| 1 1 75 75 75 75 75 75 52 52 88 | 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 | /* 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_RAZ (1 << 1) /* RAZ from userspace and guest */ #define REG_USER_WI (1 << 2) /* 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_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); int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu); #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)) #define CP15_SYS_DESC(reg) \ .name = #reg, \ .aarch32_map = AA32_DIRECT, \ Op0(0), 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__ */ |
| 175 12 168 175 | 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 | // 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/text-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(); } |
| 24 24 24 24 24 24 9 9 9 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 80 520 366 | 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; bool inaccessible; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the page again. */ void (*page_free)(struct page *page); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; DECLARE_FLEX_ARRAY(struct range, ranges); }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) { return is_device_private_page(&folio->page); } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) { return is_device_coherent_page(&folio->page); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 262 156 156 156 262 262 262 262 262 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 107 107 25 25 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_INTERNAL_H #define _LINUX_HIGHMEM_INTERNAL_H /* * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft. */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); static inline void kmap_assert_nomap(void) { DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx); } #else static inline void kmap_local_fork(struct task_struct *tsk) { } static inline void kmap_assert_nomap(void) { } #endif #ifdef CONFIG_HIGHMEM #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); void kunmap_high(struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } static inline void kunmap(struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } static inline struct page *kmap_to_page(void *addr) { return __kmap_to_page(addr); } static inline void kmap_flush_unused(void) { __kmap_flush_unused(); } static inline void *kmap_local_page(struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } static inline void *kmap_local_pfn(unsigned long pfn) { return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_page_prot(page, prot); } static inline void *kmap_atomic(struct page *page) { return kmap_atomic_prot(page, kmap_prot); } static inline void *kmap_atomic_pfn(unsigned long pfn) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } unsigned long __nr_free_highpages(void); unsigned long __totalhigh_pages(void); static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || (addr >= __fix_to_virt(FIX_KMAP_END) && addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(struct page *page) { } static inline void kmap_flush_unused(void) { } static inline void kunmap(struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_local_page(struct page *page) { return page_address(page); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { return page_address(&folio->page) + offset; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); } static inline void *kmap_local_pfn(unsigned long pfn) { return kmap_local_page(pfn_to_page(pfn)); } static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } static inline void *kmap_atomic(struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return page_address(page); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { return kmap_atomic(page); } static inline void *kmap_atomic_pfn(unsigned long pfn) { return kmap_atomic(pfn_to_page(pfn)); } static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } static inline unsigned long nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { return false; } #endif /* CONFIG_HIGHMEM */ /** * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! * @__addr: Virtual address to be unmapped * * Unmaps an address previously mapped by kmap_atomic() and re-enables * pagefaults. Depending on PREEMP_RT configuration, re-enables also * migration and preemption. Users should not count on these side effects. * * Mappings should be unmapped in the reverse order that they were mapped. * See kmap_local_page() for details on nesting. * * @__addr can be any address within the mapped page, so there is no need * to subtract any offset that has been added. In contrast to kunmap(), * this function takes the address returned from kmap_atomic(), not the * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_atomic(__addr); \ } while (0) /** * kunmap_local - Unmap a page mapped via kmap_local_page(). * @__addr: An address within the page mapped * * @__addr can be any address within the mapped page. Commonly it is the * address return from kmap_local_page(), but it can also include offsets. * * Unmapping should be done in the reverse order of the mapping. See * kmap_local_page() for details. */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_local(__addr); \ } while (0) #endif |
| 1 66 35 35 66 66 65 1 1 1 1 84 66 65 75 75 252 252 19 19 74 75 8 8 8 8 7 7 75 76 76 75 75 75 74 35 35 35 35 351 352 25 25 1 4 250 254 254 252 252 252 19 19 19 66 66 66 66 75 74 74 74 84 83 2 60 58 84 21 4 74 13 13 77 77 77 13 74 75 75 5 4 74 75 75 1 75 75 75 59 86 87 87 1 87 87 4 87 63 84 10 53 84 75 34 87 24 24 72 4 66 1 66 66 74 74 3 72 27 71 71 72 7 74 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/mman.h> #include <linux/kvm_host.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/sched/signal.h> #include <trace/events/kvm.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> #include <asm/kvm_pkvm.h> #include <asm/kvm_ras.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/virt.h> #include "trace.h" static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); static unsigned long __ro_after_init hyp_idmap_start; static unsigned long __ro_after_init hyp_idmap_end; static phys_addr_t __ro_after_init hyp_idmap_vector; u32 __ro_after_init __hyp_va_bits; static unsigned long __ro_after_init io_map_base; #define KVM_PGT_FN(fn) (!is_protected_kvm_enabled() ? fn : p ## fn) static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end, phys_addr_t size) { phys_addr_t boundary = ALIGN_DOWN(addr + size, size); return (boundary - 1 < end - 1) ? boundary : end; } static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) { phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); return __stage2_range_addr_end(addr, end, size); } /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, * we may see kernel panics with CONFIG_DETECT_HUNG_TASK, * CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; if (resched && next != end) cond_resched_rwlock_write(&kvm->mmu_lock); } while (addr = next, addr != end); return ret; } #define stage2_apply_range_resched(mmu, addr, end, fn) \ stage2_apply_range(mmu, addr, end, fn, true) /* * Get the maximum number of page-tables pages needed to split a range * of blocks into PAGE_SIZE PTEs. It assumes the range is already * mapped at level 2, or at level 1 if allowed. */ static int kvm_mmu_split_nr_page_tables(u64 range) { int n = 0; if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2) n += DIV_ROUND_UP(range, PUD_SIZE); n += DIV_ROUND_UP(range, PMD_SIZE); return n; } static bool need_split_memcache_topup_or_resched(struct kvm *kvm) { struct kvm_mmu_memory_cache *cache; u64 chunk_size, min; if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) return true; chunk_size = kvm->arch.mmu.split_page_chunk_size; min = kvm_mmu_split_nr_page_tables(chunk_size); cache = &kvm->arch.mmu.split_page_cache; return kvm_mmu_memory_cache_nr_free_objects(cache) < min; } static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { struct kvm_mmu_memory_cache *cache; struct kvm_pgtable *pgt; int ret, cache_capacity; u64 next, chunk_size; lockdep_assert_held_write(&kvm->mmu_lock); chunk_size = kvm->arch.mmu.split_page_chunk_size; cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size); if (chunk_size == 0) return 0; cache = &kvm->arch.mmu.split_page_cache; do { if (need_split_memcache_topup_or_resched(kvm)) { write_unlock(&kvm->mmu_lock); cond_resched(); /* Eager page splitting is best-effort. */ ret = __kvm_mmu_topup_memory_cache(cache, cache_capacity, cache_capacity); write_lock(&kvm->mmu_lock); if (ret) break; } pgt = kvm->arch.mmu.pgt; if (!pgt) return -EINVAL; next = __stage2_range_addr_end(addr, end, chunk_size); ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache); if (ret) break; } while (addr = next, addr != end); return ret; } static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); } /** * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8 * @kvm: pointer to kvm structure. * * Interface to HYP function to flush all VM TLB entries */ int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { if (is_protected_kvm_enabled()) kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); else kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); return 0; } int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { u64 size = nr_pages << PAGE_SHIFT; u64 addr = gfn << PAGE_SHIFT; if (is_protected_kvm_enabled()) kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); else kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size); return 0; } static bool kvm_is_device_pfn(unsigned long pfn) { return !pfn_is_map_memory(pfn); } static void *stage2_memcache_zalloc_page(void *arg) { struct kvm_mmu_memory_cache *mc = arg; void *virt; /* Allocated with __GFP_ZERO, so no need to zero */ virt = kvm_mmu_memory_cache_alloc(mc); if (virt) kvm_account_pgtable_pages(virt, 1); return virt; } static void *kvm_host_zalloc_pages_exact(size_t size) { return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } static void *kvm_s2_zalloc_pages_exact(size_t size) { void *virt = kvm_host_zalloc_pages_exact(size); if (virt) kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT)); return virt; } static void kvm_s2_free_pages_exact(void *virt, size_t size) { kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT)); free_pages_exact(virt, size); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops; static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head) { struct page *page = container_of(head, struct page, rcu_head); void *pgtable = page_to_virt(page); s8 level = page_private(page); KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level); } static void stage2_free_unlinked_table(void *addr, s8 level) { struct page *page = virt_to_page(addr); set_page_private(page, (unsigned long)level); call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb); } static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); } static void kvm_host_put_page(void *addr) { put_page(virt_to_page(addr)); } static void kvm_s2_put_page(void *addr) { struct page *p = virt_to_page(addr); /* Dropping last refcount, the page will be freed */ if (page_count(p) == 1) kvm_account_pgtable_pages(addr, -1); put_page(p); } static int kvm_host_page_count(void *addr) { return page_count(virt_to_page(addr)); } static phys_addr_t kvm_host_pa(void *addr) { return __pa(addr); } static void *kvm_host_va(phys_addr_t phys) { return __va(phys); } static void clean_dcache_guest_page(void *va, size_t size) { __clean_dcache_guest_page(va, size); } static void invalidate_icache_guest_page(void *va, size_t size) { __invalidate_icache_guest_page(va, size); } /* * Unmapping vs dcache management: * * If a guest maps certain memory pages as uncached, all writes will * bypass the data cache and go directly to RAM. However, the CPUs * can still speculate reads (not writes) and fill cache lines with * data. * * Those cache lines will be *clean* cache lines though, so a * clean+invalidate operation is equivalent to an invalidate * operation, because no cache lines are marked dirty. * * Those clean cache lines could be filled prior to an uncached write * by the guest, and the cache coherent IO subsystem would therefore * end up writing old data to disk. * * This is why right after unmapping a page/section and invalidating * the corresponding TLBs, we flush to make sure the IO subsystem will * never hit in the cache. * * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as * we then fully enforce cacheability of RAM, no matter what the guest * does. */ /** * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range * @mmu: The KVM stage-2 MMU pointer * @start: The intermediate physical base address of the range to unmap * @size: The size of the area to unmap * @may_block: Whether or not we are permitted to block * * Clear a range of stage-2 mappings, lowering the various ref-counts. Must * be called while holding mmu_lock (unless for freeing the stage2 pgd before * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); phys_addr_t end = start + size; lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap), may_block)); } void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { __unmap_stage2_range(mmu, start, size, may_block); } void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush)); } static void stage2_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; kvm_stage2_flush_range(&kvm->arch.mmu, addr, end); } /** * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 * @kvm: The struct kvm pointer * * Go through the stage 2 page tables and invalidate any cache lines * backing memory already mapped to the VM. */ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); kvm_nested_s2_flush(kvm); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } /** * free_hyp_pgds - free Hyp-mode page tables */ void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { kvm_pgtable_hyp_destroy(hyp_pgtable); kfree(hyp_pgtable); hyp_pgtable = NULL; } mutex_unlock(&kvm_hyp_pgd_mutex); } static bool kvm_host_owns_hyp_mappings(void) { if (is_kernel_in_hyp_mode()) return false; if (static_branch_likely(&kvm_protected_mode_initialized)) return false; /* * This can happen at boot time when __create_hyp_mappings() is called * after the hyp protection has been enabled, but the static key has * not been flipped yet. */ if (!hyp_pgtable && is_protected_kvm_enabled()) return false; WARN_ON(!hyp_pgtable); return true; } int __create_hyp_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot) { int err; if (WARN_ON(!kvm_host_owns_hyp_mappings())) return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot); mutex_unlock(&kvm_hyp_pgd_mutex); return err; } static phys_addr_t kvm_kaddr_to_phys(void *kaddr) { if (!is_vmalloc_addr(kaddr)) { BUG_ON(!virt_addr_valid(kaddr)); return __pa(kaddr); } else { return page_to_phys(vmalloc_to_page(kaddr)) + offset_in_page(kaddr); } } struct hyp_shared_pfn { u64 pfn; int count; struct rb_node node; }; static DEFINE_MUTEX(hyp_shared_pfns_lock); static struct rb_root hyp_shared_pfns = RB_ROOT; static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node, struct rb_node **parent) { struct hyp_shared_pfn *this; *node = &hyp_shared_pfns.rb_node; *parent = NULL; while (**node) { this = container_of(**node, struct hyp_shared_pfn, node); *parent = **node; if (this->pfn < pfn) *node = &((**node)->rb_left); else if (this->pfn > pfn) *node = &((**node)->rb_right); else return this; } return NULL; } static int share_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (this) { this->count++; goto unlock; } this = kzalloc(sizeof(*this), GFP_KERNEL); if (!this) { ret = -ENOMEM; goto unlock; } this->pfn = pfn; this->count = 1; rb_link_node(&this->node, parent, node); rb_insert_color(&this->node, &hyp_shared_pfns); ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } static int unshare_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (WARN_ON(!this)) { ret = -ENOENT; goto unlock; } this->count--; if (this->count) goto unlock; rb_erase(&this->node, &hyp_shared_pfns); kfree(this); ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } int kvm_share_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; int ret; if (is_kernel_in_hyp_mode()) return 0; /* * The share hcall maps things in the 'fixed-offset' region of the hyp * VA space, so we can only share physically contiguous data-structures * for now. */ if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to)) return -EINVAL; if (kvm_host_owns_hyp_mappings()) return create_hyp_mappings(from, to, PAGE_HYP); start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); ret = share_pfn_hyp(pfn); if (ret) return ret; } return 0; } void kvm_unshare_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from) return; start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); WARN_ON(unshare_pfn_hyp(pfn)); } } /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range * @to: The virtual kernel end address of the range (exclusive) * @prot: The protection to be applied to this range * * The same virtual address as the kernel virtual address is also used * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying * physical pages. */ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) { phys_addr_t phys_addr; unsigned long virt_addr; unsigned long start = kern_hyp_va((unsigned long)from); unsigned long end = kern_hyp_va((unsigned long)to); if (is_kernel_in_hyp_mode()) return 0; if (!kvm_host_owns_hyp_mappings()) return -EPERM; start = start & PAGE_MASK; end = PAGE_ALIGN(end); for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { int err; phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr, prot); if (err) return err; } return 0; } static int __hyp_alloc_private_va_range(unsigned long base) { lockdep_assert_held(&kvm_hyp_pgd_mutex); if (!PAGE_ALIGNED(base)) return -EINVAL; /* * Verify that BIT(VA_BITS - 1) hasn't been flipped by * allocating the new area, as it would indicate we've * overflowed the idmap/IO address range. */ if ((base ^ io_map_base) & BIT(VA_BITS - 1)) return -ENOMEM; io_map_base = base; return 0; } /** * hyp_alloc_private_va_range - Allocates a private VA range. * @size: The size of the VA range to reserve. * @haddr: The hypervisor virtual start address of the allocation. * * The private virtual address (VA) range is allocated below io_map_base * and aligned based on the order of @size. * * Return: 0 on success or negative error code on failure. */ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) { unsigned long base; int ret = 0; mutex_lock(&kvm_hyp_pgd_mutex); /* * This assumes that we have enough space below the idmap * page to allocate our VAs. If not, the check in * __hyp_alloc_private_va_range() will kick. A potential * alternative would be to detect that overflow and switch * to an allocation above the idmap. * * The allocated size is always a multiple of PAGE_SIZE. */ size = PAGE_ALIGN(size); base = io_map_base - size; ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (!ret) *haddr = base; return ret; } static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, unsigned long *haddr, enum kvm_pgtable_prot prot) { unsigned long addr; int ret = 0; if (!kvm_host_owns_hyp_mappings()) { addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, phys_addr, size, prot); if (IS_ERR_VALUE(addr)) return addr; *haddr = addr; return 0; } size = PAGE_ALIGN(size + offset_in_page(phys_addr)); ret = hyp_alloc_private_va_range(size, &addr); if (ret) return ret; ret = __create_hyp_mappings(addr, size, phys_addr, prot); if (ret) return ret; *haddr = addr + offset_in_page(phys_addr); return ret; } int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) { unsigned long base; size_t size; int ret; mutex_lock(&kvm_hyp_pgd_mutex); /* * Efficient stack verification using the NVHE_STACK_SHIFT bit implies * an alignment of our allocation on the order of the size. */ size = NVHE_STACK_SIZE * 2; base = ALIGN_DOWN(io_map_base - size, size); ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (ret) { kvm_err("Cannot allocate hyp stack guard page\n"); return ret; } /* * Since the stack grows downwards, map the stack to the page * at the higher address and leave the lower guard page * unbacked. * * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 * and addresses corresponding to the guard page have the * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. */ ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE, phys_addr, PAGE_HYP); if (ret) kvm_err("Cannot map hyp stack\n"); *haddr = base + size; return ret; } /** * create_hyp_io_mappings - Map IO into both kernel and HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @kaddr: Kernel VA for this mapping * @haddr: HYP VA for this mapping */ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr) { unsigned long addr; int ret; if (is_protected_kvm_enabled()) return -EPERM; *kaddr = ioremap(phys_addr, size); if (!*kaddr) return -ENOMEM; if (is_kernel_in_hyp_mode()) { *haddr = *kaddr; return 0; } ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_DEVICE); if (ret) { iounmap(*kaddr); *kaddr = NULL; *haddr = NULL; return ret; } *haddr = (void __iomem *)addr; return 0; } /** * create_hyp_exec_mappings - Map an executable range into HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @haddr: HYP VA for this mapping */ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr) { unsigned long addr; int ret; BUG_ON(is_kernel_in_hyp_mode()); ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_EXEC); if (ret) { *haddr = NULL; return ret; } *haddr = (void *)addr; return 0; } static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { /* We shouldn't need any other callback to walk the PT */ .phys_to_virt = kvm_host_va, }; static int get_user_mapping_size(struct kvm *kvm, u64 addr) { struct kvm_pgtable pgt = { .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_LAST_LEVEL - ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ s8 level = S8_MAX; int ret; /* * Disable IRQs so that we hazard against a concurrent * teardown of the userspace page tables (which relies on * IPI-ing threads). */ local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); local_irq_restore(flags); if (ret) return ret; /* * Not seeing an error, but not updating level? Something went * deeply wrong... */ if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL)) return -EFAULT; if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL)) return -EFAULT; /* Oops, the userspace PTs are gone... Replay the fault */ if (!kvm_pte_valid(pte)) return -EAGAIN; return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, .free_pages_exact = kvm_s2_free_pages_exact, .free_unlinked_table = stage2_free_unlinked_table, .get_page = kvm_host_get_page, .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, .dcache_clean_inval_poc = clean_dcache_guest_page, .icache_inval_pou = invalidate_icache_guest_page, }; static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) { u32 kvm_ipa_limit = get_kvm_ipa_limit(); u64 mmfr0, mmfr1; u32 phys_shift; if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK) return -EINVAL; phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); if (is_protected_kvm_enabled()) { phys_shift = kvm_ipa_limit; } else if (phys_shift) { if (phys_shift > kvm_ipa_limit || phys_shift < ARM64_MIN_PARANGE_BITS) return -EINVAL; } else { phys_shift = KVM_PHYS_SHIFT; if (phys_shift > kvm_ipa_limit) { pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n", current->comm); return -EINVAL; } } mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); return 0; } /** * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure * @mmu: The pointer to the s2 MMU structure * @type: The machine type of the virtual machine * * Allocates only the stage-2 HW PGD level table(s). * Note we don't need locking here as this is only called in two cases: * * - when the VM is created, which can't race against anything * * - when secondary kvm_s2_mmu structures are initialised for NV * guests, and the caller must hold kvm->lock as this is called on a * per-vcpu basis. */ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) { int cpu, err; struct kvm_pgtable *pgt; /* * If we already have our page tables in place, and that the * MMU context is the canonical one, we have a bug somewhere, * as this is only supposed to ever happen once per VM. * * Otherwise, we're building nested page tables, and that's * probably because userspace called KVM_ARM_VCPU_INIT more * than once on the same vcpu. Since that's actually legal, * don't kick a fuss and leave gracefully. */ if (mmu->pgt != NULL) { if (kvm_is_nested_s2_mmu(kvm, mmu)) return 0; kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } err = kvm_init_ipa_range(mmu, type); if (err) return err; pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT); if (!pgt) return -ENOMEM; mmu->arch = &kvm->arch; err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops); if (err) goto out_free_pgtable; mmu->pgt = pgt; if (is_protected_kvm_enabled()) return 0; mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); if (!mmu->last_vcpu_ran) { err = -ENOMEM; goto out_destroy_pgtable; } for_each_possible_cpu(cpu) *per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1; /* The eager page splitting is disabled by default */ mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; mmu->split_page_cache.gfp_zero = __GFP_ZERO; mmu->pgd_phys = __pa(pgt->pgd); if (kvm_is_nested_s2_mmu(kvm, mmu)) kvm_init_nested_s2_mmu(mmu); return 0; out_destroy_pgtable: KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); out_free_pgtable: kfree(pgt); return err; } void kvm_uninit_stage2_mmu(struct kvm *kvm) { kvm_free_stage2_pgd(&kvm->arch.mmu); kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } static void stage2_unmap_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { hva_t hva = memslot->userspace_addr; phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t size = PAGE_SIZE * memslot->npages; hva_t reg_end = hva + size; /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we should * unmap any of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; hva_t vm_start, vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; /* * Take the intersection of this VMA with the memory region */ vm_start = max(hva, vma->vm_start); vm_end = min(reg_end, vma->vm_end); if (!(vma->vm_flags & VM_PFNMAP)) { gpa_t gpa = addr + (vm_start - memslot->userspace_addr); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true); } hva = vm_end; } while (hva < reg_end); } /** * stage2_unmap_vm - Unmap Stage-2 RAM mappings * @kvm: The struct kvm pointer * * Go through the memregions and unmap any regular RAM * backing memory already mapped to the VM. */ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); mmap_read_unlock(current->mm); srcu_read_unlock(&kvm->srcu, idx); } void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); struct kvm_pgtable *pgt = NULL; write_lock(&kvm->mmu_lock); pgt = mmu->pgt; if (pgt) { mmu->pgd_phys = 0; mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } write_unlock(&kvm->mmu_lock); if (pgt) { KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); kfree(pgt); } } static void hyp_mc_free_fn(void *addr, void *unused) { free_page((unsigned long)addr); } static void *hyp_mc_alloc_fn(void *unused) { return (void *)__get_free_page(GFP_KERNEL_ACCOUNT); } void free_hyp_memcache(struct kvm_hyp_memcache *mc) { if (!is_protected_kvm_enabled()) return; kfree(mc->mapping); __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) { if (!is_protected_kvm_enabled()) return 0; if (!mc->mapping) { mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT); if (!mc->mapping) return -ENOMEM; } return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, kvm_host_pa, NULL); } /** * kvm_phys_addr_ioremap - map a device range to guest IPA * * @kvm: The KVM pointer * @guest_ipa: The IPA at which to insert the mapping * @pa: The physical address of the device * @size: The size of the mapping * @writable: Whether or not to create a writable mapping */ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable) { phys_addr_t addr; int ret = 0; struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; struct kvm_s2_mmu *mmu = &kvm->arch.mmu; struct kvm_pgtable *pgt = mmu->pgt; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); if (is_protected_kvm_enabled()) return -EPERM; size += offset_in_page(guest_ipa); guest_ipa &= PAGE_MASK; for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) { ret = kvm_mmu_topup_memory_cache(&cache, kvm_mmu_cache_min_pages(mmu)); if (ret) break; write_lock(&kvm->mmu_lock); ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE, pa, prot, &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; pa += PAGE_SIZE; } kvm_mmu_free_memory_cache(&cache); return ret; } /** * kvm_stage2_wp_range() - write protect stage2 memory region range * @mmu: The KVM stage-2 MMU pointer * @addr: Start address of range * @end: End address of range */ void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect)); } /** * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot * @kvm: The KVM pointer * @slot: The memory slot to write protect * * Called to start logging dirty pages after memory region * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns * all present PUD, PMD and PTEs are write protected in the memory region. * Afterwards read of dirty page log can be called. * * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); phys_addr_t start, end; if (WARN_ON_ONCE(!memslot)) return; start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); kvm_nested_s2_wp(kvm); write_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs_memslot(kvm, memslot); } /** * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE * pages for memory slot * @kvm: The KVM pointer * @slot: The memory slot to split * * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; phys_addr_t start, end; lockdep_assert_held(&kvm->slots_lock); slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, slot); start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_mmu_split_huge_pages(kvm, start, end); write_unlock(&kvm->mmu_lock); } /* * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages. * @kvm: The KVM pointer * @slot: The memory slot associated with mask * @gfn_offset: The gfn offset in memory slot * @mask: The mask of pages at offset 'gfn_offset' in this memory * slot to enable dirty logging on * * Writes protect selected pages to enable dirty logging, and then * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { phys_addr_t base_gfn = slot->base_gfn + gfn_offset; phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; lockdep_assert_held_write(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); /* * Eager-splitting is done when manual-protect is set. We * also check for initially-all-set because we can avoid * eager-splitting if initially-all-set is false. * Initially-all-set equal false implies that huge-pages were * already split when enabling dirty logging: no need to do it * again. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) kvm_mmu_split_huge_pages(kvm, start, end); kvm_nested_s2_wp(kvm); } static void kvm_send_hwpoison_signal(unsigned long address, short lsb) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); } static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, unsigned long hva, unsigned long map_size) { gpa_t gpa_start; hva_t uaddr_start, uaddr_end; size_t size; /* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */ if (map_size == PAGE_SIZE) return true; size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; uaddr_start = memslot->userspace_addr; uaddr_end = uaddr_start + size; /* * Pages belonging to memslots that don't have the same alignment * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2 * PMD/PUD entries, because we'll end up mapping the wrong pages. * * Consider a layout like the following: * * memslot->userspace_addr: * +-----+--------------------+--------------------+---+ * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz| * +-----+--------------------+--------------------+---+ * * memslot->base_gfn << PAGE_SHIFT: * +---+--------------------+--------------------+-----+ * |abc|def Stage-2 block | Stage-2 block |tvxyz| * +---+--------------------+--------------------+-----+ * * If we create those stage-2 blocks, we'll end up with this incorrect * mapping: * d -> f * e -> g * f -> h */ if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) return false; /* * Next, let's make sure we're not trying to map anything not covered * by the memslot. This means we have to prohibit block size mappings * for the beginning and end of a non-block aligned and non-block sized * memory slot (illustrated by the head and tail parts of the * userspace view above containing pages 'abcde' and 'xyz', * respectively). * * Note that it doesn't matter if we do the check using the * userspace_addr or the base_gfn, as both are equally aligned (per * the check above) and equally sized. */ return (hva & ~(map_size - 1)) >= uaddr_start && (hva & ~(map_size - 1)) + map_size <= uaddr_end; } /* * Check if the given hva is backed by a transparent huge page (THP) and * whether it can be mapped using block mapping in stage2. If so, adjust * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently * supported. This will need to be updated to support other THP sizes. * * Returns the size of the mapping. */ static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) { kvm_pfn_t pfn = *pfnp; /* * Make sure the adjustment is done only for THP pages. Also make * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { int sz = get_user_mapping_size(kvm, hva); if (sz < 0) return sz; if (sz < PMD_SIZE) return PAGE_SIZE; *ipap &= PMD_MASK; pfn &= ~(PTRS_PER_PMD - 1); *pfnp = pfn; return PMD_SIZE; } /* Use page mapping if we cannot use block mapping. */ return PAGE_SIZE; } static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) { unsigned long pa; if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP)) return huge_page_shift(hstate_vma(vma)); if (!