive_cpumask(trialcs, NULL); /* * Check all the descendants in update_cpumasks_hier() if * effective_xcpus is to be changed. */ if (!cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus)) hier_flags = HIER_CHECKALL; retval = validate_change(cs, trialcs); if (retval) return retval; if (alloc_cpumasks(NULL, &tmp)) return -ENOMEM; if (old_prs) { if (cpumask_empty(trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_INVCPUS; } else if (prstate_housekeeping_conflict(old_prs, trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_HKEEPING; } else if (tasks_nocpu_error(parent, cs, trialcs->effective_xcpus)) { invalidate = true; cs->prs_err = PERR_NOCPUS; } if (is_remote_partition(cs)) { if (invalidate) remote_partition_disable(cs, &tmp); else remote_cpus_update(cs, trialcs->effective_xcpus, &tmp); } else if (invalidate) { update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, &tmp); } else { update_parent_effective_cpumask(cs, partcmd_update, trialcs->effective_xcpus, &tmp); } } else if (!cpumask_empty(trialcs->exclusive_cpus)) { /* * Use trialcs->effective_cpus as a temp cpumask */ remote_partition_check(cs, trialcs->effective_xcpus, trialcs->effective_cpus, &tmp); } spin_lock_irq(&callback_lock); cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus); cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus); if ((old_prs > 0) && !is_partition_valid(cs)) reset_partition_data(cs); spin_unlock_irq(&callback_lock); /* * Call update_cpumasks_hier() to update effective_cpus/effective_xcpus * of the subtree when it is a valid partition root or effective_xcpus * is updated. */ if (is_partition_valid(cs) || hier_flags) update_cpumasks_hier(cs, &tmp, hier_flags); /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */ if (cs->partition_root_state) update_partition_sd_lb(cs, old_prs); free_cpumasks(NULL, &tmp); return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; if (nodes_equal(*from, *to)) { mmput(mm); return; } mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; check_insane_mems_config(&trialcs->mems_allowed); spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flags(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /** * update_prstate - update partition_root_state * @cs: the cpuset to update * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err = PERR_NONE, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; bool new_xcpus_state = false; if (old_prs == new_prs) return 0; /* * Treat a previously invalid partition root as if it is a "member". */ if (new_prs && is_prs_invalid(old_prs)) old_prs = PRS_MEMBER; if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; /* * Setup effective_xcpus if not properly set yet, it will be cleared * later if partition becomes invalid. */ if ((new_prs > 0) && cpumask_empty(cs->exclusive_cpus)) { spin_lock_irq(&callback_lock); cpumask_and(cs->effective_xcpus, cs->cpus_allowed, parent->effective_xcpus); spin_unlock_irq(&callback_lock); } err = update_partition_exclusive(cs, new_prs); if (err) goto out; if (!old_prs) { enum partition_cmd cmd = (new_prs == PRS_ROOT) ? partcmd_enable : partcmd_enablei; /* * cpus_allowed and exclusive_cpus cannot be both empty. */ if (xcpus_empty(cs)) { err = PERR_CPUSEMPTY; goto out; } err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask); /* * If an attempt to become local partition root fails, * try to become a remote partition root instead. */ if (err && remote_partition_enable(cs, new_prs, &tmpmask)) err = 0; } else if (old_prs && new_prs) { /* * A change in load balance state only, no change in cpumasks. */ new_xcpus_state = true; } else { /* * Switching back to member is always allowed even if it * disables child partitions. */ if (is_remote_partition(cs)) remote_partition_disable(cs, &tmpmask); else update_parent_effective_cpumask(cs, partcmd_disable, NULL, &tmpmask); /* * Invalidation of child partitions will be done in * update_cpumasks_hier(). */ } out: /* * Make partition invalid & disable CS_CPU_EXCLUSIVE if an error * happens. */ if (err) { new_prs = -new_prs; update_partition_exclusive(cs, new_prs); } spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; WRITE_ONCE(cs->prs_err, err); if (!is_partition_valid(cs)) reset_partition_data(cs); else if (new_xcpus_state) partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); update_unbound_workqueue_cpumask(new_xcpus_state); /* Force update if switching back to member */ update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0); /* Update sched domains and load balance flag */ update_partition_sd_lb(cs, old_prs); notify_partition_change(cs, old_prs); free_cpumasks(NULL, &tmpmask); return 0; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; /* * Check to see if a cpuset can accept a new task * For v1, cpus_allowed and mems_allowed can't be empty. * For v2, effective_cpus can't be empty. * Note that in v1, effective_cpus = cpus_allowed. */ static int cpuset_can_attach_check(struct cpuset *cs) { if (cpumask_empty(cs->effective_cpus) || (!is_in_v2_mode() && nodes_empty(cs->mems_allowed))) return -ENOSPC; return 0; } static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; bool cpus_updated, mems_updated; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); if (ret) goto out_unlock; cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; /* * Skip rights over task check in v2 when nothing changes, * migration permission derives from hierarchy ownership in * cgroup_procs_write_permission()). */ if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpus_updated || mems_updated)) { ret = security_task_setscheduler(task); if (ret) goto out_unlock; } if (dl_task(task)) { cs->nr_migrate_dl_tasks++; cs->sum_migrate_dl_bw += task->dl.dl_bw; } } if (!cs->nr_migrate_dl_tasks) goto out_success; if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) { reset_migrate_dl_data(cs); goto out_unlock; } } out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); if (cs->nr_migrate_dl_tasks) { int cpu = cpumask_any(cs->effective_cpus); dl_bw_free(cpu, cs->sum_migrate_dl_bw); reset_migrate_dl_data(cs); } mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static nodemask_t cpuset_attach_nodemask_to; static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { lockdep_assert_held(&cpuset_mutex); if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); else cpumask_andnot(cpus_attach, task_cpu_possible_mask(task), subpartitions_cpus); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flags(cs, task); } static void cpuset_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; bool cpus_updated, mems_updated; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); /* * In the default hierarchy, enabling cpuset in the child cgroups * will trigger a number of cpuset_attach() calls with no change * in effective cpus and mems. In that case, we can optimize out * by skipping the task iteration and update. */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && !cpus_updated && !mems_updated) { cpuset_attach_nodemask_to = cs->effective_mems; goto out; } guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) cpuset_attach_task(cs, task); /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. Skip it * if there is no change in effective_mems and CS_MEMORY_MIGRATE is * not set. */ cpuset_attach_nodemask_to = cs->effective_mems; if (!is_memory_migrate(cs) && !mems_updated) goto out; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } out: cs->old_mems_allowed = cpuset_attach_nodemask_to; if (cs->nr_migrate_dl_tasks) { cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; reset_migrate_dl_data(cs); } cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_EXCLUSIVE_CPULIST, FILE_EFFECTIVE_XCPULIST, FILE_ISOLATED_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_handle_hotplug may call back into cgroup core asynchronously * via cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_EXCLUSIVE_CPULIST: retval = update_exclusive_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_EXCLUSIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->exclusive_cpus)); break; case FILE_EFFECTIVE_XCPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_xcpus)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus)); break; case FILE_ISOLATED_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); const char *err, *type = NULL; switch (cs->partition_root_state) { case PRS_ROOT: seq_puts(seq, "root\n"); break; case PRS_ISOLATED: seq_puts(seq, "isolated\n"); break; case PRS_MEMBER: seq_puts(seq, "member\n"); break; case PRS_INVALID_ROOT: type = "root"; fallthrough; case PRS_INVALID_ISOLATED: if (!type) type = "isolated"; err = perr_strings[READ_ONCE(cs->prs_err)]; if (err) seq_printf(seq, "%s invalid (%s)\n", type, err); else seq_printf(seq, "%s invalid\n", type); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); if (!strcmp(buf, "root")) val = PRS_ROOT; else if (!strcmp(buf, "member")) val = PRS_MEMBER; else if (!strcmp(buf, "isolated")) val = PRS_ISOLATED; else return -EINVAL; css_get(&cs->css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { /* obsolete, may be removed in the future */ .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cpuset, partition_file), }, { .name = "cpus.exclusive", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_EXCLUSIVE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.exclusive.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_XCPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG, }, { .name = "cpus.isolated", .seq_show = cpuset_common_seq_show, .private = FILE_ISOLATED_CPULIST, .flags = CFTYPE_ONLY_ON_ROOT, }, { } /* terminate */ }; /** * cpuset_css_alloc - Allocate a cpuset css * @parent_css: Parent css of the control group that the new cpuset will be * part of * Return: cpuset css on success, -ENOMEM on failure. * * Allocate and initialize a new cpuset css, for non-NULL @parent_css, return * top cpuset css otherwise. */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; INIT_LIST_HEAD(&cs->remote_sibling); /* Set CS_MEMORY_MIGRATE for default hierarchy */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) __set_bit(CS_MEMORY_MIGRATE, &cs->flags); return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); /* * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && !is_sched_load_balance(parent)) clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * historical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (is_partition_valid(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * In case the child is cloned into a cpuset different from its parent, * additional checks are done to see if the move is allowed. */ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) { struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); bool same_cs; int ret; rcu_read_lock(); same_cs = (cs == task_cs(current)); rcu_read_unlock(); if (same_cs) return 0; lockdep_assert_held(&cgroup_mutex); mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); if (ret) goto out_unlock; ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) { struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); bool same_cs; rcu_read_lock(); same_cs = (cs == task_cs(current)); rcu_read_unlock(); if (same_cs) return; mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { struct cpuset *cs; bool same_cs; rcu_read_lock(); cs = task_cs(task); same_cs = (cs == task_cs(current)); rcu_read_unlock(); if (same_cs) { if (cs == &top_cpuset) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; return; } /* CLONE_INTO_CGROUP */ mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .can_fork = cpuset_can_fork, .cancel_fork = cpuset_cancel_fork, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); cpumask_setall(top_cpuset.effective_xcpus); cpumask_setall(top_cpuset.exclusive_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); INIT_LIST_HEAD(&remote_children); BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void cpuset_migrate_tasks_workfn(struct work_struct *work) { struct cpuset_remove_tasks_struct *s; s = container_of(work, struct cpuset_remove_tasks_struct, work); remove_tasks_in_empty_cpuset(s->cs); css_put(&s->cs->css); kfree(s); } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migrated to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs, new_cpus); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Execute it asynchronously using workqueue. */ if (is_empty && cs->css.cgroup->nr_populated_csets && css_tryget_online(&cs->css)) { struct cpuset_remove_tasks_struct *s; s = kzalloc(sizeof(*s), GFP_KERNEL); if (WARN_ON_ONCE(!s)) { css_put(&cs->css); return; } s->cs = cs; INIT_WORK(&s->work, cpuset_migrate_tasks_workfn); schedule_work(&s->work); } } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { /* A partition root is allowed to have empty effective cpus */ if (cpumask_empty(new_cpus) && !is_partition_valid(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs, new_cpus); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; bool remote; int partcmd = -1; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { mutex_unlock(&cpuset_mutex); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * Compute effective_cpus for valid partition root, may invalidate * child partition roots if necessary. */ remote = is_remote_partition(cs); if (remote || (is_partition_valid(cs) && is_partition_valid(parent))) compute_partition_effective_cpumask(cs, &new_cpus); if (remote && cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) { remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; cpuset_force_rebuild(); } /* * Force the partition to become invalid if either one of * the following conditions hold: * 1) empty effective cpus but not valid empty partition. * 2) parent is invalid or doesn't grant any cpus to child * partitions. */ if (is_local_partition(cs) && (!is_partition_valid(parent) || tasks_nocpu_error(parent, cs, &new_cpus))) partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned * back to a regular one. */ else if (is_partition_valid(parent) && is_partition_invalid(cs)) partcmd = partcmd_update; if (partcmd >= 0) { update_parent_effective_cpumask(cs, partcmd, NULL, tmp); if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) { compute_partition_effective_cpumask(cs, &new_cpus); cpuset_force_rebuild(); } } update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (!cpus_updated && !mems_updated) goto unlock; /* Hotplug doesn't affect this cpuset */ if (mems_updated) check_insane_mems_config(&new_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); unlock: mutex_unlock(&cpuset_mutex); } /** * cpuset_handle_hotplug - handle CPU/memory hot{,un}plug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. * * CPU / memory hotplug is handled synchronously. */ static void cpuset_handle_hotplug(void) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subpartitions_cpus is populated, it is likely that the check * below will produce a false positive on cpus_updated when the cpu * list isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus) || !cpumask_empty(subpartitions_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in * subpartitions_cpus, we assumed that cpus are updated. */ if (!cpus_updated && !cpumask_empty(subpartitions_cpus)) cpus_updated = true; /* For v1, synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subpartitions_cpus & let the child partitions * fight for the CPUs again. */ if (!cpumask_empty(subpartitions_cpus)) { if (cpumask_subset(&new_cpus, subpartitions_cpus)) { top_cpuset.nr_subparts = 0; cpumask_clear(subpartitions_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, subpartitions_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains_cpuslocked(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ cpuset_handle_hotplug(); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { cpuset_handle_hotplug(); return NOTIFY_OK; } /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; hotplug_memory_notifier(cpuset_track_online_nodes, CPUSET_CALLBACK_PRI); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; struct cpuset *cs; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = task_cs(tsk); if (cs != &top_cpuset) guarantee_online_cpus(tsk, pmask); /* * Tasks in the top cpuset won't get update to their cpumasks * when a hotplug online/offline event happens. So we include all * offline cpus in the allowed cpu list. */ if ((cs == &top_cpuset) || cpumask_empty(pmask)) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); /* * We first exclude cpus allocated to partitions. If there is no * allowable online cpu left, we fall back to all possible cpus. */ cpumask_andnot(pmask, possible_mask, subpartitions_cpus); if (!cpumask_intersects(pmask, cpu_online_mask)) cpumask_copy(pmask, possible_mask); } rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. * * Returns true if the affinity of @tsk was changed, false otherwise. **/ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); const struct cpumask *cs_mask; bool changed = false; rcu_read_lock(); cs_mask = task_cs(tsk)->cpus_allowed; if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { do_set_cpus_allowed(tsk, cs_mask); changed = true; } rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ return changed; } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /* * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ bool allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_spread_node() - On which node to begin search for a page * @rotor: round robin rotor * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } /** * cpuset_mem_spread_node() - On which node to begin search for a file page */ int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } /** * cpuset_slab_spread_node() - On which node to begin search for a slab page */ int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /* * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. */ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); css = task_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); spin_unlock_irq(&css_set_lock); rcu_read_unlock(); if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 124 123 124 124 124 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { const struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (ret) return ret; /* * Annoying legacy format with 64-bit capabilities exposed * as two sets of 32-bit fields, so we need to split the * capability values up. */ kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) return -EFAULT; return 0; } static kernel_cap_t mk_kernel_cap(u32 low, u32 high) { return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[2] = { { 0, }, }; unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode) { return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 166 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/drivers/clocksource/arm_arch_timer.c * * Copyright (C) 2011 ARM Ltd. * All Rights Reserved */ #define pr_fmt(fmt) "arch_timer: " fmt #include <linux/init.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/clockchips.h> #include <linux/clocksource.h> #include <linux/clocksource_ids.h> #include <linux/interrupt.h> #include <linux/kstrtox.h> #include <linux/of_irq.h> #include <linux/of_address.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/sched_clock.h> #include <linux/acpi.h> #include <linux/arm-smccc.h> #include <linux/ptp_kvm.h> #include <asm/arch_timer.h> #include <asm/virt.h> #include <clocksource/arm_arch_timer.h> #define CNTTIDR 0x08 #define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4)) #define CNTACR(n) (0x40 + ((n) * 4)) #define CNTACR_RPCT BIT(0) #define CNTACR_RVCT BIT(1) #define CNTACR_RFRQ BIT(2) #define CNTACR_RVOFF BIT(3) #define CNTACR_RWVT BIT(4) #define CNTACR_RWPT BIT(5) #define CNTPCT_LO 0x00 #define CNTVCT_LO 0x08 #define CNTFRQ 0x10 #define CNTP_CVAL_LO 0x20 #define CNTP_CTL 0x2c #define CNTV_CVAL_LO 0x30 #define CNTV_CTL 0x3c /* * The minimum amount of time a generic counter is guaranteed to not roll over * (40 years) */ #define MIN_ROLLOVER_SECS (40ULL * 365 * 24 * 3600) static unsigned arch_timers_present __initdata; struct arch_timer { void __iomem *base; struct clock_event_device evt; }; static struct arch_timer *arch_timer_mem __ro_after_init; #define to_arch_timer(e) container_of(e, struct arch_timer, evt) static u32 arch_timer_rate __ro_after_init; static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init; static const char *arch_timer_ppi_names[ARCH_TIMER_MAX_TIMER_PPI] = { [ARCH_TIMER_PHYS_SECURE_PPI] = "sec-phys", [ARCH_TIMER_PHYS_NONSECURE_PPI] = "phys", [ARCH_TIMER_VIRT_PPI] = "virt", [ARCH_TIMER_HYP_PPI] = "hyp-phys", [ARCH_TIMER_HYP_VIRT_PPI] = "hyp-virt", }; static struct clock_event_device __percpu *arch_timer_evt; static enum arch_timer_ppi_nr arch_timer_uses_ppi __ro_after_init = ARCH_TIMER_VIRT_PPI; static bool arch_timer_c3stop __ro_after_init; static bool arch_timer_mem_use_virtual __ro_after_init; static bool arch_counter_suspend_stop __ro_after_init; #ifdef CONFIG_GENERIC_GETTIMEOFDAY static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_ARCHTIMER; #else static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_NONE; #endif /* CONFIG_GENERIC_GETTIMEOFDAY */ static cpumask_t evtstrm_available = CPU_MASK_NONE; static bool evtstrm_enable __ro_after_init = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM); static int __init early_evtstrm_cfg(char *buf) { return kstrtobool(buf, &evtstrm_enable); } early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg); /* * Makes an educated guess at a valid counter width based on the Generic Timer * specification. Of note: * 1) the system counter is at least 56 bits wide * 2) a roll-over time of not less than 40 years * * See 'ARM DDI 0487G.a D11.1.2 ("The system counter")' for more details. */ static int arch_counter_get_width(void) { u64 min_cycles = MIN_ROLLOVER_SECS * arch_timer_rate; /* guarantee the returned width is within the valid range */ return clamp_val(ilog2(min_cycles - 1) + 1, 56, 64); } /* * Architected system timer support. */ static __always_inline void arch_timer_reg_write(int access, enum arch_timer_reg reg, u64 val, struct clock_event_device *clk) { if (access == ARCH_TIMER_MEM_PHYS_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: writel_relaxed((u32)val, timer->base + CNTP_CTL); break; case ARCH_TIMER_REG_CVAL: /* * Not guaranteed to be atomic, so the timer * must be disabled at this point. */ writeq_relaxed(val, timer->base + CNTP_CVAL_LO); break; default: BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: writel_relaxed((u32)val, timer->base + CNTV_CTL); break; case ARCH_TIMER_REG_CVAL: /* Same restriction as above */ writeq_relaxed(val, timer->base + CNTV_CVAL_LO); break; default: BUILD_BUG(); } } else { arch_timer_reg_write_cp15(access, reg, val); } } static __always_inline u32 arch_timer_reg_read(int access, enum arch_timer_reg reg, struct clock_event_device *clk) { u32 val; if (access == ARCH_TIMER_MEM_PHYS_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: val = readl_relaxed(timer->base + CNTP_CTL); break; default: BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: val = readl_relaxed(timer->base + CNTV_CTL); break; default: BUILD_BUG(); } } else { val = arch_timer_reg_read_cp15(access, reg); } return val; } static noinstr u64 raw_counter_get_cntpct_stable(void) { return __arch_counter_get_cntpct_stable(); } static notrace u64 arch_counter_get_cntpct_stable(void) { u64 val; preempt_disable_notrace(); val = __arch_counter_get_cntpct_stable(); preempt_enable_notrace(); return val; } static noinstr u64 arch_counter_get_cntpct(void) { return __arch_counter_get_cntpct(); } static noinstr u64 raw_counter_get_cntvct_stable(void) { return __arch_counter_get_cntvct_stable(); } static notrace u64 arch_counter_get_cntvct_stable(void) { u64 val; preempt_disable_notrace(); val = __arch_counter_get_cntvct_stable(); preempt_enable_notrace(); return val; } static noinstr u64 arch_counter_get_cntvct(void) { return __arch_counter_get_cntvct(); } /* * Default to cp15 based access because arm64 uses this function for * sched_clock() before DT is probed and the cp15 method is guaranteed * to exist on arm64. arm doesn't use this before DT is probed so even * if we don't have the cp15 accessors we won't have a problem. */ u64 (*arch_timer_read_counter)(void) __ro_after_init = arch_counter_get_cntvct; EXPORT_SYMBOL_GPL(arch_timer_read_counter); static u64 arch_counter_read(struct clocksource *cs) { return arch_timer_read_counter(); } static u64 arch_counter_read_cc(const struct cyclecounter *cc) { return arch_timer_read_counter(); } static struct clocksource clocksource_counter = { .name = "arch_sys_counter", .id = CSID_ARM_ARCH_COUNTER, .rating = 400, .read = arch_counter_read, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static struct cyclecounter cyclecounter __ro_after_init = { .read = arch_counter_read_cc, }; struct ate_acpi_oem_info { char oem_id[ACPI_OEM_ID_SIZE + 1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; u32 oem_revision; }; #ifdef CONFIG_FSL_ERRATUM_A008585 /* * The number of retries is an arbitrary value well beyond the highest number * of iterations the loop has been observed to take. */ #define __fsl_a008585_read_reg(reg) ({ \ u64 _old, _new; \ int _retries = 200; \ \ do { \ _old = read_sysreg(reg); \ _new = read_sysreg(reg); \ _retries--; \ } while (unlikely(_old != _new) && _retries); \ \ WARN_ON_ONCE(!_retries); \ _new; \ }) static u64 notrace fsl_a008585_read_cntpct_el0(void) { return __fsl_a008585_read_reg(cntpct_el0); } static u64 notrace fsl_a008585_read_cntvct_el0(void) { return __fsl_a008585_read_reg(cntvct_el0); } #endif #ifdef CONFIG_HISILICON_ERRATUM_161010101 /* * Verify whether the value of the second read is larger than the first by * less than 32 is the only way to confirm the value is correct, so clear the * lower 5 bits to check whether the difference is greater than 32 or not. * Theoretically the erratum should not occur more than twice in succession * when reading the system counter, but it is possible that some interrupts * may lead to more than twice read errors, triggering the warning, so setting * the number of retries far beyond the number of iterations the loop has been * observed to take. */ #define __hisi_161010101_read_reg(reg) ({ \ u64 _old, _new; \ int _retries = 50; \ \ do { \ _old = read_sysreg(reg); \ _new = read_sysreg(reg); \ _retries--; \ } while (unlikely((_new - _old) >> 5) && _retries); \ \ WARN_ON_ONCE(!_retries); \ _new; \ }) static u64 notrace hisi_161010101_read_cntpct_el0(void) { return __hisi_161010101_read_reg(cntpct_el0); } static u64 notrace hisi_161010101_read_cntvct_el0(void) { return __hisi_161010101_read_reg(cntvct_el0); } static const struct ate_acpi_oem_info hisi_161010101_oem_info[] = { /* * Note that trailing spaces are required to properly match * the OEM table information. */ { .oem_id = "HISI ", .oem_table_id = "HIP05 ", .oem_revision = 0, }, { .oem_id = "HISI ", .oem_table_id = "HIP06 ", .oem_revision = 0, }, { .oem_id = "HISI ", .oem_table_id = "HIP07 ", .oem_revision = 0, }, { /* Sentinel indicating the end of the OEM array */ }, }; #endif #ifdef CONFIG_ARM64_ERRATUM_858921 static u64 notrace arm64_858921_read_cntpct_el0(void) { u64 old, new; old = read_sysreg(cntpct_el0); new = read_sysreg(cntpct_el0); return (((old ^ new) >> 32) & 1) ? old : new; } static u64 notrace arm64_858921_read_cntvct_el0(void) { u64 old, new; old = read_sysreg(cntvct_el0); new = read_sysreg(cntvct_el0); return (((old ^ new) >> 32) & 1) ? old : new; } #endif #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1 /* * The low bits of the counter registers are indeterminate while bit 10 or * greater is rolling over. Since the counter value can jump both backward * (7ff -> 000 -> 800) and forward (7ff -> fff -> 800), ignore register values * with all ones or all zeros in the low bits. Bound the loop by the maximum * number of CPU cycles in 3 consecutive 24 MHz counter periods. */ #define __sun50i_a64_read_reg(reg) ({ \ u64 _val; \ int _retries = 150; \ \ do { \ _val = read_sysreg(reg); \ _retries--; \ } while (((_val + 1) & GENMASK(8, 0)) <= 1 && _retries); \ \ WARN_ON_ONCE(!