(vma->vm_flags & VM_PFNMAP)) return PAGE_SHIFT; VM_BUG_ON(is_vm_hugetlb_page(vma)); pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start); #ifndef __PAGETABLE_PMD_FOLDED if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) && ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start && ALIGN(hva, PUD_SIZE) <= vma->vm_end) return PUD_SHIFT; #endif if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) && ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start && ALIGN(hva, PMD_SIZE) <= vma->vm_end) return PMD_SHIFT; return PAGE_SHIFT; } /* * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be * able to see the page's tags and therefore they must be initialised first. If * PG_mte_tagged is set, tags have already been initialised. * * The race in the test/set of the PG_mte_tagged flag is handled by: * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs * racing to santise the same page * - mmap_lock protects between a VM faulting a page in and the VMM performing * an mprotect() to add VM_MTE */ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, unsigned long size) { unsigned long i, nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); if (!kvm_has_mte(kvm)) return; if (folio_test_hugetlb(folio)) { /* Hugetlb has MTE flags set on head page only */ if (folio_try_hugetlb_mte_tagging(folio)) { for (i = 0; i < nr_pages; i++, page++) mte_clear_page_tags(page_address(page)); folio_set_hugetlb_mte_tagged(folio); } return; } for (i = 0; i < nr_pages; i++, page++) { if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } } } static bool kvm_vma_mte_allowed(struct vm_area_struct *vma) { return vma->vm_flags & VM_MTE_ALLOWED; } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_trans *nested, struct kvm_memory_slot *memslot, unsigned long hva, bool fault_is_perm) { int ret = 0; bool write_fault, writable, force_pte = false; bool exec_fault, mte_allowed; bool device = false, vfio_allow_any_uc = false; unsigned long mmu_seq; phys_addr_t ipa = fault_ipa; struct kvm *kvm = vcpu->kvm; struct vm_area_struct *vma; short vma_shift; void *memcache; gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; struct page *page; enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_is_perm && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The * only exception to this is when dirty logging is enabled at runtime * and a write fault needs to collapse a block entry into a table. */ if (!fault_is_perm || (logging_active && write_fault)) { int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); if (!is_protected_kvm_enabled()) { memcache = &vcpu->arch.mmu_page_cache; ret = kvm_mmu_topup_memory_cache(memcache, min_pages); } else { memcache = &vcpu->arch.pkvm_memcache; ret = topup_hyp_memcache(memcache, min_pages); } if (ret) return ret; } /* * Let's check if we will get back a huge page backed by hugetlbfs, or * get block mapping for device MMIO region. */ mmap_read_lock(current->mm); vma = vma_lookup(current->mm, hva); if (unlikely(!vma)) { kvm_err("Failed to find VMA for hva 0x%lx\n", hva); mmap_read_unlock(current->mm); return -EFAULT; } /* * logging_active is guaranteed to never be true for VM_PFNMAP * memslots. */ if (logging_active || is_protected_kvm_enabled()) { force_pte = true; vma_shift = PAGE_SHIFT; } else { vma_shift = get_vma_page_shift(vma, hva); } switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; #endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; case PMD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) break; fallthrough; case CONT_PTE_SHIFT: vma_shift = PAGE_SHIFT; force_pte = true; fallthrough; case PAGE_SHIFT: break; default: WARN_ONCE(1, "Unknown vma_shift %d", vma_shift); } vma_pagesize = 1UL << vma_shift; if (nested) { unsigned long max_map_size; max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE; ipa = kvm_s2_trans_output(nested); /* * If we're about to create a shadow stage 2 entry, then we * can only create a block mapping if the guest stage 2 page * table uses at least as big a mapping. */ max_map_size = min(kvm_s2_trans_size(nested), max_map_size); /* * Be careful that if the mapping size falls between * two host sizes, take the smallest of the two. */ if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE) max_map_size = PMD_SIZE; else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE) max_map_size = PAGE_SIZE; force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min(vma_pagesize, (long)max_map_size); } /* * Both the canonical IPA and fault IPA must be hugepage-aligned to * ensure we find the right PFN and lay down the mapping in the right * place. */ if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { fault_ipa &= ~(vma_pagesize - 1); ipa &= ~(vma_pagesize - 1); } gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED; /* Don't use the VMA after the unlock -- it may have vanished */ vma = NULL; /* * Read mmu_invalidate_seq so that KVM can detect if the results of * vma_lookup() or __kvm_faultin_pfn() become stale prior to * acquiring kvm->mmu_lock. * * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs * with the smp_wmb() in kvm_mmu_invalidate_end(). */ mmu_seq = vcpu->kvm->mmu_invalidate_seq; mmap_read_unlock(current->mm); pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, &writable, &page); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); return 0; } if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { /* * If the page was identified as device early by looking at * the VMA flags, vma_pagesize is already representing the * largest quantity we can map. If instead it was mapped * via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE * and must not be upgraded. * * In both cases, we don't let transparent_hugepage_adjust() * change things at the last minute. */ device = true; } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write * fault. */ writable = false; } if (exec_fault && device) return -ENOEXEC; /* * Potentially reduce shadow S2 permissions to match the guest's own * S2. For exec faults, we'd only reach this point if the guest * actually allowed it (see kvm_s2_handle_perm_fault). * * Also encode the level of the original translation in the SW bits * of the leaf entry as a proxy for the span of that translation. * This will be retrieved on TLB invalidation from the guest and * used to limit the invalidation scope if a TTL hint or a range * isn't provided. */ if (nested) { writable &= kvm_s2_trans_writable(nested); if (!kvm_s2_trans_readable(nested)) prot &= ~KVM_PGTABLE_PROT_R; prot |= kvm_encode_nested_level(nested); } kvm_fault_lock(kvm); pgt = vcpu->arch.hw_mmu->pgt; if (mmu_invalidate_retry(kvm, mmu_seq)) { ret = -EAGAIN; goto out_unlock; } /* * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { if (fault_is_perm && fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); if (vma_pagesize < 0) { ret = vma_pagesize; goto out_unlock; } } if (!fault_is_perm && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ if (mte_allowed) { sanitise_mte_tags(kvm, pfn, vma_pagesize); } else { ret = -EFAULT; goto out_unlock; } } if (writable) prot |= KVM_PGTABLE_PROT_W; if (exec_fault) prot |= KVM_PGTABLE_PROT_X; if (device) { if (vfio_allow_any_uc) prot |= KVM_PGTABLE_PROT_NORMAL_NC; else prot |= KVM_PGTABLE_PROT_DEVICE; } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) && (!nested || kvm_s2_trans_executable(nested))) { prot |= KVM_PGTABLE_PROT_X; } /* * Under the premise of getting a FSC_PERM fault, we just need to relax * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ if (fault_is_perm && vma_pagesize == fault_granule) { /* * Drop the SW bits in favour of those stored in the * PTE, which will be preserved. */ prot &= ~KVM_NV_GUEST_MAP_SZ; ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags); } else { ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache, flags); } out_unlock: kvm_release_faultin_page(kvm, page, !!ret, writable); kvm_fault_unlock(kvm); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0; } /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags); read_unlock(&vcpu->kvm->mmu_lock); } /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer * * Any abort that gets to the host is almost guaranteed to be caused by a * missing second stage translation table entry, which can mean that either the * guest simply needs more memory and we must allocate an appropriate page or it * can mean that the guest tried to access I/O memory, which is emulated by user * space. The distinction is based on the IPA causing the fault and whether this * memory region has been registered as standard RAM by user space. */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) { struct kvm_s2_trans nested_trans, *nested = NULL; unsigned long esr; phys_addr_t fault_ipa; /* The address we faulted on */ phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */ struct kvm_memory_slot *memslot; unsigned long hva; bool is_iabt, write_fault, writable; gfn_t gfn; int ret, idx; esr = kvm_vcpu_get_esr(vcpu); ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); return 1; } /* Falls between the IPA range and the PARange? */ if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) { fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); if (is_iabt) kvm_inject_pabt(vcpu, fault_ipa); else kvm_inject_dabt(vcpu, fault_ipa); return 1; } } /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* * For RAS the host kernel may handle this abort. * There is no need to pass the error into the guest. */ if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu))) kvm_inject_vabt(vcpu); return 1; } trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr) && !esr_fsc_is_access_flag_fault(esr)) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), (unsigned long)kvm_vcpu_get_esr(vcpu)); return -EFAULT; } idx = srcu_read_lock(&vcpu->kvm->srcu); /* * We may have faulted on a shadow stage 2 page table if we are * running a nested guest. In this case, we have to resolve the L2 * IPA to the L1 IPA first, before knowing what kind of memory should * back the L1 IPA. * * If the shadow stage 2 page table walk faults, then we simply inject * this to the guest and carry on. * * If there are no shadow S2 PTs because S2 is disabled, there is * nothing to walk and we treat it as a 1:1 before going through the * canonical translation. */ if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) && vcpu->arch.hw_mmu->nested_stage2_enabled) { u32 esr; ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ipa = kvm_s2_trans_output(&nested_trans); nested = &nested_trans; } gfn = ipa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); write_fault = kvm_is_write_fault(vcpu); if (kvm_is_error_hva(hva) || (write_fault && !writable)) { /* * The guest has put either its instructions or its page-tables * somewhere it shouldn't have. Userspace won't be able to do * anything about this (there's no syndrome for a start), so * re-inject the abort back into the guest. */ if (is_iabt) { ret = -ENOEXEC; goto out; } if (kvm_vcpu_abt_iss1tw(vcpu)) { kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; } /* * Check for a cache maintenance operation. Since we * ended-up here, we know it is outside of any memory * slot. But we can't find out if that is for a device, * or if the guest is just being stupid. The only thing * we know for sure is that this range cannot be cached. * * So let's assume that the guest is just being * cautious, and skip the instruction. */ if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { kvm_incr_pc(vcpu); ret = 1; goto out_unlock; } /* * The IPA is reported as [MAX:12], so we need to * complement it with the bottom 12 bits from the * faulting VA. This is always 12 bits, irrespective * of the page size. */ ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); ret = io_mem_abort(vcpu, ipa); goto out_unlock; } /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu)); if (esr_fsc_is_access_flag_fault(esr)) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; } ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva, esr_fsc_is_permission_fault(esr)); if (ret == 0) ret = 1; out: if (ret == -ENOEXEC) { kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); kvm_nested_s2_unmap(kvm, range->may_block); return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, true); /* * TODO: Handle nested_mmu structures here using the reverse mapping in * a later version of patch series. */ } bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, false); } phys_addr_t kvm_mmu_get_httbr(void) { return __pa(hyp_pgtable->pgd); } phys_addr_t kvm_get_idmap_vector(void) { return hyp_idmap_vector; } static int kvm_map_idmap_text(void) { unsigned long size = hyp_idmap_end - hyp_idmap_start; int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start, PAGE_HYP_EXEC); if (err) kvm_err("Failed to idmap %lx-%lx\n", hyp_idmap_start, hyp_idmap_end); return err; } static void *kvm_hyp_zalloc_page(void *arg) { return (void *)get_zeroed_page(GFP_KERNEL); } static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .zalloc_page = kvm_hyp_zalloc_page, .get_page = kvm_host_get_page, .put_page = kvm_host_put_page, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, }; int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; u32 kernel_bits; hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start); hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE); hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end); hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE); hyp_idmap_vector = __pa_symbol(__kvm_hyp_init); /* * We rely on the linker script to ensure at build time that the HYP * init code does not cross a page boundary. */ BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* * The ID map is always configured for 48 bits of translation, which * may be fewer than the number of VA bits used by the regular kernel * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom * line: we need to use the extended range with *both* our translation * tables. * * So use the maximum of the idmap VA bits and the regular kernel stage * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits); kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); kvm_debug("HYP VA range: %lx:%lx\n", kern_hyp_va(PAGE_OFFSET), kern_hyp_va((unsigned long)high_memory - 1)); if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && hyp_idmap_start < kern_hyp_va((unsigned long)high_memory - 1) && hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) { /* * The idmap page is intersecting with the VA space, * it is not safe to continue further. */ kvm_err("IDMAP intersecting with HYP VA, unable to continue\n"); err = -EINVAL; goto out; } hyp_pgtable = kzalloc(sizeof(*hyp_pgtable), GFP_KERNEL); if (!hyp_pgtable) { kvm_err("Hyp mode page-table not allocated\n"); err = -ENOMEM; goto out; } err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops); if (err) goto out_free_pgtable; err = kvm_map_idmap_text(); if (err) goto out_destroy_pgtable; io_map_base = hyp_idmap_start; __hyp_va_bits = *hyp_va_bits; return 0; out_destroy_pgtable: kvm_pgtable_hyp_destroy(hyp_pgtable); out_free_pgtable: kfree(hyp_pgtable); hyp_pgtable = NULL; out: return err; } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES; /* * At this point memslot has been committed and there is an * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ if (log_dirty_pages) { if (change == KVM_MR_DELETE) return; /* * Huge and normal pages are write-protected and split * on either of these two cases: * * 1. with initial-all-set: gradually with CLEAR ioctls, */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; /* * or * 2. without initial-all-set: all in one shot when * enabling dirty logging. */ kvm_mmu_wp_memory_region(kvm, new->id); kvm_mmu_split_memory_region(kvm, new->id); } else { /* * Free any leftovers from the eager page splitting cache. Do * this when deleting, moving, disabling dirty logging, or * creating the memslot (a nop). Doing it for deletes makes * sure we don't leak memory, and there's no need to keep the * cache around for any of the other cases. */ kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } } int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && change != KVM_MR_FLAGS_ONLY) return 0; /* * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT)) return -EFAULT; hva = new->userspace_addr; reg_end = hva + (new->npages << PAGE_SHIFT); mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) { ret = -EINVAL; break; } if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } } hva = min(reg_end, vma->vm_end); } while (hva < reg_end); mmap_read_unlock(current->mm); return ret; } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { } void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { gpa_t gpa = slot->base_gfn << PAGE_SHIFT; phys_addr_t size = slot->npages << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); } /* * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). * * Main problems: * - S/W ops are local to a CPU (not broadcast) * - We have line migration behind our back (speculation) * - System caches don't support S/W at all (damn!) * * In the face of the above, the best we can do is to try and convert * S/W ops to VA ops. Because the guest is not allowed to infer the * S/W to PA mapping, it can only use S/W to nuke the whole cache, * which is a rather good thing for us. * * Also, it is only used when turning caches on/off ("The expected * usage of the cache maintenance instructions that operate by set/way * is associated with the cache maintenance instructions associated * with the powerdown and powerup of caches, if this is required by * the implementation."). * * We use the following policy: * * - If we trap a S/W operation, we enable VM trapping to detect * caches being turned on/off, and do a full clean. * * - We flush the caches on both caches being turned on and off. * * - Once the caches are enabled, we stop trapping VM ops. */ void kvm_set_way_flush(struct kvm_vcpu *vcpu) { unsigned long hcr = *vcpu_hcr(vcpu); /* * If this is the first time we do a S/W operation * (i.e. HCR_TVM not set) flush the whole memory, and set the * VM trapping. * * Otherwise, rely on the VM trapping to wait for the MMU + * Caches to be turned off. At that point, we'll be able to * clean the caches again. */ if (!(hcr & HCR_TVM)) { trace_kvm_set_way_flush(*vcpu_pc(vcpu), vcpu_has_cache_enabled(vcpu)); stage2_flush_vm(vcpu->kvm); *vcpu_hcr(vcpu) = hcr | HCR_TVM; } } void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) { bool now_enabled = vcpu_has_cache_enabled(vcpu); /* * If switching the MMU+caches on, need to invalidate the caches. * If switching it off, need to clean the caches. * Clean + invalidate does the trick always. */ if (now_enabled != was_enabled) stage2_flush_vm(vcpu->kvm); /* Caches are now on, stop trapping VM ops (until a S/W op) */ if (now_enabled) *vcpu_hcr(vcpu) &= ~HCR_TVM; trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); } |
| 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 _NET_IP6_ROUTE_H #define _NET_IP6_ROUTE_H #include <net/addrconf.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> #include <net/lwtunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> #include <net/nexthop.h> struct route_info { __u8 type; __u8 length; __u8 prefix_len; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved_h:3, route_pref:2, reserved_l:3; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved_l:3, route_pref:2, reserved_h:3; #endif __be32 lifetime; __u8 prefix[]; /* 0,8 or 16 */ }; #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 #define RT6_LOOKUP_F_HAS_SADDR 0x00000004 #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 #define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header */ #define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr)) /* * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate * between IPV6_ADDR_PREFERENCES socket option values * IPV6_PREFER_SRC_TMP = 0x1 * IPV6_PREFER_SRC_PUBLIC = 0x2 * IPV6_PREFER_SRC_COA = 0x4 * and above RT6_LOOKUP_F_SRCPREF_xxx flags. */ static inline int rt6_srcprefs2flags(unsigned int srcprefs) { return (srcprefs & IPV6_PREFER_SRC_MASK) << 3; } static inline unsigned int rt6_flags2srcprefs(int flags) { return (flags >> 3) & IPV6_PREFER_SRC_MASK; } static inline bool rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* fib entries using a nexthop object can not be coalesced into * a multipath route */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && f6i->fib6_nh->fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); static inline struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { return ip6_route_output_flags(net, sk, fl6, 0); } /* Only conditionally release dst if flags indicates * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. */ static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) { if (!(flags & RT6_LOOKUP_F_DST_NOREF) || !list_empty(&rt->dst.rt_uncached)) ip6_rt_put(rt); } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int ifindex, struct flowi6 *fl6, const struct sk_buff *skb, int flags); void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg); int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); int ip6_ins_rt(struct net *net, struct fib6_info *f6i); int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify); void rt6_flush_exceptions(struct fib6_info *f6i); void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now); static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, unsigned int prefs, int l3mdev_index, struct in6_addr *saddr) { struct net_device *l3mdev; struct net_device *dev; bool same_vrf; int err = 0; rcu_read_lock(); l3mdev = dev_get_by_index_rcu(net, l3mdev_index); if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev) dev = f6i ? fib6_info_nh_dev(f6i) : NULL; same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev; if (f6i && f6i->fib6_prefsrc.plen && same_vrf) *saddr = f6i->fib6_prefsrc.addr; else err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr); rcu_read_unlock(); return err; } struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int flags); u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *hkeys); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); void fib6_force_start_gc(struct net *net); struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); /* * support functions for ND * */ struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime); void rt6_purge_dflt_routers(struct net *net); int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; struct fib_dump_filter filter; }; int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned char nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct fib6_info *f6i); void rt6_uncached_list_add(struct rt6_info *rt); void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); if (dst) return dst_rt6_info(dst); return NULL; } /* * Store a destination cache entry in a socket */ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif } void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6); static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) { mtu = READ_ONCE(dst->dev->mtu); mtu -= lwtunnel_headroom(dst->lwtstate, mtu); } else { mtu = dst_mtu(dst); } return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc != IPV6_PMTUDISC_INTERFACE && pmtudisc != IPV6_PMTUDISC_OMIT; } static inline bool ip6_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc < IPV6_PMTUDISC_DO || pmtudisc == IPV6_PMTUDISC_OMIT; } static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; else if (unlikely(rt->rt6i_flags & RTF_CACHE)) return &rt->rt6i_dst.addr; else return daddr; } static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { struct fib6_nh *nha, *nhb; if (a->nh || b->nh) return nexthop_cmp(a->nh, b->nh); nha = a->fib6_nh; nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct inet6_dev *idev; unsigned int mtu; if (!forwarding || dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; } mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); if (idev) mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr); #endif |
| 88 88 76 87 88 79 88 | 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); } |
| 4 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Skb ref helpers. * */ #ifndef _LINUX_SKBUFF_REF_H #define _LINUX_SKBUFF_REF_H #include <linux/skbuff.h> /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment * * Takes an additional reference on the paged fragment @frag. */ static inline void __skb_frag_ref(skb_frag_t *frag) { get_page(skb_frag_page(frag)); } /** * skb_frag_ref - take an addition reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset. * * Takes an additional reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_ref(struct sk_buff *skb, int f) { __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } bool napi_pp_put_page(netmem_ref netmem); static inline void skb_page_unref(netmem_ref netmem, bool recycle) { #ifdef CONFIG_PAGE_POOL if (recycle && napi_pp_put_page(netmem)) return; #endif put_page(netmem_to_page(netmem)); } /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment * @recycle: recycle the page if allocated via page_pool * * Releases a reference on the paged fragment @frag * or recycles the page via the page_pool API. */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { skb_page_unref(skb_frag_netmem(frag), recycle); } /** * skb_frag_unref - release a reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset * * Releases a reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (!skb_zcopy_managed(skb)) __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } #endif /* _LINUX_SKBUFF_REF_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; u32 location; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 245 271 190 331 180 60 18 14 54 65 143 15 178 352 352 306 82 173 261 291 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MIN_HEAP_H #define _LINUX_MIN_HEAP_H #include <linux/bug.h> #include <linux/string.h> #include <linux/types.h> /* * The Min Heap API provides utilities for managing min-heaps, a binary tree * structure where each node's value is less than or equal to its children's * values, ensuring the smallest element is at the root. * * Users should avoid directly calling functions prefixed with __min_heap_*(). * Instead, use the provided macro wrappers. * * For further details and examples, refer to Documentation/core-api/min_heap.rst. */ /** * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. * @data: Pointer to the start of array holding the heap elements. * @preallocated: Start of the static preallocated array holding the heap elements. */ #define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ struct _name { \ size_t nr; \ size_t size; \ _type *data; \ _type preallocated[_nr]; \ } #define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0) typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; #define __minheap_cast(_heap) (typeof((_heap)->data[0]) *) #define __minheap_obj_size(_heap) sizeof((_heap)->data[0]) /** * struct min_heap_callbacks - Data/functions to customise the min_heap. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { bool (*less)(const void *lhs, const void *rhs, void *args); void (*swp)(void *lhs, void *rhs, void *args); }; /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static __always_inline void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static __always_inline void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static __always_inline void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0) #define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1) #define SWAP_BYTES ((void (*)(void *, void *, void *))2) /* * Selects the appropriate swap function based on the element size. */ static __always_inline void *select_swap_func(const void *base, size_t size) { if (is_aligned(base, size, 8)) return SWAP_WORDS_64; else if (is_aligned(base, size, 4)) return SWAP_WORDS_32; else return SWAP_BYTES; } static __always_inline void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args), void *priv) { if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /* Initialize a min-heap. */ static __always_inline void __min_heap_init_inline(min_heap_char *heap, void *data, int size) { heap->nr = 0; heap->size = size; if (data) heap->data = data; else heap->data = heap->preallocated; } #define min_heap_init_inline(_heap, _data, _size) \ __min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) /* Get the minimum element from the heap. */ static __always_inline void *__min_heap_peek_inline(struct min_heap_char *heap) { return heap->nr ? heap->data : NULL; } #define min_heap_peek_inline(_heap) \ (__minheap_cast(_heap) \ __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr))) /* Check if the heap is full. */ static __always_inline bool __min_heap_full_inline(min_heap_char *heap) { return heap->nr == heap->size; } #define min_heap_full_inline(_heap) \ __min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr)) /* Sift the element at pos down the heap. */ static __always_inline void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size, const struct min_heap_callbacks *func, void *args) { const unsigned long lsbit = elem_size & -elem_size; void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; /* pre-scale counters for performance */ size_t a = pos * elem_size; size_t b, c, d; size_t n = heap->nr * elem_size; if (!swp) swp = select_swap_func(data, elem_size); /* Find the sift-down path all the way to the leaves. */ for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;) b = func->less(data + c, data + d, args) ? c : d; /* Special case for the last leaf with no sibling. */ if (d == n) b = c; /* Backtrack to the correct location. */ while (b != a && func->less(data + a, data + b, args)) b = parent(b, lsbit, elem_size); /* Shift the element into its correct place. */ c = b; while (b != a) { b = parent(b, lsbit, elem_size); do_swap(data + b, data + c, elem_size, swp, args); } } #define min_heap_sift_down_inline(_heap, _pos, _func, _args) \ __min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ __minheap_obj_size(_heap), _func, _args) /* Sift up ith element from the heap, O(log2(nr)). */ static __always_inline void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args) { const unsigned long lsbit = elem_size & -elem_size; void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; /* pre-scale counters for performance */ size_t a = idx * elem_size, b; if (!swp) swp = select_swap_func(data, elem_size); while (a) { b = parent(a, lsbit, elem_size); if (func->less(data + b, data + a, args)) break; do_swap(data + a, data + b, elem_size, swp, args); a = b; } } #define min_heap_sift_up_inline(_heap, _idx, _func, _args) \ __min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) /* Floyd's approach to heapification that is O(nr). */ static __always_inline void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) __min_heap_sift_down_inline(heap, i, elem_size, func, args); } #define min_heapify_all_inline(_heap, _func, _args) \ __min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return false; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; memcpy(data, data + (heap->nr * elem_size), elem_size); __min_heap_sift_down_inline(heap, 0, elem_size, func, args); return true; } #define min_heap_pop_inline(_heap, _func, _args) \ __min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args) { memcpy(heap->data, element, elem_size); __min_heap_sift_down_inline(heap, 0, elem_size, func, args); } #define min_heap_pop_push_inline(_heap, _element, _func, _args) \ __min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) /* Push an element on to the heap, O(log2(nr)). */ static __always_inline bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) return false; /* Place at the end of data. */ pos = heap->nr; memcpy(data + (pos * elem_size), element, elem_size); heap->nr++; /* Sift child at pos up. */ __min_heap_sift_up_inline(heap, elem_size, pos, func, args); return true; } #define min_heap_push_inline(_heap, _element, _func, _args) \ __min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) /* Remove ith element from the heap, O(log2(nr)). */ static __always_inline bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return false; if (!swp) swp = select_swap_func(data, elem_size); /* Place last element at the root (position 0) and then sift down. */ heap->nr--; if (idx == heap->nr) return true; do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args); __min_heap_sift_up_inline(heap, elem_size, idx, func, args); __min_heap_sift_down_inline(heap, idx, elem_size, func, args); return true; } #define min_heap_del_inline(_heap, _idx, _func, _args) \ __min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) void __min_heap_init(min_heap_char *heap, void *data, int size); void *__min_heap_peek(struct min_heap_char *heap); bool __min_heap_full(min_heap_char *heap); void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, const struct min_heap_callbacks *func, void *args); void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); void __min_heapify_all(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_pop(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args); void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); #define min_heap_init(_heap, _data, _size) \ __min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) #define min_heap_peek(_heap) \ (__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr))) #define min_heap_full(_heap) \ __min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr)) #define min_heap_sift_down(_heap, _pos, _func, _args) \ __min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_sift_up(_heap, _idx, _func, _args) \ __min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) #define min_heapify_all(_heap, _func, _args) \ __min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) #define min_heap_pop(_heap, _func, _args) \ __min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) #define min_heap_pop_push(_heap, _element, _func, _args) \ __min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_push(_heap, _element, _func, _args) \ __min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_del(_heap, _idx, _func, _args) \ __min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) #endif /* _LINUX_MIN_HEAP_H */ |
| 764 712 306 766 9 2 527 522 19 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> #include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline const seqcount_t * \ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lockbase##_lock(s->lock)); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(s->lock)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop, \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr)(s) #define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s) #define seqprop_sequence(s) __seqprop(s, sequence)(s) #define seqprop_preemptible(s) __seqprop(s, preemptible)(s) #define seqprop_assert(s) __seqprop(s, assert)(s) /** * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while (unlikely((__seq = seqprop_sequence(s)) & 1)) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_try_begin() - begin a seqcount_t read critical section * w/o lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count to be passed to read_seqcount_retry() * * Similar to raw_seqcount_begin(), except it enables eliding the critical * section entirely if odd, instead of doing the speculation knowing it will * fail. * * Useful when counter stabilization is more or less equivalent to taking * the lock and there is a slowpath that does that. * * If true, start will be set to the (even) sequence count read. * * Return: true when a read critical section is started. */ #define raw_seqcount_try_begin(s, start) \ ({ \ start = raw_read_seqcount(s); \ !(start & 1); \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_begin() */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_end() */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst * Context: check write_seqcount_begin() */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: sequence counter write side sections must be serialized and * non-preemptible. Preemption will be automatically disabled if and * only if the seqcount write serialization lock is associated, and * preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: Preemption will be automatically re-enabled if and only if * the seqcount write serialization lock is associated, and preemptible. */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before nor after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with raw_read_seqcount_latch_retry(). */ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See write_seqcount_latch() for details and a full reader/writer usage * example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) { kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return raw_read_seqcount_latch(s); } /** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { smp_rmb(); return unlikely(READ_ONCE(s->seqcount.sequence) != start); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { kcsan_atomic_next(0); return raw_read_seqcount_latch_retry(s, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t */ static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /** * write_seqcount_latch_begin() - redirect latch readers to odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { kcsan_nestable_atomic_begin(); raw_write_seqcount_latch(s); } /** * write_seqcount_latch() - redirect latch readers to even copy * @s: Pointer to seqcount_latch_t */ static __always_inline void write_seqcount_latch(seqcount_latch_t *s) { raw_write_seqcount_latch(s); } /** * write_seqcount_latch_end() - end a seqcount_latch_t write section * @s: Pointer to seqcount_latch_t * * Marks the end of a seqcount_latch_t writer section, after all copies of the * latch-protected data have been updated. */ static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) { kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 976 29 955 998 36 35 995 998 995 192 190 1 190 996 995 190 978 996 994 994 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/util.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/slab.h> #include <linux/rculist.h> #include "common.h" /* Lock for protecting policy. */ DEFINE_MUTEX(tomoyo_policy_lock); /* Has /sbin/init started? */ bool tomoyo_policy_loaded; /* * Mapping table from "enum tomoyo_mac_index" to * "enum tomoyo_mac_category_index". */ const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_OPEN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CREATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UNLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_GETATTR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RMDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKFIFO] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKSOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_TRUNCATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_SYMLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKBLOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKCHAR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_LINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RENAME] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHMOD] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHOWN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHGRP] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_IOCTL] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHROOT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UMOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE, /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = TOMOYO_MAC_CATEGORY_MISC, }; /** * tomoyo_convert_time - Convert time_t to YYYY/MM/DD hh/mm/ss. * * @time64: Seconds since 1970/01/01 00:00:00. * @stamp: Pointer to "struct tomoyo_time". * * Returns nothing. */ void tomoyo_convert_time(time64_t time64, struct tomoyo_time *stamp) { struct tm tm; time64_to_tm(time64, 0, &tm); stamp->sec = tm.tm_sec; stamp->min = tm.tm_min; stamp->hour = tm.tm_hour; stamp->day = tm.tm_mday; stamp->month = tm.tm_mon + 1; stamp->year = tm.tm_year + 1900; } /** * tomoyo_permstr - Find permission keywords. * * @string: String representation for permissions in foo/bar/buz format. * @keyword: Keyword to find from @string/ * * Returns true if @keyword was found in @string, false otherwise. * * This function assumes that strncmp(w1, w2, strlen(w1)) != 0 if w1 != w2. */ bool tomoyo_permstr(const char *string, const char *keyword) { const char *cp = strstr(string, keyword); if (cp) return cp == string || *(cp - 1) == '/'; return false; } /** * tomoyo_read_token - Read a word from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a word on success, "" otherwise. * * To allow the caller to skip NULL check, this function returns "" rather than * NULL if there is no more words to read. */ char *tomoyo_read_token(struct tomoyo_acl_param *param) { char *pos = param->data; char *del = strchr(pos, ' '); if (del) *del++ = '\0'; else del = pos + strlen(pos); param->data = del; return pos; } static bool tomoyo_correct_path2(const char *filename, const size_t len); /** * tomoyo_get_domainname - Read a domainname from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a domainname on success, NULL otherwise. */ const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param) { char *start = param->data; char *pos = start; while (*pos) { if (*pos++ != ' ' || tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos)) continue; *(pos - 1) = '\0'; break; } param->data = pos; if (tomoyo_correct_domain(start)) return tomoyo_get_name(start); return NULL; } /** * tomoyo_parse_ulong - Parse an "unsigned long" value. * * @result: Pointer to "unsigned long". * @str: Pointer to string to parse. * * Returns one of values in "enum tomoyo_value_type". * * The @src is updated to point the first character after the value * on success. */ u8 tomoyo_parse_ulong(unsigned long *result, char **str) { const char *cp = *str; char *ep; int base = 10; if (*cp == '0') { char c = *(cp + 1); if (c == 'x' || c == 'X') { base = 16; cp += 2; } else if (c >= '0' && c <= '7') { base = 8; cp++; } } *result = simple_strtoul(cp, &ep, base); if (cp == ep) return TOMOYO_VALUE_TYPE_INVALID; *str = ep; switch (base) { case 16: return TOMOYO_VALUE_TYPE_HEXADECIMAL; case 8: return TOMOYO_VALUE_TYPE_OCTAL; default: return TOMOYO_VALUE_TYPE_DECIMAL; } } /** * tomoyo_print_ulong - Print an "unsigned long" value. * * @buffer: Pointer to buffer. * @buffer_len: Size of @buffer. * @value: An "unsigned long" value. * @type: Type of @value. * * Returns nothing. */ void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type) { if (type == TOMOYO_VALUE_TYPE_DECIMAL) snprintf(buffer, buffer_len, "%lu", value); else if (type == TOMOYO_VALUE_TYPE_OCTAL) snprintf(buffer, buffer_len, "0%lo", value); else if (type == TOMOYO_VALUE_TYPE_HEXADECIMAL) snprintf(buffer, buffer_len, "0x%lX", value); else snprintf(buffer, buffer_len, "type(%u)", type); } /** * tomoyo_parse_name_union - Parse a tomoyo_name_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr) { char *filename; if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_PATH_GROUP); return ptr->group != NULL; } filename = tomoyo_read_token(param); if (!tomoyo_correct_word(filename)) return false; ptr->filename = tomoyo_get_name(filename); return ptr->filename != NULL; } /** * tomoyo_parse_number_union - Parse a tomoyo_number_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr) { char *data; u8 type; unsigned long v; memset(ptr, 0, sizeof(*ptr)); if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_NUMBER_GROUP); return ptr->group != NULL; } data = tomoyo_read_token(param); type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID) return false; ptr->values[0] = v; ptr->value_type[0] = type; if (!*data) { ptr->values[1] = v; ptr->value_type[1] = type; return true; } if (*data++ != '-') return false; type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID || *data || ptr->values[0] > v) return false; ptr->values[1] = v; ptr->value_type[1] = type; return true; } /** * tomoyo_byte_range - Check whether the string is a \ooo style octal value. * * @str: Pointer to the string. * * Returns true if @str is a \ooo style octal value, false otherwise. * * TOMOYO uses \ooo style representation for 0x01 - 0x20 and 0x7F - 0xFF. * This function verifies that \ooo is in valid range. */ static inline bool tomoyo_byte_range(const char *str) { return *str >= '0' && *str++ <= '3' && *str >= '0' && *str++ <= '7' && *str >= '0' && *str <= '7'; } /** * tomoyo_alphabet_char - Check whether the character is an alphabet. * * @c: The character to check. * * Returns true if @c is an alphabet character, false otherwise. */ static inline bool tomoyo_alphabet_char(const char c) { return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); } /** * tomoyo_make_byte - Make byte value from three octal characters. * * @c1: The first character. * @c2: The second character. * @c3: The third character. * * Returns byte value. */ static inline u8 tomoyo_make_byte(const u8 c1, const u8 c2, const u8 c3) { return ((c1 - '0') << 6) + ((c2 - '0') << 3) + (c3 - '0'); } /** * tomoyo_valid - Check whether the character is a valid char. * * @c: The character to check. * * Returns true if @c is a valid character, false otherwise. */ static inline bool tomoyo_valid(const unsigned char c) { return c > ' ' && c < 127; } /** * tomoyo_invalid - Check whether the character is an invalid char. * * @c: The character to check. * * Returns true if @c is an invalid character, false otherwise. */ static inline bool tomoyo_invalid(const unsigned char c) { return c && (c <= ' ' || c >= 127); } /** * tomoyo_str_starts - Check whether the given string starts with the given keyword. * * @src: Pointer to pointer to the string. * @find: Pointer to the keyword. * * Returns true if @src starts with @find, false otherwise. * * The @src is updated to point the first character after the @find * if @src starts with @find. */ bool tomoyo_str_starts(char **src, const char *find) { const int len = strlen(find); char *tmp = *src; if (strncmp(tmp, find, len)) return false; tmp += len; *src = tmp; return true; } /** * tomoyo_normalize_line - Format string. * * @buffer: The line to normalize. * * Leading and trailing whitespaces are removed. * Multiple whitespaces are packed into single space. * * Returns nothing. */ void tomoyo_normalize_line(unsigned char *buffer) { unsigned char *sp = buffer; unsigned char *dp = buffer; bool first = true; while (tomoyo_invalid(*sp)) sp++; while (*sp) { if (!first) *dp++ = ' '; first = false; while (tomoyo_valid(*sp)) *dp++ = *sp++; while (tomoyo_invalid(*sp)) sp++; } *dp = '\0'; } /** * tomoyo_correct_word2 - Validate a string. * * @string: The string to check. Maybe non-'\0'-terminated. * @len: Length of @string. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ static bool tomoyo_correct_word2(const char *string, size_t len) { u8 recursion = 20; const char *const start = string; bool in_repetition = false; if (!len) goto out; while (len--) { unsigned char c = *string++; if (c == '\\') { if (!len--) goto out; c = *string++; if (c >= '0' && c <= '3') { unsigned char d; unsigned char e; if (!len-- || !len--) goto out; d = *string++; e = *string++; if (d < '0' || d > '7' || e < '0' || e > '7') goto out; c = tomoyo_make_byte(c, d, e); if (c <= ' ' || c >= 127) continue; goto out; } switch (c) { case '\\': /* "\\" */ case '+': /* "\+" */ case '?': /* "\?" */ case 'x': /* "\x" */ case 'a': /* "\a" */ case '-': /* "\-" */ continue; } if (!recursion--) goto out; switch (c) { case '*': /* "\*" */ case '@': /* "\@" */ case '$': /* "\$" */ case 'X': /* "\X" */ case 'A': /* "\A" */ continue; case '{': /* "/\{" */ if (string - 3 < start || *(string - 3) != '/') goto out; in_repetition = true; continue; case '}': /* "\}/" */ if (*string != '/') goto out; if (!in_repetition) goto out; in_repetition = false; continue; } goto out; } else if (in_repetition && c == '/') { goto out; } else if (c <= ' ' || c >= 127) { goto out; } } if (in_repetition) goto out; return true; out: return false; } /** * tomoyo_correct_word - Validate a string. * * @string: The string to check. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ bool tomoyo_correct_word(const char *string) { return tomoyo_correct_word2(string, strlen(string)); } /** * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules. * * @filename: The pathname to check. * @len: Length of @filename. * * Returns true if @filename follows the naming rules, false otherwise. */ static bool tomoyo_correct_path2(const char *filename, const size_t len) { const char *cp1 = memchr(filename, '/', len); const char *cp2 = memchr(filename, '.', len); return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len); } /** * tomoyo_correct_path - Validate a pathname. * * @filename: The pathname to check. * * Check whether the given pathname follows the naming rules. * Returns true if @filename follows the naming rules, false otherwise. */ bool tomoyo_correct_path(const char *filename) { return tomoyo_correct_path2(filename, strlen(filename)); } /** * tomoyo_correct_domain - Check whether the given domainname follows the naming rules. * * @domainname: The domainname to check. * * Returns true if @domainname follows the naming rules, false otherwise. */ bool tomoyo_correct_domain(const unsigned char *domainname) { if (!domainname || !tomoyo_domain_def(domainname)) return false; domainname = strchr(domainname, ' '); if (!domainname++) return true; while (1) { const unsigned char *cp = strchr(domainname, ' '); if (!cp) break; if (!tomoyo_correct_path2(domainname, cp - domainname)) return false; domainname = cp + 1; } return tomoyo_correct_path(domainname); } /** * tomoyo_domain_def - Check whether the given token can be a domainname. * * @buffer: The token to check. * * Returns true if @buffer possibly be a domainname, false otherwise. */ bool tomoyo_domain_def(const unsigned char *buffer) { const unsigned char *cp; int len; if (*buffer != '<') return false; cp = strchr(buffer, ' '); if (!cp) len = strlen(buffer); else len = cp - buffer; if (buffer[len - 1] != '>' || !tomoyo_correct_word2(buffer + 1, len - 2)) return false; return true; } /** * tomoyo_find_domain - Find a domain by the given name. * * @domainname: The domainname to find. * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; } return NULL; } /** * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token. * * @filename: The string to evaluate. * * Returns the initial length without a pattern in @filename. */ static int tomoyo_const_part_length(const char *filename) { char c; int len = 0; if (!filename) return 0; while ((c = *filename++) != '\0') { if (c != '\\') { len++; continue; } c = *filename++; switch (c) { case '\\': /* "\\" */ len += 2; continue; case '0': /* "\ooo" */ case '1': case '2': case '3': c = *filename++; if (c < '0' || c > '7') break; c = *filename++; if (c < '0' || c > '7') break; len += 4; continue; } break; } return len; } /** * tomoyo_fill_path_info - Fill in "struct tomoyo_path_info" members. * * @ptr: Pointer to "struct tomoyo_path_info" to fill in. * * The caller sets "struct tomoyo_path_info"->name. */ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) { const char *name = ptr->name; const int len = strlen(name); ptr->const_len = tomoyo_const_part_length(name); ptr->is_dir = len && (name[len - 1] == '/'); ptr->is_patterned = (ptr->const_len < len); ptr->hash = full_name_hash(NULL, name, len); } /** * tomoyo_file_matches_pattern2 - Pattern matching without '/' character and "\-" pattern. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern2(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { while (filename < filename_end && pattern < pattern_end) { char c; int i; int j; if (*pattern != '\\') { if (*filename++ != *pattern++) return false; continue; } c = *filename; pattern++; switch (*pattern) { case '?': if (c == '/') { return false; } else if (c == '\\') { if (filename[1] == '\\') filename++; else if (tomoyo_byte_range(filename + 1)) filename += 3; else return false; } break; case '\\': if (c != '\\') return false; if (*++filename != '\\') return false; break; case '+': if (!isdigit(c)) return false; break; case 'x': if (!isxdigit(c)) return false; break; case 'a': if (!tomoyo_alphabet_char(c)) return false; break; case '0': case '1': case '2': case '3': if (c == '\\' && tomoyo_byte_range(filename + 1) && strncmp(filename + 1, pattern, 3) == 0) { filename += 3; pattern += 2; break; } return false; /* Not matched. */ case '*': case '@': for (i = 0; i <= filename_end - filename; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; c = filename[i]; if (c == '.' && *pattern == '@') break; if (c != '\\') continue; if (filename[i + 1] == '\\') i++; else if (tomoyo_byte_range(filename + i + 1)) i += 3; else break; /* Bad pattern. */ } return false; /* Not matched. */ default: j = 0; c = *pattern; if (c == '$') { while (isdigit(filename[j])) j++; } else if (c == 'X') { while (isxdigit(filename[j])) j++; } else if (c == 'A') { while (tomoyo_alphabet_char(filename[j])) j++; } for (i = 1; i <= j; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; } return false; /* Not matched or bad pattern. */ } filename++; pattern++; } while (*pattern == '\\' && (*(pattern + 1) == '*' || *(pattern + 1) == '@')) pattern += 2; return filename == filename_end && pattern == pattern_end; } /** * tomoyo_file_matches_pattern - Pattern matching without '/' character. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { const char *pattern_start = pattern; bool first = true; bool result; while (pattern < pattern_end - 1) { /* Split at "\-" pattern. */ if (*pattern++ != '\\' || *pattern++ != '-') continue; result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern - 2); if (first) result = !result; if (result) return false; first = false; pattern_start = pattern; } result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern_end); return first ? result : !result; } /** * tomoyo_path_matches_pattern2 - Do pathname pattern matching. * * @f: The start of string to check. * @p: The start of pattern to compare. * * Returns true if @f matches @p, false otherwise. */ static bool tomoyo_path_matches_pattern2(const char *f, const char *p) { const char *f_delimiter; const char *p_delimiter; while (*f && *p) { f_delimiter = strchr(f, '/'); if (!f_delimiter) f_delimiter = f + strlen(f); p_delimiter = strchr(p, '/'); if (!p_delimiter) p_delimiter = p + strlen(p); if (*p == '\\' && *(p + 1) == '{') goto recursive; if (!tomoyo_file_matches_pattern(f, f_delimiter, p, p_delimiter)) return false; f = f_delimiter; if (*f) f++; p = p_delimiter; if (*p) p++; } /* Ignore trailing "\*" and "\@" in @pattern. */ while (*p == '\\' && (*(p + 1) == '*' || *(p + 1) == '@')) p += 2; return !*f && !*p; recursive: /* * The "\{" pattern is permitted only after '/' character. * This guarantees that below "*(p - 1)" is safe. * Also, the "\}" pattern is permitted only before '/' character * so that "\{" + "\}" pair will not break the "\-" operator. */ if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' || *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\') return false; /* Bad pattern. */ do { /* Compare current component with pattern. */ if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2, p_delimiter - 2)) break; /* Proceed to next component. */ f = f_delimiter; if (!*f) break; f++; /* Continue comparison. */ if (tomoyo_path_matches_pattern2(f, p_delimiter + 1)) return true; f_delimiter = strchr(f, '/'); } while (f_delimiter); return false; /* Not matched. */ } /** * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern. * * @filename: The filename to check. * @pattern: The pattern to compare. * * Returns true if matches, false otherwise. * * The following patterns are available. * \\ \ itself. * \ooo Octal representation of a byte. * \* Zero or more repetitions of characters other than '/'. * \@ Zero or more repetitions of characters other than '/' or '.'. * \? 1 byte character other than '/'. * \$ One or more repetitions of decimal digits. * \+ 1 decimal digit. * \X One or more repetitions of hexadecimal digits. * \x 1 hexadecimal digit. * \A One or more repetitions of alphabet characters. * \a 1 alphabet character. * * \- Subtraction operator. * * /\{dir\}/ '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/ * /dir/dir/dir/ ). */ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern) { const char *f = filename->name; const char *p = pattern->name; const int len = pattern->const_len; /* If @pattern doesn't contain pattern, I can use strcmp(). */ if (!pattern->is_patterned) return !tomoyo_pathcmp(filename, pattern); /* Don't compare directory and non-directory. */ if (filename->is_dir != pattern->is_dir) return false; /* Compare the initial length without patterns. */ if (strncmp(f, p, len)) return false; f += len; p += len; return tomoyo_path_matches_pattern2(f, p); } /** * tomoyo_get_exe - Get tomoyo_realpath() of current process. * * Returns the tomoyo_realpath() of current process on success, NULL otherwise. * * This function uses kzalloc(), so the caller must call kfree() * if this function didn't return NULL. */ const char *tomoyo_get_exe(void) { struct file *exe_file; const char *cp; struct mm_struct *mm = current->mm; if (!mm) return NULL; exe_file = get_mm_exe_file(mm); if (!exe_file) return NULL; cp = tomoyo_realpath_from_path(&exe_file->f_path); fput(exe_file); return cp; } /** * tomoyo_get_mode - Get MAC mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * * Returns mode. */ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index) { u8 mode; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return TOMOYO_CONFIG_DISABLED; p = tomoyo_profile(ns, profile); mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; return mode & 3; } /** * tomoyo_init_request_info - Initialize "struct tomoyo_request_info" members. * * @r: Pointer to "struct tomoyo_request_info" to initialize. * @domain: Pointer to "struct tomoyo_domain_info". NULL for tomoyo_domain(). * @index: Index number of functionality. * * Returns mode. */ int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index) { u8 profile; memset(r, 0, sizeof(*r)); if (!domain) domain = tomoyo_domain(); r->domain = domain; profile = domain->profile; r->profile = profile; r->type = index; r->mode = tomoyo_get_mode(domain->ns, profile, index); return r->mode; } /** * tomoyo_domain_quota_is_ok - Check for domain's quota. * * @r: Pointer to "struct tomoyo_request_info". * * Returns true if the domain is not exceeded quota, false otherwise. * * Caller holds tomoyo_read_lock(). */ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) { unsigned int count = 0; struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; if (r->mode != TOMOYO_CONFIG_LEARNING) return false; if (!domain) return true; if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED])) return false; list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, srcu_read_lock_held(&tomoyo_ss)) { u16 perm; if (ptr->is_deleted) continue; /* * Reading perm bitmap might race with tomoyo_merge_*() because * caller does not hold tomoyo_policy_lock mutex. But exceeding * max_learning_entry parameter by a few entries does not harm. */ switch (ptr->type) { case TOMOYO_TYPE_PATH_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm); break; case TOMOYO_TYPE_PATH2_ACL: perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm); break; case TOMOYO_TYPE_PATH_NUMBER_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head) ->perm); break; case TOMOYO_TYPE_MKDEV_ACL: perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm); break; case TOMOYO_TYPE_INET_ACL: perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm); break; case TOMOYO_TYPE_UNIX_ACL: perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm); break; case TOMOYO_TYPE_MANUAL_TASK_ACL: perm = 0; break; default: perm = 1; } count += hweight16(perm); } if (count < tomoyo_profile(domain->ns, domain->profile)-> pref[TOMOYO_PREF_MAX_LEARNING_ENTRY]) return true; WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true); /* r->granted = false; */ tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]); #ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n", domain->domainname->name); #endif return false; } |
| 11 263 | 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> |
| 779 779 137 781 24 24 21 24 24 24 21 21 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * Add to a counter while respecting batch size. * * There are 2 implementations, both dealing with the following problem: * * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ #ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* * Safety against interrupts is achieved in 2 ways: * 1. the fast path uses local cmpxchg (note: no lock prefix) * 2. the slow path operates with interrupts disabled */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; count = this_cpu_read(*fbc->counters); do { if (unlikely(abs(count + amount) >= batch)) { raw_spin_lock_irqsave(&fbc->lock, flags); /* * Note: by now we might have migrated to another CPU * or the value might have changed. */ count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); return; } } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); } #else /* * local_irq_save() is used to make the function irq safe: * - The slow path would be ok as protected by an irq-safe spinlock. * - this_cpu_add would be ok as it is irq-safe by definition. */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; local_irq_save(flags); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { raw_spin_lock(&fbc->lock); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock(&fbc->lock); } else { this_cpu_add(*fbc->counters, amount); } local_irq_restore(flags); } #endif EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). * * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums * from CPUs that are in the process of being taken offline. Dying cpus have * been removed from the online mask, but may not have had the hotplug dead * notifier called to fold the percpu count back into the global counter sum. * By including dying CPUs in the iteration mask, we avoid this race condition * so __percpu_counter_sum() just does the right thing when CPUs are being taken * offline. */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key) { unsigned long flags __maybe_unused; size_t counter_size; s32 __percpu *counters; u32 i; counter_size = ALIGN(sizeof(*counters), __alignof__(*counters)); counters = __alloc_percpu_gfp(nr_counters * counter_size, __alignof__(*counters), gfp); if (!counters) { fbc[0].counters = NULL; return -ENOMEM; } for (i = 0; i < nr_counters; i++) { raw_spin_lock_init(&fbc[i].lock); lockdep_set_class(&fbc[i].lock, key); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; fbc[i].counters = (void __percpu *)counters + i * counter_size; debug_percpu_counter_activate(&fbc[i]); } #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_add(&fbc[i].list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init_many); void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { unsigned long flags __maybe_unused; u32 i; if (WARN_ON_ONCE(!fbc)) return; if (!fbc[0].counters) return; for (i = 0; i < nr_counters; i++) debug_percpu_counter_deactivate(&fbc[i]); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_del(&fbc[i].list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc[0].counters); for (i = 0; i < nr_counters; i++) fbc[i].counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy_many); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); /* * Compare counter, and add amount if total is: less than or equal to limit if * amount is positive, or greater than or equal to limit if amount is negative. * Return true if amount is added, or false if total would be beyond the limit. * * Negative limit is allowed, but unusual. * When negative amounts (subs) are given to percpu_counter_limited_add(), * the limit would most naturally be 0 - but other limits are also allowed. * * Overflow beyond S64_MAX is not allowed for: counter, limit and amount * are all assumed to be sane (far from S64_MIN and S64_MAX). */ bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch) { s64 count; s64 unknown; unsigned long flags; bool good = false; if (amount == 0) return true; local_irq_save(flags); unknown = batch * num_online_cpus(); count = __this_cpu_read(*fbc->counters); /* Skip taking the lock when safe */ if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) || (amount < 0 && fbc->count - unknown >= limit))) { this_cpu_add(*fbc->counters, amount); local_irq_restore(flags); return true; } raw_spin_lock(&fbc->lock); count = fbc->count + amount; /* Skip percpu_counter_sum() when safe */ if (amount > 0) { if (count - unknown > limit) goto out; if (count + unknown <= limit) good = true; } else { if (count + unknown < limit) goto out; if (count - unknown >= limit) good = true; } if (!good) { s32 *pcount; int cpu; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { pcount = per_cpu_ptr(fbc->counters, cpu); count += *pcount; } if (amount > 0) { if (count > limit) goto out; } else { if (count < limit) goto out; } good = true; } count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); out: raw_spin_unlock(&fbc->lock); local_irq_restore(flags); return good; } static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 513 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2005-2010 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm.h */ #ifndef __INTEGRITY_EVM_H #define __INTEGRITY_EVM_H #include <linux/xattr.h> #include <linux/security.h> #include "../integrity.h" #define EVM_INIT_HMAC 0x0001 #define EVM_INIT_X509 0x0002 #define EVM_ALLOW_METADATA_WRITES 0x0004 #define EVM_SETUP_COMPLETE 0x80000000 /* userland has signaled key load */ #define EVM_KEY_MASK (EVM_INIT_HMAC | EVM_INIT_X509) #define EVM_INIT_MASK (EVM_INIT_HMAC | EVM_INIT_X509 | EVM_SETUP_COMPLETE | \ EVM_ALLOW_METADATA_WRITES) struct xattr_list { struct list_head list; char *name; bool enabled; }; #define EVM_NEW_FILE 0x00000001 #define EVM_IMMUTABLE_DIGSIG 0x00000002 /* EVM integrity metadata associated with an inode */ struct evm_iint_cache { unsigned long flags; enum integrity_status evm_status:4; struct integrity_inode_attributes metadata_inode; }; extern struct lsm_blob_sizes evm_blob_sizes; static inline struct evm_iint_cache *evm_iint_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + evm_blob_sizes.lbs_inode; } extern int evm_initialized; #define EVM_ATTR_FSUUID 0x0001 extern int evm_hmac_attrs; /* List of EVM protected security xattrs */ extern struct list_head evm_config_xattrnames; struct evm_digest { struct ima_digest_data_hdr hdr; char digest[IMA_MAX_DIGEST_SIZE]; } __packed; int evm_protected_xattr(const char *req_xattr_name); int evm_init_key(void); int evm_update_evmxattr(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len); int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, struct evm_digest *data, struct evm_iint_cache *iint); int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, char type, struct evm_digest *data, struct evm_iint_cache *iint); int evm_init_hmac(struct inode *inode, const struct xattr *xattrs, char *hmac_val); int evm_init_secfs(void); #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM notifier #if !defined(_TRACE_NOTIFIERS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NOTIFIERS_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(notifier_info, TP_PROTO(void *cb), TP_ARGS(cb), TP_STRUCT__entry( __field(void *, cb) ), TP_fast_assign( __entry->cb = cb; ), TP_printk("%ps", __entry->cb) ); /* * notifier_register - called upon notifier callback registration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_register, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_unregister - called upon notifier callback unregistration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_unregister, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_run - called upon notifier callback execution * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_run, TP_PROTO(void *cb), TP_ARGS(cb) ); #endif /* _TRACE_NOTIFIERS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 497 495 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 296 297 297 255 296 297 3 297 297 297 297 296 297 296 296 297 309 309 21 21 21 21 21 21 21 27 297 297 29 29 29 308 309 307 309 285 250 309 309 88 108 27 88 296 308 309 309 297 297 297 11 296 296 297 88 296 87 296 295 297 297 297 297 259 267 297 297 297 297 297 297 296 296 296 27 27 27 27 27 27 2 2 2 26 27 27 297 297 296 27 30 9 27 22 27 26 27 66 297 296 255 255 1 297 297 296 2 297 296 297 296 296 297 297 297 297 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 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 | // 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 (unlikely(!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. */ 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_size(va); 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_size(va); 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) { LIST_HEAD(decay_list); struct rb_root decay_root = RB_ROOT; struct vmap_area *va, *nva; unsigned long n_decay; int i; for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { LIST_HEAD(tmp_list); if (list_empty(&vn->pool[i].head)) continue; /* 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 kasan_release_vmalloc_node(struct vmap_node *vn) { struct vmap_area *va; unsigned long start, end; start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; list_for_each_entry(va, &vn->purge_list, list) { if (is_vmalloc_or_module_addr((void *) va->va_start)) kasan_release_vmalloc(va->va_start, va->va_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE); } kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); } static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); unsigned long nr_purged_pages = 0; struct vmap_area *va, *n_va; LIST_HEAD(local_list); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_release_vmalloc_node(vn); vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = va_size(va) >> PAGE_SHIFT; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); nr_purged_pages += 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); } atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); 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_size(va) >> 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); vb->cpu = raw_smp_processor_id(); 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. */ 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_size(va)); 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 } unsigned int get_vm_area_page_order(struct vm_struct *vm) { return vm_area_page_order(vm); } 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; } 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); if (!(vm->flags & VM_MAP_PUT_PAGES)) 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(); } if (!(vm->flags & VM_MAP_PUT_PAGES)) 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; 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) { 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_mempolicy_noprof(gfp, nr_pages_request, pages + nr_allocated); else nr = alloc_pages_bulk_node_noprof(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; } } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(gfp, order); else page = alloc_pages_node_noprof(nid, gfp, order); if (unlikely(!page)) break; /* * High-order allocations must be able to be treated as * independent 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); /* * High-order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. * * Please note, the __vmalloc_node_range_noprof() falls-back * to order-0 pages if high-order attempt is unsuccessful. */ area->nr_pages = vm_area_alloc_pages((page_order ? gfp_mask & ~__GFP_NOFAIL : 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)) { /* * 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. */ if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) shift = PMD_SHIFT; else shift = arch_vmap_pte_supported_shift(size); 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); /** * vrealloc - reallocate virtually contiguous memory; contents remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @flags: the flags for the page level allocator * * If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and * @p is not a %NULL pointer, the object pointed to is freed. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or vfree() for the * same memory allocation. * * Return: pointer to the allocated memory; %NULL if @size is zero or in case of * failure */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { size_t old_size = 0; void *n; if (!size) { vfree(p); return NULL; } if (p) { struct vm_struct *vm; vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } old_size = get_vm_area_size(vm); } /* * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { /* Zero out spare memory. */ if (want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); kasan_poison_vmalloc(p + size, old_size - size); kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); return (void *)p; } /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ n = __vmalloc_noprof(size, flags); if (!n) return NULL; if (p) { memcpy(n, p, old_size); vfree(p); } return n; } #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, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); 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, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); 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_size(va)); } 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_size(va)); 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); } |
| 133 49 147 999 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifndef TIF_NEED_RESCHED_LAZY #ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY #error Inconsistent PREEMPT_LAZY #endif #define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_test_bit(int bit) { return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_test_bit(int bit) { return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ static __always_inline bool tif_need_resched(void) { return tif_test_bit(TIF_NEED_RESCHED); } #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 24 24 24 | 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 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2022 Linutronix GmbH, John Ogness // Copyright (C) 2022 Intel, Thomas Gleixner #include <linux/atomic.h> #include <linux/bug.h> #include <linux/console.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kthread.h> #include <linux/minmax.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include "internal.h" #include "printk_ringbuffer.h" /* * Printk console printing implementation for consoles which does not depend * on the legacy style console_lock mechanism. * * The state of the console is maintained in the "nbcon_state" atomic * variable. * * The console is locked when: * * - The 'prio' field contains the priority of the context that owns the * console. Only higher priority contexts are allowed to take over the * lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked. * * - The 'cpu' field denotes on which CPU the console is locked. It is used * to prevent busy waiting on the same CPU. Also it informs the lock owner * that it has lost the lock in a more complex scenario when the lock was * taken over by a higher priority context, released, and taken on another * CPU with the same priority as the interrupted owner. * * The acquire mechanism uses a few more fields: * * - The 'req_prio' field is used by the handover approach to make the * current owner aware that there is a context with a higher priority * waiting for the friendly handover. * * - The 'unsafe' field allows to take over the console in a safe way in the * middle of emitting a message. The field is set only when accessing some * shared resources or when the console device is manipulated. It can be * cleared, for example, after emitting one character when the console * device is in a consistent state. * * - The 'unsafe_takeover' field is set when a hostile takeover took the * console in an unsafe state. The console will stay in the unsafe state * until re-initialized. * * The acquire mechanism uses three approaches: * * 1) Direct acquire when the console is not owned or is owned by a lower * priority context and is in a safe state. * * 2) Friendly handover mechanism uses a request/grant handshake. It is used * when the current owner has lower priority and the console is in an * unsafe state. * * The requesting context: * * a) Sets its priority into the 'req_prio' field. * * b) Waits (with a timeout) for the owning context to unlock the * console. * * c) Takes the lock and clears the 'req_prio' field. * * The owning context: * * a) Observes the 'req_prio' field set on exit from the unsafe * console state. * * b) Gives up console ownership by clearing the 'prio' field. * * 3) Unsafe hostile takeover allows to take over the lock even when the * console is an unsafe state. It is used only in panic() by the final * attempt to flush consoles in a try and hope mode. * * Note that separate record buffers are used in panic(). As a result, * the messages can be read and formatted without any risk even after * using the hostile takeover in unsafe state. * * The release function simply clears the 'prio' field. * * All operations on @console::nbcon_state are atomic cmpxchg based to * handle concurrency. * * The acquire/release functions implement only minimal policies: * * - Preference for higher priority contexts. * - Protection of the panic CPU. * * All other policy decisions must be made at the call sites: * * - What is marked as an unsafe section. * - Whether to spin-wait if there is already an owner and the console is * in an unsafe state. * - Whether to attempt an unsafe hostile takeover. * * The design allows to implement the well known: * * acquire() * output_one_printk_record() * release() * * The output of one printk record might be interrupted with a higher priority * context. The new owner is supposed to reprint the entire interrupted record * from scratch. */ /** * nbcon_state_set - Helper function to set the console state * @con: Console to update * @new: The new state to write * * Only to be used when the console is not yet or no longer visible in the * system. Otherwise use nbcon_state_try_cmpxchg(). */ static inline void nbcon_state_set(struct console *con, struct nbcon_state *new) { atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom); } /** * nbcon_state_read - Helper function to read the console state * @con: Console to read * @state: The state to store the result */ static inline void nbcon_state_read(struct console *con, struct nbcon_state *state) { state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state)); } /** * nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state * @con: Console to update * @cur: Old/expected state * @new: New state * * Return: True on success. False on fail and @cur is updated. */ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur, struct nbcon_state *new) { return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of * * Return: Sequence number of the next record to print on @con. */ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); return __ulseq_to_u64seq(prb, nbcon_seq); } /** * nbcon_seq_force - Force console sequence to a specific value * @con: Console to work on * @seq: Sequence number value to set * * Only to be used during init (before registration) or in extreme situations * (such as panic with CONSOLE_REPLAY_ALL). */ void nbcon_seq_force(struct console *con, u64 seq) { /* * If the specified record no longer exists, the oldest available record * is chosen. This is especially important on 32bit systems because only * the lower 32 bits of the sequence number are stored. The upper 32 bits * are derived from the sequence numbers available in the ringbuffer. */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); } /** * nbcon_seq_try_update - Try to update the console sequence number * @ctxt: Pointer to an acquire context that contains * all information about the acquire mode * @new_seq: The new sequence number to set * * @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to * the 64bit value). This could be a different value than @new_seq if * nbcon_seq_force() was used or the current context no longer owns the * console. In the later case, it will stop printing anyway. */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); } } /** * nbcon_context_try_acquire_direct - Try to acquire directly * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console when it is released. Also acquire the console when * the current owner has a lower priority and the console is in a safe state. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or the current owner or waiter has the same or higher * priority. No acquire method can be successful in * this case. * * -EBUSY: The current owner has a lower priority but the console * in an unsafe state. The caller should try using * the handover acquire method. */ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; do { /* * Panic does not imply that the console is owned. However, it * is critical that non-panic CPUs during panic are unable to * acquire ownership in order to satisfy the assumptions of * nbcon_waiter_matches(). In particular, the assumption that * lower priorities are ignored during panic. */ if (other_cpu_in_panic()) return -EPERM; if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio) return -EPERM; if (cur->unsafe) return -EBUSY; /* * The console should never be safe for a direct acquire * if an unsafe hostile takeover has ever happened. */ WARN_ON_ONCE(cur->unsafe_takeover); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio) { /* * The request context is well defined by the @req_prio because: * * - Only a context with a priority higher than the owner can become * a waiter. * - Only a context with a priority higher than the waiter can * directly take over the request. * - There are only three priorities. * - Only one CPU is allowed to request PANIC priority. * - Lower priorities are ignored during panic() until reboot. * * As a result, the following scenario is *not* possible: * * 1. This context is currently a waiter. * 2. Another context with a higher priority than this context * directly takes ownership. * 3. The higher priority context releases the ownership. * 4. Another lower priority context takes the ownership. * 5. Another context with the same priority as this context * creates a request and starts waiting. * * Event #1 implies this context is EMERGENCY. * Event #2 implies the new context is PANIC. * Event #3 occurs when panic() has flushed the console. * Events #4 and #5 are not possible due to the other_cpu_in_panic() * check in nbcon_context_try_acquire_direct(). */ return (cur->req_prio == expected_prio); } /** * nbcon_context_try_acquire_requested - Try to acquire after having * requested a handover * @ctxt: The context of the caller * @cur: The current console state * * This is a helper function for nbcon_context_try_acquire_handover(). * It is called when the console is in an unsafe state. The current * owner will release the console on exit from the unsafe region. * * Return: 0 on success and @cur is updated to the new console state. * Otherwise an error code on failure. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU * or this context is no longer the waiter. * * -EBUSY: The console is still locked. The caller should * continue waiting. * * Note: The caller must still remove the request when an error has occurred * except when this context is no longer the waiter. */ static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; /* Note that the caller must still remove the request! */ if (other_cpu_in_panic()) return -EPERM; /* * Note that the waiter will also change if there was an unsafe * hostile takeover. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* If still locked, caller should continue waiting. */ if (cur->prio != NBCON_PRIO_NONE) return -EBUSY; /* * The previous owner should have never released ownership * in an unsafe region. */ WARN_ON_ONCE(cur->unsafe); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; if (!nbcon_state_try_cmpxchg(con, cur, &new)) { /* * The acquire could fail only when it has been taken * over by a higher priority context. */ WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio)); return -EPERM; } /* Handover success. This context now owns the console. */ return 0; } /** * nbcon_context_try_acquire_handover - Try to acquire via handover * @ctxt: The context of the caller * @cur: The current console state * * The function must be called only when the context has higher priority * than the current owner and the console is in an unsafe state. * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY. * * The function sets "req_prio" field to make the current owner aware of * the request. Then it waits until the current owner releases the console, * or an even higher context takes over the request, or timeout expires. * * The current owner checks the "req_prio" field on exit from the unsafe * region and releases the console. It does not touch the "req_prio" field * so that the console stays reserved for the waiter. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or a higher priority context has taken over the * console or the handover request. * * -EBUSY: The current owner is on the same CPU so that the hand * shake could not work. Or the current owner is not * willing to wait (zero timeout). Or the console does * not enter the safe state before timeout passed. The * caller might still use the unsafe hostile takeover * when allowed. * * -EAGAIN: @cur has changed when creating the handover request. * The caller should retry with direct acquire. */ static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; int timeout; int request_err = -EBUSY; /* * Check that the handover is called when the direct acquire failed * with -EBUSY. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(!cur->unsafe); /* Handover is not possible on the same CPU. */ if (cur->cpu == cpu) return -EBUSY; /* * Console stays unsafe after an unsafe takeover until re-initialized. * Waiting is not going to help in this case. */ if (cur->unsafe_takeover) return -EBUSY; /* Is the caller willing to wait? */ if (ctxt->spinwait_max_us == 0) return -EBUSY; /* * Setup a request for the handover. The caller should try to acquire * the console directly when the current state has been modified. */ new.atom = cur->atom; new.req_prio = ctxt->prio; if (!nbcon_state_try_cmpxchg(con, cur, &new)) return -EAGAIN; cur->atom = new.atom; /* Wait until there is no owner and then acquire the console. */ for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) { /* On successful acquire, this request is cleared. */ request_err = nbcon_context_try_acquire_requested(ctxt, cur); if (!request_err) return 0; /* * If the acquire should be aborted, it must be ensured * that the request is removed before returning to caller. */ if (request_err == -EPERM) break; udelay(1); /* Re-read the state because some time has passed. */ nbcon_state_read(con, cur); } /* Timed out or aborted. Carefully remove handover request. */ do { /* * No need to remove request if there is a new waiter. This * can only happen if a higher priority context has taken over * the console or the handover request. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* Unset request for handover. */ new.atom = cur->atom; new.req_prio = NBCON_PRIO_NONE; if (nbcon_state_try_cmpxchg(con, cur, &new)) { /* * Request successfully unset. Report failure of * acquiring via handover. */ cur->atom = new.atom; return request_err; } /* * Unable to remove request. Try to acquire in case * the owner has released the lock. */ } while (nbcon_context_try_acquire_requested(ctxt, cur)); /* Lucky timing. The acquire succeeded while removing the request. */ return 0; } /** * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console even in the unsafe state. * * It can be permitted by setting the 'allow_unsafe_takeover' field only * by the final attempt to flush messages in panic(). * * Return: 0 on success. -EPERM when not allowed by the context. */ static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; if (!ctxt->allow_unsafe_takeover) return -EPERM; /* Ensure caller is allowed to perform unsafe hostile takeovers. */ if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC)) return -EPERM; /* * Check that try_acquire_direct() and try_acquire_handover() returned * -EBUSY in the right situation. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(cur->unsafe != true); do { new.atom = cur->atom; new.cpu = cpu; new.prio = ctxt->prio; new.unsafe |= cur->unsafe_takeover; new.unsafe_takeover |= cur->unsafe; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static struct printk_buffers panic_nbcon_pbufs; /** * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the * caller should check the current console state to see if it is * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ static bool nbcon_context_try_acquire(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; int err; nbcon_state_read(con, &cur); try_again: err = nbcon_context_try_acquire_direct(ctxt, &cur); if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_handover(ctxt, &cur); if (err == -EAGAIN) goto try_again; if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_hostile(ctxt, &cur); out: if (err) return false; /* Acquire succeeded. */ /* Assign the appropriate buffer for this context. */ if (atomic_read(&panic_cpu) == cpu) ctxt->pbufs = &panic_nbcon_pbufs; else ctxt->pbufs = con->pbufs; /* Set the record sequence for this context to print. */ ctxt->seq = nbcon_seq_read(ctxt->console); return true; } static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu, int expected_prio) { /* * A similar function, nbcon_waiter_matches(), only deals with * EMERGENCY and PANIC priorities. However, this function must also * deal with the NORMAL priority, which requires additional checks * and constraints. * * For the case where preemption and interrupts are disabled, it is * enough to also verify that the owning CPU has not changed. * * For the case where preemption or interrupts are enabled, an * external synchronization method *must* be used. In particular, * the driver-specific locking mechanism used in device_lock() * (including disabling migration) should be used. It prevents * scenarios such as: * * 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and * is scheduled out. * 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY * and releases it. * 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X] * and is scheduled out. * 4. [Task A] gets running on [CPU X] and sees that the console is * still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus * [Task A] thinks it is the owner when it is not. */ if (cur->prio != expected_prio) return false; if (cur->cpu != expected_cpu) return false; return true; } /** * nbcon_context_release - Release the console * @ctxt: The nbcon context from nbcon_context_try_acquire() */ static void nbcon_context_release(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { if (!nbcon_owner_matches(&cur, cpu, ctxt->prio)) break; new.atom = cur.atom; new.prio = NBCON_PRIO_NONE; /* * If @unsafe_takeover is set, it is kept set so that * the state remains permanently unsafe. */ new.unsafe |= cur.unsafe_takeover; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); ctxt->pbufs = NULL; } /** * nbcon_context_can_proceed - Check whether ownership can proceed * @ctxt: The nbcon context from nbcon_context_try_acquire() * @cur: The current console state * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * Must be invoked when entering the unsafe state to make sure that it still * owns the lock. Also must be invoked when exiting the unsafe context * to eventually free the lock for a higher priority context which asked * for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe * state. * * Also it can be called in the safe context before doing an expensive * safe operation. It does not make sense to do the operation when * a higher priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); /* Make sure this context still owns the console. */ if (!nbcon_owner_matches(cur, cpu, ctxt->prio)) return false; /* The console owner can proceed if there is no waiter. */ if (cur->req_prio == NBCON_PRIO_NONE) return true; /* * A console owner within an unsafe region is always allowed to * proceed, even if there are waiters. It can perform a handover * when exiting the unsafe region. Otherwise the waiter will * need to perform an unsafe hostile takeover. */ if (cur->unsafe) return true; /* Waiters always have higher priorities than owners. */ WARN_ON_ONCE(cur->req_prio <= cur->prio); /* * Having a safe point for take over and eventually a few * duplicated characters or a full line is way better than a * hostile takeover. Post processing can take care of the garbage. * Release and hand over. */ nbcon_context_release(ctxt); /* * It is not clear whether the waiter really took over ownership. The * outermost callsite must make the final decision whether console * ownership is needed for it to proceed. If yes, it must reacquire * ownership (possibly hostile) before carefully proceeding. * * The calling context no longer owns the console so go back all the * way instead of trying to implement reacquire heuristics in tons of * places. */ return false; } /** * nbcon_can_proceed - Check whether ownership can proceed * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * It is used in nbcon_enter_unsafe() to make sure that it still owns the * lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock * for a higher priority context which asked for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe state. * * Also it can be called in the safe context before doing an expensive safe * operation. It does not make sense to do the operation when a higher * priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; nbcon_state_read(con, &cur); return nbcon_context_can_proceed(ctxt, &cur); } EXPORT_SYMBOL_GPL(nbcon_can_proceed); #define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true) #define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false) /** * __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state * @ctxt: The nbcon context from nbcon_context_try_acquire() * @unsafe: The new value for the unsafe bit * * Return: True if the unsafe state was updated and this context still * owns the console. Otherwise false if ownership was handed * over or taken. * * This function allows console owners to modify the unsafe status of the * console. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. * * Internal helper to avoid duplicated code. */ static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe) { struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { /* * The unsafe bit must not be cleared if an * unsafe hostile takeover has occurred. */ if (!unsafe && cur.unsafe_takeover) goto out; if (!nbcon_context_can_proceed(ctxt, &cur)) return false; new.atom = cur.atom; new.unsafe = unsafe; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); cur.atom = new.atom; out: return nbcon_context_can_proceed(ctxt, &cur); } static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; wctxt->outbuf = buf; wctxt->len = len; nbcon_state_read(con, &cur); wctxt->unsafe_takeover = cur.unsafe_takeover; } /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool is_owner; is_owner = nbcon_context_enter_unsafe(ctxt); if (!is_owner) nbcon_write_context_set_buf(wctxt, NULL, 0); return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); /** * nbcon_exit_unsafe - Exit an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool ret; ret = nbcon_context_exit_unsafe(ctxt); if (!ret) nbcon_write_context_set_buf(wctxt, NULL, 0); return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); /** * nbcon_reacquire_nobuf - Reacquire a console after losing ownership * while printing * @wctxt: The write context that was handed to the write callback * * Since ownership can be lost at any time due to handover or takeover, a * printing context _must_ be prepared to back out immediately and * carefully. However, there are scenarios where the printing context must * reacquire ownership in order to finalize or revert hardware changes. * * This function allows a printing context to reacquire ownership using the * same priority as its previous ownership. * * Note that after a successful reacquire the printing context will have no * output buffer because that has been lost. This function cannot be used to * resume printing. */ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); while (!nbcon_context_try_acquire(ctxt)) cpu_relax(); nbcon_write_context_set_buf(wctxt, NULL, 0); } EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function * @use_atomic: True if the write_atomic() callback is to be used * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. If the caller * wants to do more it must reacquire the console first. * * When true is returned, @wctxt->ctxt.backlog indicates whether there are * still records pending in the ringbuffer, */ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; struct printk_message pmsg = { .pbufs = ctxt->pbufs, }; unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; unsigned long ulseq; /* * This function should never be called for consoles that have not * implemented the necessary callback for writing: i.e. legacy * consoles and, when atomic, nbcon consoles with no write_atomic(). * Handle it as if ownership was lost and try to continue. * * Note that for nbcon consoles the write_thread() callback is * mandatory and was already checked in nbcon_alloc(). */ if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || !(console_srcu_read_flags(con) & CON_NBCON))) { nbcon_context_release(ctxt); return false; } /* * The printk buffers are filled within an unsafe section. This * prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from * clobbering each other. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true); if (!ctxt->backlog) return nbcon_context_exit_unsafe(ctxt); /* * @con->dropped is not protected in case of an unsafe hostile * takeover. In that situation the update can be racy so * annotate it accordingly. */ con_dropped = data_race(READ_ONCE(con->dropped)); dropped = con_dropped + pmsg.dropped; if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); /* * If the previous owner was assigned the same record, this context * has taken over ownership and is replaying the record. Prepend a * message to let the user know the record is replayed. */ ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { console_prepend_replay(&pmsg); } else { /* * Ensure this context is still the owner before trying to * update @nbcon_prev_seq. Otherwise the value in @ulseq may * not be from the previous owner and instead be some later * value from the context that took over ownership. */ nbcon_state_read(con, &cur); if (!nbcon_context_can_proceed(ctxt, &cur)) return false; atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, __u64seq_to_ulseq(pmsg.seq)); } if (!nbcon_context_exit_unsafe(ctxt)) return false; /* For skipped records just update seq/dropped in @con. */ if (pmsg.outbuf_len == 0) goto update_con; /* Initialize the write context for driver callbacks. */ nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); if (use_atomic) con->write_atomic(con, wctxt); else con->write_thread(con, wctxt); if (!wctxt->outbuf) { /* * Ownership was lost and reacquired by the driver. Handle it * as if ownership was lost. */ nbcon_context_release(ctxt); return false; } /* * Ownership may have been lost but _not_ reacquired by the driver. * This case is detected and handled when entering unsafe to update * dropped/seq values. */ /* * Since any dropped message was successfully output, reset the * dropped count for the console. */ dropped = 0; update_con: /* * The dropped count and the sequence number are updated within an * unsafe section. This limits update races to the panic context and * allows the panic context to win. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; if (dropped != con_dropped) { /* Counterpart to the READ_ONCE() above. */ WRITE_ONCE(con->dropped, dropped); } nbcon_seq_try_update(ctxt, pmsg.seq + 1); return nbcon_context_exit_unsafe(ctxt); } /* * nbcon_emit_one - Print one record for an nbcon console using the * specified callback * @wctxt: An initialized write context struct to use for this context * @use_atomic: True if the write_atomic() callback is to be used * * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This is an internal helper to handle the locking of the console before * calling nbcon_emit_next_record(). */ static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; unsigned long flags; bool ret = false; if (!use_atomic) { con->device_lock(con, &flags); /* * Ensure this stays on the CPU to make handover and * takeover possible. */ cant_migrate(); } if (!nbcon_context_try_acquire(ctxt)) goto out; /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. * * The higher priority printing context takes over responsibility * to print the pending records. */ if (!nbcon_emit_next_record(wctxt, use_atomic)) goto out; nbcon_context_release(ctxt); ret = ctxt->backlog; out: if (!use_atomic) con->device_unlock(con, flags); return ret; } /** * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup * @con: Console to operate on * @ctxt: The nbcon context from nbcon_context_try_acquire() * * Return: True if the thread should shutdown or if the console is * allowed to print and a record is available. False otherwise. * * After the thread wakes up, it must first check if it should shutdown before * attempting any printing. */ static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) { bool ret = false; short flags; int cookie; if (kthread_should_stop()) return true; cookie = console_srcu_read_lock(); flags = console_srcu_read_flags(con); if (console_is_usable(con, flags, false)) { /* Bring the sequence in @ctxt up to date */ ctxt->seq = nbcon_seq_read(con); ret = prb_read_valid(prb, ctxt->seq, NULL); } console_srcu_read_unlock(cookie); return ret; } /** * nbcon_kthread_func - The printer thread function * @__console: Console to operate on * * Return: 0 */ static int nbcon_kthread_func(void *__console) { struct console *con = __console; struct nbcon_write_context wctxt = { .ctxt.console = con, .ctxt.prio = NBCON_PRIO_NORMAL, }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); short con_flags; bool backlog; int cookie; wait_for_event: /* * Guarantee this task is visible on the rcuwait before * checking the wake condition. * * The full memory barrier within set_current_state() of * ___rcuwait_wait_event() pairs with the full memory * barrier within rcuwait_has_sleeper(). * * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. */ rcuwait_wait_event(&con->rcuwait, nbcon_kthread_should_wakeup(con, ctxt), TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ do { if (kthread_should_stop()) return 0; backlog = false; /* * Keep the srcu read lock around the entire operation so that * synchronize_srcu() can guarantee that the kthread stopped * or suspended printing. */ cookie = console_srcu_read_lock(); con_flags = console_srcu_read_flags(con); if (console_is_usable(con, con_flags, false)) backlog = nbcon_emit_one(&wctxt, false); console_srcu_read_unlock(cookie); cond_resched(); } while (backlog); goto wait_for_event; } /** * nbcon_irq_work - irq work to wake console printer thread * @irq_work: The irq work to operate on */ static void nbcon_irq_work(struct irq_work *irq_work) { struct console *con = container_of(irq_work, struct console, irq_work); nbcon_kthread_wake(con); } static inline bool rcuwait_has_sleeper(struct rcuwait *w) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * This full memory barrier pairs with the full memory barrier within * set_current_state() of ___rcuwait_wait_event(), which is called * after prepare_to_rcuwait() adds the waiter but before it has * checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ return rcuwait_active(w); } /** * nbcon_kthreads_wake - Wake up printing threads using irq_work */ void nbcon_kthreads_wake(void) { struct console *con; int cookie; if (!printk_kthreads_running) return; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON)) continue; /* * Only schedule irq_work if the printing thread is * actively waiting. If not waiting, the thread will * notice by itself that it has work to do. */ if (rcuwait_has_sleeper(&con->rcuwait)) irq_work_queue(&con->irq_work); } console_srcu_read_unlock(cookie); } /* * nbcon_kthread_stop - Stop a console printer thread * @con: Console to operate on */ void nbcon_kthread_stop(struct console *con) { lockdep_assert_console_list_lock_held(); if (!con->kthread) return; kthread_stop(con->kthread); con->kthread = NULL; } /** * nbcon_kthread_create - Create a console printer thread * @con: Console to operate on * * Return: True if the kthread was started or already exists. * Otherwise false and @con must not be registered. * * This function is called when it will be expected that nbcon consoles are * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL * will be no longer flushed by the legacy loop. This is why failure must * be fatal for console registration. * * If @con was already registered and this function fails, @con must be * unregistered before the global state variable @printk_kthreads_running * can be set. */ bool nbcon_kthread_create(struct console *con) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); if (con->kthread) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); if (WARN_ON(IS_ERR(kt))) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } con->kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(con->kthread, -20); return true; } /* Track the nbcon emergency nesting per CPU. */ static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; /** * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer * * Context: For reading, any context. For writing, any context which could * not be migrated to another CPU. * Return: Either a pointer to the per CPU emergency nesting counter of * the current CPU or to the init data during early boot. * * The function is safe for reading per-CPU variables in any context because * preemption is disabled if the current CPU is in the emergency state. See * also nbcon_cpu_emergency_enter(). */ static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) { /* * The value of __printk_percpu_data_ready gets set in normal * context and before SMP initialization. As a result it could * never change while inside an nbcon emergency section. */ if (!printk_percpu_data_ready()) return &early_nbcon_pcpu_emergency_nesting; return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting); } /** * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon * printing on the current CPU * * Context: Any context. * Return: The nbcon_prio to use for acquiring an nbcon console in this * context for printing. * * The function is safe for reading per-CPU data in any context because * preemption is disabled if the current CPU is in the emergency or panic * state. */ enum nbcon_prio nbcon_get_default_prio(void) { unsigned int *cpu_emergency_nesting; if (this_cpu_in_panic()) return NBCON_PRIO_PANIC; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (*cpu_emergency_nesting) return NBCON_PRIO_EMERGENCY; return NBCON_PRIO_NORMAL; } /** * nbcon_legacy_emit_next_record - Print one record for an nbcon console * in legacy contexts * @con: The console to print on * @handover: Will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding * both the console_lock and the SRCU read lock. Otherwise it * is set to false. * @cookie: The cookie from the SRCU read lock. * @use_atomic: Set true when called in an atomic or unknown context. * It affects which nbcon callback will be used: write_atomic() * or write_thread(). * * When false, the write_thread() callback is used and would be * called in a preemtible context unless disabled by the * device_lock. The legacy handover is not allowed in this mode. * * Context: Any context except NMI. * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This function is meant to be called by console_flush_all() to print records * on nbcon consoles from legacy context (printing via console unlocking). * Essentially it is the nbcon version of console_emit_next_record(). */ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); unsigned long flags; bool progress; ctxt->console = con; ctxt->prio = nbcon_get_default_prio(); if (use_atomic) { /* * In an atomic or unknown context, use the same procedure as * in console_emit_next_record(). It allows to handover. */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); } progress = nbcon_emit_one(&wctxt, use_atomic); if (use_atomic) { start_critical_timings(); *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } else { /* Non-atomic does not perform legacy spinning handovers. */ *handover = false; } return progress; } /** * __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on * failure. * * Errors: * * -EPERM: Unable to acquire console ownership. * * -EAGAIN: Another context took over ownership while printing. * * -ENOENT: A record before @stop_seq is not available. * * If flushing up to @stop_seq was not successful, it only makes sense for the * caller to try again when -EAGAIN was returned. When -EPERM is returned, * this context is not allowed to acquire the console. When -ENOENT is * returned, it cannot be expected that the unfinalized record will become * available. */ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); int err = 0; ctxt->console = con; ctxt->spinwait_max_us = 2000; ctxt->prio = nbcon_get_default_prio(); ctxt->allow_unsafe_takeover = allow_unsafe_takeover; if (!nbcon_context_try_acquire(ctxt)) return -EPERM; while (nbcon_seq_read(con) < stop_seq) { /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. */ if (!nbcon_emit_next_record(&wctxt, true)) return -EAGAIN; if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ if (nbcon_seq_read(con) < stop_seq) err = -ENOENT; break; } } nbcon_context_release(ctxt); return err; } /** * nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * This will stop flushing before @stop_seq if another context has ownership. * That context is then responsible for the flushing. Likewise, if new records * are added while this context was flushing and there is no other context * to handle the printing, this context must also flush those records. */ static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct console_flush_type ft; unsigned long flags; int err; again: /* * Atomic flushing does not use console driver synchronization (i.e. * it does not hold the port lock for uart consoles). Therefore IRQs * must be disabled to avoid being interrupted and then calling into * a driver that will deadlock trying to acquire console ownership. */ local_irq_save(flags); err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); local_irq_restore(flags); /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. * * Do not wait for records not yet finalized (-ENOENT) to avoid a * possible deadlock. They will either get flushed by the writer or * eventually skipped on panic CPU. */ if (err) return; /* * If flushing was successful but more records are available, this * context must flush those remaining records if the printer thread * is not available do it. */ printk_get_console_flush_type(&ft); if (!ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { stop_seq = prb_next_reserve_seq(prb); goto again; } } /** * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers */ static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover) { struct console *con; int cookie; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); if (!(flags & CON_NBCON)) continue; if (!console_is_usable(con, flags, true)) continue; if (nbcon_seq_read(con) >= stop_seq) continue; nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); } console_srcu_read_unlock(cookie); } /** * nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * * Flush the backlog up through the currently newest record. Any new * records added while flushing will not be flushed if there is another * context available to handle the flushing. This is to avoid one CPU * printing unbounded because other CPUs continue to add records. */ void nbcon_atomic_flush_pending(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false); } /** * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their * write_atomic() callback and allowing unsafe hostile takeovers * * Flush the backlog up through the currently newest record. Unsafe hostile * takeovers will be performed, if necessary. */ void nbcon_atomic_flush_unsafe(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); } /** * nbcon_cpu_emergency_enter - Enter an emergency section where printk() * messages for that CPU are flushed directly * * Context: Any context. Disables preemption. * * When within an emergency section, printk() calls will attempt to flush any * pending messages in the ringbuffer. */ void nbcon_cpu_emergency_enter(void) { unsigned int *cpu_emergency_nesting; preempt_disable(); cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); (*cpu_emergency_nesting)++; } /** * nbcon_cpu_emergency_exit - Exit an emergency section * * Context: Within an emergency section. Enables preemption. */ void nbcon_cpu_emergency_exit(void) { unsigned int *cpu_emergency_nesting; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) (*cpu_emergency_nesting)--; preempt_enable(); } /** * nbcon_alloc - Allocate and init the nbcon console specific data * @con: Console to initialize * * Return: True if the console was fully allocated and initialized. * Otherwise @con must not be registered. * * When allocation and init was successful, the console must be properly * freed using nbcon_free() once it is no longer needed. */ bool nbcon_alloc(struct console *con) { struct nbcon_state state = { }; /* The write_thread() callback is mandatory. */ if (WARN_ON(!con->write_thread)) return false; rcuwait_init(&con->rcuwait); init_irq_work(&con->irq_work, nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); /* * Initialize @nbcon_seq to the highest possible sequence number so * that practically speaking it will have nothing to print until a * desired initial sequence number has been set via nbcon_seq_force(). */ atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb)); if (con->flags & CON_BOOT) { /* * Boot console printing is synchronized with legacy console * printing, so boot consoles can share the same global printk * buffers. */ con->pbufs = &printk_shared_pbufs; } else { con->pbufs = kmalloc(sizeof(*con->pbufs), GFP_KERNEL); if (!con->pbufs) { con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } if (printk_kthreads_running) { if (!nbcon_kthread_create(con)) { kfree(con->pbufs); con->pbufs = NULL; return false; } } } return true; } /** * nbcon_free - Free and cleanup the nbcon console specific data * @con: Console to free/cleanup nbcon data */ void nbcon_free(struct console *con) { struct nbcon_state state = { }; if (printk_kthreads_running) nbcon_kthread_stop(con); nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ if (!(con->flags & CON_BOOT)) kfree(con->pbufs); con->pbufs = NULL; } /** * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe * section * @con: The nbcon console to acquire * * Context: Under the locking mechanism implemented in * @con->device_lock() including disabling migration. * Return: True if the console was acquired. False otherwise. * * Console drivers will usually use their own internal synchronization * mechasism to synchronize between console printing and non-printing * activities (such as setting baud rates). However, nbcon console drivers * supporting atomic consoles may also want to mark unsafe sections when * performing non-printing activities in order to synchronize against their * atomic_write() callback. * * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL * and marks it unsafe for handover/takeover. */ bool nbcon_device_try_acquire(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); cant_migrate(); memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; ctxt->prio = NBCON_PRIO_NORMAL; if (!nbcon_context_try_acquire(ctxt)) return false; if (!nbcon_context_enter_unsafe(ctxt)) return false; return true; } EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); /** * nbcon_device_release - Exit unsafe section and release the nbcon console * @con: The nbcon console acquired in nbcon_device_try_acquire() */ void nbcon_device_release(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); struct console_flush_type ft; int cookie; if (!nbcon_context_exit_unsafe(ctxt)) return; nbcon_context_release(ctxt); /* * This context must flush any new records added while the console * was locked if the printer thread is not available to do it. The * console_srcu_read_lock must be taken to ensure the console is * usable throughout flushing. */ cookie = console_srcu_read_lock(); printk_get_console_flush_type(&ft); if (console_is_usable(con, console_srcu_read_flags(con), true) && !ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { /* * If nbcon_atomic flushing is not available, fallback to * using the legacy loop. */ if (ft.nbcon_atomic) { __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false); } else if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } else if (ft.legacy_offload) { printk_trigger_flush(); } } console_srcu_read_unlock(cookie); } EXPORT_SYMBOL_GPL(nbcon_device_release); |
| 27 18 18 18 2 2 2 2 2 2 2 3 3 3 3 1 1 2 2 2 2 11 75 75 50 75 75 75 9 9 9 9 5 5 4 4 4 81 2 2 5 2 5 5 5 2 5 5 5 5 5 5 5 5 84 5 2 46 45 37 35 2 88 88 88 88 2 2 3 3 2 3 3 1 2 2 2 5 5 5 5 5 2 2 2 2 2 2 2 2 2 17 5 5 5 5 5 93 87 2 5 5 1 1 1 1 1 1 17 17 17 17 1 1 1 1 23 23 2 1 1 1 3 1 1 11 11 11 1 1 2 7 4 4 2 3 4 1 1 1 1 1 1 72 81 3 81 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Linaro Ltd. * Author: Shannon Zhao <shannon.zhao@linaro.org> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/perf_event.h> #include <linux/perf/arm_pmu.h> #include <linux/uaccess.h> #include <asm/kvm_emulate.h> #include <kvm/arm_pmu.h> #include <kvm/arm_vgic.h> #define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0) DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static LIST_HEAD(arm_pmus); static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]); } static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx) { return &vcpu->arch.pmu.pmc[cnt_idx]; } static u32 __kvm_pmu_event_mask(unsigned int pmuver) { switch (pmuver) { case ID_AA64DFR0_EL1_PMUVer_IMP: return GENMASK(9, 0); case ID_AA64DFR0_EL1_PMUVer_V3P1: case ID_AA64DFR0_EL1_PMUVer_V3P4: case ID_AA64DFR0_EL1_PMUVer_V3P5: case ID_AA64DFR0_EL1_PMUVer_V3P7: return GENMASK(15, 0); default: /* Shouldn't be here, just for sanity */ WARN_ONCE(1, "Unknown PMU version %d\n", pmuver); return 0; } } static u32 kvm_pmu_event_mask(struct kvm *kvm) { u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1); u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0); return __kvm_pmu_event_mask(pmuver); } u64 kvm_pmu_evtyper_mask(struct kvm *kvm) { u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 | kvm_pmu_event_mask(kvm); if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL2, IMP)) mask |= ARMV8_PMU_INCLUDE_EL2; if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP)) mask |= ARMV8_PMU_EXCLUDE_NS_EL0 | ARMV8_PMU_EXCLUDE_NS_EL1 | ARMV8_PMU_EXCLUDE_EL3; return mask; } /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context */ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (pmc->idx == ARMV8_PMU_CYCLE_IDX || kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)); } static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 val = kvm_vcpu_read_pmcr(vcpu); if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return __vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HLP; return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); } static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc) { return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX && !kvm_pmc_has_64bit_overflow(pmc)); } static u32 counter_index_to_reg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx; } static u32 counter_index_to_evtreg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx; } static u64 kvm_pmc_read_evtreg(const struct kvm_pmc *pmc) { return __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), counter_index_to_evtreg(pmc->idx)); } static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 counter, reg, enabled, running; reg = counter_index_to_reg(pmc->idx); counter = __vcpu_sys_reg(vcpu, reg); /* * The real counter value is equal to the value of counter register plus * the value perf event counts. */ if (pmc->perf_event) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); if (!kvm_pmc_is_64bit(pmc)) counter = lower_32_bits(counter); return counter; } /** * kvm_pmu_get_counter_value - get PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index */ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); } static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg; kvm_pmu_release_perf_event(pmc); reg = counter_index_to_reg(pmc->idx); if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX && !force) { /* * Even with PMUv3p5, AArch32 cannot write to the top * 32bit of the counters. The only possible course of * action is to use PMCR.P, which will reset them to * 0 (the only use of the 'force' parameter). */ val = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32); val |= lower_32_bits(val); } __vcpu_sys_reg(vcpu, reg) = val; /* Recreate the perf event to reflect the updated sample_period */ kvm_pmu_create_perf_event(pmc); } /** * kvm_pmu_set_counter_value - set PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index * @val: The counter value */ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { if (!kvm_vcpu_has_pmu(vcpu)) return; kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** * kvm_pmu_release_perf_event - remove the perf event * @pmc: The PMU counter pointer */ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { perf_event_disable(pmc->perf_event); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; } } /** * kvm_pmu_stop_counter - stop PMU counter * @pmc: The PMU counter pointer * * If this counter has been configured to monitor some event, release it here. */ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg, val; if (!pmc->perf_event) return; val = kvm_pmu_get_pmc_value(pmc); reg = counter_index_to_reg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = val; kvm_pmu_release_perf_event(pmc); } /** * kvm_pmu_vcpu_init - assign pmu counter idx for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) { int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) pmu->pmc[i].idx = i; } /** * kvm_pmu_vcpu_reset - reset pmu state for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) { unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu); int i; for_each_set_bit(i, &mask, 32) kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i)); } /** * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu) { unsigned int hpmn, n; if (!vcpu_has_nv(vcpu)) return 0; hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2)); n = vcpu->kvm->arch.pmcr_n; /* * Programming HPMN to a value greater than PMCR_EL0.N is * CONSTRAINED UNPREDICTABLE. Make the implementation choice that an * UNKNOWN number of counters (in our case, zero) are reserved for EL2. */ if (hpmn >= n) return 0; /* * Programming HPMN=0 is CONSTRAINED UNPREDICTABLE if FEAT_HPMN0 isn't * implemented. Since KVM's ability to emulate HPMN=0 does not directly * depend on hardware (all PMU registers are trapped), make the * implementation choice that all counters are included in the second * range reserved for EL2/EL3. */ return GENMASK(n - 1, hpmn); } bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx) { return kvm_pmu_hyp_counter_mask(vcpu) & BIT(idx); } u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu)) return mask; return mask & ~kvm_pmu_hyp_counter_mask(vcpu); } u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) { u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu)); if (val == 0) return BIT(ARMV8_PMU_CYCLE_IDX); else return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { if (!pmc->perf_event) { kvm_pmu_create_perf_event(pmc); return; } perf_event_enable(pmc->perf_event); if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) kvm_debug("fail to enable perf event\n"); } static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) perf_event_disable(pmc->perf_event); } void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; if (kvm_pmu_counter_is_enabled(pmc)) kvm_pmc_enable_perf_event(pmc); else kvm_pmc_disable_perf_event(pmc); } kvm_vcpu_pmu_restore_guest(vcpu); } /* * Returns the PMU overflow state, which is true if there exists an event * counter where the values of the global enable control, PMOVSSET_EL0[n], and * PMINTENSET_EL1[n] are all 1. */ static bool kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) { u64 reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); /* * PMCR_EL0.E is the global enable control for event counters available * to EL0 and EL1. */ if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) reg &= kvm_pmu_hyp_counter_mask(vcpu); /* * Otherwise, MDCR_EL2.HPME is the global enable control for event * counters reserved for EL2. */ if (!