_retries); \ _val; \ }) static u64 notrace sun50i_a64_read_cntpct_el0(void) { return __sun50i_a64_read_reg(cntpct_el0); } static u64 notrace sun50i_a64_read_cntvct_el0(void) { return __sun50i_a64_read_reg(cntvct_el0); } #endif #ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround); EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround); static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0); /* * Force the inlining of this function so that the register accesses * can be themselves correctly inlined. */ static __always_inline void erratum_set_next_event_generic(const int access, unsigned long evt, struct clock_event_device *clk) { unsigned long ctrl; u64 cval; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_PHYS_ACCESS) { cval = evt + arch_counter_get_cntpct_stable(); write_sysreg(cval, cntp_cval_el0); } else { cval = evt + arch_counter_get_cntvct_stable(); write_sysreg(cval, cntv_cval_el0); } arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static __maybe_unused int erratum_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) { erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk); return 0; } static __maybe_unused int erratum_set_next_event_phys(unsigned long evt, struct clock_event_device *clk) { erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk); return 0; } static const struct arch_timer_erratum_workaround ool_workarounds[] = { #ifdef CONFIG_FSL_ERRATUM_A008585 { .match_type = ate_match_dt, .id = "fsl,erratum-a008585", .desc = "Freescale erratum a005858", .read_cntpct_el0 = fsl_a008585_read_cntpct_el0, .read_cntvct_el0 = fsl_a008585_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_HISILICON_ERRATUM_161010101 { .match_type = ate_match_dt, .id = "hisilicon,erratum-161010101", .desc = "HiSilicon erratum 161010101", .read_cntpct_el0 = hisi_161010101_read_cntpct_el0, .read_cntvct_el0 = hisi_161010101_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, { .match_type = ate_match_acpi_oem_info, .id = hisi_161010101_oem_info, .desc = "HiSilicon erratum 161010101", .read_cntpct_el0 = hisi_161010101_read_cntpct_el0, .read_cntvct_el0 = hisi_161010101_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 { .match_type = ate_match_local_cap_id, .id = (void *)ARM64_WORKAROUND_858921, .desc = "ARM erratum 858921", .read_cntpct_el0 = arm64_858921_read_cntpct_el0, .read_cntvct_el0 = arm64_858921_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1 { .match_type = ate_match_dt, .id = "allwinner,erratum-unknown1", .desc = "Allwinner erratum UNKNOWN1", .read_cntpct_el0 = sun50i_a64_read_cntpct_el0, .read_cntvct_el0 = sun50i_a64_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_ARM64_ERRATUM_1418040 { .match_type = ate_match_local_cap_id, .id = (void *)ARM64_WORKAROUND_1418040, .desc = "ARM erratum 1418040", .disable_compat_vdso = true, }, #endif }; typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *, const void *); static bool arch_timer_check_dt_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { const struct device_node *np = arg; return of_property_read_bool(np, wa->id); } static bool arch_timer_check_local_cap_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { return this_cpu_has_cap((uintptr_t)wa->id); } static bool arch_timer_check_acpi_oem_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { static const struct ate_acpi_oem_info empty_oem_info = {}; const struct ate_acpi_oem_info *info = wa->id; const struct acpi_table_header *table = arg; /* Iterate over the ACPI OEM info array, looking for a match */ while (memcmp(info, &empty_oem_info, sizeof(*info))) { if (!memcmp(info->oem_id, table->oem_id, ACPI_OEM_ID_SIZE) && !memcmp(info->oem_table_id, table->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) && info->oem_revision == table->oem_revision) return true; info++; } return false; } static const struct arch_timer_erratum_workaround * arch_timer_iterate_errata(enum arch_timer_erratum_match_type type, ate_match_fn_t match_fn, void *arg) { int i; for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) { if (ool_workarounds[i].match_type != type) continue; if (match_fn(&ool_workarounds[i], arg)) return &ool_workarounds[i]; } return NULL; } static void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa, bool local) { int i; if (local) { __this_cpu_write(timer_unstable_counter_workaround, wa); } else { for_each_possible_cpu(i) per_cpu(timer_unstable_counter_workaround, i) = wa; } if (wa->read_cntvct_el0 || wa->read_cntpct_el0) atomic_set(&timer_unstable_counter_workaround_in_use, 1); /* * Don't use the vdso fastpath if errata require using the * out-of-line counter accessor. We may change our mind pretty * late in the game (with a per-CPU erratum, for example), so * change both the default value and the vdso itself. */ if (wa->read_cntvct_el0) { clocksource_counter.vdso_clock_mode = VDSO_CLOCKMODE_NONE; vdso_default = VDSO_CLOCKMODE_NONE; } else if (wa->disable_compat_vdso && vdso_default != VDSO_CLOCKMODE_NONE) { vdso_default = VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT; clocksource_counter.vdso_clock_mode = vdso_default; } } static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type, void *arg) { const struct arch_timer_erratum_workaround *wa, *__wa; ate_match_fn_t match_fn = NULL; bool local = false; switch (type) { case ate_match_dt: match_fn = arch_timer_check_dt_erratum; break; case ate_match_local_cap_id: match_fn = arch_timer_check_local_cap_erratum; local = true; break; case ate_match_acpi_oem_info: match_fn = arch_timer_check_acpi_oem_erratum; break; default: WARN_ON(1); return; } wa = arch_timer_iterate_errata(type, match_fn, arg); if (!wa) return; __wa = __this_cpu_read(timer_unstable_counter_workaround); if (__wa && wa != __wa) pr_warn("Can't enable workaround for %s (clashes with %s\n)", wa->desc, __wa->desc); if (__wa) return; arch_timer_enable_workaround(wa, local); pr_info("Enabling %s workaround for %s\n", local ? "local" : "global", wa->desc); } static bool arch_timer_this_cpu_has_cntvct_wa(void) { return has_erratum_handler(read_cntvct_el0); } static bool arch_timer_counter_has_wa(void) { return atomic_read(&timer_unstable_counter_workaround_in_use); } #else #define arch_timer_check_ool_workaround(t,a) do { } while(0) #define arch_timer_this_cpu_has_cntvct_wa() ({false;}) #define arch_timer_counter_has_wa() ({false;}) #endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */ static __always_inline irqreturn_t timer_handler(const int access, struct clock_event_device *evt) { unsigned long ctrl; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, evt); if (ctrl & ARCH_TIMER_CTRL_IT_STAT) { ctrl |= ARCH_TIMER_CTRL_IT_MASK; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, evt); evt->event_handler(evt); return IRQ_HANDLED; } return IRQ_NONE; } static irqreturn_t arch_timer_handler_virt(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_VIRT_ACCESS, evt); } static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt); } static irqreturn_t arch_timer_handler_phys_mem(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_MEM_PHYS_ACCESS, evt); } static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt); } static __always_inline int arch_timer_shutdown(const int access, struct clock_event_device *clk) { unsigned long ctrl; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl &= ~ARCH_TIMER_CTRL_ENABLE; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); return 0; } static int arch_timer_shutdown_virt(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_PHYS_ACCESS, clk); } static int arch_timer_shutdown_virt_mem(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_MEM_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys_mem(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_MEM_PHYS_ACCESS, clk); } static __always_inline void set_next_event(const int access, unsigned long evt, struct clock_event_device *clk) { unsigned long ctrl; u64 cnt; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_PHYS_ACCESS) cnt = __arch_counter_get_cntpct(); else cnt = __arch_counter_get_cntvct(); arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk); arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static int arch_timer_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) { set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk); return 0; } static int arch_timer_set_next_event_phys(unsigned long evt, struct clock_event_device *clk) { set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk); return 0; } static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo) { u32 cnt_lo, cnt_hi, tmp_hi; do { cnt_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4)); cnt_lo = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo)); tmp_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4)); } while (cnt_hi != tmp_hi); return ((u64) cnt_hi << 32) | cnt_lo; } static __always_inline void set_next_event_mem(const int access, unsigned long evt, struct clock_event_device *clk) { struct arch_timer *timer = to_arch_timer(clk); unsigned long ctrl; u64 cnt; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); /* Timer must be disabled before programming CVAL */ if (ctrl & ARCH_TIMER_CTRL_ENABLE) { ctrl &= ~ARCH_TIMER_CTRL_ENABLE; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_MEM_VIRT_ACCESS) cnt = arch_counter_get_cnt_mem(timer, CNTVCT_LO); else cnt = arch_counter_get_cnt_mem(timer, CNTPCT_LO); arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk); arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static int arch_timer_set_next_event_virt_mem(unsigned long evt, struct clock_event_device *clk) { set_next_event_mem(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk); return 0; } static int arch_timer_set_next_event_phys_mem(unsigned long evt, struct clock_event_device *clk) { set_next_event_mem(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk); return 0; } static u64 __arch_timer_check_delta(void) { #ifdef CONFIG_ARM64 const struct midr_range broken_cval_midrs[] = { /* * XGene-1 implements CVAL in terms of TVAL, meaning * that the maximum timer range is 32bit. Shame on them. * * Note that TVAL is signed, thus has only 31 of its * 32 bits to express magnitude. */ MIDR_REV_RANGE(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, APM_CPU_PART_XGENE), APM_CPU_VAR_POTENZA, 0x0, 0xf), {}, }; if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) { pr_warn_once("Broken CNTx_CVAL_EL1, using 31 bit TVAL instead.\n"); return CLOCKSOURCE_MASK(31); } #endif return CLOCKSOURCE_MASK(arch_counter_get_width()); } static void __arch_timer_setup(unsigned type, struct clock_event_device *clk) { u64 max_delta; clk->features = CLOCK_EVT_FEAT_ONESHOT; if (type == ARCH_TIMER_TYPE_CP15) { typeof(clk->set_next_event) sne; arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL); if (arch_timer_c3stop) clk->features |= CLOCK_EVT_FEAT_C3STOP; clk->name = "arch_sys_timer"; clk->rating = 450; clk->cpumask = cpumask_of(smp_processor_id()); clk->irq = arch_timer_ppi[arch_timer_uses_ppi]; switch (arch_timer_uses_ppi) { case ARCH_TIMER_VIRT_PPI: clk->set_state_shutdown = arch_timer_shutdown_virt; clk->set_state_oneshot_stopped = arch_timer_shutdown_virt; sne = erratum_handler(set_next_event_virt); break; case ARCH_TIMER_PHYS_SECURE_PPI: case ARCH_TIMER_PHYS_NONSECURE_PPI: case ARCH_TIMER_HYP_PPI: clk->set_state_shutdown = arch_timer_shutdown_phys; clk->set_state_oneshot_stopped = arch_timer_shutdown_phys; sne = erratum_handler(set_next_event_phys); break; default: BUG(); } clk->set_next_event = sne; max_delta = __arch_timer_check_delta(); } else { clk->features |= CLOCK_EVT_FEAT_DYNIRQ; clk->name = "arch_mem_timer"; clk->rating = 400; clk->cpumask = cpu_possible_mask; if (arch_timer_mem_use_virtual) { clk->set_state_shutdown = arch_timer_shutdown_virt_mem; clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem; clk->set_next_event = arch_timer_set_next_event_virt_mem; } else { clk->set_state_shutdown = arch_timer_shutdown_phys_mem; clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem; clk->set_next_event = arch_timer_set_next_event_phys_mem; } max_delta = CLOCKSOURCE_MASK(56); } clk->set_state_shutdown(clk); clockevents_config_and_register(clk, arch_timer_rate, 0xf, max_delta); } static void arch_timer_evtstrm_enable(unsigned int divider) { u32 cntkctl = arch_timer_get_cntkctl(); #ifdef CONFIG_ARM64 /* ECV is likely to require a large divider. Use the EVNTIS flag. */ if (cpus_have_final_cap(ARM64_HAS_ECV) && divider > 15) { cntkctl |= ARCH_TIMER_EVT_INTERVAL_SCALE; divider -= 8; } #endif divider = min(divider, 15U); cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK; /* Set the divider and enable virtual event stream */ cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT) | ARCH_TIMER_VIRT_EVT_EN; arch_timer_set_cntkctl(cntkctl); arch_timer_set_evtstrm_feature(); cpumask_set_cpu(smp_processor_id(), &evtstrm_available); } static void arch_timer_configure_evtstream(void) { int evt_stream_div, lsb; /* * As the event stream can at most be generated at half the frequency * of the counter, use half the frequency when computing the divider. */ evt_stream_div = arch_timer_rate / ARCH_TIMER_EVT_STREAM_FREQ / 2; /* * Find the closest power of two to the divisor. If the adjacent bit * of lsb (last set bit, starts from 0) is set, then we use (lsb + 1). */ lsb = fls(evt_stream_div) - 1; if (lsb > 0 && (evt_stream_div & BIT(lsb - 1))) lsb++; /* enable event stream */ arch_timer_evtstrm_enable(max(0, lsb)); } static int arch_timer_evtstrm_starting_cpu(unsigned int cpu) { arch_timer_configure_evtstream(); return 0; } static int arch_timer_evtstrm_dying_cpu(unsigned int cpu) { cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); return 0; } static int __init arch_timer_evtstrm_register(void) { if (!arch_timer_evt || !evtstrm_enable) return 0; return cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING, "clockevents/arm/arch_timer_evtstrm:starting", arch_timer_evtstrm_starting_cpu, arch_timer_evtstrm_dying_cpu); } core_initcall(arch_timer_evtstrm_register); static void arch_counter_set_user_access(void) { u32 cntkctl = arch_timer_get_cntkctl(); /* Disable user access to the timers and both counters */ /* Also disable virtual event stream */ cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN | ARCH_TIMER_USR_VT_ACCESS_EN | ARCH_TIMER_USR_VCT_ACCESS_EN | ARCH_TIMER_VIRT_EVT_EN | ARCH_TIMER_USR_PCT_ACCESS_EN); /* * Enable user access to the virtual counter if it doesn't * need to be workaround. The vdso may have been already * disabled though. */ if (arch_timer_this_cpu_has_cntvct_wa()) pr_info("CPU%d: Trapping CNTVCT access\n", smp_processor_id()); else cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN; arch_timer_set_cntkctl(cntkctl); } static bool arch_timer_has_nonsecure_ppi(void) { return (arch_timer_uses_ppi == ARCH_TIMER_PHYS_SECURE_PPI && arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); } static u32 check_ppi_trigger(int irq) { u32 flags = irq_get_trigger_type(irq); if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) { pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq); pr_warn("WARNING: Please fix your firmware\n"); flags = IRQF_TRIGGER_LOW; } return flags; } static int arch_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); u32 flags; __arch_timer_setup(ARCH_TIMER_TYPE_CP15, clk); flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]); enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags); if (arch_timer_has_nonsecure_ppi()) { flags = check_ppi_trigger(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); enable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI], flags); } arch_counter_set_user_access(); return 0; } static int validate_timer_rate(void) { if (!arch_timer_rate) return -EINVAL; /* Arch timer frequency < 1MHz can cause trouble */ WARN_ON(arch_timer_rate < 1000000); return 0; } /* * For historical reasons, when probing with DT we use whichever (non-zero) * rate was probed first, and don't verify that others match. If the first node * probed has a clock-frequency property, this overrides the HW register. */ static void __init arch_timer_of_configure_rate(u32 rate, struct device_node *np) { /* Who has more than one independent system counter? */ if (arch_timer_rate) return; if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) arch_timer_rate = rate; /* Check the timer frequency. */ if (validate_timer_rate()) pr_warn("frequency not available\n"); } static void __init arch_timer_banner(unsigned type) { pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n", type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "", type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? " and " : "", type & ARCH_TIMER_TYPE_MEM ? "mmio" : "", (unsigned long)arch_timer_rate / 1000000, (unsigned long)(arch_timer_rate / 10000) % 100, type & ARCH_TIMER_TYPE_CP15 ? (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ? "virt" : "phys" : "", type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? "/" : "", type & ARCH_TIMER_TYPE_MEM ? arch_timer_mem_use_virtual ? "virt" : "phys" : ""); } u32 arch_timer_get_rate(void) { return arch_timer_rate; } bool arch_timer_evtstrm_available(void) { /* * We might get called from a preemptible context. This is fine * because availability of the event stream should be always the same * for a preemptible context and context where we might resume a task. */ return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available); } static noinstr u64 arch_counter_get_cntvct_mem(void) { return arch_counter_get_cnt_mem(arch_timer_mem, CNTVCT_LO); } static struct arch_timer_kvm_info arch_timer_kvm_info; struct arch_timer_kvm_info *arch_timer_get_kvm_info(void) { return &arch_timer_kvm_info; } static void __init arch_counter_register(unsigned type) { u64 (*scr)(void); u64 start_count; int width; /* Register the CP15 based counter if we have one */ if (type & ARCH_TIMER_TYPE_CP15) { u64 (*rd)(void); if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) || arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) { if (arch_timer_counter_has_wa()) { rd = arch_counter_get_cntvct_stable; scr = raw_counter_get_cntvct_stable; } else { rd = arch_counter_get_cntvct; scr = arch_counter_get_cntvct; } } else { if (arch_timer_counter_has_wa()) { rd = arch_counter_get_cntpct_stable; scr = raw_counter_get_cntpct_stable; } else { rd = arch_counter_get_cntpct; scr = arch_counter_get_cntpct; } } arch_timer_read_counter = rd; clocksource_counter.vdso_clock_mode = vdso_default; } else { arch_timer_read_counter = arch_counter_get_cntvct_mem; scr = arch_counter_get_cntvct_mem; } width = arch_counter_get_width(); clocksource_counter.mask = CLOCKSOURCE_MASK(width); cyclecounter.mask = CLOCKSOURCE_MASK(width); if (!arch_counter_suspend_stop) clocksource_counter.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; start_count = arch_timer_read_counter(); clocksource_register_hz(&clocksource_counter, arch_timer_rate); cyclecounter.mult = clocksource_counter.mult; cyclecounter.shift = clocksource_counter.shift; timecounter_init(&arch_timer_kvm_info.timecounter, &cyclecounter, start_count); sched_clock_register(scr, width, arch_timer_rate); } static void arch_timer_stop(struct clock_event_device *clk) { pr_debug("disable IRQ%d cpu #%d\n", clk->irq, smp_processor_id()); disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]); if (arch_timer_has_nonsecure_ppi()) disable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); clk->set_state_shutdown(clk); } static int arch_timer_dying_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); arch_timer_stop(clk); return 0; } #ifdef CONFIG_CPU_PM static DEFINE_PER_CPU(unsigned long, saved_cntkctl); static int arch_timer_cpu_pm_notify(struct notifier_block *self, unsigned long action, void *hcpu) { if (action == CPU_PM_ENTER) { __this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl()); cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); } else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) { arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl)); if (arch_timer_have_evtstrm_feature()) cpumask_set_cpu(smp_processor_id(), &evtstrm_available); } return NOTIFY_OK; } static struct notifier_block arch_timer_cpu_pm_notifier = { .notifier_call = arch_timer_cpu_pm_notify, }; static int __init arch_timer_cpu_pm_init(void) { return cpu_pm_register_notifier(&arch_timer_cpu_pm_notifier); } static void __init arch_timer_cpu_pm_deinit(void) { WARN_ON(cpu_pm_unregister_notifier(&arch_timer_cpu_pm_notifier)); } #else static int __init arch_timer_cpu_pm_init(void) { return 0; } static void __init arch_timer_cpu_pm_deinit(void) { } #endif static int __init arch_timer_register(void) { int err; int ppi; arch_timer_evt = alloc_percpu(struct clock_event_device); if (!arch_timer_evt) { err = -ENOMEM; goto out; } ppi = arch_timer_ppi[arch_timer_uses_ppi]; switch (arch_timer_uses_ppi) { case ARCH_TIMER_VIRT_PPI: err = request_percpu_irq(ppi, arch_timer_handler_virt, "arch_timer", arch_timer_evt); break; case ARCH_TIMER_PHYS_SECURE_PPI: case ARCH_TIMER_PHYS_NONSECURE_PPI: err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); if (!err && arch_timer_has_nonsecure_ppi()) { ppi = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]; err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); if (err) free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_SECURE_PPI], arch_timer_evt); } break; case ARCH_TIMER_HYP_PPI: err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); break; default: BUG(); } if (err) { pr_err("can't register interrupt %d (%d)\n", ppi, err); goto out_free; } err = arch_timer_cpu_pm_init(); if (err) goto out_unreg_notify; /* Register and immediately configure the timer on the boot CPU */ err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING, "clockevents/arm/arch_timer:starting", arch_timer_starting_cpu, arch_timer_dying_cpu); if (err) goto out_unreg_cpupm; return 0; out_unreg_cpupm: arch_timer_cpu_pm_deinit(); out_unreg_notify: free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt); if (arch_timer_has_nonsecure_ppi()) free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI], arch_timer_evt); out_free: free_percpu(arch_timer_evt); arch_timer_evt = NULL; out: return err; } static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq) { int ret; irq_handler_t func; arch_timer_mem = kzalloc(sizeof(*arch_timer_mem), GFP_KERNEL); if (!arch_timer_mem) return -ENOMEM; arch_timer_mem->base = base; arch_timer_mem->evt.irq = irq; __arch_timer_setup(ARCH_TIMER_TYPE_MEM, &arch_timer_mem->evt); if (arch_timer_mem_use_virtual) func = arch_timer_handler_virt_mem; else func = arch_timer_handler_phys_mem; ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &arch_timer_mem->evt); if (ret) { pr_err("Failed to request mem timer irq\n"); kfree(arch_timer_mem); arch_timer_mem = NULL; } return ret; } static const struct of_device_id arch_timer_of_match[] __initconst = { { .compatible = "arm,armv7-timer", }, { .compatible = "arm,armv8-timer", }, {}, }; static const struct of_device_id arch_timer_mem_of_match[] __initconst = { { .compatible = "arm,armv7-timer-mem", }, {}, }; static bool __init arch_timer_needs_of_probing(void) { struct device_node *dn; bool needs_probing = false; unsigned int mask = ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM; /* We have two timers, and both device-tree nodes are probed. */ if ((arch_timers_present & mask) == mask) return false; /* * Only one type of timer is probed, * check if we have another type of timer node in device-tree. */ if (arch_timers_present & ARCH_TIMER_TYPE_CP15) dn = of_find_matching_node(NULL, arch_timer_mem_of_match); else dn = of_find_matching_node(NULL, arch_timer_of_match); if (dn && of_device_is_available(dn)) needs_probing = true; of_node_put(dn); return needs_probing; } static int __init arch_timer_common_init(void) { arch_timer_banner(arch_timers_present); arch_counter_register(arch_timers_present); return arch_timer_arch_init(); } /** * arch_timer_select_ppi() - Select suitable PPI for the current system. * * If HYP mode is available, we know that the physical timer * has been configured to be accessible from PL1. Use it, so * that a guest can use the virtual timer instead. * * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE * accesses to CNTP_*_EL1 registers are silently redirected to * their CNTHP_*_EL2 counterparts, and use a different PPI * number. * * If no interrupt provided for virtual timer, we'll have to * stick to the physical timer. It'd better be accessible... * For arm64 we never use the secure interrupt. * * Return: a suitable PPI type for the current system. */ static enum arch_timer_ppi_nr __init arch_timer_select_ppi(void) { if (is_kernel_in_hyp_mode()) return ARCH_TIMER_HYP_PPI; if (!is_hyp_mode_available() && arch_timer_ppi[ARCH_TIMER_VIRT_PPI]) return ARCH_TIMER_VIRT_PPI; if (IS_ENABLED(CONFIG_ARM64)) return ARCH_TIMER_PHYS_NONSECURE_PPI; return ARCH_TIMER_PHYS_SECURE_PPI; } static void __init arch_timer_populate_kvm_info(void) { arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI]; if (is_kernel_in_hyp_mode()) arch_timer_kvm_info.physical_irq = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]; } static int __init arch_timer_of_init(struct device_node *np) { int i, irq, ret; u32 rate; bool has_names; if (arch_timers_present & ARCH_TIMER_TYPE_CP15) { pr_warn("multiple nodes in dt, skipping\n"); return 0; } arch_timers_present |= ARCH_TIMER_TYPE_CP15; has_names = of_property_read_bool(np, "interrupt-names"); for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++) { if (has_names) irq = of_irq_get_byname(np, arch_timer_ppi_names[i]); else irq = of_irq_get(np, i); if (irq > 0) arch_timer_ppi[i] = irq; } arch_timer_populate_kvm_info(); rate = arch_timer_get_cntfrq(); arch_timer_of_configure_rate(rate, np); arch_timer_c3stop = !of_property_read_bool(np, "always-on"); /* Check for globally applicable workarounds */ arch_timer_check_ool_workaround(ate_match_dt, np); /* * If we cannot rely on firmware initializing the timer registers then * we should use the physical timers instead. */ if (IS_ENABLED(CONFIG_ARM) && of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) arch_timer_uses_ppi = ARCH_TIMER_PHYS_SECURE_PPI; else arch_timer_uses_ppi = arch_timer_select_ppi(); if (!arch_timer_ppi[arch_timer_uses_ppi]) { pr_err("No interrupt available, giving up\n"); return -EINVAL; } /* On some systems, the counter stops ticking when in suspend. */ arch_counter_suspend_stop = of_property_read_bool(np, "arm,no-tick-in-suspend"); ret = arch_timer_register(); if (ret) return ret; if (arch_timer_needs_of_probing()) return 0; return arch_timer_common_init(); } TIMER_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init); TIMER_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init); static u32 __init arch_timer_mem_frame_get_cntfrq(struct arch_timer_mem_frame *frame) { void __iomem *base; u32 rate; base = ioremap(frame->cntbase, frame->size); if (!base) { pr_err("Unable to map frame @ %pa\n", &frame->cntbase); return 0; } rate = readl_relaxed(base + CNTFRQ); iounmap(base); return rate; } static struct arch_timer_mem_frame * __init arch_timer_mem_find_best_frame(struct arch_timer_mem *timer_mem) { struct arch_timer_mem_frame *frame, *best_frame = NULL; void __iomem *cntctlbase; u32 cnttidr; int i; cntctlbase = ioremap(timer_mem->cntctlbase, timer_mem->size); if (!cntctlbase) { pr_err("Can't map CNTCTLBase @ %pa\n", &timer_mem->cntctlbase); return NULL; } cnttidr = readl_relaxed(cntctlbase + CNTTIDR); /* * Try to find a virtual capable frame. Otherwise fall back to a * physical capable frame. */ for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) { u32 cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT | CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT; frame = &timer_mem->frame[i]; if (!frame->valid) continue; /* Try enabling everything, and see what sticks */ writel_relaxed(cntacr, cntctlbase + CNTACR(i)); cntacr = readl_relaxed(cntctlbase + CNTACR(i)); if ((cnttidr & CNTTIDR_VIRT(i)) && !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) { best_frame = frame; arch_timer_mem_use_virtual = true; break; } if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT)) continue; best_frame = frame; } iounmap(cntctlbase); return best_frame; } static int __init arch_timer_mem_frame_register(struct arch_timer_mem_frame *frame) { void __iomem *base; int ret, irq; if (arch_timer_mem_use_virtual) irq = frame->virt_irq; else irq = frame->phys_irq; if (!irq) { pr_err("Frame missing %s irq.\n", arch_timer_mem_use_virtual ? "virt" : "phys"); return -EINVAL; } if (!request_mem_region(frame->cntbase, frame->size, "arch_mem_timer")) return -EBUSY; base = ioremap(frame->cntbase, frame->size); if (!base) { pr_err("Can't map frame's registers\n"); return -ENXIO; } ret = arch_timer_mem_register(base, irq); if (ret) { iounmap(base); return ret; } arch_timers_present |= ARCH_TIMER_TYPE_MEM; return 0; } static int __init arch_timer_mem_of_init(struct device_node *np) { struct arch_timer_mem *timer_mem; struct arch_timer_mem_frame *frame; struct device_node *frame_node; struct resource res; int ret = -EINVAL; u32 rate; timer_mem = kzalloc(sizeof(*timer_mem), GFP_KERNEL); if (!timer_mem) return -ENOMEM; if (of_address_to_resource(np, 0, &res)) goto out; timer_mem->cntctlbase = res.start; timer_mem->size = resource_size(&res); for_each_available_child_of_node(np, frame_node) { u32 n; struct arch_timer_mem_frame *frame; if (of_property_read_u32(frame_node, "frame-number", &n)) { pr_err(FW_BUG "Missing frame-number.\n"); of_node_put(frame_node); goto out; } if (n >= ARCH_TIMER_MEM_MAX_FRAMES) { pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n", ARCH_TIMER_MEM_MAX_FRAMES - 1); of_node_put(frame_node); goto out; } frame = &timer_mem->frame[n]; if (frame->valid) { pr_err(FW_BUG "Duplicated frame-number.\n"); of_node_put(frame_node); goto out; } if (of_address_to_resource(frame_node, 0, &res)) { of_node_put(frame_node); goto out; } frame->cntbase = res.start; frame->size = resource_size(&res); frame->virt_irq = irq_of_parse_and_map(frame_node, ARCH_TIMER_VIRT_SPI); frame->phys_irq = irq_of_parse_and_map(frame_node, ARCH_TIMER_PHYS_SPI); frame->valid = true; } frame = arch_timer_mem_find_best_frame(timer_mem); if (!frame) { pr_err("Unable to find a suitable frame in timer @ %pa\n", &timer_mem->cntctlbase); ret = -EINVAL; goto out; } rate = arch_timer_mem_frame_get_cntfrq(frame); arch_timer_of_configure_rate(rate, np); ret = arch_timer_mem_frame_register(frame); if (!ret && !arch_timer_needs_of_probing()) ret = arch_timer_common_init(); out: kfree(timer_mem); return ret; } TIMER_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem", arch_timer_mem_of_init); #ifdef CONFIG_ACPI_GTDT static int __init arch_timer_mem_verify_cntfrq(struct arch_timer_mem *timer_mem) { struct arch_timer_mem_frame *frame; u32 rate; int i; for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) { frame = &timer_mem->frame[i]; if (!frame->valid) continue; rate = arch_timer_mem_frame_get_cntfrq(frame); if (rate == arch_timer_rate) continue; pr_err(FW_BUG "CNTFRQ mismatch: frame @ %pa: (0x%08lx), CPU: (0x%08lx)\n", &frame->cntbase, (unsigned long)rate, (unsigned long)arch_timer_rate); return -EINVAL; } return 0; } static int __init arch_timer_mem_acpi_init(int platform_timer_count) { struct arch_timer_mem *timers, *timer; struct arch_timer_mem_frame *frame, *best_frame = NULL; int timer_count, i, ret = 0; timers = kcalloc(platform_timer_count, sizeof(*timers), GFP_KERNEL); if (!timers) return -ENOMEM; ret = acpi_arch_timer_mem_init(timers, &timer_count); if (ret || !timer_count) goto out; /* * While unlikely, it's theoretically possible that none of the frames * in a timer expose the combination of feature we want. */ for (i = 0; i < timer_count; i++) { timer = &timers[i]; frame = arch_timer_mem_find_best_frame(timer); if (!best_frame) best_frame = frame; ret = arch_timer_mem_verify_cntfrq(timer); if (ret) { pr_err("Disabling MMIO timers due to CNTFRQ mismatch\n"); goto out; } if (!best_frame) /* implies !frame */ /* * Only complain about missing suitable frames if we * haven't already found one in a previous iteration. */ pr_err("Unable to find a suitable frame in timer @ %pa\n", &timer->cntctlbase); } if (best_frame) ret = arch_timer_mem_frame_register(best_frame); out: kfree(timers); return ret; } /* Initialize per-processor generic timer and memory-mapped timer(if present) */ static int __init arch_timer_acpi_init(struct acpi_table_header *table) { int ret, platform_timer_count; if (arch_timers_present & ARCH_TIMER_TYPE_CP15) { pr_warn("already initialized, skipping\n"); return -EINVAL; } arch_timers_present |= ARCH_TIMER_TYPE_CP15; ret = acpi_gtdt_init(table, &platform_timer_count); if (ret) return ret; arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_PHYS_NONSECURE_PPI); arch_timer_ppi[ARCH_TIMER_VIRT_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_VIRT_PPI); arch_timer_ppi[ARCH_TIMER_HYP_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_HYP_PPI); arch_timer_populate_kvm_info(); /* * When probing via ACPI, we have no mechanism to override the sysreg * CNTFRQ value. This *must* be correct. */ arch_timer_rate = arch_timer_get_cntfrq(); ret = validate_timer_rate(); if (ret) { pr_err(FW_BUG "frequency not available.\n"); return ret; } arch_timer_uses_ppi = arch_timer_select_ppi(); if (!arch_timer_ppi[arch_timer_uses_ppi]) { pr_err("No interrupt available, giving up\n"); return -EINVAL; } /* Always-on capability */ arch_timer_c3stop = acpi_gtdt_c3stop(arch_timer_uses_ppi); /* Check for globally applicable workarounds */ arch_timer_check_ool_workaround(ate_match_acpi_oem_info, table); ret = arch_timer_register(); if (ret) return ret; if (platform_timer_count && arch_timer_mem_acpi_init(platform_timer_count)) pr_err("Failed to initialize memory-mapped timer.\n"); return arch_timer_common_init(); } TIMER_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init); #endif int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts, enum clocksource_ids *cs_id) { struct arm_smccc_res hvc_res; u32 ptp_counter; ktime_t ktime; if (!IS_ENABLED(CONFIG_HAVE_ARM_SMCCC_DISCOVERY)) return -EOPNOTSUPP; if (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ptp_counter = KVM_PTP_VIRT_COUNTER; else ptp_counter = KVM_PTP_PHYS_COUNTER; arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID, ptp_counter, &hvc_res); if ((int)(hvc_res.a0) < 0) return -EOPNOTSUPP; ktime = (u64)hvc_res.a0 << 32 | hvc_res.a1; *ts = ktime_to_timespec64(ktime); if (cycle) *cycle = (u64)hvc_res.a2 << 32 | hvc_res.a3; if (cs_id) *cs_id = CSID_ARM_ARCH_COUNTER; return 0; } EXPORT_SYMBOL_GPL(kvm_arch_ptp_get_crosststamp); |