(vcpu_read_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HPME)) reg &= ~kvm_pmu_hyp_counter_mask(vcpu); return reg; } static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; bool overflow; if (!kvm_vcpu_has_pmu(vcpu)) return; overflow = kvm_pmu_overflow_status(vcpu); if (pmu->irq_level == overflow) return; pmu->irq_level = overflow; if (likely(irqchip_in_kernel(vcpu->kvm))) { int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, pmu->irq_num, overflow, pmu); WARN_ON(ret); } } bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_sync_regs *sregs = &vcpu->run->s.regs; bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU; if (likely(irqchip_in_kernel(vcpu->kvm))) return false; return pmu->irq_level != run_level; } /* * Reflect the PMU overflow interrupt output level into the kvm_run structure */ void kvm_pmu_update_run(struct kvm_vcpu *vcpu) { struct kvm_sync_regs *regs = &vcpu->run->s.regs; /* Populate the timer bitmap for user space */ regs->device_irq_level &= ~KVM_ARM_DEV_PMU; if (vcpu->arch.pmu.irq_level) regs->device_irq_level |= KVM_ARM_DEV_PMU; } /** * kvm_pmu_flush_hwstate - flush pmu state to cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the host, and inject * an interrupt if that was the case. */ void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /** * kvm_pmu_sync_hwstate - sync pmu state from cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the guest, and * inject an interrupt if that was the case. */ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /* * When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding * to the event. * This is why we need a callback to do it once outside of the NMI context. */ static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work) { struct kvm_vcpu *vcpu; vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work); kvm_vcpu_kick(vcpu); } /* * Perform an increment on any of the counters described in @mask, * generating the overflow if required, and propagate it as a chained * event if possible. */ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, unsigned long mask, u32 event) { int i; if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) return; /* Weed out disabled counters */ mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); u64 type, reg; /* Filter on event type */ type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i)); type &= kvm_pmu_event_mask(vcpu->kvm); if (type != event) continue; /* Increment this counter */ reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1; if (!kvm_pmc_is_64bit(pmc)) reg = lower_32_bits(reg); __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg; /* No overflow? move on */ if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg)) continue; /* Mark overflow */ __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(i + 1), ARMV8_PMUV3_PERFCTR_CHAIN); } } /* Compute the sample period for a given counter value */ static u64 compute_period(struct kvm_pmc *pmc, u64 counter) { u64 val; if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc)) val = (-counter) & GENMASK(63, 0); else val = (-counter) & GENMASK(31, 0); return val; } /* * When the perf event overflows, set the overflow status and inform the vcpu. */ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, struct perf_sample_data *data, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); int idx = pmc->idx; u64 period; cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); /* * Reset the sample period to the architectural limit, * i.e. the point where the counter overflows. */ period = compute_period(pmc, local64_read(&perf_event->count)); local64_set(&perf_event->hw.period_left, 0); perf_event->attr.sample_period = period; perf_event->hw.sample_period = period; __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(idx + 1), ARMV8_PMUV3_PERFCTR_CHAIN); if (kvm_pmu_overflow_status(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); if (!in_nmi()) kvm_vcpu_kick(vcpu); else irq_work_queue(&vcpu->arch.pmu.overflow_work); } cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); } /** * kvm_pmu_software_increment - do software increment * @vcpu: The vcpu pointer * @val: the value guest writes to PMSWINC register */ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) { kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR); } /** * kvm_pmu_handle_pmcr - handle PMCR register * @vcpu: The vcpu pointer * @val: the value guest writes to PMCR register */ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu)) return; /* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */ if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; /* Request a reload of the PMU to enable/disable affected counters */ if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { /* * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply * to the 'guest' range of counters and never the 'hyp' range. */ unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & ~kvm_pmu_hyp_counter_mask(vcpu) & ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx))) return false; if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return mdcr & MDCR_EL2_HPME; return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E; } static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc) { u64 evtreg = kvm_pmc_read_evtreg(pmc); bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0; bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0; return u == nsu; } static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc) { u64 evtreg = kvm_pmc_read_evtreg(pmc); bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1; bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1; return p == nsk; } static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD)) return false; return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2; } /** * kvm_pmu_create_perf_event - create a perf event for a counter * @pmc: Counter context */ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; struct perf_event *event; struct perf_event_attr attr; u64 eventsel, evtreg; evtreg = kvm_pmc_read_evtreg(pmc); kvm_pmu_stop_counter(pmc); if (pmc->idx == ARMV8_PMU_CYCLE_IDX) eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES; else eventsel = evtreg & kvm_pmu_event_mask(vcpu->kvm); /* * Neither SW increment nor chained events need to be backed * by a perf event. */ if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR || eventsel == ARMV8_PMUV3_PERFCTR_CHAIN) return; /* * If we have a filter in place and that the event isn't allowed, do * not install a perf event either. */ if (vcpu->kvm->arch.pmu_filter && !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; attr.disabled = !kvm_pmu_counter_is_enabled(pmc); attr.exclude_user = !kvm_pmc_counts_at_el0(pmc); attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; /* * Filter events at EL1 (i.e. vEL2) when in a hyp context based on the * guest's EL2 filter. */ if (unlikely(is_hyp_ctxt(vcpu))) attr.exclude_kernel = !kvm_pmc_counts_at_el2(pmc); else attr.exclude_kernel = !kvm_pmc_counts_at_el1(pmc); /* * If counting with a 64bit counter, advertise it to the perf * code, carefully dealing with the initial sample period * which also depends on the overflow. */ if (kvm_pmc_is_64bit(pmc)) attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT; attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc)); event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc); if (IS_ERR(event)) { pr_err_once("kvm: pmu event creation failed %ld\n", PTR_ERR(event)); return; } pmc->perf_event = event; } /** * kvm_pmu_set_counter_event_type - set selected counter to monitor some event * @vcpu: The vcpu pointer * @data: The data guest writes to PMXEVTYPER_EL0 * @select_idx: The number of selected counter * * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an * event with given hardware event number. Here we call perf_event API to * emulate this action and create a kernel perf event for it. */ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); u64 reg; if (!kvm_vcpu_has_pmu(vcpu)) return; reg = counter_index_to_evtreg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); kvm_pmu_create_perf_event(pmc); } void kvm_host_pmu_init(struct arm_pmu *pmu) { struct arm_pmu_entry *entry; /* * Check the sanitised PMU version for the system, as KVM does not * support implementations where PMUv3 exists on a subset of CPUs. */ if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit())) return; mutex_lock(&arm_pmus_lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) goto out_unlock; entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus); if (list_is_singular(&arm_pmus)) static_branch_enable(&kvm_arm_pmu_available); out_unlock: mutex_unlock(&arm_pmus_lock); } static struct arm_pmu *kvm_pmu_probe_armpmu(void) { struct arm_pmu *tmp, *pmu = NULL; struct arm_pmu_entry *entry; int cpu; mutex_lock(&arm_pmus_lock); /* * It is safe to use a stale cpu to iterate the list of PMUs so long as * the same value is used for the entirety of the loop. Given this, and * the fact that no percpu data is used for the lookup there is no need * to disable preemption. * * It is still necessary to get a valid cpu, though, to probe for the * default PMU instance as userspace is not required to specify a PMU * type. In order to uphold the preexisting behavior KVM selects the * PMU instance for the core during vcpu init. A dependent use * case would be a user with disdain of all things big.LITTLE that * affines the VMM to a particular cluster of cores. * * In any case, userspace should just do the sane thing and use the UAPI * to select a PMU type directly. But, be wary of the baggage being * carried here. */ cpu = raw_smp_processor_id(); list_for_each_entry(entry, &arm_pmus, entry) { tmp = entry->arm_pmu; if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) { pmu = tmp; break; } } mutex_unlock(&arm_pmus_lock); return pmu; } u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; int base, i, nr_events; if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!pmceid1) { val = read_sysreg(pmceid0_el0); /* always support CHAIN */ val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); base = 0; } else { val = read_sysreg(pmceid1_el0); /* * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled * as RAZ */ val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32)); base = 32; } if (!bmap) return val; nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; if (nr_events >= (0x4000 + base + 32)) { byte = bitmap_get_value8(bmap, 0x4000 + base + i); mask |= byte << (32 + i); } } return val & mask; } void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!vcpu->arch.pmu.created) return -EINVAL; /* * A valid interrupt configuration for the PMU is either to have a * properly configured interrupt number and using an in-kernel * irqchip, or to not have an in-kernel GIC and not set an IRQ. */ if (irqchip_in_kernel(vcpu->kvm)) { int irq = vcpu->arch.pmu.irq_num; /* * If we are using an in-kernel vgic, at this point we know * the vgic will be initialized, so we can check the PMU irq * number against the dimensions of the vgic and make sure * it's valid. */ if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq)) return -EINVAL; } else if (kvm_arm_pmu_irq_initialized(vcpu)) { return -EINVAL; } /* One-off reload of the PMU on first run */ kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) { int ret; /* * If using the PMU with an in-kernel virtual GIC * implementation, we require the GIC to be already * initialized when initializing the PMU. */ if (!vgic_initialized(vcpu->kvm)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, &vcpu->arch.pmu); if (ret) return ret; } init_irq_work(&vcpu->arch.pmu.overflow_work, kvm_pmu_perf_overflow_notify_vcpu); vcpu->arch.pmu.created = true; return 0; } /* * For one VM the interrupt type must be same for each vcpu. * As a PPI, the interrupt number is the same for all vcpus, * while as an SPI it must be a separate number per vcpu. */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu)) continue; if (irq_is_ppi(irq)) { if (vcpu->arch.pmu.irq_num != irq) return false; } else { if (vcpu->arch.pmu.irq_num == irq) return false; } } return true; } /** * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters. * @kvm: The kvm pointer */ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* * The arm_pmu->cntr_mask considers the fixed counter(s) as well. * Ignore those and return only the general-purpose counters. */ return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) { lockdep_assert_held(&kvm->arch.config_lock); kvm->arch.arm_pmu = arm_pmu; kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm); } /** * kvm_arm_set_default_pmu - No PMU set, get the default one. * @kvm: The kvm pointer * * The observant among you will notice that the supported_cpus * mask does not get updated for the default PMU even though it * is quite possible the selected instance supports only a * subset of cores in the system. This is intentional, and * upholds the preexisting behavior on heterogeneous systems * where vCPUs can be scheduled on any core but the guest * counters could stop working. */ int kvm_arm_set_default_pmu(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu(); if (!arm_pmu) return -ENODEV; kvm_arm_set_pmu(kvm, arm_pmu); return 0; } static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) { struct kvm *kvm = vcpu->kvm; struct arm_pmu_entry *entry; struct arm_pmu *arm_pmu; int ret = -ENXIO; lockdep_assert_held(&kvm->arch.config_lock); mutex_lock(&arm_pmus_lock); list_for_each_entry(entry, &arm_pmus, entry) { arm_pmu = entry->arm_pmu; if (arm_pmu->pmu.type == pmu_id) { if (kvm_vm_has_ran_once(kvm) || (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) { ret = -EBUSY; break; } kvm_arm_set_pmu(kvm, arm_pmu); cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus); ret = 0; break; } } mutex_unlock(&arm_pmus_lock); return ret; } int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) return -EBUSY; switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(kvm)) return -EINVAL; if (get_user(irq, uaddr)) return -EFAULT; /* The PMU overflow interrupt can be a PPI or a valid SPI. */ if (!(irq_is_ppi(irq) || irq_is_spi(irq))) return -EINVAL; if (!pmu_irq_is_valid(kvm, irq)) return -EINVAL; if (kvm_arm_pmu_irq_initialized(vcpu)) return -EBUSY; kvm_debug("Set kvm ARM PMU irq: %d\n", irq); vcpu->arch.pmu.irq_num = irq; return 0; } case KVM_ARM_VCPU_PMU_V3_FILTER: { u8 pmuver = kvm_arm_pmu_get_pmuver_limit(); struct kvm_pmu_event_filter __user *uaddr; struct kvm_pmu_event_filter filter; int nr_events; /* * Allow userspace to specify an event filter for the entire * event range supported by PMUVer of the hardware, rather * than the guest's PMUVer for KVM backward compatibility. */ nr_events = __kvm_pmu_event_mask(pmuver) + 1; uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (((u32)filter.base_event + filter.nevents) > nr_events || (filter.action != KVM_PMU_EVENT_ALLOW && filter.action != KVM_PMU_EVENT_DENY)) return -EINVAL; if (kvm_vm_has_ran_once(kvm)) return -EBUSY; if (!kvm->arch.pmu_filter) { kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT); if (!kvm->arch.pmu_filter) return -ENOMEM; /* * The default depends on the first applied filter. * If it allows events, the default is to deny. * Conversely, if the first filter denies a set of * events, the default is to allow. */ if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_zero(kvm->arch.pmu_filter, nr_events); else bitmap_fill(kvm->arch.pmu_filter, nr_events); } if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents); else bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents); return 0; } case KVM_ARM_VCPU_PMU_V3_SET_PMU: { int __user *uaddr = (int __user *)(long)attr->addr; int pmu_id; if (get_user(pmu_id, uaddr)) return -EFAULT; return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id); } case KVM_ARM_VCPU_PMU_V3_INIT: return kvm_arm_pmu_v3_init(vcpu); } return -ENXIO; } int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; irq = vcpu->arch.pmu.irq_num; return put_user(irq, uaddr); } } return -ENXIO; } int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: case KVM_ARM_VCPU_PMU_V3_INIT: case KVM_ARM_VCPU_PMU_V3_FILTER: case KVM_ARM_VCPU_PMU_V3_SET_PMU: if (kvm_vcpu_has_pmu(vcpu)) return 0; } return -ENXIO; } u8 kvm_arm_pmu_get_pmuver_limit(void) { u64 tmp; tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); tmp = cpuid_feature_cap_perfmon_field(tmp, ID_AA64DFR0_EL1_PMUVer_SHIFT, ID_AA64DFR0_EL1_PMUVer_V3P5); return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); } /** * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU * @vcpu: The vcpu pointer */ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N); } void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) { bool reprogrammed = false; unsigned long mask; int i; if (!kvm_vcpu_has_pmu(vcpu)) return; mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, 32) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); /* * We only need to reconfigure events where the filter is * different at EL1 vs. EL2, as we're multiplexing the true EL1 * event filter bit for nested. */ if (kvm_pmc_counts_at_el1(pmc) == kvm_pmc_counts_at_el2(pmc)) continue; kvm_pmu_create_perf_event(pmc); reprogrammed = true; } if (reprogrammed) kvm_vcpu_pmu_restore_guest(vcpu); } |
| 193 194 194 191 623 622 624 623 622 625 512 46 484 511 2 506 7 510 2 511 513 511 175 173 174 173 2 147 30 170 5 175 173 175 146 1118 1131 22 147 34 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/swap.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ static struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __ro_after_init; static struct kmem_cache *bfilp_cachep __ro_after_init; static struct percpu_counter nr_files __cacheline_aligned_in_smp; /* Container for backing file with optional user path */ struct backing_file { struct file file; union { struct path user_path; freeptr_t bf_freeptr; }; }; static inline struct backing_file *backing_file(struct file *f) { return container_of(f, struct backing_file, file); } struct path *backing_file_user_path(struct file *f) { return &backing_file(f)->user_path; } EXPORT_SYMBOL_GPL(backing_file_user_path); static inline void file_free(struct file *f) { security_file_free(f); if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { path_put(backing_file_user_path(f)); kmem_cache_free(bfilp_cachep, backing_file(f)); } else { kmem_cache_free(filp_cachep, f); } } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Handle nr_files sysctl */ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = SYSCTL_LONG_ZERO, .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, }; static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } return 0; } fs_initcall(init_fs_stat_sysctls); #endif static int init_file(struct file *f, int flags, const struct cred *cred) { int error; f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { put_cred(f->f_cred); return error; } spin_lock_init(&f->f_lock); /* * Note that f_pos_lock is only used for files raising * FMODE_ATOMIC_POS and directories. Other files such as pipes * don't need it and since f_pos_lock is in a union may reuse * the space for other purposes. They are expected to initialize * the respective member when opening the file. */ mutex_init(&f->f_pos_lock); memset(&f->f_path, 0, sizeof(f->f_path)); memset(&f->f_ra, 0, sizeof(f->f_ra)); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); f->f_op = NULL; f->f_mapping = NULL; f->private_data = NULL; f->f_inode = NULL; f->f_owner = NULL; #ifdef CONFIG_EPOLL f->f_ep = NULL; #endif f->f_iocb_flags = 0; f->f_pos = 0; f->f_wb_err = 0; f->f_sb_err = 0; /* * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While * fget-rcu pattern users need to be able to handle spurious * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); /* * Disable permission and pre-content events for all files by default. * They may be enabled later by file_set_fsnotify_mode_from_watchers(). */ file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); return 0; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; int error; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } f->f_mode |= FMODE_NOACCOUNT; return f; } /* * Variant of alloc_empty_file() that allocates a backing_file container * and doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_backing_file(int flags, const struct cred *cred) { struct backing_file *ff; int error; ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL); if (unlikely(!ff)) return ERR_PTR(-ENOMEM); error = init_file(&ff->file, flags, cred); if (unlikely(error)) { kmem_cache_free(bfilp_cachep, ff); return ERR_PTR(error); } ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; return &ff->file; } /** * file_init_path - initialize a 'struct file' based on path * * @file: the file to set up * @path: the (dentry, vfsmount) pair for the new file * @fop: the 'struct file_operations' for the new file */ static void file_init_path(struct file *file, const struct path *path, const struct file_operations *fop) { file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if (fop->llseek) file->f_mode |= FMODE_LSEEK; if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_iocb_flags = iocb_flags(file); file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (!IS_ERR(file)) file_init_path(file, path, fop); return file; } static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name)); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); d_instantiate(path->dentry, inode); return 0; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_pseudo_noaccount(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_empty_file_noaccount(flags, current_cred()); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } file_init_path(file, &path, fops); /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f; f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); security_file_release(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); file_f_owner_release(file); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_task_work)); } static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); flush_delayed_work(&delayed_fput_work); } EXPORT_SYMBOL_GPL(flush_delayed_fput); void fput(struct file *file) { if (file_ref_put(&file->f_ref)) { struct task_struct *task = current; if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { file_free(file); return; } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_task_work, ____fput); if (!task_work_add(task, &file->f_task_work, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (file_ref_put(&file->f_ref)) __fput(file); } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct file, f_freeptr), }; filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); args.freeptr_offset = offsetof(struct backing_file, bf_freeptr); bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 336 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AArch64-specific system calls implementation * * Copyright (C) 2012 ARM Ltd. * Author: Catalin Marinas <catalin.marinas@arm.com> */ #include <linux/compiler.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <asm/cpufeature.h> #include <asm/syscall.h> SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, off) { if (offset_in_page(off) != 0) return -EINVAL; return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } SYSCALL_DEFINE1(arm64_personality, unsigned int, personality) { if (personality(personality) == PER_LINUX32 && !system_supports_32bit_el0()) return -EINVAL; return ksys_personality(personality); } asmlinkage long sys_ni_syscall(void); asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused) { return sys_ni_syscall(); } /* * Wrappers to pass the pt_regs argument. */ #define __arm64_sys_personality __arm64_sys_arm64_personality #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) #undef __SYSCALL #define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *); #include <asm/syscall_table_64.h> #undef __SYSCALL #define __SYSCALL(nr, sym) [nr] = __arm64_##sym, const syscall_fn_t sys_call_table[__NR_syscalls] = { [0 ... __NR_syscalls - 1] = __arm64_sys_ni_syscall, #include <asm/syscall_table_64.h> }; |
| 1 75 146 75 76 75 75 147 118 146 9 65 147 147 146 147 76 76 75 8 147 147 147 130 147 147 147 147 147 146 252 252 252 76 66 86 86 75 74 75 75 75 75 74 75 75 7 7 76 65 75 74 75 75 75 75 75 75 65 65 74 75 75 75 65 75 75 75 75 34 34 7 7 7 7 7 7 7 7 35 35 67 66 1 1 1 1 66 1 1 1 1 1 1 251 251 19 19 1 1 19 19 19 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Stand-alone page-table allocator for hyp stage-1 and guest stage-2. * No bombay mix was harmed in the writing of this file. * * Copyright (C) 2020 Google LLC * Author: Will Deacon <will@kernel.org> */ #include <linux/bitfield.h> #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> #define KVM_PTE_TYPE BIT(1) #define KVM_PTE_TYPE_BLOCK 0 #define KVM_PTE_TYPE_PAGE 1 #define KVM_PTE_TYPE_TABLE 1 struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; const u64 start; u64 addr; const u64 end; }; static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI); } static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); } static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { u64 granule = kvm_granule_size(ctx->level); if (!kvm_level_supports_block_mapping(ctx->level)) return false; if (granule > (ctx->end - ctx->addr)) return false; if (!IS_ALIGNED(phys, granule)) return false; return IS_ALIGNED(ctx->addr, granule); } static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level) { u64 shift = kvm_granule_shift(level); u64 mask = BIT(PAGE_SHIFT - 3) - 1; return (data->addr >> shift) & mask; } static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) { u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */ u64 mask = BIT(pgt->ia_bits) - 1; return (addr & mask) >> shift; } static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level) { struct kvm_pgtable pgt = { .ia_bits = ia_bits, .start_level = start_level, }; return kvm_pgd_page_idx(&pgt, -1ULL) + 1; } static bool kvm_pte_table(kvm_pte_t pte, s8 level) { if (level == KVM_PGTABLE_LAST_LEVEL) return false; if (!kvm_pte_valid(pte)) return false; return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; } static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops) { return mm_ops->phys_to_virt(kvm_pte_to_phys(pte)); } static void kvm_clear_pte(kvm_pte_t *ptep) { WRITE_ONCE(*ptep, 0); } static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops) { kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level) { kvm_pte_t pte = kvm_phys_to_pte(pa); u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE : KVM_PTE_TYPE_BLOCK; pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI); pte |= FIELD_PREP(KVM_PTE_TYPE, type); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id) { return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id); } static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_walker *walker = data->walker; /* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */ WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held()); return walker->cb(ctx, visit); } static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, int r) { /* * Visitor callbacks return EAGAIN when the conditions that led to a * fault are no longer reflected in the page tables due to a race to * update a PTE. In the context of a fault handler this is interpreted * as a signal to retry guest execution. * * Ignore the return code altogether for walkers outside a fault handler * (e.g. write protecting a range of memory) and chug along with the * page table walk. */ if (r == -EAGAIN) return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); return !r; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level); static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pteref, s8 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, .start = data->start, .addr = data->addr, .end = data->end, .level = level, .flags = flags, }; int ret = 0; bool reload = false; kvm_pteref_t childp; bool table = kvm_pte_table(ctx.old, level); if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); reload = true; } if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); reload = true; } /* * Reload the page table after invoking the walker callback for leaf * entries or after pre-order traversal, to allow the walker to descend * into a newly installed or replaced table. */ if (reload) { ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); } if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (!table) { data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level)); data->addr += kvm_granule_size(level); goto out; } childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: if (kvm_pgtable_walk_continue(data->walker, ret)) return 0; return ret; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level) { u32 idx; int ret = 0; if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL || level > KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) { kvm_pteref_t pteref = &pgtable[idx]; if (data->addr >= data->end) break; ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); if (ret) break; } return ret; } static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data) { u32 idx; int ret = 0; u64 limit = BIT(pgt->ia_bits); if (data->addr > limit || data->end > limit) return -ERANGE; if (!pgt->pgd) return -EINVAL; for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); if (ret) break; } return ret; } int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, }; int r; r = kvm_pgtable_walk_begin(walker); if (r) return r; r = _kvm_pgtable_walk(pgt, &walk_data); kvm_pgtable_walk_end(walker); return r; } struct leaf_walk_data { kvm_pte_t pte; s8 level; }; static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct leaf_walk_data *data = ctx->arg; data->pte = ctx->old; data->level = ctx->level; return 0; } int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, kvm_pte_t *ptep, s8 *level) { struct leaf_walk_data data; struct kvm_pgtable_walker walker = { .cb = leaf_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &data, }; int ret; ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), PAGE_SIZE, &walker); if (!ret) { if (ptep) *ptep = data.pte; if (level) *level = data.level; } return ret; } struct hyp_map_data { const u64 phys; kvm_pte_t attr; }; static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { bool device = prot & KVM_PGTABLE_PROT_DEVICE; u32 mtype = device ? MT_DEVICE_nGnRE : MT_NORMAL; kvm_pte_t attr = FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX, mtype); u32 sh = KVM_PTE_LEAF_ATTR_LO_S1_SH_IS; u32 ap = (prot & KVM_PGTABLE_PROT_W) ? KVM_PTE_LEAF_ATTR_LO_S1_AP_RW : KVM_PTE_LEAF_ATTR_LO_S1_AP_RO; if (!(prot & KVM_PGTABLE_PROT_R)) return -EINVAL; if (prot & KVM_PGTABLE_PROT_X) { if (prot & KVM_PGTABLE_PROT_W) return -EINVAL; if (device) return -EINVAL; if (system_supports_bti_kernel()) attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; } else { attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; } attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap); if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; u32 ap; if (!kvm_pte_valid(pte)) return prot; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN)) prot |= KVM_PGTABLE_PROT_X; ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte); if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO) prot |= KVM_PGTABLE_PROT_R; else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW) prot |= KVM_PGTABLE_PROT_RW; return prot; } static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; if (!kvm_block_mapping_supported(ctx, phys)) return false; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; if (!kvm_pte_valid(ctx->old)) ctx->mm_ops->get_page(ctx->ptep); else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; smp_store_release(ctx->ptep, new); return true; } static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp, new; struct hyp_map_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (hyp_map_walker_try_leaf(ctx, data)) return 0; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL); if (!childp) return -ENOMEM; new = kvm_init_table_pte(childp, mm_ops); mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); return 0; } int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot) { int ret; struct hyp_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), }; struct kvm_pgtable_walker walker = { .cb = hyp_map_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; ret = hyp_set_prot_attr(prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); isb(); return ret; } static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp = NULL; u64 granule = kvm_granule_size(ctx->level); u64 *unmapped = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EINVAL; if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN); } else { if (ctx->end - ctx->addr < granule) return -EINVAL; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); *unmapped += granule; } dsb(ish); isb(); mm_ops->put_page(ctx->ptep); if (childp) mm_ops->put_page(childp); return 0; } u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { u64 unmapped = 0; struct kvm_pgtable_walker walker = { .cb = hyp_unmap_walker, .arg = &unmapped, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; if (!pgt->mm_ops->page_count) return 0; kvm_pgtable_walk(pgt, addr, size, &walker); return unmapped; } int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops) { s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 - ARM64_HW_PGTABLE_LEVELS(va_bits); if (start_level < KVM_PGTABLE_FIRST_LEVEL || start_level > KVM_PGTABLE_LAST_LEVEL) return -EINVAL; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = va_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = NULL; pgt->force_pte_cb = NULL; return 0; } static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) { struct kvm_pgtable_walker walker = { .cb = hyp_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } struct stage2_map_data { const u64 phys; kvm_pte_t attr; u8 owner_id; kvm_pte_t *anchor; kvm_pte_t *childp; struct kvm_s2_mmu *mmu; void *memcache; /* Force mappings to page granularity */ bool force_pte; /* Walk should update owner_id only */ bool annotation; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) { u64 vtcr = VTCR_EL2_FLAGS; s8 lvls; vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT; vtcr |= VTCR_EL2_T0SZ(phys_shift); /* * Use a minimum 2 level page table to prevent splitting * host PMD huge pages at stage2. */ lvls = stage2_pgtable_levels(phys_shift); if (lvls < 2) lvls = 2; /* * When LPA2 is enabled, the HW supports an extra level of translation * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2 * to as an addition to SL0 to enable encoding this extra start level. * However, since we always use concatenated pages for the first level * lookup, we will never need this extra level and therefore do not need * to touch SL2. */ vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally * on all CPUs. In systems that have asymmetric support for the feature * this allows KVM to leverage hardware support on the subset of cores * that implement the feature. * * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by * hardware) on implementations that do not advertise support for the * feature. As such, setting HA unconditionally is safe, unless you * happen to be running on a design that has unadvertised support for * HAFDBS. Here be dragons. */ if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) vtcr |= VTCR_EL2_HA; #endif /* CONFIG_ARM64_HW_AFDBM */ if (kvm_lpa2_is_enabled()) vtcr |= VTCR_EL2_DS; /* Set the vmid bits */ vtcr |= (get_vmid_bits(mmfr1) == 16) ? VTCR_EL2_VS_16BIT : VTCR_EL2_VS_8BIT; return vtcr; } static bool stage2_has_fwb(struct kvm_pgtable *pgt) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return false; return !(pgt->flags & KVM_PGTABLE_S2_NOFWB); } void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, size_t size) { unsigned long pages, inval_pages; if (!system_supports_tlb_range()) { kvm_call_hyp(__kvm_tlb_flush_vmid, mmu); return; } pages = size >> PAGE_SHIFT; while (pages > 0) { inval_pages = min(pages, MAX_TLBI_RANGE_PAGES); kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages); addr += inval_pages << PAGE_SHIFT; pages -= inval_pages; } } #define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt)) static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { kvm_pte_t attr; u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS; switch (prot & (KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC)) { case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC: return -EINVAL; case KVM_PGTABLE_PROT_DEVICE: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE); break; case KVM_PGTABLE_PROT_NORMAL_NC: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, NORMAL_NC); break; default: attr = KVM_S2_MEMATTR(pgt, NORMAL); } if (!(prot & KVM_PGTABLE_PROT_X)) attr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; if (prot & KVM_PGTABLE_PROT_R) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; if (!kvm_pte_valid(pte)) return prot; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R) prot |= KVM_PGTABLE_PROT_R; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W) prot |= KVM_PGTABLE_PROT_W; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN)) prot |= KVM_PGTABLE_PROT_X; return prot; } static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new) { if (!kvm_pte_valid(old) || !kvm_pte_valid(new)) return true; return ((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS)); } static bool stage2_pte_is_counted(kvm_pte_t pte) { /* * The refcount tracks valid entries as well as invalid entries if they * encode ownership of a page to another entity than the page-table * owner, whose id is 0. */ return !!pte; } static bool stage2_pte_is_locked(kvm_pte_t pte) { return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED); } static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { if (!kvm_pgtable_walk_shared(ctx)) { WRITE_ONCE(*ctx->ptep, new); return true; } return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old; } /** * stage2_try_break_pte() - Invalidates a pte according to the * 'break-before-make' requirements of the * architecture. * * @ctx: context of the visited pte. * @mmu: stage-2 mmu * * Returns: true if the pte was successfully broken. * * If the removed pte was valid, performs the necessary serialization and TLB * invalidation for the old value. For counted ptes, drops the reference count * on the containing table page. */ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (stage2_pte_is_locked(ctx->old)) { /* * Should never occur if this walker has exclusive access to the * page tables. */ WARN_ON(!kvm_pgtable_walk_shared(ctx)); return false; } if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED)) return false; if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) { /* * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ if (kvm_pte_table(ctx->old, ctx->level)) { u64 size = kvm_granule_size(ctx->level); u64 addr = ALIGN_DOWN(ctx->addr, size); kvm_tlb_flush_vmid_range(mmu, addr, size); } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } if (stage2_pte_is_counted(ctx->old)) mm_ops->put_page(ctx->ptep); return true; } static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; WARN_ON(!stage2_pte_is_locked(*ctx->ptep)); if (stage2_pte_is_counted(new)) mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); } static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt) { /* * If FEAT_TLBIRANGE is implemented, defer the individual * TLB invalidations until the entire walk is finished, and * then use the range-based TLBI instructions to do the * invalidations. Condition deferred TLB invalidation on the * system supporting FWB as the optimization is entirely * pointless when the unmap walker needs to perform CMOs. */ return system_supports_tlb_range() && stage2_has_fwb(pgt); } static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { struct kvm_pgtable *pgt = ctx->arg; /* * Clear the existing PTE, and perform break-before-make if it was * valid. Depending on the system support, defer the TLB maintenance * for the same until the entire unmap walk is completed. */ if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, TLBI_TTL_UNKNOWN); } else if (!stage2_unmap_defer_tlb_flush(pgt)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } mm_ops->put_page(ctx->ptep); } static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) { u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR; return kvm_pte_valid(pte) && memattr == KVM_S2_MEMATTR(pgt, NORMAL); } static bool stage2_pte_executable(kvm_pte_t pte) { return kvm_pte_valid(pte) && !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, const struct stage2_map_data *data) { u64 phys = data->phys; /* Work out the correct PA based on how far the walk has gotten */ return phys + (ctx->addr - ctx->start); } static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { u64 phys = stage2_map_walker_phys_addr(ctx, data); if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) return false; if (data->annotation) return true; return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; u64 phys = stage2_map_walker_phys_addr(ctx, data); u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; if (!data->annotation) new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); /* * Skip updating the PTE if we are 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. */ if (!stage2_pte_needs_update(ctx->old, new)) return -EAGAIN; /* If we're only changing software bits, then store them and go! */ if (!kvm_pgtable_walk_shared(ctx) && !((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) { bool old_is_counted = stage2_pte_is_counted(ctx->old); if (old_is_counted != stage2_pte_is_counted(new)) { if (old_is_counted) mm_ops->put_page(ctx->ptep); else mm_ops->get_page(ctx->ptep); } WARN_ON_ONCE(!stage2_try_set_pte(ctx, new)); return 0; } if (!stage2_try_break_pte(ctx, data->mmu)) return -EAGAIN; /* Perform CMOs before installation of the guest stage-2 PTE */ if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new)) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops), granule); if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou && stage2_pte_executable(new)) mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); stage2_make_pte(ctx, new); return 0; } static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); int ret; if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; ret = stage2_map_walker_try_leaf(ctx, data); if (ret) return ret; mm_ops->free_unlinked_table(childp, ctx->level); return 0; } static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp, new; int ret; ret = stage2_map_walker_try_leaf(ctx, data); if (ret != -E2BIG) return ret; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; if (!data->memcache) return -ENOMEM; childp = mm_ops->zalloc_page(data->memcache); if (!childp) return -ENOMEM; if (!stage2_try_break_pte(ctx, data->mmu)) { mm_ops->put_page(childp); return -EAGAIN; } /* * If we've run into an existing block mapping then replace it with * a table. Accesses beyond 'end' that fall within the new table * will be mapped lazily. */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } /* * The TABLE_PRE callback runs for table entries on the way down, looking * for table entries which we could conceivably replace with a block entry * for this mapping. If it finds one it replaces the entry and calls * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table. * * Otherwise, the LEAF callback performs the mapping at the existing leaves * instead. */ static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct stage2_map_data *data = ctx->arg; switch (visit) { case KVM_PGTABLE_WALK_TABLE_PRE: return stage2_map_walk_table_pre(ctx, data); case KVM_PGTABLE_WALK_LEAF: return stage2_map_walk_leaf(ctx, data); default: return -EINVAL; } } 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) { int ret; struct stage2_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), .mmu = pgt->mmu, .memcache = mc, .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = flags | KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (WARN_ON((pgt->flags & KVM_PGTABLE_S2_IDMAP) && (addr != phys))) return -EINVAL; ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc, u8 owner_id) { int ret; struct stage2_map_data map_data = { .mmu = pgt->mmu, .memcache = mc, .owner_id = owner_id, .force_pte = true, .annotation = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (owner_id > KVM_MAX_OWNER_ID) return -EINVAL; ret = kvm_pgtable_walk(pgt, addr, size, &walker); return ret; } static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_s2_mmu *mmu = pgt->mmu; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = NULL; bool need_flush = false; if (!kvm_pte_valid(ctx->old)) { if (stage2_pte_is_counted(ctx->old)) { kvm_clear_pte(ctx->ptep); mm_ops->put_page(ctx->ptep); } return 0; } if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; } else if (stage2_pte_cacheable(pgt, ctx->old)) { need_flush = !stage2_has_fwb(pgt); } /* * This is similar to the map() path in that we unmap the entire * block entry and rely on the remaining portions being faulted * back lazily. */ stage2_unmap_put_pte(ctx, mmu, mm_ops); if (need_flush && mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); if (childp) mm_ops->put_page(childp); return 0; } int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { int ret; struct kvm_pgtable_walker walker = { .cb = stage2_unmap_walker, .arg = pgt, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (stage2_unmap_defer_tlb_flush(pgt)) /* Perform the deferred TLB invalidations */ kvm_tlb_flush_vmid_range(pgt->mmu, addr, size); return ret; } struct stage2_attr_data { kvm_pte_t attr_set; kvm_pte_t attr_clr; kvm_pte_t pte; s8 level; }; static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t pte = ctx->old; struct stage2_attr_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EAGAIN; data->level = ctx->level; data->pte = pte; pte &= ~data->attr_clr; pte |= data->attr_set; /* * We may race with the CPU trying to set the access flag here, * but worst-case the access flag update gets lost and will be * set on the next access instead. */ if (data->pte != pte) { /* * Invalidate instruction cache before updating the guest * stage-2 PTE if we are going to add executable permission. */ if (mm_ops->icache_inval_pou && stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), kvm_granule_size(ctx->level)); if (!stage2_try_set_pte(ctx, pte)) return -EAGAIN; } return 0; } static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, u64 size, kvm_pte_t attr_set, kvm_pte_t attr_clr, kvm_pte_t *orig_pte, s8 *level, enum kvm_pgtable_walk_flags flags) { int ret; kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI; struct stage2_attr_data data = { .attr_set = attr_set & attr_mask, .attr_clr = attr_clr & attr_mask, }; struct kvm_pgtable_walker walker = { .cb = stage2_attr_walker, .arg = &data, .flags = flags | KVM_PGTABLE_WALK_LEAF, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (ret) return ret; if (orig_pte) *orig_pte = data.pte; if (level) *level = data.level; return 0; } int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) { return stage2_update_leaf_attrs(pgt, addr, size, 0, KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, NULL, NULL, 0); } void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags) { int ret; ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, NULL, NULL, flags); if (!ret) dsb(ishst); } struct stage2_age_data { bool mkold; bool young; }; static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF; struct stage2_age_data *data = ctx->arg; if (!kvm_pte_valid(ctx->old) || new == ctx->old) return 0; data->young = true; /* * stage2_age_walker() is always called while holding the MMU lock for * write, so this will always succeed. Nonetheless, this deliberately * follows the race detection pattern of the other stage-2 walkers in * case the locking mechanics of the MMU notifiers is ever changed. */ if (data->mkold && !stage2_try_set_pte(ctx, new)) return -EAGAIN; /* * "But where's the TLBI?!", you scream. * "Over in the core code", I sigh. * * See the '->clear_flush_young()' callback on the KVM mmu notifier. */ return 0; } bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold) { struct stage2_age_data data = { .mkold = mkold, }; struct kvm_pgtable_walker walker = { .cb = stage2_age_walker, .arg = &data, .flags = KVM_PGTABLE_WALK_LEAF, }; WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); return data.young; } int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags) { int ret; s8 level; kvm_pte_t set = 0, clr = 0; if (prot & KVM_PTE_LEAF_ATTR_HI_SW) return -EINVAL; if (prot & KVM_PGTABLE_PROT_R) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (prot & KVM_PGTABLE_PROT_X) clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags); if (!ret || ret == -EAGAIN) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; } static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; if (!stage2_pte_cacheable(pgt, ctx->old)) return 0; if (mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); return 0; } int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm_pgtable_walker walker = { .cb = stage2_flush_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = pgt, }; if (stage2_has_fwb(pgt)) return 0; return kvm_pgtable_walk(pgt, addr, size, &walker); } 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) { struct stage2_map_data map_data = { .phys = phys, .mmu = pgt->mmu, .memcache = mc, .force_pte = force_pte, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_SKIP_BBM_TLBI | KVM_PGTABLE_WALK_SKIP_CMO, .arg = &map_data, }; /* * The input address (.addr) is irrelevant for walking an * unlinked table. Construct an ambiguous IA range to map * kvm_granule_size(level) worth of memory. */ struct kvm_pgtable_walk_data data = { .walker = &walker, .addr = 0, .end = kvm_granule_size(level), }; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t *pgtable; int ret; if (!IS_ALIGNED(phys, kvm_granule_size(level))) return ERR_PTR(-EINVAL); ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ERR_PTR(ret); pgtable = mm_ops->zalloc_page(mc); if (!pgtable) return ERR_PTR(-ENOMEM); ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable, level + 1); if (ret) { kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level); return ERR_PTR(ret); } return pgtable; } /* * Get the number of page-tables needed to replace a block with a * fully populated tree up to the PTE entries. Note that @level is * interpreted as in "level @level entry". */ static int stage2_block_get_nr_page_tables(s8 level) { switch (level) { case 1: return PTRS_PER_PTE + 1; case 2: return 1; case 3: return 0; default: WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL || level > KVM_PGTABLE_LAST_LEVEL); return -EINVAL; }; } static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; struct kvm_mmu_memory_cache *mc = ctx->arg; struct kvm_s2_mmu *mmu; kvm_pte_t pte = ctx->old, new, *childp; enum kvm_pgtable_prot prot; s8 level = ctx->level; bool force_pte; int nr_pages; u64 phys; /* No huge-pages exist at the last level */ if (level == KVM_PGTABLE_LAST_LEVEL) return 0; /* We only split valid block mappings */ if (!kvm_pte_valid(pte)) return 0; nr_pages = stage2_block_get_nr_page_tables(level); if (nr_pages < 0) return nr_pages; if (mc->nobjs >= nr_pages) { /* Build a tree mapped down to the PTE granularity. */ force_pte = true; } else { /* * Don't force PTEs, so create_unlinked() below does * not populate the tree up to the PTE level. The * consequence is that the call will require a single * page of level 2 entries at level 1, or a single * page of PTEs at level 2. If we are at level 1, the * PTEs will be created recursively. */ force_pte = false; nr_pages = 1; } if (mc->nobjs < nr_pages) return -ENOMEM; mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache); phys = kvm_pte_to_phys(pte); prot = kvm_pgtable_stage2_pte_prot(pte); childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys, level, prot, mc, force_pte); if (IS_ERR(childp)) return PTR_ERR(childp); if (!stage2_try_break_pte(ctx, mmu)) { kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); return -EAGAIN; } /* * Note, the contents of the page table are guaranteed to be made * visible before the new PTE is assigned because stage2_make_pte() * writes the PTE using smp_store_release(). */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc) { struct kvm_pgtable_walker walker = { .cb = stage2_split_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = mc, }; int ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } 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) { size_t pgd_sz; u64 vtcr = mmu->vtcr; u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = ia_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = mmu; pgt->flags = flags; pgt->force_pte_cb = force_pte_cb; /* Ensure zeroed PGD pages are visible to the hardware walker */ dsb(ishst); return 0; } size_t kvm_pgtable_stage2_pgd_size(u64 vtcr) { u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; } static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_pte_is_counted(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { size_t pgd_sz; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; struct kvm_pgtable_walk_data data = { .walker = &walker, /* * At this point the IPA really doesn't matter, as the page * table being traversed has already been removed from the stage * 2. Set an appropriate range to cover the entire page table. */ .addr = 0, .end = kvm_granule_size(level), }; WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); WARN_ON(mm_ops->page_count(pgtable) != 1); mm_ops->put_page(pgtable); } |
| 4 4 4 27 27 195 5 144 26 27 190 190 190 190 189 190 190 189 1 190 190 151 42 195 2 194 1 1 209 9 48 174 217 47 175 1 213 4 206 9 177 15 28 215 217 3 9 22 193 218 218 218 34 34 1 33 37 7 34 31 31 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/dnotify.h> #include <linux/compat.h> #include <linux/mnt_idmapping.h> #include <linux/filelock.h> #include "internal.h" int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { struct mnt_idmap *idmap; struct inode *inode; long error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; error = fsnotify_truncate_perm(path, length); if (error) return error; error = mnt_want_write(path->mnt); if (error) return error; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = security_path_truncate(path); if (!error) error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); return error; } EXPORT_SYMBOL_GPL(vfs_truncate); long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_truncate(&path, length); path_put(&path); } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return do_sys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return do_sys_truncate(path, length); } #endif long do_ftruncate(struct file *file, loff_t length, int small) { struct inode *inode; struct dentry *dentry; int error; /* explicitly opened as large or we are on 64-bit box */ if (file->f_flags & O_LARGEFILE) small = 0; dentry = file->f_path.dentry; inode = dentry->d_inode; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) return -EINVAL; /* Cannot ftruncate over 2^31 bytes without large file support */ if (small && length > MAX_NON_LFS) return -EINVAL; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; error = security_file_truncate(file); if (error) return error; error = fsnotify_truncate_perm(&file->f_path, length); if (error) return error; sb_start_write(inode->i_sb); error = do_truncate(file_mnt_idmap(file), dentry, length, ATTR_MTIME | ATTR_CTIME, file); sb_end_write(inode->i_sb); return error; } long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { if (length < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return do_ftruncate(fd_file(f), length, small); } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return do_sys_ftruncate(fd, length, 1); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return do_sys_ftruncate(fd, length, 0); } #endif /* BITS_PER_LONG == 32 */ #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64) COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname, compat_arg_u64_dual(length)) { return ksys_truncate(pathname, compat_arg_u64_glue(length)); } #endif #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64) COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd, compat_arg_u64_dual(length)) { return ksys_ftruncate(fd, compat_arg_u64_glue(length)); } #endif int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; loff_t sum; if (offset < 0 || len <= 0) return -EINVAL; if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* * Modes are exclusive, even if that is not obvious from the encoding * as bit masks and the mix with the flag in the same namespace. * * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is * encoded as no bit set. */ switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: case FALLOC_FL_UNSHARE_RANGE: case FALLOC_FL_ZERO_RANGE: break; case FALLOC_FL_PUNCH_HOLE: if (!(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; break; case FALLOC_FL_COLLAPSE_RANGE: case FALLOC_FL_INSERT_RANGE: if (mode & FALLOC_FL_KEEP_SIZE) return -EOPNOTSUPP; break; default: return -EOPNOTSUPP; } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wraparound */ if (check_add_overflow(offset, len, &sum)) return -EFBIG; if (sum > inode->i_sb->s_maxbytes) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fallocate(fd_file(f), mode, offset, len); } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE) COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset), compat_arg_u64_dual(len)) { return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset), compat_arg_u64_glue(len)); } #endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. * * Creating new credentials is expensive, so we try to skip doing it, * which we can if the result would match what we already got. */ static bool access_need_override_creds(int flags) { const struct cred *cred; if (flags & AT_EACCESS) return false; cred = current_cred(); if (!uid_eq(cred->fsuid, cred->uid) || !gid_eq(cred->fsgid, cred->gid)) return true; if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { if (!cap_isclear(cred->cap_effective)) return true; } else { if (!cap_isidentical(cred->cap_effective, cred->cap_permitted)) return true; } } return false; } static const struct cred *access_override_creds(void) { struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; /* * XXX access_need_override_creds performs checks in hopes of skipping * this work. Make sure it stays in sync if making any changes in this * routine. */ override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-racy to avoid RCU * freeing. */ override_cred->non_rcu = 1; return override_creds(override_cred); } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (access_need_override_creds(flags)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } retry: res = user_path_at(dfd, filename, lookup_flags, &path); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) put_cred(revert_creds(old_cred)); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; set_fs_pwd(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { CLASS(fd_raw, f)(fd); int error; if (fd_empty(f)) return -EBADF; if (!d_can_lookup(fd_file(f)->f_path.dentry)) return -ENOTDIR; error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &fd_file(f)->f_path); return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) goto dput_and_out; set_fs_root(current->fs, &path); error = 0; dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: inode_lock(inode); error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fchmod(fd_file(f), mode); } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode, unsigned int flags) { struct path path; int error; unsigned int lookup_flags; if (unlikely(flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))) return -EINVAL; lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(fchmodat2, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, flags) { return do_fchmodat(dfd, filename, mode, flags); } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode, 0); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode, 0); } /* * Check whether @kuid is valid and if so generate and set vfsuid_t in * ia_vfsuid. * * Return: true if @kuid is valid, false if not. */ static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid) { if (!uid_valid(kuid)) return false; attr->ia_valid |= ATTR_UID; attr->ia_vfsuid = VFSUIDT_INIT(kuid); return true; } /* * Check whether @kgid is valid and if so generate and set vfsgid_t in * ia_vfsgid. * * Return: true if @kgid is valid, false if not. */ static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid) { if (!gid_valid(kgid)) return false; attr->ia_valid |= ATTR_GID; attr->ia_vfsgid = VFSGIDT_INIT(kgid); return true; } int chown_common(const struct path *path, uid_t user, gid_t group) { struct mnt_idmap *idmap; struct user_namespace *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); idmap = mnt_idmap(path->mnt); fs_userns = i_user_ns(inode); retry_deleg: newattrs.ia_vfsuid = INVALID_VFSUID; newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid)) return -EINVAL; inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(idmap, inode); /* Continue to send actual fs values, not the mount values. */ error = security_path_chown( path, from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid), from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid)); if (!error) error = notify_change(idmap, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error = -EINVAL; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); if (error) goto out_release; error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fchown(fd_file(f), user, group); } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static inline int file_get_write_access(struct file *f) { int error; error = get_write_access(f->f_inode); if (unlikely(error)) return error; error = mnt_get_write_access(f->f_path.mnt); if (unlikely(error)) goto cleanup_inode; if (unlikely(f->f_mode & FMODE_BACKING)) { error = mnt_get_write_access(backing_file_user_path(f)->mnt); if (unlikely(error)) goto cleanup_mnt; } return 0; cleanup_mnt: mnt_put_write_access(f->f_path.mnt); cleanup_inode: put_write_access(f->f_inode); return error; } static int do_dentry_open(struct file *f, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; struct inode *inode = f->f_path.dentry->d_inode; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; file_set_fsnotify_mode(f, FMODE_NONOTIFY); f->f_op = &empty_fops; return 0; } if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = file_get_write_access(f); if (unlikely(error)) goto cleanup_file; f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (error) goto cleanup_all; /* * Set FMODE_NONOTIFY_* bits according to existing permission watches. * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a * pseudo file, this call will not change the mode. */ file_set_fsnotify_mode_from_watchers(f); error = fsnotify_open_perm(f); if (error) goto cleanup_all; error = break_lease(file_inode(f), f->f_flags); if (error) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; if ((f->f_mode & FMODE_LSEEK) && !f->f_op->llseek) f->f_mode &= ~FMODE_LSEEK; if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) f->f_mode |= FMODE_CAN_ODIRECT; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); f->f_iocb_flags = iocb_flags(f); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if (f->f_mode & FMODE_WRITE) { /* * Depends on full fence from get_write_access() to synchronize * against collapse_file() regarding i_writecount and nr_thps * updates. Ensures subsequent insertion of THPs into the page * cache will fail. */ if (filemap_nr_thps(inode->i_mapping)) { struct address_space *mapping = inode->i_mapping; filemap_invalidate_lock(inode->i_mapping); /* * unmap_mapping_range just need to be called once * here, because the private pages is not need to be * unmapped mapping (e.g. data segment of dynamic * shared libraries here). */ unmap_mapping_range(mapping, 0, 0, 0); truncate_inode_pages(mapping, 0); filemap_invalidate_unlock(inode->i_mapping); } } return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); put_file_access(f); cleanup_file: path_put(&f->f_path); f->f_path.mnt = NULL; f->f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; return do_dentry_open(file, open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry or NULL (as returned from ->lookup()) * * This can be used to set the result of a successful lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns "0" which must be the return value of ->atomic_open() after having * called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { file->f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized */ int vfs_open(const struct path *path, struct file *file) { int ret; file->f_path = *path; ret = do_dentry_open(file, NULL); if (!ret) { /* * Once we return a file with FMODE_OPENED, __fput() will call * fsnotify_close(), so we need fsnotify_open() here for * symmetry. */ fsnotify_open(file); } return ret; } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred) { struct file *f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { int error; file_set_fsnotify_mode(f, FMODE_NONOTIFY); error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } /** * dentry_create - Create and open a file * @path: path to create * @flags: O_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a "struct file *". Otherwise a ERR_PTR * is returned. */ struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *f; int error; f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; error = vfs_create(mnt_idmap(path->mnt), d_inode(path->dentry->d_parent), path->dentry, mode, true); if (!error) error = vfs_open(path, f); if (unlikely(error)) { fput(f); return ERR_PTR(error); } return f; } EXPORT_SYMBOL(dentry_create); /** * kernel_file_open - open a file for kernel internal use * @path: path of the file to open * @flags: open flags * @cred: credentials for open * * Open a file for use by in-kernel consumers. The file is not accounted * against nr_files and must not be installed into the file descriptor * table. * * Return: Opened file on success, an error pointer on failure. */ struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred) { struct file *f; int error; f = alloc_empty_file_noaccount(flags, cred); if (IS_ERR(f)) return f; f->f_path = *path; error = do_dentry_open(f, NULL); if (error) { fput(f); return ERR_PTR(error); } fsnotify_open(f); return f; } EXPORT_SYMBOL_GPL(kernel_file_open); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that aren't relevant in determining struct open_flags. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * Block bugs where O_DIRECTORY | O_CREAT created regular files. * Note, that blocking O_DIRECTORY | O_CREAT here also protects * O_TMPFILE below which requires O_DIRECTORY being raised. */ if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT)) return -EINVAL; /* Now handle the creative implementation of O_TMPFILE. */ if (flags & __O_TMPFILE) { /* * In order to ensure programs get explicit errors when trying * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY * is raised alongside __O_TMPFILE. */ if (!(flags & O_DIRECTORY)) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_filp_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { struct filename *name = getname_kernel(filename); struct file *file = ERR_CAST(name); if (!IS_ERR(name)) { file = file_open_name(name, flags, mode); putname(name); } return file; } EXPORT_SYMBOL(filp_open); struct file *file_open_root(const struct path *root, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(root, filename, &op); } EXPORT_SYMBOL(file_open_root); static long do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int fd = build_open_flags(how, &op); struct filename *tmp; if (fd) return fd; tmp = getname(filename); if (IS_ERR(tmp)) return PTR_ERR(tmp); fd = get_unused_fd_flags(how->flags); if (fd >= 0) { struct file *f = do_filp_open(dfd, tmp, &op); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else { fd_install(fd, f); } } putname(tmp); return fd; } long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; audit_openat2_how(&tmp); /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ static int filp_flush(struct file *filp, fl_owner_t id) { int retval = 0; if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp, "VFS: Close: file count is 0 (f_op=%ps)", filp->f_op)) { return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } return retval; } int filp_close(struct file *filp, fl_owner_t id) { int retval; retval = filp_flush(filp, id); fput(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval; struct file *file; file = file_close_fd(fd); if (!file) return -EBADF; retval = filp_flush(file, current->files); /* * We're returning to user space. Don't bother * with any delayed fput() cases. */ __fput_sync(file); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; return retval; } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 312 312 | 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_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 108 93 92 92 95 93 93 123 123 124 78 77 77 49 135 135 134 135 2 2 2 91 46 46 2 91 3 37 36 1 37 92 92 92 92 49 52 91 91 76 76 76 76 76 76 76 76 76 90 90 91 91 91 91 91 91 91 91 91 48 51 91 91 91 91 90 91 91 91 91 91 91 91 91 46 1 75 76 76 76 76 46 1 45 45 46 75 75 75 73 2 2 1 75 75 50 1 48 49 251 5 1 1 1 1 1 2 6 1 1 1 1 1 1 2 2 9 52 51 52 50 94 1 50 52 1 50 4 4 1 2 3 1 1 1 3 1 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/uaccess.h> #include <clocksource/arm_arch_timer.h> #include <asm/arch_timer.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> #include "trace.h" static struct timecounter *timecounter; static unsigned int host_vtimer_irq; static unsigned int host_ptimer_irq; static u32 host_vtimer_irq_flags; static u32 host_ptimer_irq_flags; static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); DEFINE_STATIC_KEY_FALSE(broken_cntvoff_key); static const u8 default_ppi[] = { [TIMER_PTIMER] = 30, [TIMER_VTIMER] = 27, [TIMER_HPTIMER] = 26, [TIMER_HVTIMER] = 28, }; static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx); static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx); static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg, u64 val); static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg); static bool kvm_arch_timer_get_input_level(int vintid); static struct irq_ops arch_timer_irq_ops = { .get_input_level = kvm_arch_timer_get_input_level, }; static int nr_timers(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) return NR_KVM_EL0_TIMERS; return NR_KVM_TIMERS; } u32 timer_get_ctl(struct arch_timer_context *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; switch(arch_timer_ctx_index(ctxt)) { case TIMER_VTIMER: return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); case TIMER_PTIMER: return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); case TIMER_HVTIMER: return __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2); case TIMER_HPTIMER: return __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2); default: WARN_ON(1); return 0; } } u64 timer_get_cval(struct arch_timer_context *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; switch(arch_timer_ctx_index(ctxt)) { case TIMER_VTIMER: return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); case TIMER_PTIMER: return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); case TIMER_HVTIMER: return __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2); case TIMER_HPTIMER: return __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); default: WARN_ON(1); return 0; } } static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) { struct kvm_vcpu *vcpu = ctxt->vcpu; switch(arch_timer_ctx_index(ctxt)) { case TIMER_VTIMER: __vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl; break; case TIMER_PTIMER: __vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl; break; case TIMER_HVTIMER: __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl; break; case TIMER_HPTIMER: __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl; break; default: WARN_ON(1); } } static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval) { struct kvm_vcpu *vcpu = ctxt->vcpu; switch(arch_timer_ctx_index(ctxt)) { case TIMER_VTIMER: __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval; break; case TIMER_PTIMER: __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval; break; case TIMER_HVTIMER: __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval; break; case TIMER_HPTIMER: __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval; break; default: WARN_ON(1); } } static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) { if (!ctxt->offset.vm_offset) { WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt)); return; } WRITE_ONCE(*ctxt->offset.vm_offset, offset); } u64 kvm_phys_timer_read(void) { return timecounter->cc->read(timecounter->cc); } void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) { if (vcpu_has_nv(vcpu)) { if (is_hyp_ctxt(vcpu)) { map->direct_vtimer = vcpu_hvtimer(vcpu); map->direct_ptimer = vcpu_hptimer(vcpu); map->emul_vtimer = vcpu_vtimer(vcpu); map->emul_ptimer = vcpu_ptimer(vcpu); } else { map->direct_vtimer = vcpu_vtimer(vcpu); map->direct_ptimer = vcpu_ptimer(vcpu); map->emul_vtimer = vcpu_hvtimer(vcpu); map->emul_ptimer = vcpu_hptimer(vcpu); } } else if (has_vhe()) { map->direct_vtimer = vcpu_vtimer(vcpu); map->direct_ptimer = vcpu_ptimer(vcpu); map->emul_vtimer = NULL; map->emul_ptimer = NULL; } else { map->direct_vtimer = vcpu_vtimer(vcpu); map->direct_ptimer = NULL; map->emul_vtimer = NULL; map->emul_ptimer = vcpu_ptimer(vcpu); } trace_kvm_get_timer_map(vcpu->vcpu_id, map); } static inline bool userspace_irqchip(struct kvm *kvm) { return unlikely(!irqchip_in_kernel(kvm)); } static void soft_timer_start(struct hrtimer *hrt, u64 ns) { hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), HRTIMER_MODE_ABS_HARD); } static void soft_timer_cancel(struct hrtimer *hrt) { hrtimer_cancel(hrt); } static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; struct arch_timer_context *ctx; struct timer_map map; /* * We may see a timer interrupt after vcpu_put() has been called which * sets the CPU's vcpu pointer to NULL, because even though the timer * has been disabled in timer_save_state(), the hardware interrupt * signal may not have been retired from the interrupt controller yet. */ if (!vcpu) return IRQ_HANDLED; get_timer_map(vcpu, &map); if (irq == host_vtimer_irq) ctx = map.direct_vtimer; else ctx = map.direct_ptimer; if (kvm_timer_should_fire(ctx)) kvm_timer_update_irq(vcpu, true, ctx); if (userspace_irqchip(vcpu->kvm) && !static_branch_unlikely(&has_gic_active_state)) disable_percpu_irq(host_vtimer_irq); return IRQ_HANDLED; } static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx, u64 val) { u64 now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); if (now < val) { u64 ns; ns = cyclecounter_cyc2ns(timecounter->cc, val - now, timecounter->mask, &timer_ctx->ns_frac); return ns; } return 0; } static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) { return kvm_counter_compute_delta(timer_ctx, timer_get_cval(timer_ctx)); } static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) { WARN_ON(timer_ctx && timer_ctx->loaded); return timer_ctx && ((timer_get_ctl(timer_ctx) & (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE); } static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu) { return (cpus_have_final_cap(ARM64_HAS_WFXT) && vcpu_get_flag(vcpu, IN_WFIT)); } static u64 wfit_delay_ns(struct kvm_vcpu *vcpu) { u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); struct arch_timer_context *ctx; ctx = is_hyp_ctxt(vcpu) ? vcpu_hvtimer(vcpu) : vcpu_vtimer(vcpu); return kvm_counter_compute_delta(ctx, val); } /* * Returns the earliest expiration time in ns among guest timers. * Note that it will return 0 if none of timers can fire. */ static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) { u64 min_delta = ULLONG_MAX; int i; for (i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i]; WARN(ctx->loaded, "timer %d loaded\n", i); if (kvm_timer_irq_can_fire(ctx)) min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); } if (vcpu_has_wfit_active(vcpu)) min_delta = min(min_delta, wfit_delay_ns(vcpu)); /* If none of timers can fire, then return 0 */ if (min_delta == ULLONG_MAX) return 0; return min_delta; } static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt) { struct arch_timer_cpu *timer; struct kvm_vcpu *vcpu; u64 ns; timer = container_of(hrt, struct arch_timer_cpu, bg_timer); vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu); /* * Check that the timer has really expired from the guest's * PoV (NTP on the host may have forced it to expire * early). If we should have slept longer, restart it. */ ns = kvm_timer_earliest_exp(vcpu); if (unlikely(ns)) { hrtimer_forward_now(hrt, ns_to_ktime(ns)); return HRTIMER_RESTART; } kvm_vcpu_wake_up(vcpu); return HRTIMER_NORESTART; } static enum hrtimer_restart kvm_hrtimer_expire(struct hrtimer *hrt) { struct arch_timer_context *ctx; struct kvm_vcpu *vcpu; u64 ns; ctx = container_of(hrt, struct arch_timer_context, hrtimer); vcpu = ctx->vcpu; trace_kvm_timer_hrtimer_expire(ctx); /* * Check that the timer has really expired from the guest's * PoV (NTP on the host may have forced it to expire * early). If not ready, schedule for a later time. */ ns = kvm_timer_compute_delta(ctx); if (unlikely(ns)) { hrtimer_forward_now(hrt, ns_to_ktime(ns)); return HRTIMER_RESTART; } kvm_timer_update_irq(vcpu, true, ctx); return HRTIMER_NORESTART; } static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) { enum kvm_arch_timers index; u64 cval, now; if (!timer_ctx) return false; index = arch_timer_ctx_index(timer_ctx); if (timer_ctx->loaded) { u32 cnt_ctl = 0; switch (index) { case TIMER_VTIMER: case TIMER_HVTIMER: cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); break; case TIMER_PTIMER: case TIMER_HPTIMER: cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); break; case NR_KVM_TIMERS: /* GCC is braindead */ cnt_ctl = 0; break; } return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); } if (!kvm_timer_irq_can_fire(timer_ctx)) return false; cval = timer_get_cval(timer_ctx); now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); return cval <= now; } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0; } /* * Reflect the timer output level into the kvm_run structure */ void kvm_timer_update_run(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); struct kvm_sync_regs *regs = &vcpu->run->s.regs; /* Populate the device bitmap with the timer states */ regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER | KVM_ARM_DEV_EL1_PTIMER); if (kvm_timer_should_fire(vtimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; if (kvm_timer_should_fire(ptimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; } static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level) { /* * Paper over NV2 brokenness by publishing the interrupt status * bit. This still results in a poor quality of emulation (guest * writes will have no effect until the next exit). * * But hey, it's fast, right? */ if (is_hyp_ctxt(ctx->vcpu) && (ctx == vcpu_vtimer(ctx->vcpu) || ctx == vcpu_ptimer(ctx->vcpu))) { unsigned long val = timer_get_ctl(ctx); __assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &val, level); timer_set_ctl(ctx, val); } } static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx) { kvm_timer_update_status(timer_ctx, new_level); timer_ctx->irq.level = new_level; trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); if (userspace_irqchip(vcpu->kvm)) return; kvm_vgic_inject_irq(vcpu->kvm, vcpu, timer_irq(timer_ctx), timer_ctx->irq.level, timer_ctx); } /* Only called for a fully emulated timer */ static void timer_emulate(struct arch_timer_context *ctx) { bool should_fire = kvm_timer_should_fire(ctx); trace_kvm_timer_emulate(ctx, should_fire); if (should_fire != ctx->irq.level) kvm_timer_update_irq(ctx->vcpu, should_fire, ctx); kvm_timer_update_status(ctx, should_fire); /* * If the timer can fire now, we don't need to have a soft timer * scheduled for the future. If the timer cannot fire at all, * then we also don't need a soft timer. */ if (should_fire || !kvm_timer_irq_can_fire(ctx)) return; soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); } static void set_cntvoff(u64 cntvoff) { kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); } static void set_cntpoff(u64 cntpoff) { if (has_cntpoff()) write_sysreg_s(cntpoff, SYS_CNTPOFF_EL2); } static void timer_save_state(struct arch_timer_context *ctx) { struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); enum kvm_arch_timers index = arch_timer_ctx_index(ctx); unsigned long flags; if (!timer->enabled) return; local_irq_save(flags); if (!ctx->loaded) goto out; switch (index) { u64 cval; case TIMER_VTIMER: case TIMER_HVTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL)); cval = read_sysreg_el0(SYS_CNTV_CVAL); if (has_broken_cntvoff()) cval -= timer_get_offset(ctx); timer_set_cval(ctx, cval); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTV_CTL); isb(); /* * The kernel may decide to run userspace after * calling vcpu_put, so we reset cntvoff to 0 to * ensure a consistent read between user accesses to * the virtual counter and kernel access to the * physical counter of non-VHE case. * * For VHE, the virtual counter uses a fixed virtual * offset of zero, so no need to zero CNTVOFF_EL2 * register, but this is actually useful when switching * between EL1/vEL2 with NV. * * Do it unconditionally, as this is either unavoidable * or dirt cheap. */ set_cntvoff(0); break; case TIMER_PTIMER: case TIMER_HPTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); cval = read_sysreg_el0(SYS_CNTP_CVAL); cval -= timer_get_offset(ctx); timer_set_cval(ctx, cval); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTP_CTL); isb(); set_cntpoff(0); break; case NR_KVM_TIMERS: BUG(); } trace_kvm_timer_save_state(ctx); ctx->loaded = false; out: local_irq_restore(flags); } /* * Schedule the background timer before calling kvm_vcpu_halt, so that this * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ static void kvm_timer_blocking(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; get_timer_map(vcpu, &map); /* * If no timers are capable of raising interrupts (disabled or * masked), then there's no more work for us to do. */ if (!kvm_timer_irq_can_fire(map.direct_vtimer) && !kvm_timer_irq_can_fire(map.direct_ptimer) && !kvm_timer_irq_can_fire(map.emul_vtimer) && !kvm_timer_irq_can_fire(map.emul_ptimer) && !vcpu_has_wfit_active(vcpu)) return; /* * At least one guest time will expire. Schedule a background timer. * Set the earliest expiration time among the guest timers. */ soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu)); } static void kvm_timer_unblocking(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); soft_timer_cancel(&timer->bg_timer); } static void timer_restore_state(struct arch_timer_context *ctx) { struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); enum kvm_arch_timers index = arch_timer_ctx_index(ctx); unsigned long flags; if (!timer->enabled) return; local_irq_save(flags); if (ctx->loaded) goto out; switch (index) { u64 cval, offset; case TIMER_VTIMER: case TIMER_HVTIMER: cval = timer_get_cval(ctx); offset = timer_get_offset(ctx); if (has_broken_cntvoff()) { set_cntvoff(0); cval += offset; } else { set_cntvoff(offset); } write_sysreg_el0(cval, SYS_CNTV_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; case TIMER_PTIMER: case TIMER_HPTIMER: cval = timer_get_cval(ctx); offset = timer_get_offset(ctx); set_cntpoff(offset); cval += offset; write_sysreg_el0(cval, SYS_CNTP_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); break; case NR_KVM_TIMERS: BUG(); } trace_kvm_timer_restore_state(ctx); ctx->loaded = true; out: local_irq_restore(flags); } static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) { int r; r = irq_set_irqchip_state(ctx->host_timer_irq, IRQCHIP_STATE_ACTIVE, active); WARN_ON(r); } static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) { struct kvm_vcpu *vcpu = ctx->vcpu; bool phys_active = false; /* * Update the timer output so that it is likely to match the * state we're about to restore. If the timer expires between * this point and the register restoration, we'll take the * interrupt anyway. */ kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx); if (irqchip_in_kernel(vcpu->kvm)) phys_active = kvm_vgic_map_is_active(vcpu, timer_irq(ctx)); phys_active |= ctx->irq.level; set_timer_irq_phys_active(ctx, phys_active); } static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); /* * Update the timer output so that it is likely to match the * state we're about to restore. If the timer expires between * this point and the register restoration, we'll take the * interrupt anyway. */ kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer); /* * When using a userspace irqchip with the architected timers and a * host interrupt controller that doesn't support an active state, we * must still prevent continuously exiting from the guest, and * therefore mask the physical interrupt by disabling it on the host * interrupt controller when the virtual level is high, such that the * guest can make forward progress. Once we detect the output level * being de-asserted, we unmask the interrupt again so that we exit * from the guest when the timer fires. */ if (vtimer->irq.level) disable_percpu_irq(host_vtimer_irq); else enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } /* If _pred is true, set bit in _set, otherwise set it in _clr */ #define assign_clear_set_bit(_pred, _bit, _clr, _set) \ do { \ if (_pred) \ (_set) |= (_bit); \ else \ (_clr) |= (_bit); \ } while (0) static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, struct timer_map *map) { int hw, ret; if (!irqchip_in_kernel(vcpu->kvm)) return; /* * We only ever unmap the vtimer irq on a VHE system that runs nested * virtualization, in which case we have both a valid emul_vtimer, * emul_ptimer, direct_vtimer, and direct_ptimer. * * Since this is called from kvm_timer_vcpu_load(), a change between * vEL2 and vEL1/0 will have just happened, and the timer_map will * represent this, and therefore we switch the emul/direct mappings * below. */ hw = kvm_vgic_get_map(vcpu, timer_irq(map->direct_vtimer)); if (hw < 0) { kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_vtimer)); kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_ptimer)); ret = kvm_vgic_map_phys_irq(vcpu, map->direct_vtimer->host_timer_irq, timer_irq(map->direct_vtimer), &arch_timer_irq_ops); WARN_ON_ONCE(ret); ret = kvm_vgic_map_phys_irq(vcpu, map->direct_ptimer->host_timer_irq, timer_irq(map->direct_ptimer), &arch_timer_irq_ops); WARN_ON_ONCE(ret); } } static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) { bool tvt, tpt, tvc, tpc, tvt02, tpt02; u64 clr, set; /* * No trapping gets configured here with nVHE. See * __timer_enable_traps(), which is where the stuff happens. */ if (!has_vhe()) return; /* * Our default policy is not to trap anything. As we progress * within this function, reality kicks in and we start adding * traps based on emulation requirements. */ tvt = tpt = tvc = tpc = false; tvt02 = tpt02 = false; /* * NV2 badly breaks the timer semantics by redirecting accesses to * the EL1 timer state to memory, so let's call ECV to the rescue if * available: we trap all CNT{P,V}_{CTL,CVAL,TVAL}_EL0 accesses. * * The treatment slightly varies depending whether we run a nVHE or * VHE guest: nVHE will use the _EL0 registers directly, while VHE * will use the _EL02 accessors. This translates in different trap * bits. * * None of the trapping is required when running in non-HYP context, * unless required by the L1 hypervisor settings once we advertise * ECV+NV in the guest, or that we need trapping for other reasons. */ if (cpus_have_final_cap(ARM64_HAS_ECV) && is_hyp_ctxt(vcpu)) { if (vcpu_el2_e2h_is_set(vcpu)) tvt02 = tpt02 = true; else tvt = tpt = true; } /* * We have two possibility to deal with a physical offset: * * - Either we have CNTPOFF (yay!) or the offset is 0: * we let the guest freely access the HW * * - or neither of these condition apply: * we trap accesses to the HW, but still use it * after correcting the physical offset */ if (!has_cntpoff() && timer_get_offset(map->direct_ptimer)) tpt = tpc = true; /* * For the poor sods that could not correctly substract one value * from another, trap the full virtual timer and counter. */ if (has_broken_cntvoff() && timer_get_offset(map->direct_vtimer)) tvt = tvc = true; /* * Apply the enable bits that the guest hypervisor has requested for * its own guest. We can only add traps that wouldn't have been set * above. * Implementation choices: we do not support NV when E2H=0 in the * guest, and we don't support configuration where E2H is writable * by the guest (either FEAT_VHE or FEAT_E2H0 is implemented, but * not both). This simplifies the handling of the EL1NV* bits. */ if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); /* Use the VHE format for mental sanity */ if (!vcpu_el2_e2h_is_set(vcpu)) val = (val & (CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN)) << 10; tpt |= !(val & (CNTHCTL_EL1PCEN << 10)); tpc |= !(val & (CNTHCTL_EL1PCTEN << 10)); tpt02 |= (val & CNTHCTL_EL1NVPCT); tvt02 |= (val & CNTHCTL_EL1NVVCT); } /* * Now that we have collected our requirements, compute the * trap and enable bits. */ set = 0; clr = 0; assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr); assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr); assign_clear_set_bit(tvt, CNTHCTL_EL1TVT, clr, set); assign_clear_set_bit(tvc, CNTHCTL_EL1TVCT, clr, set); assign_clear_set_bit(tvt02, CNTHCTL_EL1NVVCT, clr, set); assign_clear_set_bit(tpt02, CNTHCTL_EL1NVPCT, clr, set); /* This only happens on VHE, so use the CNTHCTL_EL2 accessor. */ sysreg_clear_set(cnthctl_el2, clr, set); } void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; if (unlikely(!timer->enabled)) return; get_timer_map(vcpu, &map); if (static_branch_likely(&has_gic_active_state)) { if (vcpu_has_nv(vcpu)) kvm_timer_vcpu_load_nested_switch(vcpu, &map); kvm_timer_vcpu_load_gic(map.direct_vtimer); if (map.direct_ptimer) kvm_timer_vcpu_load_gic(map.direct_ptimer); } else { kvm_timer_vcpu_load_nogic(vcpu); } kvm_timer_unblocking(vcpu); timer_restore_state(map.direct_vtimer); if (map.direct_ptimer) timer_restore_state(map.direct_ptimer); if (map.emul_vtimer) timer_emulate(map.emul_vtimer); if (map.emul_ptimer) timer_emulate(map.emul_ptimer); timer_set_traps(vcpu, &map); } bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); struct kvm_sync_regs *sregs = &vcpu->run->s.regs; bool vlevel, plevel; if (likely(irqchip_in_kernel(vcpu->kvm))) return false; vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER; plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER; return kvm_timer_should_fire(vtimer) != vlevel || kvm_timer_should_fire(ptimer) != plevel; } void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; if (unlikely(!timer->enabled)) return; get_timer_map(vcpu, &map); timer_save_state(map.direct_vtimer); if (map.direct_ptimer) timer_save_state(map.direct_ptimer); /* * Cancel soft timer emulation, because the only case where we * need it after a vcpu_put is in the context of a sleeping VCPU, and * in that case we already factor in the deadline for the physical * timer when scheduling the bg_timer. * * In any case, we re-schedule the hrtimer for the physical timer when * coming back to the VCPU thread in kvm_timer_vcpu_load(). */ if (map.emul_vtimer) soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); } void kvm_timer_sync_nested(struct kvm_vcpu *vcpu) { /* * When NV2 is on, guest hypervisors have their EL1 timer register * accesses redirected to the VNCR page. Any guest action taken on * the timer is postponed until the next exit, leading to a very * poor quality of emulation. * * This is an unmitigated disaster, only papered over by FEAT_ECV, * which allows trapping of the timer registers even with NV2. * Still, this is still worse than FEAT_NV on its own. Meh. */ if (!cpus_have_final_cap(ARM64_HAS_ECV)) { /* * For a VHE guest hypervisor, the EL2 state is directly * stored in the host EL1 timers, while the emulated EL1 * state is stored in the VNCR page. The latter could have * been updated behind our back, and we must reset the * emulation of the timers. * * A non-VHE guest hypervisor doesn't have any direct access * to its timers: the EL2 registers trap despite being * notionally direct (we use the EL1 HW, as for VHE), while * the EL1 registers access memory. * * In both cases, process the emulated timers on each guest * exit. Boo. */ struct timer_map map; get_timer_map(vcpu, &map); soft_timer_cancel(&map.emul_vtimer->hrtimer); soft_timer_cancel(&map.emul_ptimer->hrtimer); timer_emulate(map.emul_vtimer); timer_emulate(map.emul_ptimer); } } /* * With a userspace irqchip we have to check if the guest de-asserted the * timer and if so, unmask the timer irq signal on the host interrupt * controller to ensure that we see future timer signals. */ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); if (!kvm_timer_should_fire(vtimer)) { kvm_timer_update_irq(vcpu, false, vtimer); if (static_branch_likely(&has_gic_active_state)) set_timer_irq_phys_active(vtimer, false); else enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } } void kvm_timer_sync_user(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); if (unlikely(!timer->enabled)) return; if (unlikely(!irqchip_in_kernel(vcpu->kvm))) unmask_vtimer_irq_user(vcpu); } void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; get_timer_map(vcpu, &map); /* * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8 * and to 0 for ARMv7. We provide an implementation that always * resets the timer to be disabled and unmasked and is compliant with * the ARMv7 architecture. */ for (int i = 0; i < nr_timers(vcpu); i++) timer_set_ctl(vcpu_get_timer(vcpu, i), 0); /* * A vcpu running at EL2 is in charge of the offset applied to * the virtual timer, so use the physical VM offset, and point * the vcpu offset to CNTVOFF_EL2. */ if (vcpu_has_nv(vcpu)) { struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset; offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2); offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset; } if (timer->enabled) { for (int i = 0; i < nr_timers(vcpu); i++) kvm_timer_update_irq(vcpu, false, vcpu_get_timer(vcpu, i)); if (irqchip_in_kernel(vcpu->kvm)) { kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_vtimer)); if (map.direct_ptimer) kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_ptimer)); } } if (map.emul_vtimer) soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); } static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) { struct arch_timer_context *ctxt = vcpu_get_timer(vcpu, timerid); struct kvm *kvm = vcpu->kvm; ctxt->vcpu = vcpu; if (timerid == TIMER_VTIMER) ctxt->offset.vm_offset = &kvm->arch.timer_data.voffset; else ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset; hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ctxt->hrtimer.function = kvm_hrtimer_expire; switch (timerid) { case TIMER_PTIMER: case TIMER_HPTIMER: ctxt->host_timer_irq = host_ptimer_irq; break; case TIMER_VTIMER: case TIMER_HVTIMER: ctxt->host_timer_irq = host_vtimer_irq; break; } } void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); for (int i = 0; i < NR_KVM_TIMERS; i++) timer_context_init(vcpu, i); /* Synchronize offsets across timers of a VM if not already provided */ if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { timer_set_offset(vcpu_vtimer(vcpu), kvm_phys_timer_read()); timer_set_offset(vcpu_ptimer(vcpu), 0); } hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; } void kvm_timer_init_vm(struct kvm *kvm) { for (int i = 0; i < NR_KVM_TIMERS; i++) kvm->arch.timer_data.ppi[i] = default_ppi[i]; } void kvm_timer_cpu_up(void) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); if (host_ptimer_irq) enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); } void kvm_timer_cpu_down(void) { disable_percpu_irq(host_vtimer_irq); if (host_ptimer_irq) disable_percpu_irq(host_ptimer_irq); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) { struct arch_timer_context *timer; switch (regid) { case KVM_REG_ARM_TIMER_CTL: timer = vcpu_vtimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_TIMER_CNT: if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { timer = vcpu_vtimer(vcpu); timer_set_offset(timer, kvm_phys_timer_read() - value); } break; case KVM_REG_ARM_TIMER_CVAL: timer = vcpu_vtimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); break; case KVM_REG_ARM_PTIMER_CTL: timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_PTIMER_CNT: if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { timer = vcpu_ptimer(vcpu); timer_set_offset(timer, kvm_phys_timer_read() - value); } break; case KVM_REG_ARM_PTIMER_CVAL: timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); break; default: return -1; } return 0; } static u64 read_timer_ctl(struct arch_timer_context *timer) { /* * Set ISTATUS bit if it's expired. * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit * regardless of ENABLE bit for our implementation convenience. */ u32 ctl = timer_get_ctl(timer); if (!kvm_timer_compute_delta(timer)) ctl |= ARCH_TIMER_CTRL_IT_STAT; return ctl; } u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) { switch (regid) { case KVM_REG_ARM_TIMER_CTL: return kvm_arm_timer_read(vcpu, vcpu_vtimer(vcpu), TIMER_REG_CTL); case KVM_REG_ARM_TIMER_CNT: return kvm_arm_timer_read(vcpu, vcpu_vtimer(vcpu), TIMER_REG_CNT); case KVM_REG_ARM_TIMER_CVAL: return kvm_arm_timer_read(vcpu, vcpu_vtimer(vcpu), TIMER_REG_CVAL); case KVM_REG_ARM_PTIMER_CTL: return kvm_arm_timer_read(vcpu, vcpu_ptimer(vcpu), TIMER_REG_CTL); case KVM_REG_ARM_PTIMER_CNT: return kvm_arm_timer_read(vcpu, vcpu_ptimer(vcpu), TIMER_REG_CNT); case KVM_REG_ARM_PTIMER_CVAL: return kvm_arm_timer_read(vcpu, vcpu_ptimer(vcpu), TIMER_REG_CVAL); } return (u64)-1; } static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg) { u64 val; switch (treg) { case TIMER_REG_TVAL: val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer); val = lower_32_bits(val); break; case TIMER_REG_CTL: val = read_timer_ctl(timer); break; case TIMER_REG_CVAL: val = timer_get_cval(timer); break; case TIMER_REG_CNT: val = kvm_phys_timer_read() - timer_get_offset(timer); break; case TIMER_REG_VOFF: val = *timer->offset.vcpu_offset; break; default: BUG(); } return val; } u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg) { struct arch_timer_context *timer; struct timer_map map; u64 val; get_timer_map(vcpu, &map); timer = vcpu_get_timer(vcpu, tmr); if (timer == map.emul_vtimer || timer == map.emul_ptimer) return kvm_arm_timer_read(vcpu, timer, treg); preempt_disable(); timer_save_state(timer); val = kvm_arm_timer_read(vcpu, timer, treg); timer_restore_state(timer); preempt_enable(); return val; } static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg, u64 val) { switch (treg) { case TIMER_REG_TVAL: timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val); break; case TIMER_REG_CTL: timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT); break; case TIMER_REG_CVAL: timer_set_cval(timer, val); break; case TIMER_REG_VOFF: *timer->offset.vcpu_offset = val; break; default: BUG(); } } void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg, u64 val) { struct arch_timer_context *timer; struct timer_map map; get_timer_map(vcpu, &map); timer = vcpu_get_timer(vcpu, tmr); if (timer == map.emul_vtimer || timer == map.emul_ptimer) { soft_timer_cancel(&timer->hrtimer); kvm_arm_timer_write(vcpu, timer, treg, val); timer_emulate(timer); } else { preempt_disable(); timer_save_state(timer); kvm_arm_timer_write(vcpu, timer, treg, val); timer_restore_state(timer); preempt_enable(); } } static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (vcpu) irqd_set_forwarded_to_vcpu(d); else irqd_clr_forwarded_to_vcpu(d); return 0; } static int timer_irq_set_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool val) { if (which != IRQCHIP_STATE_ACTIVE || !irqd_is_forwarded_to_vcpu(d)) return irq_chip_set_parent_state(d, which, val); if (val) irq_chip_mask_parent(d); else irq_chip_unmask_parent(d); return 0; } static void timer_irq_eoi(struct irq_data *d) { if (!irqd_is_forwarded_to_vcpu(d)) irq_chip_eoi_parent(d); } static void timer_irq_ack(struct irq_data *d) { d = d->parent_data; if (d->chip->irq_ack) d->chip->irq_ack(d); } static struct irq_chip timer_chip = { .name = "KVM", .irq_ack = timer_irq_ack, .irq_mask = irq_chip_mask_parent, .irq_unmask = irq_chip_unmask_parent, .irq_eoi = timer_irq_eoi, .irq_set_type = irq_chip_set_type_parent, .irq_set_vcpu_affinity = timer_irq_set_vcpu_affinity, .irq_set_irqchip_state = timer_irq_set_irqchip_state, }; static int timer_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { irq_hw_number_t hwirq = (uintptr_t)arg; return irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &timer_chip, NULL); } static void timer_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { } static const struct irq_domain_ops timer_domain_ops = { .alloc = timer_irq_domain_alloc, .free = timer_irq_domain_free, }; static void kvm_irq_fixup_flags(unsigned int virq, u32 *flags) { *flags = irq_get_trigger_type(virq); if (*flags != IRQF_TRIGGER_HIGH && *flags != IRQF_TRIGGER_LOW) { kvm_err("Invalid trigger for timer IRQ%d, assuming level low\n", virq); *flags = IRQF_TRIGGER_LOW; } } static int kvm_irq_init(struct arch_timer_kvm_info *info) { struct irq_domain *domain = NULL; if (info->virtual_irq <= 0) { kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n", info->virtual_irq); return -ENODEV; } host_vtimer_irq = info->virtual_irq; kvm_irq_fixup_flags(host_vtimer_irq, &host_vtimer_irq_flags); if (kvm_vgic_global_state.no_hw_deactivation) { struct fwnode_handle *fwnode; struct irq_data *data; fwnode = irq_domain_alloc_named_fwnode("kvm-timer"); if (!fwnode) return -ENOMEM; /* Assume both vtimer and ptimer in the same parent */ data = irq_get_irq_data(host_vtimer_irq); domain = irq_domain_create_hierarchy(data->domain, 0, NR_KVM_TIMERS, fwnode, &timer_domain_ops, NULL); if (!domain) { irq_domain_free_fwnode(fwnode); return -ENOMEM; } arch_timer_irq_ops.flags |= VGIC_IRQ_SW_RESAMPLE; WARN_ON(irq_domain_push_irq(domain, host_vtimer_irq, (void *)TIMER_VTIMER)); } if (info->physical_irq > 0) { host_ptimer_irq = info->physical_irq; kvm_irq_fixup_flags(host_ptimer_irq, &host_ptimer_irq_flags); if (domain) WARN_ON(irq_domain_push_irq(domain, host_ptimer_irq, (void *)TIMER_PTIMER)); } return 0; } static void kvm_timer_handle_errata(void) { u64 mmfr0, mmfr1, mmfr4; /* * CNTVOFF_EL2 is broken on some implementations. For those, we trap * all virtual timer/counter accesses, requiring FEAT_ECV. * * However, a hypervisor supporting nesting is likely to mitigate the * erratum at L0, and not require other levels to mitigate it (which * would otherwise be a terrible performance sink due to trap * amplification). * * Given that the affected HW implements both FEAT_VHE and FEAT_E2H0, * and that NV is likely not to (because of limitations of the * architecture), only enable the workaround when FEAT_VHE and * FEAT_E2H0 are both detected. Time will tell if this actually holds. */ mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); mmfr4 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR4_EL1); if (SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1) && !SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4) && SYS_FIELD_GET(ID_AA64MMFR0_EL1, ECV, mmfr0) && (has_vhe() || has_hvhe()) && cpus_have_final_cap(ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF)) { static_branch_enable(&broken_cntvoff_key); kvm_info("Broken CNTVOFF_EL2, trapping virtual timer\n"); } } int __init kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; int err; info = arch_timer_get_kvm_info(); timecounter = &info->timecounter; if (!timecounter->cc) { kvm_err("kvm_arch_timer: uninitialized timecounter\n"); return -ENODEV; } err = kvm_irq_init(info); if (err) return err; /* First, do the virtual EL1 timer irq */ err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, "kvm guest vtimer", kvm_get_running_vcpus()); if (err) { kvm_err("kvm_arch_timer: can't request vtimer interrupt %d (%d)\n", host_vtimer_irq, err); return err; } if (has_gic) { err = irq_set_vcpu_affinity(host_vtimer_irq, kvm_get_running_vcpus()); if (err) { kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); goto out_free_vtimer_irq; } static_branch_enable(&has_gic_active_state); } kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq); /* Now let's do the physical EL1 timer irq */ if (info->physical_irq > 0) { err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler, "kvm guest ptimer", kvm_get_running_vcpus()); if (err) { kvm_err("kvm_arch_timer: can't request ptimer interrupt %d (%d)\n", host_ptimer_irq, err); goto out_free_vtimer_irq; } if (has_gic) { err = irq_set_vcpu_affinity(host_ptimer_irq, kvm_get_running_vcpus()); if (err) { kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); goto out_free_ptimer_irq; } } kvm_debug("physical timer IRQ%d\n", host_ptimer_irq); } else if (has_vhe()) { kvm_err("kvm_arch_timer: invalid physical timer IRQ: %d\n", info->physical_irq); err = -ENODEV; goto out_free_vtimer_irq; } kvm_timer_handle_errata(); return 0; out_free_ptimer_irq: if (info->physical_irq > 0) free_percpu_irq(host_ptimer_irq, kvm_get_running_vcpus()); out_free_vtimer_irq: free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); return err; } void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); soft_timer_cancel(&timer->bg_timer); } static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { u32 ppis = 0; bool valid; mutex_lock(&vcpu->kvm->arch.config_lock); for (int i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx; int irq; ctx = vcpu_get_timer(vcpu, i); irq = timer_irq(ctx); if (kvm_vgic_set_owner(vcpu, irq, ctx)) break; /* * We know by construction that we only have PPIs, so * all values are less than 32. */ ppis |= BIT(irq); } valid = hweight32(ppis) == nr_timers(vcpu); if (valid) set_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags); mutex_unlock(&vcpu->kvm->arch.config_lock); return valid; } static bool kvm_arch_timer_get_input_level(int vintid) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); if (WARN(!vcpu, "No vcpu context!\n")) return false; for (int i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx; ctx = vcpu_get_timer(vcpu, i); if (timer_irq(ctx) == vintid) return kvm_timer_should_fire(ctx); } /* A timer IRQ has fired, but no matching timer was found? */ WARN_RATELIMIT(1, "timer INTID%d unknown\n", vintid); return false; } int kvm_timer_enable(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; int ret; if (timer->enabled) return 0; /* Without a VGIC we do not map virtual IRQs to physical IRQs */ if (!irqchip_in_kernel(vcpu->kvm)) goto no_vgic; /* * At this stage, we have the guarantee that the vgic is both * available and initialized. */ if (!timer_irqs_are_valid(vcpu)) { kvm_debug("incorrectly configured timer irqs\n"); return -EINVAL; } get_timer_map(vcpu, &map); ret = kvm_vgic_map_phys_irq(vcpu, map.direct_vtimer->host_timer_irq, timer_irq(map.direct_vtimer), &arch_timer_irq_ops); if (ret) return ret; if (map.direct_ptimer) { ret = kvm_vgic_map_phys_irq(vcpu, map.direct_ptimer->host_timer_irq, timer_irq(map.direct_ptimer), &arch_timer_irq_ops); } if (ret) return ret; no_vgic: timer->enabled = 1; return 0; } /* If we have CNTPOFF, permanently set ECV to enable it */ void kvm_timer_init_vhe(void) { if (cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)) sysreg_clear_set(cnthctl_el2, 0, CNTHCTL_ECV); } int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int __user *uaddr = (int __user *)(long)attr->addr; int irq, idx, ret = 0; if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; if (get_user(irq, uaddr)) return -EFAULT; if (!(irq_is_ppi(irq))) return -EINVAL; mutex_lock(&vcpu->kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags)) { ret = -EBUSY; goto out; } switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: idx = TIMER_VTIMER; break; case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: idx = TIMER_PTIMER; break; case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: idx = TIMER_HVTIMER; break; case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: idx = TIMER_HPTIMER; break; default: ret = -ENXIO; goto out; } /* * We cannot validate the IRQ unicity before we run, so take it at * face value. The verdict will be given on first vcpu run, for each * vcpu. Yes this is late. Blame it on the stupid API. */ vcpu->kvm->arch.timer_data.ppi[idx] = irq; out: mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; } int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int __user *uaddr = (int __user *)(long)attr->addr; struct arch_timer_context *timer; int irq; switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: timer = vcpu_vtimer(vcpu); break; case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: timer = vcpu_ptimer(vcpu); break; case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: timer = vcpu_hvtimer(vcpu); break; case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: timer = vcpu_hptimer(vcpu); break; default: return -ENXIO; } irq = timer_irq(timer); return put_user(irq, uaddr); } int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: return 0; } return -ENXIO; } int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset) { int ret = 0; if (offset->reserved) return -EINVAL; mutex_lock(&kvm->lock); if (lock_all_vcpus(kvm)) { set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags); /* * If userspace decides to set the offset using this * API rather than merely restoring the counter * values, the offset applies to both the virtual and * physical views. */ kvm->arch.timer_data.voffset = offset->counter_offset; kvm->arch.timer_data.poffset = offset->counter_offset; unlock_all_vcpus(kvm); } else { ret = -EBUSY; } mutex_unlock(&kvm->lock); return ret; } |
| 190 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * If we have pre-content watches we need to disable readahead to make * sure that we don't find 0 filled pages in cache that we never emitted * events for. Filesystems supporting HSM must make sure to not call * this function with ractl->file unset for files handled by HSM. */ if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) return; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* See the comment in page_cache_sync_ra. */ if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { CLASS(fd, f)(fd); if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || (!S_ISREG(file_inode(fd_file(f))->i_mode) && !S_ISBLK(file_inode(fd_file(f))->i_mode))) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 992 996 992 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/audit.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /** * tomoyo_print_bprm - Print "struct linux_binprm" for auditing. * * @bprm: Pointer to "struct linux_binprm". * @dump: Pointer to "struct tomoyo_page_dump". * * Returns the contents of @bprm on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_bprm(struct linux_binprm *bprm, struct tomoyo_page_dump *dump) { static const int tomoyo_buffer_len = 4096 * 2; char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS); char *cp; char *last_start; int len; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; bool truncated = false; if (!buffer) return NULL; len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ "); cp = buffer + len; if (!argv_count) { memmove(cp, "} envp[]={ ", 11); cp += 11; } last_start = cp; while (argv_count || envp_count) { if (!tomoyo_dump_page(bprm, pos, dump)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (offset < PAGE_SIZE) { const char *kaddr = dump->data; const unsigned char c = kaddr[offset++]; if (cp == last_start) *cp++ = '"'; if (cp >= buffer + tomoyo_buffer_len - 32) { /* Reserve some room for "..." string. */ truncated = true; } else if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else if (!c) { *cp++ = '"'; *cp++ = ' '; last_start = cp; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } if (c) continue; if (argv_count) { if (--argv_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } memmove(cp, "} envp[]={ ", 11); cp += 11; last_start = cp; truncated = false; } } else if (envp_count) { if (--envp_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } } } if (!argv_count && !envp_count) break; } offset = 0; } *cp++ = '}'; *cp = '\0'; return buffer; out: snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ... } envp[]= { ... }"); return buffer; } /** * tomoyo_filetype - Get string representation of file type. * * @mode: Mode value for stat(). * * Returns file type string. */ static inline const char *tomoyo_filetype(const umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case 0: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE]; case S_IFDIR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY]; case S_IFLNK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK]; case S_IFIFO: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO]; case S_IFSOCK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET]; case S_IFBLK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV]; case S_IFCHR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV]; } return "unknown"; /* This should not happen. */ } /** * tomoyo_print_header - Get header line of audit log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns string representation. * * This function uses kmalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_header(struct tomoyo_request_info *r) { struct tomoyo_time stamp; const pid_t gpid = task_pid_nr(current); struct tomoyo_obj_info *obj = r->obj; static const int tomoyo_buffer_len = 4096; char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS); int pos; u8 i; if (!buffer) return NULL; tomoyo_convert_time(ktime_get_real_seconds(), &stamp); pos = snprintf(buffer, tomoyo_buffer_len - 1, "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode], str_yes_no(r->granted), gpid, tomoyo_sys_getpid(), tomoyo_sys_getppid(), from_kuid(&init_user_ns, current_uid()), from_kgid(&init_user_ns, current_gid()), from_kuid(&init_user_ns, current_euid()), from_kgid(&init_user_ns, current_egid()), from_kuid(&init_user_ns, current_suid()), from_kgid(&init_user_ns, current_sgid()), from_kuid(&init_user_ns, current_fsuid()), from_kgid(&init_user_ns, current_fsgid())); if (!obj) goto no_obj_info; if (!obj->validate_done) { tomoyo_get_attributes(obj); obj->validate_done = true; } for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) { struct tomoyo_mini_stat *stat; unsigned int dev; umode_t mode; if (!obj->stat_valid[i]) continue; stat = &obj->stat[i]; dev = stat->dev; mode = stat->mode; if (i & 1) { pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u.parent={ uid=%u gid=%u ino=%lu perm=0%o }", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), (unsigned long)stat->ino, stat->mode & S_IALLUGO); continue; } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u={ uid=%u gid=%u ino=%lu major=%u minor=%u perm=0%o type=%s", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), (unsigned long)stat->ino, MAJOR(dev), MINOR(dev), mode & S_IALLUGO, tomoyo_filetype(mode)); if (S_ISCHR(mode) || S_ISBLK(mode)) { dev = stat->rdev; pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " dev_major=%u dev_minor=%u", MAJOR(dev), MINOR(dev)); } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " }"); } no_obj_info: if (pos < tomoyo_buffer_len - 1) return buffer; kfree(buffer); return NULL; } /** * tomoyo_init_log - Allocate buffer for audit logs. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns pointer to allocated memory. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf = NULL; char *bprm_info = NULL; const char *header = NULL; char *realpath = NULL; const char *symlink = NULL; int pos; const char *domainname = r->domain->domainname->name; header = tomoyo_print_header(r); if (!header) return NULL; /* +10 is for '\n' etc. and '\0'. */ len += strlen(domainname) + strlen(header) + 10; if (r->ee) { struct file *file = r->ee->bprm->file; realpath = tomoyo_realpath_from_path(&file->f_path); bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump); if (!realpath || !bprm_info) goto out; /* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */ len += strlen(realpath) + 80 + strlen(bprm_info); } else if (r->obj && r->obj->symlink_target) { symlink = r->obj->symlink_target->name; /* +18 is for " symlink.target=\"%s\"" */ len += 18 + strlen(symlink); } len = kmalloc_size_roundup(len); buf = kzalloc(len, GFP_NOFS); if (!buf) goto out; len--; pos = snprintf(buf, len, "%s", header); if (realpath) { struct linux_binprm *bprm = r->ee->bprm; pos += snprintf(buf + pos, len - pos, " exec={ realpath=\"%s\" argc=%d envc=%d %s }", realpath, bprm->argc, bprm->envc, bprm_info); } else if (symlink) pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"", symlink); pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname); vsnprintf(buf + pos, len - pos, fmt, args); out: kfree(realpath); kfree(bprm_info); kfree(header); return buf; } /* Wait queue for /sys/kernel/security/tomoyo/audit. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait); /* Structure for audit log. */ struct tomoyo_log { struct list_head list; char *log; int size; }; /* The list for "struct tomoyo_log". */ static LIST_HEAD(tomoyo_log); /* Lock for "struct list_head tomoyo_log". */ static DEFINE_SPINLOCK(tomoyo_log_lock); /* Length of "struct list_head tomoyo_log". */ static unsigned int tomoyo_log_count; /** * tomoyo_get_audit - Get audit mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * @matched_acl: Pointer to "struct tomoyo_acl_info". * @is_granted: True if granted log, false otherwise. * * Returns true if this request should be audited, false otherwise. */ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index, const struct tomoyo_acl_info *matched_acl, const bool is_granted) { u8 mode; const u8 category = tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return false; p = tomoyo_profile(ns, profile); if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG]) return false; if (is_granted && matched_acl && matched_acl->cond && matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO) return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES; mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[category]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; if (is_granted) return mode & TOMOYO_CONFIG_WANT_GRANT_LOG; return mode & TOMOYO_CONFIG_WANT_REJECT_LOG; } /** * tomoyo_write_log2 - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns nothing. */ void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf; struct tomoyo_log *entry; bool quota_exceeded = false; if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, r->matched_acl, r->granted)) goto out; buf = tomoyo_init_log(r, len, fmt, args); if (!buf) goto out; entry = kzalloc(sizeof(*entry), GFP_NOFS); if (!entry) { kfree(buf); goto out; } entry->log = buf; len = kmalloc_size_roundup(strlen(buf) + 1); /* * The entry->size is used for memory quota checks. * Don't go beyond strlen(entry->log). */ entry->size = len + kmalloc_size_roundup(sizeof(*entry)); spin_lock(&tomoyo_log_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] && tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >= tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) { quota_exceeded = true; } else { tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size; list_add_tail(&entry->list, &tomoyo_log); tomoyo_log_count++; } spin_unlock(&tomoyo_log_lock); if (quota_exceeded) { kfree(buf); kfree(entry); goto out; } wake_up(&tomoyo_log_wait); out: return; } /** * tomoyo_write_log - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int len; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); } /** * tomoyo_read_log - Read an audit log. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ void tomoyo_read_log(struct tomoyo_io_buffer *head) { struct tomoyo_log *ptr = NULL; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_log_lock); if (!list_empty(&tomoyo_log)) { ptr = list_entry(tomoyo_log.next, typeof(*ptr), list); list_del(&ptr->list); tomoyo_log_count--; tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size; } spin_unlock(&tomoyo_log_lock); if (ptr) { head->read_buf = ptr->log; head->r.w[head->r.w_pos++] = head->read_buf; kfree(ptr); } } /** * tomoyo_poll_log - Wait for an audit log. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log. */ __poll_t tomoyo_poll_log(struct file *file, poll_table *wait) { if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_log_wait, wait); if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; return 0; } |