| 239 135 288 288 264 288 264 264 264 264 287 287 62 61 62 155 155 155 155 229 229 229 229 229 228 229 101 155 155 155 155 155 155 155 101 229 229 229 124 125 125 125 246 239 240 240 18 167 134 135 135 129 264 174 161 173 8 168 36 263 263 167 13 1 12 167 167 166 167 123 58 248 248 61 62 62 8 8 8 264 264 8 264 264 264 264 264 264 263 8 18 18 18 18 18 18 18 18 344 337 336 200 337 345 9 3 6 1 3 3 337 344 162 162 11 27 151 156 102 5 109 157 157 162 109 162 160 167 167 236 160 160 160 229 228 229 132 134 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 | // SPDX-License-Identifier: GPL-2.0-only /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include <linux/io_uring/cmd.h> #include <uapi/linux/lsm.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" #define SELINUX_INODE_INIT_XATTRS 1 struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { if (checkreqprot) pr_err("SELinux: checkreqprot set to 1 via kernel parameter. This is no longer supported.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct task_security_struct *tsec; tsec = selinux_cred(unrcu_pointer(current->real_cred)); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } static void __ad_net_init(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, struct sock *sk, u16 family) { ad->type = LSM_AUDIT_DATA_NET; ad->u.net = net; net->netif = ifindex; net->sk = sk; net->family = family; } static void ad_net_init_from_sk(struct common_audit_data *ad, struct lsm_network_audit *net, struct sock *sk) { __ad_net_init(ad, net, 0, sk, 0); } static void ad_net_init_from_iif(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, u16 family) { __ad_net_init(ad, net, ifindex, NULL, family); } /* * get the objective security ID of a task */ static inline u32 task_sid_obj(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); if (selinux_initialized() && isec->initialized != LABEL_INITIALIZED) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = selinux_superblock(inode->i_sb); /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } struct selinux_mnt_opts { u32 fscontext_sid; u32 context_sid; u32 rootcontext_sid; u32 defcontext_sid; }; static void selinux_free_mnt_opts(void *mnt_opts) { kfree(mnt_opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static const struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_check_xattr_support(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); u32 sid; int rc; /* * Make sure that the xattr handler exists and that no * error other than -ENODATA is returned by getxattr on * the root directory. -ENODATA is ok, as this may be * the first boot of the SELinux kernel before we have * assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no xattr support\n", sb->s_id, sb->s_type->name); goto fallback; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) { pr_warn("SELinux: (dev %s, type %s) has no security xattr handler\n", sb->s_id, sb->s_type->name); goto fallback; } else { pr_warn("SELinux: (dev %s, type %s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); return rc; } } return 0; fallback: /* No xattr support - try to fallback to genfs if possible. */ rc = security_genfs_sid(sb->s_type->name, "/", SECCLASS_DIR, &sid); if (rc) return -EOPNOTSUPP; pr_warn("SELinux: (dev %s, type %s) falling back to genfs\n", sb->s_id, sb->s_type->name); sbsec->behavior = SECURITY_FS_USE_GENFS; sbsec->sid = sid; return 0; } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { rc = sb_check_xattr_support(sb); if (rc) return rc; } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; /* * Specifying internal flags without providing a place to * place the results is not allowed */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&sbsec->lock); if (!selinux_initialized()) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { sbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explicit options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext_sid) { fscontext_sid = opts->fscontext_sid; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context_sid) { context_sid = opts->context_sid; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext_sid) { rootcontext_sid = opts->rootcontext_sid; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext_sid) { defcontext_sid = opts->defcontext_sid; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "securityfs")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts") && strcmp(sb->s_type->name, "overlay")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (sbsec->flags & SE_SBNATIVE) { /* * This means we are initializing a superblock that has been * mounted before the SELinux was initialized and the * filesystem requested native labeling. We had already * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags * in the original mount attempt, so now we just need to set * the SECURITY_FS_USE_NATIVE behavior. */ sbsec->behavior = SECURITY_FS_USE_NATIVE; } else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = selinux_superblock(oldsb); struct superblock_security_struct *new = selinux_superblock(newsb); char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = selinux_superblock(oldsb); struct superblock_security_struct *newsbsec = selinux_superblock(newsb); int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&newsbsec->lock); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized()) { if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { newsbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { mutex_unlock(&newsbsec->lock); if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } /* * NOTE: the caller is responsible for freeing the memory even if on error. */ static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; u32 *dst_sid; int rc; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -EINVAL; if (!selinux_initialized()) { pr_warn("SELinux: Unable to set superblock options before the security server is initialized\n"); return -EINVAL; } if (!opts) { opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; } switch (token) { case Opt_context: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->context_sid; break; case Opt_fscontext: if (opts->fscontext_sid) goto err; dst_sid = &opts->fscontext_sid; break; case Opt_rootcontext: if (opts->rootcontext_sid) goto err; dst_sid = &opts->rootcontext_sid; break; case Opt_defcontext: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->defcontext_sid; break; default: WARN_ON(1); return -EINVAL; } rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n", s, rc); return rc; err: pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(sid, &context, &len); if (!rc) { bool has_comma = strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized()) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP || protocol == IPPROTO_MPTCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { bool extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; case PF_MCTP: return SECCLASS_MCTP_SOCKET; #if PF_MAX > 46 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { /* * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels * via xattr when called from delayed_superblock_init(). */ case SECURITY_FS_USE_NATIVE: case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(const struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = selinux_superblock(dir->i_sb); if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = selinux_superblock(dir->i_sb); sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, const struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = selinux_superblock(sb); return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(const struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid_obj(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(task_sid_obj(parent), task_sid_obj(current), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(current_sid(), task_sid_obj(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, const struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { int rc, cap_sys_admin = 0; rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); if (rc == 0) cap_sys_admin = 1; return cap_sys_admin; } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid_obj(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; /* * Before policy is loaded, label any task outside kernel space * as SECINITSID_INIT, so that any userspace tasks surviving from * early boot end up with a label different from SECINITSID_KERNEL * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL). */ if (!selinux_initialized()) { new_tsec->sid = SECINITSID_INIT; /* also clear the exec_sid just in case */ new_tsec->exec_sid = 0; return 0; } if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(const struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(&unrcu_pointer(current->sighand)->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(&unrcu_pointer(current->sighand)->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, unrcu_pointer(current->real_parent)); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; return 0; } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); kfree(arg); arg = NULL; if (unlikely(rc)) { goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * Superblock not initialized (i.e. no options) - reject if any * options specified, otherwise accept. */ if (!(sbsec->flags & SE_SBINITIALIZED)) return opts ? 1 : 0; /* * Superblock initialized and no options specified - reject if * superblock has any options set, otherwise accept. */ if (!opts) return (sbsec->flags & SE_MNTMASK) ? 1 : 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) return 1; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) return 1; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) return 1; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) return 1; } return 0; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) goto out_bad_option; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) goto out_bad_option; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) goto out_bad_option; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(const struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_submount(struct fs_context *fc, struct super_block *reference) { const struct superblock_security_struct *sbsec = selinux_superblock(reference); struct selinux_mnt_opts *opts; /* * Ensure that fc->security remains NULL when no options are set * as expected by selinux_set_mnt_opts(). */ if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) return 0; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; if (sbsec->flags & CONTEXT_MNT) opts->context_sid = sbsec->mntpoint_sid; if (sbsec->flags & DEFCONTEXT_MNT) opts->defcontext_sid = sbsec->def_sid; fc->security = opts; return 0; } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; if (!src) return 0; fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL); return fc->security ? 0 : -ENOMEM; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; return selinux_add_opt(opt, param->string, &fc->security); } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; return security_sid_to_context(newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); u32 newsid, clen; u16 newsclass; int rc; char *context; sbsec = selinux_superblock(dir->i_sb); newsid = tsec->create_sid; newsclass = inode_mode_to_security_class(inode->i_mode); rc = selinux_determine_inode_label(tsec, dir, qstr, newsclass, &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = newsclass; isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized() || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (xattr) { rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; xattr->value = context; xattr->value_len = clen; xattr->name = XATTR_SELINUX_SUFFIX; } return 0; } static int selinux_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { u32 sid = current_sid(); struct common_audit_data ad; struct inode_security_struct *isec; int rc; if (unlikely(!selinux_initialized())) return 0; isec = selinux_inode(inode); /* * We only get here once per ephemeral inode. The inode has * been initialized via inode_alloc_security but is otherwise * untouched. */ if (context_inode) { struct inode_security_struct *context_isec = selinux_inode(context_inode); if (context_isec->initialized != LABEL_INITIALIZED) { pr_err("SELinux: context_inode is not initialized\n"); return -EACCES; } isec->sclass = context_isec->sclass; isec->sid = context_isec->sid; } else { isec->sclass = SECCLASS_ANON_INODE; rc = security_transition_sid( sid, sid, isec->sclass, name, &isec->sid); if (rc) return rc; } isec->initialized = LABEL_INITIALIZED; /* * Now that we've initialized security, check whether we're * allowed to actually create this type of anonymous inode. */ ad.type = LSM_AUDIT_DATA_ANONINODE; ad.u.anonclass = name ? (const char *)name->name : "?"; return avc_has_perm(sid, isec->sid, isec->sclass, FILE__CREATE, &ad); } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { struct common_audit_data ad; struct inode_security_struct *isec; u32 sid = current_sid(); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm(sid, isec->sid, isec->sclass, FILE__READ, &ad); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; return slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); } static int selinux_inode_permission(struct inode *inode, int mask) { u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid = current_sid(); struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } /** * selinux_inode_xattr_skipcap - Skip the xattr capability checks? * @name: name of the xattr * * Returns 1 to indicate that SELinux "owns" the access control rights to xattrs * named @name; the LSM layer should avoid enforcing any traditional * capability based access controls on this xattr. Returns 0 to indicate that * SELinux does not "own" the access control rights to xattrs named @name and is * deferring to the LSM layer for further access controls, including capability * based controls. */ static int selinux_inode_xattr_skipcap(const char *name) { /* require capability check if not a selinux xattr */ return !strcmp(name, XATTR_NAME_SELINUX); } static int selinux_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return rc; audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static int selinux_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static int selinux_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__GETATTR); } static int selinux_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized()) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized() || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(isec->sid, &context, &size); else error = security_sid_to_context(isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized()) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { u32 sid; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getsecid(d_inode(src), &sid); tsec->create_sid = sid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, filter out SELinux-related xattrs following * policy load. */ if (selinux_initialized() && strcmp(name, XATTR_NAME_SELINUX) == 0) return 1; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno()) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot __always_unused, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot __always_unused, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; if (vma_is_initial_heap(vma)) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid_obj(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); break; default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_current_getsecid_subj(u32 *secid) { *secid = current_sid(); } static void selinux_task_getsecid_obj(struct task_struct *p, u32 *secid) { *secid = task_sid_obj(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(secid, task_sid_obj(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid_obj(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_userns_create(const struct cred *cred) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_USER_NAMESPACE, USER_NAMESPACE__CREATE, NULL); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(tsec->sid, tsec->sid, secclass, NULL, socksid); } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; if (sksec->sid == SECINITSID_KERNEL) return 0; /* * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that * inherited the kernel context from early boot used to be skipped * here, so preserve that behavior unless the capability is set. * * By setting the capability the policy signals that it is ready * for this quirk to be fixed. Note that sockets created by a kernel * thread or a usermode helper executed without a transition will * still be skipped in this check regardless of the policycap * setting. */ if (!selinux_policycap_userspace_initial_context() && sksec->sid == SECINITSID_INIT) return 0; ad_net_init_from_sk(&ad, &net, sk); return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = sock->sk->sk_security; sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = socka->sk->sk_security; struct sk_security_struct *sksec_b = sockb->sk->sk_security; sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = sock->sk_security; struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; int err; ad_net_init_from_sk(&ad, &net, other); err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = sock->sk->sk_security; struct sk_security_struct *osec = other->sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; ad_net_init_from_sk(&ad, &net, other->sk); return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = sk->sk_security; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; struct sk_security_struct *sksec = sk->sk_security; u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = sock->sk->sk_security; u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else { *secid = SECSID_NULL; return -EINVAL; } if (sock && family == PF_UNIX) { struct inode_security_struct *isec; isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); *secid = peer_secid; if (peer_secid == SECSID_NULL) return -ENOPROTOOPT; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec; sksec = kzalloc(sizeof(*sksec), priority); if (!sksec) return -ENOMEM; sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = sk->sk_security; sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { const struct sk_security_struct *sksec = sk->sk_security; *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = sk->sk_security; if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* * Determines peer_secid for the asoc and updates socket's peer label * if it's the first association on the socket. */ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, struct sk_buff *skb) { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; int err; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; if (selinux_peerlbl_enabled()) { asoc->peer_secid = SECSID_NULL; /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, family, &asoc->peer_secid); if (err) return err; if (asoc->peer_secid == SECSID_NULL) asoc->peer_secid = SECINITSID_UNLABELED; } else { asoc->peer_secid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = asoc->peer_secid; } else if (sksec->peer_sid != asoc->peer_secid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad_net_init_from_sk(&ad, &net, asoc->base.sk); err = avc_has_perm(sksec->peer_sid, asoc->peer_secid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } return 0; } /* Called whenever SCTP receives an INIT or COOKIE ECHO chunk. This * happens on an incoming connect(2), sctp_connectx(3) or * sctp_sendmsg(3) (with no association already present). */ static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = asoc->base.sk->sk_security; u32 conn_sid; int err; if (!selinux_policycap_extsockclass()) return 0; err = selinux_sctp_process_new_assoc(asoc, skb); if (err) return err; /* Compute the MLS component for the connection and store * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, asoc->peer_secid, &conn_sid); if (err) return err; asoc->secid = conn_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Called when SCTP receives a COOKIE ACK chunk as the final * response to an association request (initited by us). */ static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = asoc->base.sk->sk_security; if (!selinux_policycap_extsockclass()) return 0; /* Inherit secid from the parent socket - this will be picked up * by selinux_sctp_sk_clone() if the association gets peeled off * into a new socket. */ asoc->secid = sksec->sid; return selinux_sctp_process_new_assoc(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { struct sk_security_struct *ssksec = ssk->sk_security; struct sk_security_struct *sksec = sk->sk_security; ssksec->sclass = sksec->sclass; ssksec->sid = sksec->sid; /* replace the existing subflow label deleting the existing one * and re-recreating a new label using the updated context */ selinux_netlbl_sk_security_free(ssksec); return selinux_netlbl_socket_post_create(ssk, ssk->sk_family); } static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = sk->sk_security; int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { return avc_has_perm(current_sid(), sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void **security) { struct tun_security_struct *tunsec; tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); if (!tunsec) return -ENOMEM; tunsec->sid = current_sid(); *security = tunsec; return 0; } static void selinux_tun_dev_free_security(void *security) { kfree(security); } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = security; return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; struct sk_security_struct *sksec = sk->sk_security; /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = security; u32 sid = current_sid(); int err; err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int ifindex; u16 family; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net; int secmark_active, peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; family = state->pf; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ifindex = state->in->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { int err; err = selinux_inet_sys_rcv_skb(state->net, ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_enabled()) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = skb->sk; if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = sk->sk_security; sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, state->pf, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net; u8 proto = 0; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; sksec = sk->sk_security; ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { u16 family; u32 secmark_perm; u32 peer_sid; int ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; int secmark_active, peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, state); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif family = state->pf; if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = sk->sk_security; peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ifindex = state->out->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(state->net, ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } #endif /* CONFIG_NETFILTER */ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security; u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { rc = sock_has_perm(sk, perm); if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled() && !security_get_allow_unknown()) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } return ipc_has_perm(msq, perms); } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid_obj(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } return ipc_has_perm(shp, perms); } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { struct ipc_security_struct *isec = selinux_ipc(ipcp); *secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p, char **value) { const struct task_security_struct *tsec; int error; u32 sid; u32 len; rcu_read_lock(); tsec = selinux_cred(__task_cred(p)); if (p != current) { error = avc_has_perm(current_sid(), tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto err_unlock; } switch (attr) { case LSM_ATTR_CURRENT: sid = tsec->sid; break; case LSM_ATTR_PREV: sid = tsec->osid; break; case LSM_ATTR_EXEC: sid = tsec->exec_sid; break; case LSM_ATTR_FSCREATE: sid = tsec->create_sid; break; case LSM_ATTR_KEYCREATE: sid = tsec->keycreate_sid; break; case LSM_ATTR_SOCKCREATE: sid = tsec->sockcreate_sid; break; default: error = -EOPNOTSUPP; goto err_unlock; } rcu_read_unlock(); if (sid == SECSID_NULL) { *value = NULL; return 0; } error = security_sid_to_context(sid, value, &len); if (error) return error; return len; err_unlock: rcu_read_unlock(); return error; } static int selinux_lsm_setattr(u64 attr, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ switch (attr) { case LSM_ATTR_EXEC: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); break; case LSM_ATTR_FSCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); break; case LSM_ATTR_KEYCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); break; case LSM_ATTR_SOCKCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); break; case LSM_ATTR_CURRENT: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); break; default: error = -EOPNOTSUPP; break; } if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(value, size, &sid, GFP_KERNEL); if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, * otherwise the context contains a nul and * we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return error; audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force(value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (attr == LSM_ATTR_EXEC) { tsec->exec_sid = sid; } else if (attr == LSM_ATTR_FSCREATE) { tsec->create_sid = sid; } else if (attr == LSM_ATTR_KEYCREATE) { if (sid) { error = avc_has_perm(mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (attr == LSM_ATTR_SOCKCREATE) { tsec->sockcreate_sid = sid; } else if (attr == LSM_ATTR_CURRENT) { error = -EINVAL; if (sid == 0) goto abort_change; if (!current_is_single_threaded()) { error = security_bounded_transition(tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } /** * selinux_getselfattr - Get SELinux current task attributes * @attr: the requested attribute * @ctx: buffer to receive the result * @size: buffer size (input), buffer size used (output) * @flags: unused * * Fill the passed user space @ctx with the details of the requested * attribute. * * Returns the number of attributes on success, an error code otherwise. * There will only ever be one attribute. */ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) { int rc; char *val = NULL; int val_len; val_len = selinux_lsm_getattr(attr, current, &val); if (val_len < 0) return val_len; rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0); kfree(val); return (!rc ? 1 : rc); } static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { int rc; rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int selinux_getprocattr(struct task_struct *p, const char *name, char **value) { unsigned int attr = lsm_name_to_attr(name); int rc; if (attr) { rc = selinux_lsm_getattr(attr, p, value); if (rc != -EOPNOTSUPP) return rc; } return -EINVAL; } static int selinux_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return selinux_lsm_setattr(attr, value, size); return -EINVAL; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec; ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); if (!ksec) return -ENOMEM; tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; k->security = ksec; return 0; } static void selinux_key_free(struct key *k) { struct key_security_struct *ksec = k->security; k->security = NULL; kfree(ksec); } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = key->security; return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = key->security; char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = key->security; u32 sid = current_sid(); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; ibendport.dev_name = dev_name; ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void **ib_sec) { struct ib_security_struct *sec; sec = kzalloc(sizeof(*sec), GFP_KERNEL); if (!sec) return -ENOMEM; sec->sid = current_sid(); *ib_sec = sec; return 0; } static void selinux_ib_free_security(void *ib_sec) { kfree(ib_sec); } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply corresponding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(const struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); prog->aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog *prog) { struct bpf_security_struct *bpfsec = prog->aux->security; prog->aux->security = NULL; kfree(bpfsec); } static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, struct path *path) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); token->security = bpfsec; return 0; } static void selinux_bpf_token_free(struct bpf_token *token) { struct bpf_security_struct *bpfsec = token->security; token->security = NULL; kfree(bpfsec); } #endif struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); if (!perfsec) return -ENOMEM; perfsec->sid = current_sid(); event->security = perfsec; return 0; } static void selinux_perf_event_free(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; event->security = NULL; kfree(perfsec); } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif #ifdef CONFIG_IO_URING /** * selinux_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int selinux_uring_override_creds(const struct cred *new) { return avc_has_perm(current_sid(), cred_sid(new), SECCLASS_IO_URING, IO_URING__OVERRIDE_CREDS, NULL); } /** * selinux_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int selinux_uring_sqpoll(void) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_IO_URING, IO_URING__SQPOLL, NULL); } /** * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed * @ioucmd: the io_uring command structure * * Check to see if the current domain is allowed to execute an * IORING_OP_URING_CMD against the device/file specified in @ioucmd. * */ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) { struct file *file = ioucmd->file; struct inode *inode = file_inode(file); struct inode_security_struct *isec = selinux_inode(inode); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return avc_has_perm(current_sid(), isec->sid, SECCLASS_IO_URING, IO_URING__CMD, &ad); } #endif /* CONFIG_IO_URING */ static const struct lsm_id selinux_lsmid = { .name = "selinux", .id = LSM_ID_SELINUX, }; /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. */ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_init_security_anon, selinux_inode_init_security_anon), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_xattr_skipcap, selinux_inode_xattr_skipcap), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_set_acl, selinux_inode_set_acl), LSM_HOOK_INIT(inode_get_acl, selinux_inode_get_acl), LSM_HOOK_INIT(inode_remove_acl, selinux_inode_remove_acl), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(current_getsecid_subj, selinux_current_getsecid_subj), LSM_HOOK_INIT(task_getsecid_obj, selinux_task_getsecid_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(userns_create, selinux_userns_create), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getselfattr, selinux_getselfattr), LSM_HOOK_INIT(setselfattr, selinux_setselfattr), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_free_security, selinux_tun_dev_free_security), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), LSM_HOOK_INIT(ib_free_security, selinux_ib_free_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll), LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd), #endif /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(selinux_enforcing_boot); selinux_avc_init(); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); if (!default_noexec) pr_notice("SELinux: virtual memory is executable by default\n"); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), &selinux_lsmid); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #endif /* CONFIG_NETFILTER */ |
| 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 | // SPDX-License-Identifier: GPL-2.0 /* Watch queue and general notification mechanism, built on pipes * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/core-api/watch_queue.rst */ #define pr_fmt(fmt) "watchq: " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/miscdevice.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/poll.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/file.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/sched/signal.h> #include <linux/watch_queue.h> #include <linux/pipe_fs_i.h> MODULE_DESCRIPTION("Watch queue"); MODULE_AUTHOR("Red Hat, Inc."); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) /* * This must be called under the RCU read-lock, which makes * sure that the wqueue still exists. It can then take the lock, * and check that the wqueue hasn't been destroyed, which in * turn makes sure that the notification pipe still exists. */ static inline bool lock_wqueue(struct watch_queue *wqueue) { spin_lock_bh(&wqueue->lock); if (unlikely(!wqueue->pipe)) { spin_unlock_bh(&wqueue->lock); return false; } return true; } static inline void unlock_wqueue(struct watch_queue *wqueue) { spin_unlock_bh(&wqueue->lock); } static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct watch_queue *wqueue = (struct watch_queue *)buf->private; struct page *page; unsigned int bit; /* We need to work out which note within the page this refers to, but * the note might have been maximum size, so merely ANDing the offset * off doesn't work. OTOH, the note must've been more than zero size. */ bit = buf->offset + buf->len; if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0) bit -= WATCH_QUEUE_NOTE_SIZE; bit /= WATCH_QUEUE_NOTE_SIZE; page = buf->page; bit += page->index; set_bit(bit, wqueue->notes_bitmap); generic_pipe_buf_release(pipe, buf); } // No try_steal function => no stealing #define watch_queue_pipe_buf_try_steal NULL /* New data written to a pipe may be appended to a buffer with this type. */ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { .release = watch_queue_pipe_buf_release, .try_steal = watch_queue_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* * Post a notification to a watch queue. * * Must be called with the RCU lock for reading, and the * watch_queue lock held, which guarantees that the pipe * hasn't been released. */ static bool post_one_notification(struct watch_queue *wqueue, struct watch_notification *n) { void *p; struct pipe_inode_info *pipe = wqueue->pipe; struct pipe_buffer *buf; struct page *page; unsigned int head, tail, mask, note, offset, len; bool done = false; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; if (pipe_full(head, tail, pipe->ring_size)) goto lost; note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes); if (note >= wqueue->nr_notes) goto lost; page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE]; offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE; get_page(page); len = n->info & WATCH_INFO_LENGTH; p = kmap_atomic(page); memcpy(p + offset, n, len); kunmap_atomic(p); buf = &pipe->bufs[head & mask]; buf->page = page; buf->private = (unsigned long)wqueue; buf->ops = &watch_queue_pipe_buf_ops; buf->offset = offset; buf->len = len; buf->flags = PIPE_BUF_FLAG_WHOLE; smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { spin_unlock_irq(&pipe->rd_wait.lock); BUG(); } wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); done = true; out: spin_unlock_irq(&pipe->rd_wait.lock); if (done) kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); return done; lost: buf = &pipe->bufs[(head - 1) & mask]; buf->flags |= PIPE_BUF_FLAG_LOSS; goto out; } /* * Apply filter rules to a notification. */ static bool filter_watch_notification(const struct watch_filter *wf, const struct watch_notification *n) { const struct watch_type_filter *wt; unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8; unsigned int st_index = n->subtype / st_bits; unsigned int st_bit = 1U << (n->subtype % st_bits); int i; if (!test_bit(n->type, wf->type_filter)) return false; for (i = 0; i < wf->nr_filters; i++) { wt = &wf->filters[i]; if (n->type == wt->type && (wt->subtype_filter[st_index] & st_bit) && (n->info & wt->info_mask) == wt->info_filter) return true; } return false; /* If there is a filter, the default is to reject. */ } /** * __post_watch_notification - Post an event notification * @wlist: The watch list to post the event to. * @n: The notification record to post. * @cred: The creds of the process that triggered the notification. * @id: The ID to match on the watch. * * Post a notification of an event into a set of watch queues and let the users * know. * * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and * should be in units of sizeof(*n). */ void __post_watch_notification(struct watch_list *wlist, struct watch_notification *n, const struct cred *cred, u64 id) { const struct watch_filter *wf; struct watch_queue *wqueue; struct watch *watch; if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) { WARN_ON(1); return; } rcu_read_lock(); hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) { if (watch->id != id) continue; n->info &= ~WATCH_INFO_ID; n->info |= watch->info_id; wqueue = rcu_dereference(watch->queue); wf = rcu_dereference(wqueue->filter); if (wf && !filter_watch_notification(wf, n)) continue; if (security_post_notification(watch->cred, cred, n) < 0) continue; if (lock_wqueue(wqueue)) { post_one_notification(wqueue, n); unlock_wqueue(wqueue); } } rcu_read_unlock(); } EXPORT_SYMBOL(__post_watch_notification); /* * Allocate sufficient pages to preallocation for the requested number of * notifications. */ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) { struct watch_queue *wqueue = pipe->watch_queue; struct page **pages; unsigned long *bitmap; unsigned long user_bufs; int ret, i, nr_pages; if (!wqueue) return -ENODEV; if (wqueue->notes) return -EBUSY; if (nr_notes < 1 || nr_notes > 512) /* TODO: choose a better hard limit */ return -EINVAL; nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1); nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages); if (nr_pages > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto error; } nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; ret = -ENOMEM; pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto error; for (i = 0; i < nr_pages; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) goto error_p; pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; } bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); if (!bitmap) goto error_p; bitmap_fill(bitmap, nr_notes); wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; wqueue->nr_notes = nr_notes; return 0; error_p: while (--i >= 0) __free_page(pages[i]); kfree(pages); error: (void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted); return ret; } /* * Set the filter on a watch queue. */ long watch_queue_set_filter(struct pipe_inode_info *pipe, struct watch_notification_filter __user *_filter) { struct watch_notification_type_filter *tf; struct watch_notification_filter filter; struct watch_type_filter *q; struct watch_filter *wfilter; struct watch_queue *wqueue = pipe->watch_queue; int ret, nr_filter = 0, i; if (!wqueue) return -ENODEV; if (!_filter) { /* Remove the old filter */ wfilter = NULL; goto set; } /* Grab the user's filter specification */ if (copy_from_user(&filter, _filter, sizeof(filter)) != 0) return -EFAULT; if (filter.nr_filters == 0 || filter.nr_filters > 16 || filter.__reserved != 0) return -EINVAL; tf = memdup_array_user(_filter->filters, filter.nr_filters, sizeof(*tf)); if (IS_ERR(tf)) return PTR_ERR(tf); ret = -EINVAL; for (i = 0; i < filter.nr_filters; i++) { if ((tf[i].info_filter & ~tf[i].info_mask) || tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } /* Now we need to build the internal filter from only the relevant * user-specified filters. */ ret = -ENOMEM; wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL); if (!wfilter) goto err_filter; wfilter->nr_filters = nr_filter; q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; q->info_filter = tf[i].info_filter; q->info_mask = tf[i].info_mask; q->subtype_filter[0] = tf[i].subtype_filter[0]; __set_bit(q->type, wfilter->type_filter); q++; } kfree(tf); set: pipe_lock(pipe); wfilter = rcu_replace_pointer(wqueue->filter, wfilter, lockdep_is_held(&pipe->mutex)); pipe_unlock(pipe); if (wfilter) kfree_rcu(wfilter, rcu); return 0; err_filter: kfree(tf); return ret; } static void __put_watch_queue(struct kref *kref) { struct watch_queue *wqueue = container_of(kref, struct watch_queue, usage); struct watch_filter *wfilter; int i; for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); kfree(wqueue->notes); bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); if (wfilter) kfree_rcu(wfilter, rcu); kfree_rcu(wqueue, rcu); } /** * put_watch_queue - Dispose of a ref on a watchqueue. * @wqueue: The watch queue to unref. */ void put_watch_queue(struct watch_queue *wqueue) { kref_put(&wqueue->usage, __put_watch_queue); } EXPORT_SYMBOL(put_watch_queue); static void free_watch(struct rcu_head *rcu) { struct watch *watch = container_of(rcu, struct watch, rcu); put_watch_queue(rcu_access_pointer(watch->queue)); atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); kfree(watch); } static void __put_watch(struct kref *kref) { struct watch *watch = container_of(kref, struct watch, usage); call_rcu(&watch->rcu, free_watch); } /* * Discard a watch. */ static void put_watch(struct watch *watch) { kref_put(&watch->usage, __put_watch); } /** * init_watch - Initialise a watch * @watch: The watch to initialise. * @wqueue: The queue to assign. * * Initialise a watch and set the watch queue. */ void init_watch(struct watch *watch, struct watch_queue *wqueue) { kref_init(&watch->usage); INIT_HLIST_NODE(&watch->list_node); INIT_HLIST_NODE(&watch->queue_node); rcu_assign_pointer(watch->queue, wqueue); } static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue) { const struct cred *cred; struct watch *w; hlist_for_each_entry(w, &wlist->watchers, list_node) { struct watch_queue *wq = rcu_access_pointer(w->queue); if (wqueue == wq && watch->id == w->id) return -EBUSY; } cred = current_cred(); if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) { atomic_dec(&cred->user->nr_watches); return -EAGAIN; } watch->cred = get_cred(cred); rcu_assign_pointer(watch->watch_list, wlist); kref_get(&wqueue->usage); kref_get(&watch->usage); hlist_add_head(&watch->queue_node, &wqueue->watches); hlist_add_head_rcu(&watch->list_node, &wlist->watchers); return 0; } /** * add_watch_to_object - Add a watch on an object to a watch list * @watch: The watch to add * @wlist: The watch list to add to * * @watch->queue must have been set to point to the queue to post notifications * to and the watch list of the object to be watched. @watch->cred must also * have been set to the appropriate credentials and a ref taken on them. * * The caller must pin the queue and the list both and must hold the list * locked against racing watch additions/removals. */ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) { struct watch_queue *wqueue; int ret = -ENOENT; rcu_read_lock(); wqueue = rcu_access_pointer(watch->queue); if (lock_wqueue(wqueue)) { spin_lock(&wlist->lock); ret = add_one_watch(watch, wlist, wqueue); spin_unlock(&wlist->lock); unlock_wqueue(wqueue); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(add_watch_to_object); /** * remove_watch_from_object - Remove a watch or all watches from an object. * @wlist: The watch list to remove from * @wq: The watch queue of interest (ignored if @all is true) * @id: The ID of the watch to remove (ignored if @all is true) * @all: True to remove all objects * * Remove a specific watch or all watches from an object. A notification is * sent to the watcher to tell them that this happened. */ int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq, u64 id, bool all) { struct watch_notification_removal n; struct watch_queue *wqueue; struct watch *watch; int ret = -EBADSLT; rcu_read_lock(); again: spin_lock(&wlist->lock); hlist_for_each_entry(watch, &wlist->watchers, list_node) { if (all || (watch->id == id && rcu_access_pointer(watch->queue) == wq)) goto found; } spin_unlock(&wlist->lock); goto out; found: ret = 0; hlist_del_init_rcu(&watch->list_node); rcu_assign_pointer(watch->watch_list, NULL); spin_unlock(&wlist->lock); /* We now own the reference on watch that used to belong to wlist. */ n.watch.type = WATCH_TYPE_META; n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION; n.watch.info = watch->info_id | watch_sizeof(n.watch); n.id = id; if (id != 0) n.watch.info = watch->info_id | watch_sizeof(n); wqueue = rcu_dereference(watch->queue); if (lock_wqueue(wqueue)) { post_one_notification(wqueue, &n.watch); if (!hlist_unhashed(&watch->queue_node)) { hlist_del_init_rcu(&watch->queue_node); put_watch(watch); } unlock_wqueue(wqueue); } if (wlist->release_watch) { void (*release_watch)(struct watch *); release_watch = wlist->release_watch; rcu_read_unlock(); (*release_watch)(watch); rcu_read_lock(); } put_watch(watch); if (all && !hlist_empty(&wlist->watchers)) goto again; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(remove_watch_from_object); /* * Remove all the watches that are contributory to a queue. This has the * potential to race with removal of the watches by the destruction of the * objects being watched or with the distribution of notifications. */ void watch_queue_clear(struct watch_queue *wqueue) { struct watch_list *wlist; struct watch *watch; bool release; rcu_read_lock(); spin_lock_bh(&wqueue->lock); /* * This pipe can be freed by callers like free_pipe_info(). * Removing this reference also prevents new notifications. */ wqueue->pipe = NULL; while (!hlist_empty(&wqueue->watches)) { watch = hlist_entry(wqueue->watches.first, struct watch, queue_node); hlist_del_init_rcu(&watch->queue_node); /* We now own a ref on the watch. */ spin_unlock_bh(&wqueue->lock); /* We can't do the next bit under the queue lock as we need to * get the list lock - which would cause a deadlock if someone * was removing from the opposite direction at the same time or * posting a notification. */ wlist = rcu_dereference(watch->watch_list); if (wlist) { void (*release_watch)(struct watch *); spin_lock(&wlist->lock); release = !hlist_unhashed(&watch->list_node); if (release) { hlist_del_init_rcu(&watch->list_node); rcu_assign_pointer(watch->watch_list, NULL); /* We now own a second ref on the watch. */ } release_watch = wlist->release_watch; spin_unlock(&wlist->lock); if (release) { if (release_watch) { rcu_read_unlock(); /* This might need to call dput(), so * we have to drop all the locks. */ (*release_watch)(watch); rcu_read_lock(); } put_watch(watch); } } put_watch(watch); spin_lock_bh(&wqueue->lock); } spin_unlock_bh(&wqueue->lock); rcu_read_unlock(); } /** * get_watch_queue - Get a watch queue from its file descriptor. * @fd: The fd to query. */ struct watch_queue *get_watch_queue(int fd) { struct pipe_inode_info *pipe; struct watch_queue *wqueue = ERR_PTR(-EINVAL); struct fd f; f = fdget(fd); if (f.file) { pipe = get_pipe_info(f.file, false); if (pipe && pipe->watch_queue) { wqueue = pipe->watch_queue; kref_get(&wqueue->usage); } fdput(f); } return wqueue; } EXPORT_SYMBOL(get_watch_queue); /* * Initialise a watch queue */ int watch_queue_init(struct pipe_inode_info *pipe) { struct watch_queue *wqueue; wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL); if (!wqueue) return -ENOMEM; wqueue->pipe = pipe; kref_init(&wqueue->usage); spin_lock_init(&wqueue->lock); INIT_HLIST_HEAD(&wqueue->watches); pipe->watch_queue = wqueue; return 0; } |
| 248 248 248 248 127 155 248 248 62 62 62 61 62 62 62 62 62 61 62 51 62 62 11 11 11 138 137 138 138 155 155 24 24 17 184 184 11 11 11 248 248 248 62 61 62 61 62 62 62 62 62 62 62 62 62 62 51 12 61 61 61 62 229 20 20 229 9 229 248 248 248 247 127 126 20 62 62 20 50 62 62 61 61 69 68 69 69 62 18 62 96 99 9 4 9 9 9 2 93 99 93 93 99 99 99 99 2 99 99 99 96 96 96 96 96 96 96 96 96 93 96 96 11 93 93 93 93 9 9 4 9 9 9 9 9 9 9 9 127 127 127 15 15 15 262 261 262 262 262 261 258 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <linux/rw_hint.h> #include <trace/events/writeback.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget(), inode->i_io_list * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __ro_after_init; static unsigned int i_hash_shift __ro_after_init; static struct hlist_head *inode_hashtable __ro_after_init; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __ro_after_init; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL /* * Statistics gathering.. */ static struct inodes_stat_t inodes_stat; static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, }; static int __init init_fs_inode_sysctls(void) { register_sysctl_init("fs", inodes_sysctls); return 0; } early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; inode->i_state = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->i_ino = 0; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); if (sb->s_iflags & SB_I_STABLE_WRITES) mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = alloc_inode_sb(sb, inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->i_private_list); spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); INIT_LIST_HEAD(&inode->i_sb_list); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * inode->i_lock must be held */ void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void __inode_add_lru(struct inode *inode, bool rotate) { if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; if (atomic_read(&inode->i_count)) return; if (!(inode->i_sb->s_flags & SB_ACTIVE)) return; if (!mapping_shrinkable(&inode->i_data)) return; if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) inode->i_state |= I_REFERENCED; } /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { __inode_add_lru(inode, false); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void dump_mapping(const struct address_space *mapping) { struct inode *host; const struct address_space_operations *a_ops; struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; unsigned long ino; /* * If mapping is an invalid pointer, we don't want to crash * accessing it, so probe everything depending on it carefully. */ if (get_kernel_nofault(host, &mapping->host) || get_kernel_nofault(a_ops, &mapping->a_ops)) { pr_warn("invalid mapping:%px\n", mapping); return; } if (!host) { pr_warn("aops:%ps\n", a_ops); return; } if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || get_kernel_nofault(ino, &host->i_ino)) { pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); return; } if (!dentry_first) { pr_warn("aops:%ps ino:%lx\n", a_ops, ino); return; } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); if (get_kernel_nofault(dentry, dentry_ptr) || !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; } /* * if dentry is corrupted, the %pd handler may still crash, * but it's unlikely that we reach here with a corrupt mapping */ pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); } void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __filemap_remove_folio()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); /* * Almost always, mapping_empty(&inode->i_data) here; but there are * two known and long-standing ways in which nodes may get left behind * (when deep radix-tree node allocation failed partway; or when THP * collapse_file() failed). Until those two known cases are cleaned up, * or a cleanup function is called here, do not BUG_ON(!mapping_empty), * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); /* * Wake up waiters in __wait_on_freeing_inode(). * * Lockless hash lookup may end up finding the inode before we removed * it above, but only lock it *after* we are done with the wakeup below. * In this case the potential waiter cannot safely block. * * The inode being unhashed after the call to remove_inode_hash() is * used as an indicator whether blocking on it is safe. */ spin_lock(&inode->i_lock); wake_up_bit(&inode->i_state, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * * Attempts to free all inodes (including dirty inodes) for a given superblock. */ void invalidate_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } /* * Isolate the inode from the LRU in preparation for freeing it. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * We are inverting the lru lock/inode->i_lock here, so use a * trylock. If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Inodes can get referenced, redirtied, or repopulated while * they're already on the LRU, and this can make them * unreclaimable for a while. Remove them lazily here; iput, * sync, or the last page cache deletion will requeue them. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* Recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } /* * On highmem systems, mapping_shrinkable() permits dropping * page cache in order to free up struct inodes: lowmem might * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } iput(inode); spin_lock(lru_lock); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data, bool is_inode_hash_locked) { struct inode *inode = NULL; if (is_inode_hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino, bool is_inode_hash_locked) { struct inode *inode = NULL; if (is_inode_hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { return alloc_inode(sb); } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument. Passed objects must not be directories. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); if (inode2) WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); if (inode1 > inode2) swap(inode1, inode2); if (inode1) inode_lock(inode1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) { WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); inode_unlock(inode1); } if (inode2 && inode2 != inode1) { WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); inode_unlock(inode2); } } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a variant of iget5_locked() for callers that don't want to fail on memory * allocation of inode. * * If the inode is not in cache, insert the pre-allocated inode to cache and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data, true); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); /* * Add inode to the sb list if it's not already. It has I_NEW at this * point, so it should be safe to test i_sb_list locklessly. */ if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget5_locked_rcu - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * This is equivalent to iget5_locked, except the @test callback must * tolerate the inode not being stable, including being mid-teardown. */ struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *new; again: inode = find_inode(sb, head, test, data, false); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } return inode; } EXPORT_SYMBOL_GPL(iget5_locked_rcu); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: inode = find_inode_fast(sb, head, ino, false); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino, true); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data, true); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino, true); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_ino_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { __inode_add_lru(inode, true); spin_unlock(&inode->i_lock); return; } state = inode->i_state; if (!drop) { WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); state = inode->i_state; WARN_ON(state & I_NEW); state &= ~I_WILL_FREE; } WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ atime = inode_get_atime(inode); mtime = inode_get_mtime(inode); if (timespec64_compare(&mtime, &atime) >= 0) return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); if (timespec64_compare(&ctime, &atime) >= 0) return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) return true; /* * Good, we can skip the atime update: */ return false; } /** * inode_update_timestamps - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. This function handles updating the * actual timestamps. It's up to the caller to ensure that the inode is marked * dirty appropriately. * * In the case where any of S_MTIME, S_CTIME, or S_VERSION need to be updated, * attempt to update all three of them. S_ATIME updates can be handled * independently of the rest. * * Returns a set of S_* flags indicating which values changed. */ int inode_update_timestamps(struct inode *inode, int flags) { int updated = 0; struct timespec64 now; if (flags & (S_MTIME|S_CTIME|S_VERSION)) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; if (!timespec64_equal(&now, &mtime)) { inode_set_mtime_to_ts(inode, now); updated |= S_MTIME; } if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated)) updated |= S_VERSION; } else { now = current_time(inode); } if (flags & S_ATIME) { struct timespec64 atime = inode_get_atime(inode); if (!timespec64_equal(&now, &atime)) { inode_set_atime_to_ts(inode, now); updated |= S_ATIME; } } return updated; } EXPORT_SYMBOL(inode_update_timestamps); /** * generic_update_time - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. In the case where any of S_MTIME, S_CTIME, * or S_VERSION need to be updated we attempt to update all three of them. S_ATIME * updates can be handled done independently of the rest. * * Returns a S_* mask indicating which fields were updated. */ int generic_update_time(struct inode *inode, int flags) { int updated = inode_update_timestamps(inode, flags); int dirty_flags = 0; if (updated & (S_ATIME|S_MTIME|S_CTIME)) dirty_flags = inode->i_sb->s_flags & SB_LAZYTIME ? I_DIRTY_TIME : I_DIRTY_SYNC; if (updated & S_VERSION) dirty_flags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, dirty_flags); return updated; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ int inode_update_time(struct inode *inode, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, flags); generic_update_time(inode, flags); return 0; } EXPORT_SYMBOL(inode_update_time); /** * atime_needs_update - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; atime = inode_get_atime(inode); if (timespec64_equal(&atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(idmap, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct mnt_idmap *idmap, struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(idmap, dentry, &newattrs, NULL); } int file_remove_privs_flags(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0) return kill; if (kill) { if (flags & IOCB_NOWAIT) return -EAGAIN; error = __remove_privs(file_mnt_idmap(file), dentry, kill); } if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL_GPL(file_remove_privs_flags); /** * file_remove_privs - remove special file privileges (suid, capabilities) * @file: file to remove privileges from * * When file is modified by a write or truncation ensure that special * file privileges are removed. * * Return: 0 on success, negative errno on failure. */ int file_remove_privs(struct file *file) { return file_remove_privs_flags(file, 0); } EXPORT_SYMBOL(file_remove_privs); static int inode_needs_update_time(struct inode *inode) { int sync_it = 0; struct timespec64 now = current_time(inode); struct timespec64 ts; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) sync_it = S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; return sync_it; } static int __file_update_time(struct file *file, int sync_mode) { int ret = 0; struct inode *inode = file_inode(file); /* try to update time settings */ if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode); mnt_put_write_access_file(file); } return ret; } /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode for * writeback. Note that this function is meant exclusively for usage in * the file write path of filesystems, and filesystems may choose to * explicitly ignore updates via this function with the _NOCMTIME inode * flag, e.g. for network filesystem where these imestamps are handled * by the server. This can return an error for file systems who need to * allocate space in order to update an inode. * * Return: 0 on success, negative errno on failure. */ int file_update_time(struct file *file) { int ret; struct inode *inode = file_inode(file); ret = inode_needs_update_time(inode); if (ret <= 0) return ret; return __file_update_time(file, ret); } EXPORT_SYMBOL(file_update_time); /** * file_modified_flags - handle mandated vfs changes when modifying a file * @file: file that was modified * @flags: kiocb flags * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * If IOCB_NOWAIT is set, special file privileges will not be removed and * time settings will not be updated. It will return -EAGAIN. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ static int file_modified_flags(struct file *file, int flags) { int ret; struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ ret = file_remove_privs_flags(file, flags); if (ret) return ret; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; ret = inode_needs_update_time(inode); if (ret <= 0) return ret; if (flags & IOCB_NOWAIT) return -EAGAIN; return __file_update_time(file, ret); } /** * file_modified - handle mandated vfs changes when modifying a file * @file: file that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int file_modified(struct file *file) { return file_modified_flags(file, 0); } EXPORT_SYMBOL(file_modified); /** * kiocb_modified - handle mandated vfs changes when modifying a file * @iocb: iocb that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int kiocb_modified(struct kiocb *iocb) { return file_modified_flags(iocb->ki_filp, iocb->ki_flags); } EXPORT_SYMBOL_GPL(kiocb_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); /* * Handle racing against evict(), see that routine for more details. */ if (unlikely(inode_unhashed(inode))) { WARN_ON(is_inode_hash_locked); spin_unlock(&inode->i_lock); return; } wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); rcu_read_unlock(); if (is_inode_hash_locked) spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wq_entry); if (is_inode_hash_locked) spin_lock(&inode_hash_lock); rcu_read_lock(); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { if (IS_ENABLED(CONFIG_BLOCK)) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @idmap: idmap of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode * * If the inode has been created through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions * and initializing i_uid and i_gid. On non-idmapped mounts or if permission * checking is to be performed on the raw inode simply pass @nop_mnt_idmap. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode) { inode_fsuid_set(inode, idmap); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode_fsgid_set(inode, idmap); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @idmap: idmap of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) { vfsuid_t vfsuid; struct user_namespace *ns; vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return true; ns = current_user_ns(); if (vfsuid_has_mapping(ns, vfsuid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ static void __inode_dio_wait(struct inode *inode) { wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); finish_wait(wq, &q.wq_entry); } /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { if (atomic_read(&inode->i_dio_count)) __inode_dio_wait(inode); } EXPORT_SYMBOL(inode_dio_wait); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * current_time - Return FS time * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs. * * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode->i_ctime to the current value for the inode. Returns * the current value that was assigned to i_ctime. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now = current_time(inode); inode_set_ctime_to_ts(inode, now); return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @idmap: idmap of the mount @inode was found from * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * * Check wether @vfsgid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid) { if (vfsgid_in_group_p(vfsgid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) return true; return false; } EXPORT_SYMBOL(in_group_or_capable); /** * mode_strip_sgid - handle the sgid bit for non-directories * @idmap: idmap of the mount the inode was created from * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir))) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 99 99 99 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EM( WB_REASON_FORKER_THREAD, "forker_thread") \ EMe(WB_REASON_FOREIGN_FLUSH, "foreign_flush") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_folio_template, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DEFINE_EVENT(writeback_folio_template, folio_wait_writeback, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct folio *folio, struct bdi_writeback *wb), TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> */ #ifndef _LINUX_INTEGRITY_H #define _LINUX_INTEGRITY_H #include <linux/fs.h> #include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; #ifdef CONFIG_INTEGRITY extern void __init integrity_load_keys(void); #else static inline void integrity_load_keys(void) { } #endif /* CONFIG_INTEGRITY */ /* An inode's attributes for detection of changes */ struct integrity_inode_attributes { u64 version; /* track inode changes */ unsigned long ino; dev_t dev; }; /* * On stacked filesystems the i_version alone is not enough to detect file data * or metadata change. Additional metadata is required. */ static inline void integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, u64 i_version, const struct inode *inode) { attrs->version = i_version; attrs->dev = inode->i_sb->s_dev; attrs->ino = inode->i_ino; } /* * On stacked filesystems detect whether the inode or its content has changed. */ static inline bool integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, const struct inode *inode) { return (inode->i_sb->s_dev != attrs->dev || inode->i_ino != attrs->ino || !inode_eq_iversion(inode, attrs->version)); } #endif /* _LINUX_INTEGRITY_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security identifier table (sidtab) is a lookup table * of security context structures indexed by SID value. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #ifndef _SS_SIDTAB_H_ #define _SS_SIDTAB_H_ #include <linux/spinlock_types.h> #include <linux/log2.h> #include <linux/hashtable.h> #include "context.h" struct sidtab_entry { u32 sid; u32 hash; struct context context; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 struct sidtab_str_cache __rcu *cache; #endif struct hlist_node list; }; union sidtab_entry_inner { struct sidtab_node_inner *ptr_inner; struct sidtab_node_leaf *ptr_leaf; }; /* align node size to page boundary */ #define SIDTAB_NODE_ALLOC_SHIFT PAGE_SHIFT #define SIDTAB_NODE_ALLOC_SIZE PAGE_SIZE #define size_to_shift(size) ((size) == 1 ? 1 : (const_ilog2((size)-1) + 1)) #define SIDTAB_INNER_SHIFT \ (SIDTAB_NODE_ALLOC_SHIFT - \ size_to_shift(sizeof(union sidtab_entry_inner))) #define SIDTAB_INNER_ENTRIES ((size_t)1 << SIDTAB_INNER_SHIFT) #define SIDTAB_LEAF_ENTRIES \ (SIDTAB_NODE_ALLOC_SIZE / sizeof(struct sidtab_entry)) #define SIDTAB_MAX_BITS 32 #define SIDTAB_MAX U32_MAX /* ensure enough tree levels for SIDTAB_MAX entries */ #define SIDTAB_MAX_LEVEL \ DIV_ROUND_UP(SIDTAB_MAX_BITS - size_to_shift(SIDTAB_LEAF_ENTRIES), \ SIDTAB_INNER_SHIFT) struct sidtab_node_leaf { struct sidtab_entry entries[SIDTAB_LEAF_ENTRIES]; }; struct sidtab_node_inner { union sidtab_entry_inner entries[SIDTAB_INNER_ENTRIES]; }; struct sidtab_isid_entry { int set; struct sidtab_entry entry; }; struct sidtab_convert_params { struct convert_context_args *args; struct sidtab *target; }; #define SIDTAB_HASH_BITS CONFIG_SECURITY_SELINUX_SIDTAB_HASH_BITS #define SIDTAB_HASH_BUCKETS (1 << SIDTAB_HASH_BITS) struct sidtab { /* * lock-free read access only for as many items as a prior read of * 'count' */ union sidtab_entry_inner roots[SIDTAB_MAX_LEVEL + 1]; /* * access atomically via {READ|WRITE}_ONCE(); only increment under * spinlock */ u32 count; /* access only under spinlock */ struct sidtab_convert_params *convert; bool frozen; spinlock_t lock; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 /* SID -> context string cache */ u32 cache_free_slots; struct list_head cache_lru_list; spinlock_t cache_lock; #endif /* index == SID - 1 (no entry for SECSID_NULL) */ struct sidtab_isid_entry isids[SECINITSID_NUM]; /* Hash table for fast reverse context-to-sid lookups. */ DECLARE_HASHTABLE(context_to_sid, SIDTAB_HASH_BITS); }; int sidtab_init(struct sidtab *s); int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context); struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid); struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid); static inline struct context *sidtab_search(struct sidtab *s, u32 sid) { struct sidtab_entry *entry = sidtab_search_entry(s, sid); return entry ? &entry->context : NULL; } static inline struct context *sidtab_search_force(struct sidtab *s, u32 sid) { struct sidtab_entry *entry = sidtab_search_entry_force(s, sid); return entry ? &entry->context : NULL; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params); void sidtab_cancel_convert(struct sidtab *s); void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock); void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock); int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid); void sidtab_destroy(struct sidtab *s); int sidtab_hash_stats(struct sidtab *sidtab, char *page); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len); int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len); #else static inline void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { } static inline int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { return -ENOENT; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ #endif /* _SS_SIDTAB_H_ */ |
| 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FUTEX_H #define _FUTEX_H #include <linux/futex.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #include <linux/compat.h> #ifdef CONFIG_PREEMPT_RT #include <linux/rcuwait.h> #endif #include <asm/futex.h> /* * Futex flags used to encode options to functions and preserve them across * restarts. */ #define FLAGS_SIZE_8 0x0000 #define FLAGS_SIZE_16 0x0001 #define FLAGS_SIZE_32 0x0002 #define FLAGS_SIZE_64 0x0003 #define FLAGS_SIZE_MASK 0x0003 #ifdef CONFIG_MMU # define FLAGS_SHARED 0x0010 #else /* * NOMMU does not have per process address space. Let the compiler optimize * code away. */ # define FLAGS_SHARED 0x0000 #endif #define FLAGS_CLOCKRT 0x0020 #define FLAGS_HAS_TIMEOUT 0x0040 #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) { unsigned int flags = FLAGS_SIZE_32; if (!(op & FUTEX_PRIVATE_FLAG)) flags |= FLAGS_SHARED; if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; return flags; } #define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) { unsigned int flags = flags2 & FUTEX2_SIZE_MASK; if (!(flags2 & FUTEX2_PRIVATE)) flags |= FLAGS_SHARED; if (flags2 & FUTEX2_NUMA) flags |= FLAGS_NUMA; return flags; } static inline unsigned int futex_size(unsigned int flags) { return 1 << (flags & FLAGS_SIZE_MASK); } static inline bool futex_flags_valid(unsigned int flags) { /* Only 64bit futexes for 64bit code */ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64) return false; } /* Only 32bit futexes are implemented -- for now */ if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) return false; return true; } static inline bool futex_validate_input(unsigned int flags, u64 val) { int bits = 8 * futex_size(flags); if (bits < 64 && (val >> bits)) return false; return true; } #ifdef CONFIG_FAIL_FUTEX extern bool should_fail_futex(bool fshared); #else static inline bool should_fail_futex(bool fshared) { return false; } #endif /* * Hash buckets are shared by all the futex_keys that hash to the same * location. Each key may have multiple futex_q structures, one for each task * waiting on a futex. */ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; } ____cacheline_aligned_in_smp; /* * Priority Inheritance state: */ struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex_base pi_mutex; struct task_struct *owner; refcount_t refcount; union futex_key key; } __randomize_layout; struct futex_q; typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); /** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock * @wake: the wake handler for this queue * @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakeup is always to make the first condition true, then * the second. * * PI futexes are typically woken before they are removed from the hash list via * the rt_mutex code. See futex_unqueue_pi(). */ struct futex_q { struct plist_node list; struct task_struct *task; spinlock_t *lock_ptr; futex_wake_fn *wake; void *wake_data; union futex_key key; struct futex_pi_state *pi_state; struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif } __randomize_layout; extern const struct futex_q futex_q_init; enum futex_access { FUTEX_READ, FUTEX_WRITE }; extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw); extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); /** * futex_match - Check whether two futex keys are equal * @key1: Pointer to key1 * @key2: Pointer to key2 * * Return 1 if two futex_keys are equal, 0 otherwise. */ static inline int futex_match(union futex_key *key1, union futex_key *key2) { return (key1 && key2 && key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb); extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout); extern bool __futex_wake_mark(struct futex_q *q); extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q); extern int fault_in_user_writeable(u32 __user *uaddr); extern int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval); extern int futex_get_value_locked(u32 *dest, u32 __user *from); extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); extern void __futex_unqueue(struct futex_q *q); extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The * exceptions involve the PI related operations, which may use futex_unqueue_pi() * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). */ static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) __releases(&hb->lock) { __futex_queue(q, hb); spin_unlock(&hb->lock); } extern void futex_unqueue_pi(struct futex_q *q); extern void wait_for_owner_exiting(int ret, struct task_struct *exiting); /* * Reflects a new waiter being added to the waitqueue. */ static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_inc(&hb->waiters); /* * Full barrier (A), see the ordering comment above. */ smp_mb__after_atomic(); #endif } /* * Reflects a waiter being removed from the waitqueue by wakeup * paths. */ static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_dec(&hb->waiters); #endif } static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP /* * Full barrier (B), see the ordering comment above. */ smp_mb(); return atomic_read(&hb->waiters); #else return 1; #endif } extern struct futex_hash_bucket *futex_q_lock(struct futex_q *q); extern void futex_q_unlock(struct futex_hash_bucket *hb); extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps, struct task_struct *task, struct task_struct **exiting, int set_waiters); extern int refill_pi_state_cache(void); extern void get_pi_state(struct futex_pi_state *pi_state); extern void put_pi_state(struct futex_pi_state *pi_state); extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked); /* * Express the locking dependencies for lockdep: */ static inline void double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { if (hb1 > hb2) swap(hb1, hb2); spin_lock(&hb1->lock); if (hb1 != hb2) spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); } static inline void double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { spin_unlock(&hb1->lock); if (hb1 != hb2) spin_unlock(&hb2->lock); } /* syscalls */ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2); extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1, u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi); extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset); extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); /** * struct futex_vector - Auxiliary struct for futex_waitv() * @w: Userspace provided data * @q: Kernel side data * * Struct used to build an array with all data need for futex_waitv() */ struct futex_vector { struct futex_waitv w; struct futex_q q; }; extern int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data); extern int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken); extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); #endif /* _FUTEX_H */ |
| 12 14 57 119 60 1 3 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/userfaultfd_k.h * * Copyright (C) 2015 Red Hat, Inc. * */ #ifndef _LINUX_USERFAULTFD_K_H #define _LINUX_USERFAULTFD_K_H #ifdef CONFIG_USERFAULTFD #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */ #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <asm-generic/pgtable_uffd.h> #include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from userfaultfd, in order to leave a free define-space for * shared O_* flags. */ #define UFFD_CLOEXEC O_CLOEXEC #define UFFD_NONBLOCK O_NONBLOCK #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* * Prevents userfaultfd operations (fill/move/wp) from happening while * some non-cooperative event(s) is taking place. Increments are done * in write-mode. Whereas, userfaultfd operations, which includes * reading mmap_changing, is done under read-mode. */ struct rw_semaphore map_changing_lock; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* A combined operation mode + behavior flags. */ typedef unsigned int __bitwise uffd_flags_t; /* Mutually exclusive modes of operation. */ enum mfill_atomic_mode { MFILL_ATOMIC_COPY, MFILL_ATOMIC_ZEROPAGE, MFILL_ATOMIC_CONTINUE, MFILL_ATOMIC_POISON, NR_MFILL_ATOMIC_MODES, }; #define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) #define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) #define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) #define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) { return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); } static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) { flags &= ~MFILL_ATOMIC_MODE_MASK; return flags | ((__force uffd_flags_t) mode); } /* Flags controlling behavior. These behavior changes are mode-independent. */ #define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, uffd_flags_t flags); extern ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, uffd_flags_t flags); extern ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len); extern ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len, uffd_flags_t flags); extern ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, uffd_flags_t flags); extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, bool enable_wp); extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 flags); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } /* * Never enable huge pmd sharing on some uffd registered vmas: * * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. * * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for * VMAs which share huge pmds. (If you have two mappings to the same * underlying pages, and fault in the non-UFFD-registered one with a write, * with huge pmd sharing this would *also* setup the second UFFD-registered * mapping, and we'd not get minor faults.) */ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } /* * Don't do fault around for either WP or MINOR registered uffd range. For * MINOR registered range, fault around will be a total disaster and ptes can * be installed without notifications; for WP it should mostly be fine as long * as the fault around checks for pte_none() before the installation, however * to be super safe we just forbid it. */ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_WP; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MINOR; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return userfaultfd_wp(vma) && pte_uffd_wp(pte); } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return userfaultfd_wp(vma) && pmd_uffd_wp(pmd); } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return vma->vm_flags & __VM_UFFD_FLAGS; } static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags, bool wp_async) { vm_flags &= __VM_UFFD_FLAGS; if (vm_flags & VM_DROPPABLE) return false; if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; /* * If wp async enabled, and WP is the only mode enabled, allow any * memory type. */ if (wp_async && (vm_flags == VM_UFFD_WP)) return true; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for * uffd-wp, then shmem & hugetlbfs are not supported but only * anonymous. */ if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) return false; #endif /* By default, allow any of anon|shmem|hugetlb */ return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); extern bool userfaultfd_wp_async(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ /* mm helpers */ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { return VM_FAULT_SIGBUS; } static inline long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp) { return false; } static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return true; } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return false; } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return false; } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return false; } static inline int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *l) { return 0; } static inline void dup_userfaultfd_complete(struct list_head *l) { } static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { } static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, unsigned long from, unsigned long to, unsigned long len) { } static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf) { return 0; } static inline void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { } static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) { return false; } #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) { /* Only wr-protect mode uses pte markers */ if (!userfaultfd_wp(vma)) return false; /* File-based uffd-wp always need markers */ if (!vma_is_anonymous(vma)) return true; /* * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED * enabled (to apply markers on zero pages). */ return userfaultfd_wp_unpopulated(vma); } static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); #else return false; #endif } static inline bool pte_marker_uffd_wp(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP swp_entry_t entry; if (!is_swap_pte(pte)) return false; entry = pte_to_swp_entry(pte); return pte_marker_entry_uffd_wp(entry); #else return false; #endif } /* * Returns true if this is a swap pte and was uffd-wp wr-protected in either * forms (pte marker or a normal swap pte), false otherwise. */ static inline bool pte_swp_uffd_wp_any(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP if (!is_swap_pte(pte)) return false; if (pte_swp_uffd_wp(pte)) return true; if (pte_marker_uffd_wp(pte)) return true; #endif return false; } #endif /* _LINUX_USERFAULTFD_K_H */ |
| 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_NETLINK_H #define __NET_NETLINK_H #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) * ------------------------------------------------------------------------ * Messages Interface * ------------------------------------------------------------------------ * * Message Format: * <--- nlmsg_total_size(payload) ---> * <-- nlmsg_msg_size(payload) -> * +----------+- - -+-------------+- - -+-------- - - * | nlmsghdr | Pad | Payload | Pad | nlmsghdr * +----------+- - -+-------------+- - -+-------- - - * nlmsg_data(nlh)---^ ^ * nlmsg_next(nlh)-----------------------+ * * Payload Format: * <---------------------- nlmsg_len(nlh) ---------------------> * <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) -> * +----------------------+- - -+--------------------------------+ * | Family Header | Pad | Attributes | * +----------------------+- - -+--------------------------------+ * nlmsg_attrdata(nlh, hdrlen)---^ * * Data Structures: * struct nlmsghdr netlink message header * * Message Construction: * nlmsg_new() create a new netlink message * nlmsg_put() add a netlink message to an skb * nlmsg_put_answer() callback based nlmsg_put() * nlmsg_end() finalize netlink message * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction * nlmsg_consume() free a netlink message (expected) * nlmsg_free() free a netlink message (drop) * * Message Sending: * nlmsg_multicast() multicast message to several groups * nlmsg_unicast() unicast a message to a single socket * nlmsg_notify() send notification message * * Message Length Calculations: * nlmsg_msg_size(payload) length of message w/o padding * nlmsg_total_size(payload) length of message w/ padding * nlmsg_padlen(payload) length of padding at tail * * Message Payload Access: * nlmsg_data(nlh) head of message payload * nlmsg_len(nlh) length of message payload * nlmsg_attrdata(nlh, hdrlen) head of attributes data * nlmsg_attrlen(nlh, hdrlen) length of attributes data * * Message Parsing: * nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes? * nlmsg_next(nlh, remaining) get next netlink message * nlmsg_parse() parse attributes of a message * nlmsg_find_attr() find an attribute in a message * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * * Misc: * nlmsg_report() report back to application? * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ * * Attribute Format: * <------- nla_total_size(payload) -------> * <---- nla_attr_size(payload) -----> * +----------+- - -+- - - - - - - - - +- - -+-------- - - * | Header | Pad | Payload | Pad | Header * +----------+- - -+- - - - - - - - - +- - -+-------- - - * <- nla_len(nla) -> ^ * nla_data(nla)----^ | * nla_next(nla)-----------------------------' * * Data Structures: * struct nlattr netlink attribute header * * Attribute Construction: * nla_reserve(skb, type, len) reserve room for an attribute * nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr * nla_put(skb, type, len, data) add attribute to skb * nla_put_nohdr(skb, len, data) add attribute w/o hdr * nla_append(skb, len, data) append data to skb * * Attribute Construction for Basic Types: * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb * nla_put_u64_64bit(skb, type, * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb * nla_put_s64(skb, type, value, * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies, * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding * nla_total_size(payload) length of attribute w/ padding * nla_padlen(payload) length of padding * * Attribute Payload Access: * nla_data(nla) head of attribute payload * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: * nla_get_uint(nla) get payload for a uint attribute * nla_get_sint(nla) get payload for a sint attribute * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute * nla_get_u64(nla) get payload for a u64 attribute * nla_get_s8(nla) get payload for a s8 attribute * nla_get_s16(nla) get payload for a s16 attribute * nla_get_s32(nla) get payload for a s32 attribute * nla_get_s64(nla) get payload for a s64 attribute * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area * nla_strscpy(dst, nla, size) copy attribute to a sized string * nla_strcmp(nla, str) compare attribute with string * * Attribute Parsing: * nla_ok(nla, remaining) does nla fit into remaining bytes? * nla_next(nla, remaining) get next netlink attribute * nla_validate() validate a stream of attributes * nla_validate_nested() validate a stream of nested attributes * nla_find() find attribute in stream of attributes * nla_find_nested() find attribute in nested attributes * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes * nla_for_each_attr_type() loop over all attributes with the * given type * nla_for_each_nested() loop over the nested attributes * nla_for_each_nested_type() loop over the nested attributes with * the given type *========================================================================= */ /** * Standard attribute types to specify validation policy */ enum { NLA_UNSPEC, NLA_U8, NLA_U16, NLA_U32, NLA_U64, NLA_STRING, NLA_FLAG, NLA_MSECS, NLA_NESTED, NLA_NESTED_ARRAY, NLA_NUL_STRING, NLA_BINARY, NLA_S8, NLA_S16, NLA_S32, NLA_S64, NLA_BITFIELD32, NLA_REJECT, NLA_BE16, NLA_BE32, NLA_SINT, NLA_UINT, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) struct netlink_range_validation { u64 min, max; }; struct netlink_range_validation_signed { s64 min, max; }; enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_MASK, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, }; /** * struct nla_policy - attribute validation policy * @type: Type of attribute or NLA_UNSPEC * @validation_type: type of attribute validation done in addition to * type-specific validation (e.g. range, function call), see * &enum nla_policy_validation * @len: Type specific length of payload * * Policies are defined as arrays of this struct, the array must be * accessible by attribute type up to the highest identifier to be expected. * * Meaning of `len' field: * NLA_STRING Maximum length of string * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if * nested_policy is also used, for the max attr * number in the nested policy. * NLA_SINT, NLA_UINT, * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, * NLA_BE16, NLA_BE32, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused * All other Minimum length of attribute payload * * Meaning of validation union: * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and * `bitfield32_valid' is the u32 value of valid flags * NLA_REJECT This attribute is always rejected and `reject_message' * may point to a string to report as the error instead * of the generic one in extended ACK. * NLA_NESTED `nested_policy' to a nested policy to validate, must * also set `len' to the max attribute number. Use the * provided NLA_POLICY_NESTED() macro. * Note that nla_parse() will validate, but of course not * parse, the nested sub-policies. * NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate, * must also set `len' to the max attribute number. Use * the provided NLA_POLICY_NESTED_ARRAY() macro. * The difference to NLA_NESTED is the structure: * NLA_NESTED has the nested attributes directly inside * while an array has the nested attributes at another * level down and the attribute types directly in the * nesting don't matter. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_BE16, * NLA_BE32, * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 The `min' and `max' fields are used depending on the * validation_type field, if that is min/max/range then * the min, max or both are used (respectively) to check * the value of the integer attribute. * Note that in the interest of code simplicity and * struct size both limits are s16, so you cannot * enforce a range that doesn't fall within the range * of s16 - do that using the NLA_POLICY_FULL_RANGE() * or NLA_POLICY_FULL_RANGE_SIGNED() macros instead. * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and * NLA_POLICY_RANGE() macros. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range' must be a pointer * to a struct netlink_range_validation that indicates * the min/max values. * Use NLA_POLICY_FULL_RANGE(). * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range_signed' must be a * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). * * NLA_BINARY If the validation type is like the ones for integers * above, then the min/max length (not value like for * integers) of the attribute is enforced. * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: * NLA_BINARY Validation function called for the attribute. * All other Unused - but note that it's a union * * Example: * * static const u32 myvalidflags = 0xff231023; * * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ struct nla_policy { u8 type; u8 validation_type; u16 len; union { /** * @strict_start_type: first attribute to validate strictly * * This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to * get the previous pure { .len = xyz } behaviour. The advantage * of this is that types not specified in the policy will be * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones * it should be set at least when new attributes are added to * the enum used by the policy, and be set to the new value that * was added to enforce strict validation from thereon. */ u16 strict_start_type; /* private: use NLA_POLICY_*() to set */ const u32 bitfield32_valid; const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; const struct netlink_range_validation *range; const struct netlink_range_validation_signed *range_signed; struct { s16 min, max; }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); }; }; #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) #define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .nested_policy = policy, .len = maxattr } #define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr } #define NLA_POLICY_NESTED(policy) \ _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_NESTED_ARRAY(policy) \ _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_IS_UINT_TYPE(tp) \ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ tp == NLA_U64 || tp == NLA_UINT || \ tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \ tp == NLA_SINT) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp) #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp) #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } #define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \ .type = NLA_ENSURE_SINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range_signed = _range, \ } #define NLA_POLICY_MIN(tp, _min) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } #define NLA_POLICY_MASK(tp, _mask) { \ .type = NLA_ENSURE_UINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MASK, \ .mask = _mask, \ } #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ .validate = fn, \ .len = __VA_ARGS__ + 0, \ } #define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) #define NLA_POLICY_EXACT_LEN_WARN(_len) { \ .type = NLA_BINARY, \ .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ .min = _len, \ .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application * @skip_notify: Skip netlink notifications to user space * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; u8 skip_notify:1, skip_notify_kernel:1; }; /** * enum netlink_validation - netlink message/attribute validation levels * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about * extra data at the end of the message, attributes being longer than * they should be, or unknown attributes being present. * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing. * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING * this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict(). * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy. * This can safely be set by the kernel when the given policy has no * NLA_UNSPEC anymore, and can thus be used to ensure policy entries * are enforced going forward. * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g. * U8, U16, U32 must have exact size, etc.) * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY) * and unset for other policies. */ enum netlink_validation { NL_VALIDATE_LIBERAL = 0, NL_VALIDATE_TRAILING = BIT(0), NL_VALIDATE_MAXTYPE = BIT(1), NL_VALIDATE_UNSPEC = BIT(2), NL_VALIDATE_STRICT_ATTRS = BIT(3), NL_VALIDATE_NESTED = BIT(4), }; #define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE) #define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE |\ NL_VALIDATE_UNSPEC |\ NL_VALIDATE_STRICT_ATTRS |\ NL_VALIDATE_NESTED) int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)); int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags); int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize); char *nla_strdup(const struct nlattr *nla, gfp_t flags); int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); int nla_strcmp(const struct nlattr *nla, const char *str); struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen); struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen); void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_append(struct sk_buff *skb, int attrlen, const void *data); /************************************************************************** * Netlink Messages **************************************************************************/ /** * nlmsg_msg_size - length of netlink message not including padding * @payload: length of message payload */ static inline int nlmsg_msg_size(int payload) { return NLMSG_HDRLEN + payload; } /** * nlmsg_total_size - length of netlink message including padding * @payload: length of message payload */ static inline int nlmsg_total_size(int payload) { return NLMSG_ALIGN(nlmsg_msg_size(payload)); } /** * nlmsg_padlen - length of padding at the message's tail * @payload: length of message payload */ static inline int nlmsg_padlen(int payload) { return nlmsg_total_size(payload) - nlmsg_msg_size(payload); } /** * nlmsg_data - head of message payload * @nlh: netlink message header */ static inline void *nlmsg_data(const struct nlmsghdr *nlh) { return (unsigned char *) nlh + NLMSG_HDRLEN; } /** * nlmsg_len - length of message payload * @nlh: netlink message header */ static inline int nlmsg_len(const struct nlmsghdr *nlh) { return nlh->nlmsg_len - NLMSG_HDRLEN; } /** * nlmsg_attrdata - head of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline struct nlattr *nlmsg_attrdata(const struct nlmsghdr *nlh, int hdrlen) { unsigned char *data = nlmsg_data(nlh); return (struct nlattr *) (data + NLMSG_ALIGN(hdrlen)); } /** * nlmsg_attrlen - length of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline int nlmsg_attrlen(const struct nlmsghdr *nlh, int hdrlen) { return nlmsg_len(nlh) - NLMSG_ALIGN(hdrlen); } /** * nlmsg_ok - check if the netlink message fits into the remaining bytes * @nlh: netlink message header * @remaining: number of bytes remaining in message stream */ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) { return (remaining >= (int) sizeof(struct nlmsghdr) && nlh->nlmsg_len >= sizeof(struct nlmsghdr) && nlh->nlmsg_len <= remaining); } /** * nlmsg_next - next netlink message in message stream * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * * Returns the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * nlmsg_next(const struct nlmsghdr *nlh, int *remaining) { int totlen = NLMSG_ALIGN(nlh->nlmsg_len); *remaining -= totlen; return (struct nlmsghdr *) ((unsigned char *) nlh + totlen); } /** * nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * * Returns 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_deprecated - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * __nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; } return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), policy, validate, extack); } /** * nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_parse_deprecated - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_parse_deprecated_strict - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated_strict() */ static inline int nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header * @hdrlen: length of familiy specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) { return nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), attrtype); } /** * nla_validate_deprecated - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header * @hdrlen: length of familiy specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, int hdrlen, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; return __nla_validate(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_report - need to report back to application? * @nlh: netlink message header * * Returns 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } /** * nlmsg_seq - return the seq number of netlink message * @nlh: netlink message header * * Returns 0 if netlink message is NULL */ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) { return nlh ? nlh->nlmsg_seq : 0; } /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header * @hdrlen: length of familiy specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ nla_for_each_attr(pos, nlmsg_attrdata(nlh, hdrlen), \ nlmsg_attrlen(nlh, hdrlen), rem) /** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in * @portid: netlink PORTID of requesting application * @seq: sequence number of message * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int payload, int flags) { if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload))) return NULL; return __nlmsg_put(skb, portid, seq, type, payload, flags); } /** * nlmsg_append - Add more data to a nlmsg in a skb * @skb: socket buffer to store message in * @size: length of message payload * * Append data to an existing nlmsg, used when constructing a message * with multiple fixed-format headers (which is rare). * Returns NULL if the tailroom of the skb is insufficient to store * the extra payload. */ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) { if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) return NULL; if (NLMSG_ALIGN(size) - size) memset(skb_tail_pointer(skb) + size, 0, NLMSG_ALIGN(size) - size); return __skb_put(skb, NLMSG_ALIGN(size)); } /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in * @cb: netlink callback * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, struct netlink_callback *cb, int type, int payload, int flags) { return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, type, payload, flags); } /** * nlmsg_new - Allocate a new netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. * * Use NLMSG_DEFAULT_SIZE if the size of the payload isn't known * and a good default is needed. */ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) { return alloc_skb(nlmsg_total_size(payload), flags); } /** * nlmsg_new_large - Allocate a new netlink message with non-contiguous * physical memory * @payload: size of the message payload * * The allocated skb is unable to have frag page for shinfo->frags*, * as the NULL setting for skb->head in netlink_skb_destructor() will * bypass most of the handling in skb_release_data() */ static inline struct sk_buff *nlmsg_new_large(size_t payload) { return netlink_alloc_large_skb(nlmsg_total_size(payload), 0); } /** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Corrects the netlink message header to include the appeneded * attributes. Only necessary if attributes have been added to * the message. */ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; } /** * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * * Returns a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { return skb_tail_pointer(skb); } /** * nlmsg_trim - Trim message to a mark * @skb: socket buffer the message is stored in * @mark: mark to trim to * * Trims the message to the provided mark. */ static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) { WARN_ON((unsigned char *) mark < skb->data); skb_trim(skb, (unsigned char *) mark - skb->data); } } /** * nlmsg_cancel - Cancel construction of a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Removes the complete netlink message including all * attributes from the socket buffer again. */ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { nlmsg_trim(skb, nlh); } /** * nlmsg_free - drop a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) { kfree_skb(skb); } /** * nlmsg_consume - free a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_consume(struct sk_buff *skb) { consume_skb(skb); } /** * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags * @filter: filter function * @filter_data: filter function private data * * Return: 0 on success, negative error code for failure. */ static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags, netlink_filter_fn filter, void *filter_data) { int err; NETLINK_CB(skb).dst_group = group; err = netlink_broadcast_filtered(sk, skb, portid, group, flags, filter, filter_data); if (err > 0) err = 0; return err; } /** * nlmsg_multicast - multicast a netlink message * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return nlmsg_multicast_filtered(sk, skb, portid, group, flags, NULL, NULL); } /** * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid) { int err; err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT); if (err > 0) err = 0; return err; } /** * nlmsg_for_each_msg - iterate over a stream of messages * @pos: loop counter, set to current message * @head: head of message stream * @len: length of message stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_msg(pos, head, len, rem) \ for (pos = head, rem = len; \ nlmsg_ok(pos, rem); \ pos = nlmsg_next(pos, &(rem))) /** * nl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @nlh: netlink message header to write the flag to * * This function checks if the sequence (generation) number changed during dump * and if it did, advertises it in the netlink message header. * * The correct way to use it is to set cb->seq to the generation counter when * all locks for dumping have been acquired, and then call this function for * each message that is generated. * * Note that due to initialisation concerns, 0 is an invalid sequence number * and must not be used by code that uses this functionality. */ static inline void nl_dump_check_consistent(struct netlink_callback *cb, struct nlmsghdr *nlh) { if (cb->prev_seq && cb->seq != cb->prev_seq) nlh->nlmsg_flags |= NLM_F_DUMP_INTR; cb->prev_seq = cb->seq; } /************************************************************************** * Netlink Attributes **************************************************************************/ /** * nla_attr_size - length of attribute not including padding * @payload: length of payload */ static inline int nla_attr_size(int payload) { return NLA_HDRLEN + payload; } /** * nla_total_size - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size(int payload) { return NLA_ALIGN(nla_attr_size(payload)); } /** * nla_padlen - length of padding at the tail of attribute * @payload: length of payload */ static inline int nla_padlen(int payload) { return nla_total_size(payload) - nla_attr_size(payload); } /** * nla_type - attribute type * @nla: netlink attribute */ static inline int nla_type(const struct nlattr *nla) { return nla->nla_type & NLA_TYPE_MASK; } /** * nla_data - head of payload * @nla: netlink attribute */ static inline void *nla_data(const struct nlattr *nla) { return (char *) nla + NLA_HDRLEN; } /** * nla_len - length of payload * @nla: netlink attribute */ static inline u16 nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } /** * nla_ok - check if the netlink attribute fits into the remaining bytes * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream */ static inline int nla_ok(const struct nlattr *nla, int remaining) { return remaining >= (int) sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } /** * nla_next - next netlink attribute in attribute stream * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * * Returns the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { unsigned int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; return (struct nlattr *) ((char *) nla + totlen); } /** * nla_find_nested - find attribute in a set of nested attributes * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) { return nla_find(nla_data(nla), nla_len(nla), attrtype); } /** * nla_parse_nested - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (!(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing"); return -EINVAL; } return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_nested_deprecated - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_put_u8 - Add a u8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { /* temporary variables to work around GCC PR81715 with asan-stack=1 */ u8 tmp = value; return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** * nla_put_u16 - Add a u16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { u16 tmp = value; return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** * nla_put_be16 - Add a __be16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** * nla_put_net16 - Add 16-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le16 - Add a __le16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { __le16 tmp = value; return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** * nla_put_u32 - Add a u32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { u32 tmp = value; return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** * nla_put_uint - Add a variable-size unsigned int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value) { u64 tmp64 = value; u32 tmp32 = value; if (tmp64 == tmp32) return nla_put_u32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(u64), &tmp64); } /** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** * nla_put_net32 - Add 32-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le32 - Add a __le32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { __le32 tmp = value; return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** * nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { u64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** * nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } /** * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { __le64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** * nla_put_s8 - Add a s8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { s8 tmp = value; return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** * nla_put_s16 - Add a s16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { s16 tmp = value; return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** * nla_put_s32 - Add a s32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { s32 tmp = value; return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** * nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { s64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** * nla_put_sint - Add a variable-size signed int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value) { s64 tmp64 = value; s32 tmp32 = value; if (tmp64 == tmp32) return nla_put_s32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(s64), &tmp64); } /** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @str: NUL terminated string */ static inline int nla_put_string(struct sk_buff *skb, int attrtype, const char *str) { return nla_put(skb, attrtype, strlen(str) + 1, str); } /** * nla_put_flag - Add a flag netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type */ static inline int nla_put_flag(struct sk_buff *skb, int attrtype) { return nla_put(skb, attrtype, 0, NULL); } /** * nla_put_msecs - Add a msecs netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @njiffies: number of jiffies to convert to msecs * @padattr: attribute type for the padding */ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, unsigned long njiffies, int padattr) { u64 tmp = jiffies_to_msecs(njiffies); return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv4 address */ static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { __be32 tmp = addr; return nla_put_be32(skb, attrtype, tmp); } /** * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv6 address */ static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, const struct in6_addr *addr) { return nla_put(skb, attrtype, sizeof(*addr), addr); } /** * nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: value carrying bits * @selector: selector of valid bits */ static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype, __u32 value, __u32 selector) { struct nla_bitfield32 tmp = { value, selector, }; return nla_put(skb, attrtype, sizeof(tmp), &tmp); } /** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute */ static inline u32 nla_get_u32(const struct nlattr *nla) { return *(u32 *) nla_data(nla); } /** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ static inline __be32 nla_get_be32(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ static inline __le32 nla_get_le32(const struct nlattr *nla) { return *(__le32 *) nla_data(nla); } /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ static inline u16 nla_get_u16(const struct nlattr *nla) { return *(u16 *) nla_data(nla); } /** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ static inline __be16 nla_get_be16(const struct nlattr *nla) { return *(__be16 *) nla_data(nla); } /** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ static inline __le16 nla_get_le16(const struct nlattr *nla) { return *(__le16 *) nla_data(nla); } /** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ static inline u8 nla_get_u8(const struct nlattr *nla) { return *(u8 *) nla_data(nla); } /** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ static inline u64 nla_get_u64(const struct nlattr *nla) { u64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ static inline u64 nla_get_uint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(u32)) return nla_get_u32(nla); return nla_get_u64(nla); } /** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ static inline __be64 nla_get_be64(const struct nlattr *nla) { __be64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ static inline __le64 nla_get_le64(const struct nlattr *nla) { return *(__le64 *) nla_data(nla); } /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ static inline s32 nla_get_s32(const struct nlattr *nla) { return *(s32 *) nla_data(nla); } /** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ static inline s16 nla_get_s16(const struct nlattr *nla) { return *(s16 *) nla_data(nla); } /** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ static inline s8 nla_get_s8(const struct nlattr *nla) { return *(s8 *) nla_data(nla); } /** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ static inline s64 nla_get_s64(const struct nlattr *nla) { s64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ static inline s64 nla_get_sint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(s32)) return nla_get_s32(nla); return nla_get_s64(nla); } /** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ static inline int nla_get_flag(const struct nlattr *nla) { return !!nla; } /** * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * * Returns the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { u64 msecs = nla_get_u64(nla); return msecs_to_jiffies((unsigned long) msecs); } /** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ static inline __be32 nla_get_in_addr(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) { struct in6_addr tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_bitfield32 - return payload of 32 bitfield attribute * @nla: nla_bitfield32 attribute */ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) { struct nla_bitfield32 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) { return kmemdup_noprof(nla_data(src), nla_len(src), gfp); } #define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__)) /** * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * This function exists for backward compatibility to use in APIs which never * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); if (nla_put(skb, attrtype, 0, NULL) < 0) return NULL; return start; } /** * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); } /** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in * @start: container attribute * * Corrects the container attribute header to include the all * appeneded attributes. * * Returns the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start; return skb->len; } /** * nla_nest_cancel - Cancel nesting of attributes * @skb: socket buffer the message is stored in * @start: container attribute * * Removes the container attribute and including all nested * attributes. Returns -EMSGSIZE */ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { nlmsg_trim(skb, start); } /** * __nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be * ignored. See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate(nla_data(start), nla_len(start), maxtype, policy, validate, extack); } static inline int nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_STRICT, extack); } static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * * Return true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) { #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* The nlattr header is 4 bytes in size, that's why we test * if the skb->data _is_ aligned. A NOP attribute, plus * nlattr header for next attribute, will make nla_data() * 8-byte aligned. */ if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) return true; #endif return false; } /** * nla_align_64bit - 64-bit align the nla_data() of next attribute * @skb: socket buffer the message is stored in * @padattr: attribute type for the padding * * Conditionally emit a padding netlink attribute in order to make * the next attribute we emit have a 64-bit aligned nla_data() area. * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * * Returns zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { if (nla_need_padding_for_64bit(skb) && !nla_reserve(skb, padattr, 0)) return -EMSGSIZE; return 0; } /** * nla_total_size_64bit - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size_64bit(int payload) { return NLA_ALIGN(nla_attr_size(payload)) #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + NLA_ALIGN(nla_attr_size(0)) #endif ; } /** * nla_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr(pos, head, len, rem) \ for (pos = head, rem = len; \ nla_ok(pos, rem); \ pos = nla_next(pos, &(rem))) /** * nla_for_each_attr_type - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr_type(pos, type, head, len, rem) \ nla_for_each_attr(pos, head, len, rem) \ if (nla_type(pos) == type) /** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested(pos, nla, rem) \ nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** * nla_for_each_nested_type - iterate over nested attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested_type(pos, type, nla, rem) \ nla_for_each_nested(pos, nla, rem) \ if (nla_type(pos) == type) /** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream */ static inline bool nla_is_last(const struct nlattr *nla, int rem) { return nla->nla_len == rem; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range); void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); struct netlink_policy_dump_state; int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, const struct nla_policy *policy, unsigned int maxtype); int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, const struct nla_policy *policy, unsigned int maxtype); bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); int netlink_policy_dump_write(struct sk_buff *skb, struct netlink_policy_dump_state *state); int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt); int netlink_policy_dump_write_attr(struct sk_buff *skb, const struct nla_policy *pt, int nestattr); void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif |
| 155 155 264 145 155 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif |
| 11 11 11 11 11 11 11 11 12 12 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { XA_STATE(xas, &mapping->i_pages, index); xas_set_update(&xas, workingset_update_node); if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); } static void clear_shadow_entries(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { int i; /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (xa_is_value(folio)) __clear_shadow_entry(mapping, indices[i], folio); } xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { int i, j; bool dax; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < folio_batch_count(fbatch); j++) if (xa_is_value(fbatch->folios[j])) break; if (j == folio_batch_count(fbatch)) return; dax = dax_mapping(mapping); if (!dax) { spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); } for (i = j; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; pgoff_t index = indices[i]; if (!xa_is_value(folio)) { fbatch->folios[j++] = folio; continue; } if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; } __clear_shadow_entry(mapping, index, folio); } if (!dax) { xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } fbatch->nr = j; } /** * folio_invalidate - Invalidate part or all of a folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * folio_invalidate() is called when all or part of the folio has become * invalidated by a truncate operation. * * folio_invalidate() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void folio_invalidate(struct folio *folio, size_t offset, size_t length) { const struct address_space_operations *aops = folio->mapping->a_ops; if (aops->invalidate_folio) aops->invalidate_folio(folio, offset, length); } EXPORT_SYMBOL_GPL(folio_invalidate); /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_folio(struct folio *folio) { if (folio_mapped(folio)) unmap_mapping_folio(folio); if (folio_has_private(folio)) folio_invalidate(folio, 0, folio_size(folio)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ folio_cancel_dirty(folio); folio_clear_mappedtodisk(folio); } int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return -EIO; truncate_cleanup_folio(folio); filemap_remove_folio(folio); return 0; } /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the * folio that's within the [start, end] range, and then split the folio if * it's large. split_page_range() will discard pages which now lie beyond * i_size, and we rely on the caller to discard pages which lie within a * newly created hole. * * Returns false if splitting failed so the caller can avoid * discarding the entire folio which is stubbornly unsplit. */ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); unsigned int offset, length; if (pos < start) offset = start - pos; else offset = 0; length = folio_size(folio); if (pos + length <= (u64)end) length = length - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); if (length == folio_size(folio)) { truncate_inode_folio(folio->mapping, folio); return true; } /* * We may be zeroing pages we're about to discard, but it avoids * doing a complex calculation here, and then doing the zeroing * anyway if the page split fails. */ if (!mapping_inaccessible(folio->mapping)) folio_zero_range(folio, offset, length); if (folio_has_private(folio)) folio_invalidate(folio, offset, length); if (!folio_test_large(folio)) return true; if (split_folio(folio) == 0) return true; if (folio_test_dirty(folio)) return false; truncate_inode_folio(folio->mapping, folio); return true; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_folio(struct address_space *mapping, struct folio *folio) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_folio(mapping, folio); } EXPORT_SYMBOL(generic_error_remove_folio); /** * mapping_evict_folio() - Remove an unused folio from the page-cache. * @mapping: The mapping this folio belongs to. * @folio: The folio to remove. * * Safely remove one folio from the page cache. * It only drops clean, unused folios. * * Context: Folio must be locked. * Return: The number of pages successfully removed. */ long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { /* The page may have been truncated before it was locked */ if (!mapping) return 0; if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; /* The refcount will be elevated if any page in the folio is mapped */ if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidate_folio() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; struct folio *folio; bool same_folio; if (mapping_empty(mapping)) return; /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, &index, end - 1, &fbatch, indices)) { truncate_folio_batch_exceptionals(mapping, &fbatch, indices); for (i = 0; i < folio_batch_count(&fbatch); i++) truncate_cleanup_folio(fbatch.folios[i]); delete_from_page_cache_batch(mapping, &fbatch); for (i = 0; i < folio_batch_count(&fbatch); i++) folio_unlock(fbatch.folios[i]); folio_batch_release(&fbatch); cond_resched(); } same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio_next_index(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) { folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } } index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, &index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing page->index */ if (xa_is_value(folio)) continue; folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); truncate_inode_folio(mapping, folio); folio_unlock(folio); } truncate_folio_batch_exceptionals(mapping, &fbatch, indices); folio_batch_release(&fbatch); } } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_rwsem and * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __filemap_remove_folio()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_rwsem. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); if (!mapping_empty(mapping)) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); /** * mapping_try_invalidate - Invalidate all the evictable folios of one inode * @mapping: the address_space which holds the folios to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * @nr_failed: How many folio invalidations failed * * This function is similar to invalidate_mapping_pages(), except that it * returns the number of folios which could not be evicted in @nr_failed. */ unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; bool xa_has_values = false; folio_batch_init(&fbatch); while (find_lock_entries(mapping, &index, end, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; count++; continue; } ret = mapping_evict_folio(mapping, folio); folio_unlock(folio); /* * Invalidation is a hint that the folio is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_folio(folio); /* Likely in the lru cache of a remote CPU */ if (nr_failed) (*nr_failed)++; } count += ret; } if (xa_has_values) clear_shadow_entries(mapping, &fbatch, indices); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } return count; } /** * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode * @mapping: the address_space which holds the cache to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function removes pages that are clean, unmapped and unlocked, * as well as shadow entries. It will not block on IO activity. * * If you want to remove all the pages of one inode, regardless of * their use and writeback state, use truncate_inode_pages(). * * Return: The number of indices that had their contents invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return mapping_try_invalidate(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave folios behind because * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ static int invalidate_complete_folio2(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return 0; if (!filemap_release_folio(folio, GFP_KERNEL)) return 0; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); if (folio_test_dirty(folio)) goto failed; BUG_ON(folio_has_private(folio)); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); return 1; failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); return 0; } static int folio_launder(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return 0; if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) return 0; return mapping->a_ops->launder_folio(folio); } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; bool xa_has_values = false; if (mapping_empty(mapping)) return 0; folio_batch_init(&fbatch); index = start; while (find_get_entries(mapping, &index, end, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; if (dax_mapping(mapping) && !dax_invalidate_mapping_entry_sync(mapping, indices[i])) ret = -EBUSY; continue; } if (!did_range_unmap && folio_mapped(folio)) { /* * If folio is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, indices[i], (1 + end - indices[i]), false); did_range_unmap = 1; } folio_lock(folio); if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); continue; } VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); if (folio_mapped(folio)) unmap_mapping_folio(folio); BUG_ON(folio_mapped(folio)); ret2 = folio_launder(mapping, folio); if (ret2 == 0) { if (!invalidate_complete_folio2(mapping, folio)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; folio_unlock(folio); } if (xa_has_values) clear_shadow_entries(mapping, &fbatch, indices); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_rwsem but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or * by write starting after current i_size. We mark the page straddling * current i_size RO so that page_mkwrite() is called on the first * write access to the page. The filesystem will update its per-block * information before user writes to the page via mmap after the i_size * has been changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the folio will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct folio *folio; WARN_ON(to > inode->i_size); if (from >= to || bsize >= PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; folio = filemap_lock_folio(inode->i_mapping, from / PAGE_SIZE); /* Folio not cached? Nothing to do */ if (IS_ERR(folio)) return; /* * See folio_clear_dirty_for_io() for details why folio_mark_dirty() * is needed. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 4 4 3 3 4 8 2 2 2 8 2 2 6 7 2 1 1 1 1 1 2 2 2 1 1 1 1 5 8 9 6 7 2 1 1 1 1 3 3 2 12 1 9 7 9 2 6 9 4 3 2 1 1 2 2 2 4 3 12 3 9 1 4 1 3 9 1 4 5 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC: KVM DEVICE API * * Copyright (C) 2015 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <linux/uaccess.h> #include <asm/kvm_mmu.h> #include <asm/cputype.h> #include "vgic.h" /* common helpers */ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, phys_addr_t addr, phys_addr_t alignment, phys_addr_t size) { if (!IS_VGIC_ADDR_UNDEF(ioaddr)) return -EEXIST; if (!IS_ALIGNED(addr, alignment) || !IS_ALIGNED(size, alignment)) return -EINVAL; if (addr + size < addr) return -EINVAL; if (addr & ~kvm_phys_mask(&kvm->arch.mmu) || (addr + size) > kvm_phys_size(&kvm->arch.mmu)) return -E2BIG; return 0; } static int vgic_check_type(struct kvm *kvm, int type_needed) { if (kvm->arch.vgic.vgic_model != type_needed) return -ENODEV; else return 0; } int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { struct vgic_dist *vgic = &kvm->arch.vgic; int r; mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_dist_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_DIST_SIZE); if (!r) vgic->vgic_dist_base = dev_addr->addr; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_cpu_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_CPU_SIZE); if (!r) vgic->vgic_cpu_base = dev_addr->addr; break; default: r = -ENODEV; } mutex_unlock(&kvm->arch.config_lock); return r; } /** * kvm_vgic_addr - set or get vgic VM base addresses * @kvm: pointer to the vm struct * @attr: pointer to the attribute being retrieved/updated * @write: if true set the address in the VM address space, if false read the * address * * Set or get the vgic base addresses for the distributor and the virtual CPU * interface in the VM physical address space. These addresses are properties * of the emulated core/SoC and therefore user space initially knows this * information. * Check them for sanity (alignment, double assignment). We can't check for * overlapping regions in case of a virtual GICv3 here, since we don't know * the number of VCPUs yet, so we defer this check to map_resources(). */ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool write) { u64 __user *uaddr = (u64 __user *)attr->addr; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment, size; u64 undef_value = VGIC_ADDR_UNDEF; u64 addr; int r; /* Reading a redistributor region addr implies getting the index */ if (write || attr->attr == KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION) if (get_user(addr, uaddr)) return -EFAULT; /* * Since we can't hold config_lock while registering the redistributor * iodevs, take the slots_lock immediately. */ mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_4K; size = KVM_VGIC_V2_DIST_SIZE; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_cpu_base; alignment = SZ_4K; size = KVM_VGIC_V2_CPU_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; size = KVM_VGIC_V3_DIST_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_REDIST: { struct vgic_redist_region *rdreg; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; if (write) { r = vgic_v3_set_redist_base(kvm, 0, addr, 0); goto out; } rdreg = list_first_entry_or_null(&vgic->rd_regions, struct vgic_redist_region, list); if (!rdreg) addr_ptr = &undef_value; else addr_ptr = &rdreg->base; break; } case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: { struct vgic_redist_region *rdreg; u8 index; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; index = addr & KVM_VGIC_V3_RDIST_INDEX_MASK; if (write) { gpa_t base = addr & KVM_VGIC_V3_RDIST_BASE_MASK; u32 count = FIELD_GET(KVM_VGIC_V3_RDIST_COUNT_MASK, addr); u8 flags = FIELD_GET(KVM_VGIC_V3_RDIST_FLAGS_MASK, addr); if (!count || flags) r = -EINVAL; else r = vgic_v3_set_redist_base(kvm, index, base, count); goto out; } rdreg = vgic_v3_rdist_region_from_index(kvm, index); if (!rdreg) { r = -ENOENT; goto out; } addr = index; addr |= rdreg->base; addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; goto out; } default: r = -ENODEV; } if (r) goto out; mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) *addr_ptr = addr; } else { addr = *addr_ptr; } mutex_unlock(&kvm->arch.config_lock); out: mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); return r; } static int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, true); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; u32 val; int ret = 0; if (get_user(val, uaddr)) return -EFAULT; /* * We require: * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs * - at most 1024 interrupts * - a multiple of 32 interrupts */ if (val < (VGIC_NR_PRIVATE_IRQS + 32) || val > VGIC_MAX_RESERVED || (val & 31)) return -EINVAL; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; else dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* * OK, this one isn't common at all, but we * want to handle all control group attributes * in a single place. */ if (vgic_check_type(dev->kvm, KVM_DEV_TYPE_ARM_VGIC_V3)) return -ENXIO; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; } break; } } return -ENXIO; } static int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = -ENXIO; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, false); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; r = put_user(dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS, uaddr); break; } } return r; } static int vgic_create(struct kvm_device *dev, u32 type) { return kvm_vgic_create(dev->kvm, type); } static void vgic_destroy(struct kvm_device *dev) { kfree(dev); } int kvm_register_vgic_device(unsigned long type) { int ret = -ENODEV; switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V2: ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2); break; case KVM_DEV_TYPE_ARM_VGIC_V3: ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) break; ret = kvm_vgic_register_its_device(); break; } return ret; } int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); if (!reg_attr->vcpu) return -EINVAL; return 0; } /** * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v2_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; int ret; u32 val; ret = vgic_v2_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; if (is_write) if (get_user(val, uaddr)) return -EFAULT; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); ret = vgic_init(dev->kvm); if (ret) goto out; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, &val); break; default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) ret = put_user(val, uaddr); return ret; } static int vgic_v2_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v2_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v2_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: case KVM_VGIC_V2_ADDR_TYPE_CPU: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v2_ops = { .name = "kvm-arm-vgic-v2", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v2_set_attr, .get_attr = vgic_v2_get_attr, .has_attr = vgic_v2_has_attr, }; int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { unsigned long vgic_mpidr, mpidr_reg; /* * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, * attr might not hold MPIDR. Hence assume vcpu0. */ if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); } else { reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); } if (!reg_attr->vcpu) return -EINVAL; reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; return 0; } /* * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v3_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; bool uaccess; u32 val; int ret; ret = vgic_v3_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: /* Sysregs uaccess is performed by the sysreg handling code */ uaccess = false; break; default: uaccess = true; } if (uaccess && is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; if (get_user(val, uaddr)) return -EFAULT; } mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: ret = vgic_v3_cpu_sysregs_uaccess(vcpu, attr, is_write); break; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { unsigned int info, intid; info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { intid = attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, intid, &val); } else { ret = -EINVAL; } break; } default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; ret = put_user(val, uaddr); } return ret; } static int vgic_v3_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v3_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v3_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == VGIC_LEVEL_INFO_LINE_LEVEL) return 0; break; } case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v3_ops = { .name = "kvm-arm-vgic-v3", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v3_set_attr, .get_attr = vgic_v3_get_attr, .has_attr = vgic_v3_has_attr, }; |
| 43 43 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ARM64_KVM_NESTED_H #define __ARM64_KVM_NESTED_H #include <linux/bitfield.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_pgtable.h> static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu) { return (!__is_defined(__KVM_NVHE_HYPERVISOR__) && cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2)); } /* Translation helpers from non-VHE EL2 to EL1 */ static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2) { return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT; } static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) { return TCR_EPD1_MASK | /* disable TTBR1_EL1 */ ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) | tcr_el2_ps_to_tcr_el1_ips(tcr) | (tcr & TCR_EL2_TG0_MASK) | (tcr & TCR_EL2_ORGN0_MASK) | (tcr & TCR_EL2_IRGN0_MASK) | (tcr & TCR_EL2_T0SZ_MASK); } static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2) { u64 cpacr_el1 = CPACR_ELx_RES1; if (cptr_el2 & CPTR_EL2_TTA) cpacr_el1 |= CPACR_ELx_TTA; if (!(cptr_el2 & CPTR_EL2_TFP)) cpacr_el1 |= CPACR_ELx_FPEN; if (!(cptr_el2 & CPTR_EL2_TZ)) cpacr_el1 |= CPACR_ELx_ZEN; cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM); return cpacr_el1; } static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 val) { /* Only preserve the minimal set of bits we support */ val &= (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB | SCTLR_ELx_WXN | SCTLR_ELx_EE); val |= SCTLR_EL1_RES1; return val; } static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) { /* Clear the ASID field */ return ttbr0 & ~GENMASK_ULL(63, 48); } extern bool forward_smc_trap(struct kvm_vcpu *vcpu); extern void kvm_init_nested(struct kvm *kvm); extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu); extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu); extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu); union tlbi_info; extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid, const union tlbi_info *info, void (*)(struct kvm_s2_mmu *, const union tlbi_info *)); extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu); extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu); struct kvm_s2_trans { phys_addr_t output; unsigned long block_size; bool writable; bool readable; int level; u32 esr; u64 upper_attr; }; static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans) { return trans->output; } static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans) { return trans->block_size; } static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans) { return trans->esr; } static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans) { return trans->readable; } static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans) { return trans->writable; } static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans) { return !(trans->upper_attr & BIT(54)); } extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa, struct kvm_s2_trans *result); extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans); extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2); extern void kvm_nested_s2_wp(struct kvm *kvm); extern void kvm_nested_s2_unmap(struct kvm *kvm); extern void kvm_nested_s2_flush(struct kvm *kvm); unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val); static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); if (!(sys_reg_Op0(instr) == TLBI_Op0 && sys_reg_Op1(instr) == TLBI_Op1_EL1)) return false; if (!(sys_reg_CRn(instr) == TLBI_CRn_XS || (sys_reg_CRn(instr) == TLBI_CRn_nXS && kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)))) return false; if (CRm == TLBI_CRm_nROS && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS || CRm == TLBI_CRm_RNS) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; return true; } static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); if (!(sys_reg_Op0(instr) == TLBI_Op0 && sys_reg_Op1(instr) == TLBI_Op1_EL2)) return false; if (!(sys_reg_CRn(instr) == TLBI_CRn_XS || (sys_reg_CRn(instr) == TLBI_CRn_nXS && kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)))) return false; if (CRm == TLBI_CRm_IPAIS || CRm == TLBI_CRm_IPAONS) return false; if (CRm == TLBI_CRm_nROS && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS || CRm == TLBI_CRm_RNS) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; return true; } int kvm_init_nv_sysregs(struct kvm *kvm); #ifdef CONFIG_ARM64_PTR_AUTH bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr); #else static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr) { /* We really should never execute this... */ WARN_ON_ONCE(1); *elr = 0xbad9acc0debadbad; return false; } #endif #define KVM_NV_GUEST_MAP_SZ (KVM_PGTABLE_PROT_SW1 | KVM_PGTABLE_PROT_SW0) static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans) { return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level); } #endif /* __ARM64_KVM_NESTED_H */ |
| 323 325 4 3 3 4 3 3 3 2 3 2 1 3 1 1 1 1 7 4 4 7 2 1 2 1 2 1 2 1 2 1 2 1 2 1 2 2 1 2 1 2 1 2 1 2 1 2 1 2 1 2 4 2 2 4 4 3 3 2 2 4 4 2 4 9 2 7 9 1 1 345 1 343 2 3 3 1 1 2 2 2 3 7 6 6 1 3 1 4 21 1 321 361 344 345 324 341 340 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); loff_t cloned; int ret; if (!src_file.file) return -EBADF; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; fdput(src_file); return ret; } static long ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE); return freeze_super(sb, FREEZE_HOLDER_USERSPACE); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE); return thaw_super(sb, FREEZE_HOLDER_USERSPACE); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = offsetof(struct file_dedupe_range, info[count]); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct fileattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct fileattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int copy_fsxattr_from_user(struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct fileattr *old_ma, struct fileattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } /** * vfs_fileattr_set - change miscellaneous file attributes * @idmap: idmap of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fileattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (!err) err = inode->i_op->fileattr_set(idmap, dentry, fa); } inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); static int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct fileattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } static int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct fileattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } static int ioctl_fssetxattr(struct file *file, void __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_getfsuuid(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; struct fsuuid2 u = { .len = sb->s_uuid_len, }; if (!sb->s_uuid_len) return -ENOTTY; memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; if (!strlen(sb->s_sysfs_name)) return -ENOTTY; struct fs_sysfs_path u = {}; u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. * * The LSM mailing list should also be notified of any command additions or * changes, as specific LSMs may be affected. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); case FS_IOC_GETFSUUID: return ioctl_getfsuuid(filp, argp); case FS_IOC_GETFSSYSFSPATH: return ioctl_get_fs_sysfs_path(filp, argp); default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl(f.file, cmd, arg); if (error) goto out; error = do_vfs_ioctl(f.file, fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(f.file, cmd, arg); out: fdput(f); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * @file: The file to operate on. * @cmd: The ioctl command number. * @arg: The argument to the ioctl. * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(f.file, arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(f.file, fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (f.file->f_op->compat_ioctl) error = f.file->f_op->compat_ioctl(f.file, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } out: fdput(f); return error; } #endif |
| 209 384 68 108 386 12 95 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H #define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types_raw: * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types_raw: * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() kcsan_mb() #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) #ifndef CONFIG_PREEMPT_RT /* Include rwlock functions for !RT */ #include <linux/rwlock.h> #endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* Non PREEMPT_RT kernel, map to raw spinlocks: */ #ifndef CONFIG_PREEMPT_RT /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) #else /* !CONFIG_PREEMPT_RT */ # include <linux/spinlock_rt.h> #endif /* CONFIG_PREEMPT_RT */ /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, * but a general need for low latency) */ static inline int spin_needbreak(spinlock_t *lock) { if (!preempt_model_preemptible()) return 0; return spin_is_contended(lock); } /* * Check if a rwlock is contended. * Returns non-zero if there is another task waiting on the rwlock. * Returns zero if the lock is not contended or the system / underlying * rwlock implementation does not support contention detection. * Technically does not depend on CONFIG_PREEMPTION, but a general need * for low latency. */ static inline int rwlock_needbreak(rwlock_t *lock) { if (!preempt_model_preemptible()) return 0; return rwlock_is_contended(lock); } /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock); #define atomic_dec_and_raw_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock)) extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, raw_spin_lock(_T->lock), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, raw_spin_lock_irq(_T->lock), raw_spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, raw_spin_lock_irqsave(_T->lock, _T->flags), raw_spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try, raw_spin_trylock_irqsave(_T->lock, _T->flags)) DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, spin_lock(_T->lock), spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, spin_lock_irq(_T->lock), spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try, spin_trylock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, spin_lock_irqsave(_T->lock, _T->flags), spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try, spin_trylock_irqsave(_T->lock, _T->flags)) DEFINE_LOCK_GUARD_1(read_lock, rwlock_t, read_lock(_T->lock), read_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t, read_lock_irq(_T->lock), read_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t, read_lock_irqsave(_T->lock, _T->flags), read_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1(write_lock, rwlock_t, write_lock(_T->lock), write_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t, write_lock_irq(_T->lock), write_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t, write_lock_irqsave(_T->lock, _T->flags), write_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 398 398 398 397 397 393 397 397 395 395 395 395 393 110 395 396 396 397 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; long delta; if (!c->parent) return; protected = min(usage, READ_ONCE(c->min)); old_protected = atomic_long_read(&c->min_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } protected = min(usage, READ_ONCE(c->low)); old_protected = atomic_long_read(&c->low_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); /* More uncharges than charges? */ if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n", new, nr_pages)) { new = 0; atomic_long_set(&counter->usage, new); } propagate_protected_usage(counter, new); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = page_counter_read(counter); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (page_counter_read(counter) <= usage || nr_pages >= old) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its * parent's and siblings' settings, as well as the actual memory * distribution in the tree. * * The following rules apply to the effective protection values: * * 1. At the first level of reclaim, effective protection is equal to * the declared protection in memory.min and memory.low. * * 2. To enable safe delegation of the protection configuration, at * subsequent levels the effective protection is capped to the * parent's effective protection. * * 3. To make complex and dynamic subtrees easier to configure, the * user is allowed to overcommit the declared protection at a given * level. If that is the case, the parent's effective protection is * distributed to the children in proportion to how much protection * they have declared and how much of it they are utilizing. * * This makes distribution proportional, but also work-conserving: * if one counter claims much more protection than it uses memory, * the unused remainder is available to its siblings. * * 4. Conversely, when the declared protection is undercommitted at a * given level, the distribution of the larger parental protection * budget is NOT proportional. A counter's protection from a sibling * is capped to its own memory.min/low setting. * * 5. However, to allow protecting recursive subtrees from each other * without having to declare each individual counter's fixed share * of the ancestor's claim to protection, any unutilized - * "floating" - protection from up the tree is distributed in * proportion to each counter's *usage*. This makes the protection * neutral wrt sibling cgroups and lets them compete freely over * the shared parental protection budget, but it protects the * subtree as a whole from neighboring subtrees. * * Note that 4. and 5. are not in conflict: 4. is about protecting * against immediate siblings whereas 5. is about protecting against * neighboring subtrees. */ static unsigned long effective_protection(unsigned long usage, unsigned long parent_usage, unsigned long setting, unsigned long parent_effective, unsigned long siblings_protected, bool recursive_protection) { unsigned long protected; unsigned long ep; protected = min(usage, setting); /* * If all cgroups at this level combined claim and use more * protection than what the parent affords them, distribute * shares in proportion to utilization. * * We are using actual utilization rather than the statically * claimed protection in order to be work-conserving: claimed * but unused protection is available to siblings that would * otherwise get a smaller chunk than what they claimed. */ if (siblings_protected > parent_effective) return protected * parent_effective / siblings_protected; /* * Ok, utilized protection of all children is within what the * parent affords them, so we know whatever this child claims * and utilizes is effectively protected. * * If there is unprotected usage beyond this value, reclaim * will apply pressure in proportion to that amount. * * If there is unutilized protection, the cgroup will be fully * shielded from reclaim, but we do return a smaller value for * protection than what the group could enjoy in theory. This * is okay. With the overcommit distribution above, effective * protection is always dependent on how memory is actually * consumed among the siblings anyway. */ ep = protected; /* * If the children aren't claiming (all of) the protection * afforded to them by the parent, distribute the remainder in * proportion to the (unprotected) memory of each cgroup. That * way, cgroups that aren't explicitly prioritized wrt each * other compete freely over the allowance, but they are * collectively protected from neighboring trees. * * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. * * Check both usage and parent_usage against the respective * protected values. One should imply the other, but they * aren't read atomically - make sure the division is sane. */ if (!recursive_protection) return ep; if (parent_effective > siblings_protected && parent_usage > siblings_protected && usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; unclaimed *= usage - protected; unclaimed /= parent_usage - siblings_protected; ep += unclaimed; } return ep; } /** * page_counter_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @counter: the page_counter the counter to update * @recursive_protection: Whether to use memory_recursiveprot behavior. * * Calculates elow/emin thresholds for given page_counter. * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries. */ void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) { unsigned long usage, parent_usage; struct page_counter *parent = counter->parent; /* * Effective values of the reclaim targets are ignored so they * can be stale. Have a look at mem_cgroup_protection for more * details. * TODO: calculation should be more robust so that we do not need * that special casing. */ if (root == counter) return; usage = page_counter_read(counter); if (!usage) return; if (parent == root) { counter->emin = READ_ONCE(counter->min); counter->elow = READ_ONCE(counter->low); return; } parent_usage = page_counter_read(parent); WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage, READ_ONCE(counter->min), READ_ONCE(parent->emin), atomic_long_read(&parent->children_min_usage), recursive_protection)); WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage, READ_ONCE(counter->low), READ_ONCE(parent->elow), atomic_long_read(&parent->children_low_usage), recursive_protection)); } |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 26 26 4 4 173 173 181 181 30 30 30 26 30 30 30 30 175 175 175 175 220 173 173 173 173 220 173 173 220 229 174 174 174 4 172 229 174 174 174 4 4 4 4 228 68 68 153 153 153 153 153 39 121 152 57 57 77 77 87 99 77 77 77 77 77 77 77 76 77 77 77 77 57 57 57 57 57 57 57 34 34 34 33 34 34 34 34 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 | /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * folio_lock_memcg move_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <asm/tlbflush.h> #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include <trace/events/migrate.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by vma_expand(), vma_merge(), __split_vma(), * copy_vma() and anon_vma_fork(). The first four want an exact copy of src, * while the last one, anon_vma_fork(), may try to reuse an existing anon_vma to * prevent endless growth of anon_vma. Since dst->anon_vma is set to NULL before * call, we can identify this case by checking (!dst->anon_vma && * src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if it has no vma and only one * anon_vma child. * * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its num_active_vmas can * be incorrectly decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) { vma->anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; } unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should normally hold folio lock when calling this. If * not, the caller needs to double check the anon_vma didn't change after * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; retry: rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * folio_move_anon_rmap() might have changed the anon_vma as we * might not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { up_read(&root_anon_vma->rwsem); rcu_read_unlock(); goto retry; } /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); /* * folio_move_anon_rmap() might have changed the anon_vma as we might * not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { anon_vma_unlock_read(anon_vma); put_anon_vma(anon_vma); anon_vma = NULL; goto retry; } if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { arch_flush_tlb_batched_pending(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { struct folio *folio = page_folio(page); pgoff_t pgoff; if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* The !page__anon_vma above handles KSM folios */ pgoff = folio->index + folio_page_idx(folio, page); return vma_address(vma, pgoff, 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { if (!folio_test_large(folio) || !pvmw.pte) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * For large folio fully mapped to VMA, will * be handled after the pvmw loop. * * For large folio cross VMA boundaries, it's * expected to be picked by page reclaim. But * should skip reference of pages which are in * the range of VM_LOCKED vma. As page reclaim * should just count the reference of pages out * the range of VM_LOCKED vma. */ ptes++; pra->mapcount--; continue; } if (pvmw.pte) { if (lru_gen_enabled() && pte_young(ptep_get(pvmw.pte))) { lru_gen_look_around(&pvmw); referenced++; } if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } pra->mapcount--; } if ((vma->vm_flags & VM_LOCKED) && folio_test_large(folio) && folio_within_vma(folio, vma)) { unsigned long s_align, e_align; s_align = ALIGN_DOWN(start, PMD_SIZE); e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); /* folio doesn't cross page table boundary and fully mapped */ if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first, nr = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&page->_mapcount); break; } do { first = atomic_inc_and_test(&page->_mapcount); if (first) { first = atomic_inc_return_relaxed(mapped); if (first < ENTIRELY_MAPPED) nr++; } } while (page++, --nr_pages > 0); atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { *nr_pmdmapped = folio_nr_pages(folio); nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } atomic_inc(&folio->_large_mapcount); break; } return nr; } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; __lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; __lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum rmap_level level) { int i, nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); __folio_mod_stat(folio, nr, nr_pmdmapped); if (flags & RMAP_EXCLUSIVE) { switch (level) { case RMAP_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case RMAP_LEVEL_PMD: SetPageAnonExclusive(page); break; } } for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 || (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && PageAnonExclusive(cur_page), folio); } /* * For large folio, only mlock it if it's fully mapped to VMA. It's * not easy to check whether the large folio is fully mapped to VMA * here. Only mlock normal 4K folio and leave page reclaim to handle * large folio. */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, RMAP_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const int nr = folio_nr_pages(folio); const bool exclusive = flags & RMAP_EXCLUSIVE; int nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, nr - 1); atomic_set(&folio->_nr_pages_mapped, nr); } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } __folio_mod_stat(folio, nr, nr_pmdmapped); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { int nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); __folio_mod_stat(folio, nr, nr_pmdmapped); /* See comments in folio_add_anon_rmap_*() */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &page->_mapcount); break; } atomic_sub(nr_pages, &folio->_large_mapcount); do { last = atomic_add_negative(-1, &page->_mapcount); if (last) { last = atomic_dec_return_relaxed(mapped); if (last < ENTIRELY_MAPPED) nr++; } } while (page++, --nr_pages > 0); partially_mapped = nr && atomic_read(mapped); break; case RMAP_LEVEL_PMD: atomic_dec(&folio->_large_mapcount); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pmdmapped = folio_nr_pages(folio); nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr < nr_pmdmapped; break; } if (nr) { /* * Queue anon large folio for deferred split if at least one * page of the folio is unmapped and at least one page * is still mapped. * * Check partially_mapped first to ensure it is a large folio. */ if (folio_test_anon(folio) && partially_mapped && list_empty(&folio->_deferred_list)) deferred_split_folio(folio); } __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); goto walk_abort; } if (!pvmw.pte) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false, folio); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ goto walk_done; } hugetlb_vma_unlock_write(vma); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && (!folio_test_dirty(folio) || /* * Unlike MADV_FREE mappings, VM_DROPPABLE * ones can be dropped even if they've * been dirtied. */ (vma->vm_flags & VM_DROPPABLE))) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the folio was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); /* * Unlike MADV_FREE mappings, VM_DROPPABLE ones * never get swap backed on failure to drop. */ if (!(vma->vm_flags & VM_DROPPABLE)) folio_set_swapbacked(folio); goto walk_abort; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(folio)); } discard: if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * unmap_page() in mm/huge_memory.c is the only user of migration with * TTU_SPLIT_HUGE_PMD and it wants to freeze. */ if (flags & TTU_SPLIT_HUGE_PMD) split_huge_pmd_address(vma, address, true, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { subpage = folio_page(folio, pmd_pfn(*pvmw.pmd) - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; } #endif /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); if (folio_is_zone_device(folio)) { /* * Our PTE is a non-present device exclusive entry and * calculating the subpage as for the common case would * result in an invalid pointer. * * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); subpage = &folio->page; } else { subpage = folio_page(folio, pfn - folio_pfn(folio)); } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (folio_is_device_private(folio)) { unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; if (anon_exclusive) WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio, subpage)); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); trace_set_migration_pte(pvmw.address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { struct mm_struct *mm; unsigned long address; void *owner; bool valid; }; static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; swp_entry_t entry; pte_t swp_pte; pte_t ptent; mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, address, min(vma->vm_end, address + folio_size(folio)), args->owner); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); ptent = ptep_get(pvmw.pte); if (!pte_present(ptent)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } subpage = folio_page(folio, pte_pfn(ptent) - folio_pfn(folio)); address = pvmw.address; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(ptent)); pteval = ptep_clear_flush(vma, address, pvmw.pte); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* * Check that our target page is still mapped at the expected * address. */ if (args->mm == mm && args->address == address && pte_write(pteval)) args->valid = true; /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_device_exclusive_entry( page_to_pfn(subpage)); else entry = make_readable_device_exclusive_entry( page_to_pfn(subpage)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ folio_remove_rmap_pte(folio, subpage, vma); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * folio_make_device_exclusive - Mark the folio exclusively owned by a device. * @folio: The folio to replace page table entries for. * @mm: The mm_struct where the folio is expected to be mapped. * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * * Tries to remove all the page table entries which are mapping this * folio and replace them with special device exclusive swap entries to * grant a device exclusive access to the folio. * * Context: Caller must hold the folio lock. * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ static bool folio_make_device_exclusive(struct folio *folio, struct mm_struct *mm, unsigned long address, void *owner) { struct make_exclusive_args args = { .mm = mm, .address = address, .owner = owner, .valid = false, }; struct rmap_walk_control rwc = { .rmap_one = page_make_device_exclusive_one, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, .arg = &args, }; /* * Restrict to anonymous folios for now to avoid potential writeback * issues. */ if (!folio_test_anon(folio)) return false; rmap_walk(folio, &rwc); return args.valid && !folio_mapcount(folio); } /** * make_device_exclusive_range() - Mark a range for exclusive use by a device * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * * Returns: number of pages found in the range by GUP. A page is marked for * exclusive access only if the page pointer is non-NULL. * * This function finds ptes mapping page(s) to the given address range, locks * them and replaces mappings with special swap entries preventing userspace CPU * access. On fault these entries are replaced with the original mapping after * calling MMU notifiers. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the page lock and reference after * which point CPU access to the page will revoke the exclusive access. */ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *owner) { long npages = (end - start) >> PAGE_SHIFT; long i; npages = get_user_pages_remote(mm, start, npages, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, pages, NULL); if (npages < 0) return npages; for (i = 0; i < npages; i++, start += PAGE_SIZE) { struct folio *folio = page_folio(pages[i]); if (PageTail(pages[i]) || !folio_trylock(folio)) { folio_put(folio); pages[i] = NULL; continue; } if (!folio_make_device_exclusive(folio, mm, start, owner)) { folio_unlock(folio); folio_put(folio); pages[i] = NULL; } } return npages; } EXPORT_SYMBOL_GPL(make_device_exclusive_range); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!mapping) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 99 99 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 1 101 101 101 101 101 1 1 1 100 101 101 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, const struct context *c1, const struct context *c2) { struct mls_range *dr = &dst->range; const struct mls_range *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline int mls_context_cmp(const struct context *c1, const struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, const struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); dst->str = NULL; dst->len = 0; return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline int context_cmp(const struct context *c1, const struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_cmp(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM clk #if !defined(_TRACE_CLK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CLK_H #include <linux/tracepoint.h> struct clk_core; DECLARE_EVENT_CLASS(clk, TP_PROTO(struct clk_core *core), TP_ARGS(core), TP_STRUCT__entry( __string( name, core->name ) ), TP_fast_assign( __assign_str(name); ), TP_printk("%s", __get_str(name)) ); DEFINE_EVENT(clk, clk_enable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_enable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DECLARE_EVENT_CLASS(clk_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, rate ) ), TP_fast_assign( __assign_str(name); __entry->rate = rate; ), TP_printk("%s %lu", __get_str(name), (unsigned long)__entry->rate) ); DEFINE_EVENT(clk_rate, clk_set_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_rate_complete, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_min_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_max_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DECLARE_EVENT_CLASS(clk_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, min ) __field(unsigned long, max ) ), TP_fast_assign( __assign_str(name); __entry->min = min; __entry->max = max; ), TP_printk("%s min %lu max %lu", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max) ); DEFINE_EVENT(clk_rate_range, clk_set_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max) ); DECLARE_EVENT_CLASS(clk_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent), TP_STRUCT__entry( __string( name, core->name ) __string( pname, parent ? parent->name : "none" ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); ), TP_printk("%s %s", __get_str(name), __get_str(pname)) ); DEFINE_EVENT(clk_parent, clk_set_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DEFINE_EVENT(clk_parent, clk_set_parent_complete, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DECLARE_EVENT_CLASS(clk_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase), TP_STRUCT__entry( __string( name, core->name ) __field( int, phase ) ), TP_fast_assign( __assign_str(name); __entry->phase = phase; ), TP_printk("%s %d", __get_str(name), (int)__entry->phase) ); DEFINE_EVENT(clk_phase, clk_set_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DEFINE_EVENT(clk_phase, clk_set_phase_complete, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DECLARE_EVENT_CLASS(clk_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty), TP_STRUCT__entry( __string( name, core->name ) __field( unsigned int, num ) __field( unsigned int, den ) ), TP_fast_assign( __assign_str(name); __entry->num = duty->num; __entry->den = duty->den; ), TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num, (unsigned int)__entry->den) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DECLARE_EVENT_CLASS(clk_rate_request, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req), TP_STRUCT__entry( __string( name, req->core ? req->core->name : "none") __string( pname, req->best_parent_hw ? clk_hw_get_name(req->best_parent_hw) : "none" ) __field(unsigned long, min ) __field(unsigned long, max ) __field(unsigned long, prate ) ), TP_fast_assign( __assign_str(name); __assign_str(pn |