| 269 262 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 91 91 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * IRQ subsystem internal functions and variables: * * Do not ever include this file from anything else than * kernel/irq/. Do not even think about using any information outside * of this file for your non core code. */ #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/pm_runtime.h> #include <linux/sched/clock.h> #ifdef CONFIG_SPARSE_IRQ # define MAX_SPARSE_IRQS INT_MAX #else # define MAX_SPARSE_IRQS NR_IRQS #endif #define istate core_internal_state__do_not_mess_with_it extern bool noirqdebug; extern struct irqaction chained_action; /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, IRQTF_READY, }; /* * Bit masks for desc->core_internal_state__do_not_mess_with_it * * IRQS_AUTODETECT - autodetection in progress * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt * detection * IRQS_POLL_INPROGRESS - polling in progress * IRQS_ONESHOT - irq is not unmasked in primary handler * IRQS_REPLAY - irq has been resent and will not be resent * again until the handler has run and cleared * this flag. * IRQS_WAITING - irq is waiting * IRQS_PENDING - irq needs to be resent and should be resent * at the next available opportunity. * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, IRQS_SPURIOUS_DISABLED = 0x00000002, IRQS_POLL_INPROGRESS = 0x00000008, IRQS_ONESHOT = 0x00000020, IRQS_REPLAY = 0x00000040, IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, IRQS_SYSFS = 0x00004000, }; #include "debug.h" #include "settings.h" extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags); extern void __disable_irq(struct irq_desc *desc); extern void __enable_irq(struct irq_desc *desc); #define IRQ_RESEND true #define IRQ_NORESEND false #define IRQ_START_FORCE true #define IRQ_START_COND false extern int irq_activate(struct irq_desc *desc); extern int irq_activate_and_startup(struct irq_desc *desc, bool resend); extern int irq_startup(struct irq_desc *desc, bool resend, bool force); extern void irq_shutdown(struct irq_desc *desc); extern void irq_shutdown_and_deactivate(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); extern void unmask_threaded_irq(struct irq_desc *desc); extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask); #ifdef CONFIG_SPARSE_IRQ static inline void irq_mark_irq(unsigned int irq) { } #else extern void irq_mark_irq(unsigned int irq); #endif extern int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state); irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ int check_irq_resend(struct irq_desc *desc, bool inject); void clear_irq_resend(struct irq_desc *desc); void irq_resend_init(struct irq_desc *desc); bool irq_wait_for_poll(struct irq_desc *desc); void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); void wake_threads_waitq(struct irq_desc *desc); #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); #else static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void register_handler_proc(unsigned int irq, struct irqaction *action) { } static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif extern bool irq_can_set_affinity_usr(unsigned int irq); extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force); #ifdef CONFIG_SMP extern int irq_setup_affinity(struct irq_desc *desc); #else static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; } #endif /* Inline functions for support of irq chips on slow busses */ static inline void chip_bus_lock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_lock)) desc->irq_data.chip->irq_bus_lock(&desc->irq_data); } static inline void chip_bus_sync_unlock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock)) desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data); } #define _IRQ_DESC_CHECK (1 << 0) #define _IRQ_DESC_PERCPU (1 << 1) #define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) #define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) #define for_each_action_of_desc(desc, act) \ for (act = desc->action; act; act = act->next) struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check); void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus); static inline struct irq_desc * irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, true, check); } static inline void irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, true); } static inline struct irq_desc * irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, false, check); } static inline void irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, false); } #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) static inline unsigned int irqd_get(struct irq_data *d) { return __irqd_to_state(d); } /* * Manipulation functions for irq_data.state */ static inline void irqd_set_move_pending(struct irq_data *d) { __irqd_to_state(d) |= IRQD_SETAFFINITY_PENDING; } static inline void irqd_clr_move_pending(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING; } static inline void irqd_set_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) |= IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clr_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clear(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) &= ~mask; } static inline void irqd_set(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) |= mask; } static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) { return __irqd_to_state(d) & mask; } static inline void irq_state_set_disabled(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); } static inline void irq_state_set_masked(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } #undef __irqd_to_state static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __kstat_incr_irqs_this_cpu(desc); desc->tot_count++; } static inline int irq_desc_get_node(struct irq_desc *desc) { return irq_common_data_get_node(&desc->irq_common_data); } static inline int irq_desc_is_chained(struct irq_desc *desc) { return (desc->action && desc->action == &chained_action); } static inline bool irq_is_nmi(struct irq_desc *desc) { return desc->istate & IRQS_NMI; } #ifdef CONFIG_PM_SLEEP bool irq_pm_check_wakeup(struct irq_desc *desc); void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action); #else static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; } static inline void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif #ifdef CONFIG_IRQ_TIMINGS #define IRQ_TIMINGS_SHIFT 5 #define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) #define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) /** * struct irq_timings - irq timings storing structure * @values: a circular buffer of u64 encoded <timestamp,irq> values * @count: the number of elements in the array */ struct irq_timings { u64 values[IRQ_TIMINGS_SIZE]; int count; }; DECLARE_PER_CPU(struct irq_timings, irq_timings); extern void irq_timings_free(int irq); extern int irq_timings_alloc(int irq); static inline void irq_remove_timings(struct irq_desc *desc) { desc->istate &= ~IRQS_TIMINGS; irq_timings_free(irq_desc_get_irq(desc)); } static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) { int irq = irq_desc_get_irq(desc); int ret; /* * We don't need the measurement because the idle code already * knows the next expiry event. */ if (act->flags & __IRQF_TIMER) return; /* * In case the timing allocation fails, we just want to warn, * not fail, so letting the system boot anyway. */ ret = irq_timings_alloc(irq); if (ret) { pr_warn("Failed to allocate irq timing stats for irq%d (%d)", irq, ret); return; } desc->istate |= IRQS_TIMINGS; } extern void irq_timings_enable(void); extern void irq_timings_disable(void); DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); /* * The interrupt number and the timestamp are encoded into a single * u64 variable to optimize the size. * 48 bit time stamp and 16 bit IRQ number is way sufficient. * Who cares an IRQ after 78 hours of idle time? */ static inline u64 irq_timing_encode(u64 timestamp, int irq) { return (timestamp << 16) | irq; } static inline int irq_timing_decode(u64 value, u64 *timestamp) { *timestamp = value >> 16; return value & U16_MAX; } static __always_inline void irq_timings_push(u64 ts, int irq) { struct irq_timings *timings = this_cpu_ptr(&irq_timings); timings->values[timings->count & IRQ_TIMINGS_MASK] = irq_timing_encode(ts, irq); timings->count++; } /* * The function record_irq_time is only called in one place in the * interrupts handler. We want this function always inline so the code * inside is embedded in the function and the static key branching * code can act at the higher level. Without the explicit * __always_inline we can end up with a function call and a small * overhead in the hotpath for nothing. */ static __always_inline void record_irq_time(struct irq_desc *desc) { if (!static_branch_likely(&irq_timing_enabled)) return; if (desc->istate & IRQS_TIMINGS) irq_timings_push(local_clock(), irq_desc_get_irq(desc)); } #else static inline void irq_remove_timings(struct irq_desc *desc) {} static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) {}; static inline void record_irq_time(struct irq_desc *desc) {} #endif /* CONFIG_IRQ_TIMINGS */ #ifdef CONFIG_GENERIC_IRQ_CHIP void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); #else static inline void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ #ifdef CONFIG_GENERIC_PENDING_IRQ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED); } static inline bool irq_move_pending(struct irq_data *data) { return irqd_is_setaffinity_pending(data); } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { cpumask_copy(desc->pending_mask, mask); } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { cpumask_copy(mask, desc->pending_mask); } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } static inline bool irq_move_pending(struct irq_data *data) { return false; } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return NULL; } static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve) { irqd_set_activated(data); return 0; } static inline void irq_domain_deactivate_irq(struct irq_data *data) { irqd_clr_activated(data); } #endif static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd) { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY return irqd->parent_data; #else return NULL; #endif } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include <linux/debugfs.h> struct irq_bit_descr { unsigned int mask; char *name; }; #define BIT_MASK_DESCR(m) { .mask = m, .name = #m } void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, const struct irq_bit_descr *sd, int size); void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { debugfs_remove(desc->debugfs_file); kfree(desc->dev_name); } void irq_debugfs_copy_devname(int irq, struct device *dev); # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else static inline void irq_domain_debugfs_init(struct dentry *root) { } # endif #else /* CONFIG_GENERIC_IRQ_DEBUGFS */ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) { } static inline void irq_remove_debugfs_entry(struct irq_desc *d) { } static inline void irq_debugfs_copy_devname(int irq, struct device *dev) { } #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ |
| 418 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 #define DEVCG_ACC_WRITE 4 #define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE) #define DEVCG_DEV_BLOCK 1 #define DEVCG_DEV_CHAR 2 #define DEVCG_DEV_ALL 4 /* this represents all devices */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access); static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; if (likely(!inode->i_rdev)) return 0; if (S_ISBLK(inode->i_mode)) type = DEVCG_DEV_BLOCK; else if (S_ISCHR(inode->i_mode)) type = DEVCG_DEV_CHAR; else return 0; if (mask & MAY_WRITE) access |= DEVCG_ACC_WRITE; if (mask & MAY_READ) access |= DEVCG_ACC_READ; return devcgroup_check_permission(type, imajor(inode), iminor(inode), access); } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { short type; if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; if (S_ISCHR(mode) && dev == WHITEOUT_DEV) return 0; if (S_ISBLK(mode)) type = DEVCG_DEV_BLOCK; else type = DEVCG_DEV_CHAR; return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev), DEVCG_ACC_MKNOD); } #else static inline int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { return 0; } static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { return 0; } #endif |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 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 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * Forwarding Information Database * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Changes: * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/bpf.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; bool skip_notify; }; #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else #define FWS_INIT FWS_L #endif static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the * affected subtree. This allows for cached routes to be asynchronously * tested when modifications are made to the destination cache as a * result of redirects, path MTU changes, etc. */ static void fib6_gc_timer_cb(struct timer_list *t); #define FOR_WALKERS(net, w) \ list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) static void fib6_walker_link(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_add(&w->lh, &net->ipv6.fib6_walkers); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) { int new, old = atomic_read(&net->ipv6.fib6_sernum); do { new = old < INT_MAX ? old + 1 : 1; } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); return new; } enum { FIB6_NO_SERNUM_CHANGE = 0, }; void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { struct fib6_node *fn; fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* * Auxiliary address test functions for the radix tree. * * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ #if defined(__LITTLE_ENDIAN) # define BITOP_BE32_SWIZZLE (0x1F & ~7) #else # define BITOP_BE32_SWIZZLE 0 #endif static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; size_t sz = sizeof(*f6i); if (with_fib6_nh) sz += sizeof(struct fib6_nh); f6i = kzalloc(sz, gfp_flags); if (!f6i) return NULL; /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); INIT_HLIST_NODE(&f6i->gc_link); return f6i; } void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); WARN_ON(f6i->fib6_node); if (f6i->nh) nexthop_put(f6i->nh); else fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); if (fn) net->ipv6.rt6_stats->fib_nodes++; return fn; } static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); net->ipv6.rt6_stats->fib_nodes--; } static void node_free(struct net *net, struct fib6_node *fn) { kfree_rcu(fn, rcu); net->ipv6.rt6_stats->fib_nodes--; } static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); kfree(table); } static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; /* * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation * operation, tables never disappear once they exist. */ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) { struct fib6_table *table; table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; } struct fib6_table *fib6_new_table(struct net *net, u32 id) { struct fib6_table *tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; tb = fib6_alloc_table(net, id); if (tb) fib6_link_table(net, tb); return tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT6_TABLE_MAIN; h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; } } rcu_read_unlock(); return NULL; } EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); } #else struct fib6_table *fib6_new_table(struct net *net, u32 id) { return fib6_get_table(net, id); } struct fib6_table *fib6_get_table(struct net *net, u32 id) { return net->ipv6.fib6_main_tbl; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } return &rt->dst; } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } #endif unsigned int fib6_tables_seq_read(const struct net *net) { unsigned int h, fib_seq = 0; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { const struct hlist_head *head = &net->ipv6.fib_table_hash[h]; const struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += READ_ONCE(tb->fib_seq); } rcu_read_unlock(); return fib_seq; } static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; return call_fib6_notifier(nb, event_type, &info.info); } static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, .nsiblings = rt->fib6_nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); } struct fib6_dump_arg { struct net *net; struct notifier_block *nb; struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; if (rt->fib6_nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, rt->fib6_nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, arg->extack); return err; } static int fib6_node_dump(struct fib6_walker *w) { int err; err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } static int fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { int err; w->root = &tb->tb6_root; spin_lock_bh(&tb->tb6_lock); err = fib6_walk(net, w); spin_unlock_bh(&tb->tb6_lock); return err; } /* Called with rcu_read_lock() */ int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; unsigned int h; int err = 0; w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_node_dump; arg.net = net; arg.nb = nb; arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); if (err) goto out; } } out: kfree(w); /* The tree traversal function should never return a positive value. */ return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) { int res; struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args, w->skip_in_node); if (res >= 0) { /* Frame is full, suspend walking */ w->leaf = rt; /* We'll restart from this node, so if some routes were * already dumped, skip them next time. */ w->skip_in_node += res; return 1; } w->skip_in_node = 0; /* Multipath routes are dumped in one route with the * RTA_MULTIPATH attribute. Jump 'rt' to point to the * last sibling of this route (no need to dump the * sibling routes again) */ if (rt->fib6_nsiblings) rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); } w->leaf = NULL; return 0; } static void fib6_dump_end(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); } cb->done = (void *)cb->args[3]; cb->args[1] = 3; } static int fib6_dump_done(struct netlink_callback *cb) { fib6_dump_end(cb); return cb->done ? cb->done(cb) : 0; } static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; w = (void *)cb->args[2]; w->root = &table->tb6_root; if (cb->args[4] == 0) { w->count = 0; w->skip = 0; w->skip_in_node = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { int sernum = READ_ONCE(w->root->fn_sernum); if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; w->skip_in_node = 0; } else w->skip = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; } } return res; } static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int e = 0, s_e; struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; unsigned int h, s_h; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); if (rtm->rtm_flags & RTM_F_PREFIX) arg.filter.flags = RTM_F_PREFIX; } w = (void *)cb->args[2]; if (!w) { /* New dump: * * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) { err = -ENOMEM; goto unlock; } w->func = fib6_dump_node; cb->args[2] = (long)w; /* 2. hook callback destructor. */ cb->args[3] = (long)cb->done; cb->done = fib6_dump_done; } arg.skb = skb; arg.cb = cb; arg.net = net; w->args = &arg; if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); err = -ENOENT; goto unlock; } if (!cb->args[0]) { err = fib6_dump_table(tb, skb, cb); if (!err) cb->args[0] = 1; } goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; err = fib6_dump_table(tb, skb, cb); if (err != 0) goto out; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); if (err <= 0) fib6_dump_end(cb); return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { if (!f6i) return; if (f6i->fib6_metrics == &dst_default_metrics) { struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); if (!p) return; refcount_set(&p->refcnt, 1); f6i->fib6_metrics = p; } f6i->fib6_metrics->metrics[metric - 1] = val; } /* * Routing Table * * return the appropriate node for a routing tree "add" operation * by either creating and inserting or by returning an existing * node. */ static struct fib6_node *fib6_add_1(struct net *net, struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; /* insert node in tree */ fn = root; do { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } /* * Exact match ? */ if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } return fn; } /* * We have more bits to go */ /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)) : rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { /* We should not create new node because * NLM_F_REPLACE was specified without NLM_F_CREATE * I assume it is safe to require NLM_F_CREATE when * REPLACE flag is used! Later we may want to remove the * check for replace_required, because according * to netlink specification, NLM_F_CREATE * MUST be specified if new route is created. * That would keep IPv6 consistent with IPv4 */ if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. * Create new leaf node without children. */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); return ln; insert_above: /* * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create * and the current */ pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(net); ln = node_alloc(net); if (!in || !ln) { if (in) node_free_immediate(net, in); if (ln) node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } /* * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes * in the other branch */ in->fn_bit = bit; RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; fib6_info_hold(rcu_dereference_protected(in->leaf, lockdep_is_held(&table->tb6_lock))); /* update parent pointer */ if (dir) rcu_assign_pointer(pn->right, in); else rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, in); rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { rcu_assign_pointer(in->right, ln); rcu_assign_pointer(in->left, fn); } else { rcu_assign_pointer(in->left, ln); rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) RCU_INIT_POINTER(ln->right, fn); else RCU_INIT_POINTER(ln->left, fn); rcu_assign_pointer(fn->parent, ln); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); } return ln; } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, const struct fib6_info *match, const struct fib6_table *table) { int cpu; if (!fib6_nh->rt6i_pcpu) return; rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ for_each_possible_cpu(cpu) { struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); /* Paired with xchg() in rt6_get_pcpu_route() */ pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes * from a fib6_info to NULL (ip6_dst_destroy); it can never * change from one fib6_info reference to another */ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } rcu_read_unlock(); } struct fib6_nh_pcpu_arg { struct fib6_info *from; const struct fib6_table *table; }; static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_nh_pcpu_arg *arg = _arg; __fib6_drop_pcpu_from(nh, arg->from, arg->table); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i, const struct fib6_table *table) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. */ f6i->fib6_destroying = 1; mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { struct fib6_nh_pcpu_arg arg = { .from = f6i, .table = table }; nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i, table); } } static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); fib6_drop_pcpu_from(rt, table); if (rt->nh && !list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes * and replace dummy references to this route with references * to still alive ones. */ while (fn) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); fib6_info_hold(new_leaf); rcu_assign_pointer(fn->leaf, new_leaf); fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } } fib6_clean_expires(rt); fib6_remove_gc_list(rt); } /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; break; } fallback_ins = fallback_ins ?: ins; goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); fib6_remove_gc_list(iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, * but not the same gateway, then the route we try to * add is sibling to this route, increment our counter * of siblings, and later we will add our route to the * list. * Only static routes (which don't have flag * RTF_EXPIRES) are used for ECMPv6. * * To avoid long list, we only had siblings if the * route have a gateway. */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; next_iter: ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No matching route with same ecmp-able-ness found, replace * first matching route */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ if (rt->fib6_nsiblings) { unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { list_add_tail_rcu(&rt->fib6_siblings, &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rt6_multipath_rebalance(temp_sibling); } /* * insert node */ if (!replace) { if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; /* The route should only be notified if it is the first * route in the node or if it is added as a sibling * route to the first route in the node. */ if (!info->skip_notify_kernel && (notify_sibling_rt || ins == &fn->leaf)) { enum fib_event_type fib_event; if (notify_sibling_rt) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, fib_event, rt, extack); if (err) { struct fib6_info *sibling, *next_sibling; /* If the route has siblings, then it first * needs to be unlinked from them. */ if (!rt->fib6_nsiblings) return err; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } } rcu_assign_pointer(rt->fib6_next, iter); fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } } else { int nsiblings; if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; } fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->fib6_nsiblings; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->fib6_next; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } } return 0; } static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { if (!timer_pending(&net->ipv6.ip6_fib_timer)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } } void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } /* allow ipv4 to update sernum via ipv6_stub */ void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum_upto_root(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); } /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; struct fib6_node *fn; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node *pn = NULL; #endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; if (info->nlh->nlmsg_flags & NLM_F_REPLACE) replace_required = 1; } if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, &rt->fib6_dst.addr, rt->fib6_dst.plen, offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; goto out; } #ifdef CONFIG_IPV6_SUBTREES pn = fn; if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* * Create subtree. * * fn[main tree] * | * sfn[subtree root] * \ * sn[new leaf node] */ /* Create subtree root node */ sfn = node_alloc(info->nl_net); if (!sfn) goto failure; fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); rcu_assign_pointer(sfn->leaf, info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); goto failure; } } if (!rcu_access_pointer(fn->leaf)) { if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, info->nl_net->ipv6.fib6_null_entry); } else { fib6_info_hold(rt); rcu_assign_pointer(fn->leaf, rt); } } fn = sn; } #endif err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); if (rt->fib6_flags & RTF_EXPIRES) fib6_add_gc_list(rt); fib6_start_gc(info->nl_net, rt); } out: if (err) { #ifdef CONFIG_IPV6_SUBTREES /* * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } #endif goto failure; } else if (fib6_requires_src(rt)) { fib6_routes_require_src_inc(info->nl_net); } return err; failure: /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: * 1. fn is an intermediate node and we failed to add the new * route to it in both subtree creation failure and fib6_add_rt2node() * failure case. * 2. fn is the root node in the table and we fail to add the first * default route to it. */ if (fn && (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); return err; } /* * Routing tree lookup * */ struct lookup_args { int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, struct lookup_args *args) { struct fib6_node *fn; __be32 dir; if (unlikely(args->offset == 0)) return NULL; /* * Descend on a tree */ fn = root; for (;;) { struct fib6_node *next; dir = addr_bit_set(args->addr, fn->fn_bit); next = dir ? rcu_dereference(fn->right) : rcu_dereference(fn->left); if (next) { fn = next; continue; } break; } while (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) goto backtrack; key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; sfn = fib6_node_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; } #endif if (fn->fn_flags & RTN_RTINFO) return fn; } } backtrack: if (fn->fn_flags & RTN_ROOT) break; fn = rcu_dereference(fn->parent); } return NULL; } /* called with rcu_read_lock() held */ struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif { .offset = 0, /* sentinel */ } }; fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; } /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) * exact_match == true means we try to find fn with exact match of * the passed in prefix addr * exact_match == false means we try to find fn with longest prefix * match of the passed in prefix addr. This is useful for finding fn * for cached route as it will be stored in the exception table under * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, int plen, int offset, bool exact_match) { struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ if (!leaf) { if (plen <= fn->fn_bit) goto out; else goto next; } key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) goto out; if (plen == fn->fn_bit) return fn; if (fn->fn_flags & RTN_RTINFO) prev = fn; next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) fn = rcu_dereference(fn->right); else fn = rcu_dereference(fn->left); } out: if (exact_match) return NULL; else return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct fib6_info, fib6_src), exact_match); } } } #endif if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; } /* * Deletion * */ static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); child_right = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); if (child_left) return rcu_dereference_protected(child_left->leaf, lockdep_is_held(&table->tb6_lock)); if (child_right) return rcu_dereference_protected(child_right->leaf, lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } return NULL; } /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn) { int children; int nstate; struct fib6_node *child; struct fib6_walker *w; int iter = 0; /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } for (;;) { struct fib6_node *fn_r = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *fn_l = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_r = rcu_dereference_protected(pn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); WARN_ON(fn_leaf); children = 0; child = NULL; if (fn_r) { child = fn_r; children |= 1; } if (fn_l) { child = fn_l; children |= 2; } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags & RTN_ROOT) #endif ) { new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); new_fn_leaf = net->ipv6.fib6_null_entry; } #endif fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn_r == fn) rcu_assign_pointer(pn->right, child); else if (pn_l == fn) rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } #endif read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { if (w->node == fn) { w->node = child; if (children&2) { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } } read_unlock(&net->ipv6.fib6_walker_lock); node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; bool notify_del = false; /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. */ leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); if (leaf == rt && !rt->fib6_nsiblings) { if (rcu_access_pointer(rt->fib6_next)) replace_rt = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); else notify_del = true; } /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; /* The route is deleted from a multipath route. If this * multipath route is the first route in the node, then we need * to emit a delete notification. Otherwise, we need to skip * the notification. */ if (rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf)) notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } /* Adjust walkers */ read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); /* If it was last route, call fib6_repair_tree() to: * 1. For root node, put back null_entry as how the table was created. * 2. For other nodes, expunge its radix tree node. */ if (!rcu_access_pointer(fn->leaf)) { if (!(fn->fn_flags & RTN_TL_ROOT)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; } fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); if (!info->skip_notify_kernel) { if (notify_del) call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); else if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); fib6_info_release(rt); } /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; struct fib6_table *table; struct fib6_node *fn; if (rt == net->ipv6.fib6_null_entry) return -ENOENT; table = rt->fib6_table; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { if (fib6_requires_src(cur)) fib6_routes_require_src_dec(info->nl_net); fib6_del_route(table, fn, rtp, info); return 0; } rtp_next = &cur->fib6_next; } return -ENOENT; } /* * Tree traversal function. * * Certainly, it is not interrupt safe. * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. * * Callback function w->func may return: * 0 -> continue walking. * positive value -> walking is suspended (used by tree dumps, * and probably by gc, if it will be split to several slices) * negative value -> terminate walking. * * The function itself returns: * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. * * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: if (FIB6_SUBTREE(fn)) { w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; fallthrough; #endif case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->skip) { w->skip--; goto skip; } err = w->func(w); if (err) return err; w->count++; continue; } skip: w->state = FWS_U; fallthrough; case FWS_U: if (fn == w->root) return 0; pn = rcu_dereference_protected(fn->parent, 1); left = rcu_dereference_protected(pn->left, 1); right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } #endif if (left == fn) { w->state = FWS_R; continue; } if (right == fn) { w->state = FWS_C; w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 WARN_ON(1); #endif } } } static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) fib6_walker_unlink(net, w); return res; } static int fib6_clean_node(struct fib6_walker *w) { int res; struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, .skip_notify = c->skip_notify, }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && READ_ONCE(w->node->fn_sernum) != c->sernum) WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); w->leaf = NULL; return 0; } for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { if (WARN_ON(!rt->fib6_nsiblings)) continue; rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); } w->leaf = rt; return 0; } /* * Convenient frontend to tree walker. * * func is called on each route. * It may return -2 -> skip multipath route. * -1 -> delete this route. * 0 -> continue walking */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct fib6_info *, void *arg), int sernum, void *arg, bool skip_notify) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; c.w.count = 0; c.w.skip = 0; c.w.skip_in_node = 0; c.func = func; c.sernum = sernum; c.arg = arg; c.net = net; c.skip_notify = skip_notify; fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), int sernum, void *arg, bool skip_notify) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg, skip_notify); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); } void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); } static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); __fib6_clean_all(net, NULL, new_sernum, NULL, false); } /* * Garbage collection */ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { unsigned long now = jiffies; /* * check addrconf expiration here. * Routes are expired even if they are in use. */ if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; } /* Also age clones in the exception table. * Note, that clones are aged out * only if they are not in use now. */ rt6_age_exceptions(rt, gc_args, now); return 0; } static void fib6_gc_table(struct net *net, struct fib6_table *tb6, struct fib6_gc_args *gc_args) { struct fib6_info *rt; struct hlist_node *n; struct nl_info info = { .nl_net = net, .skip_notify = false, }; hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) if (fib6_age(rt, gc_args) == -1) fib6_del(rt, &info); } static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_gc_table(net, table, gc_args); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; unsigned long now; if (force) { spin_lock_bh(&net->ipv6.fib6_gc_lock); } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(struct timer_list *t) { struct net *arg = from_timer(arg, t, ipv6.ip6_fib_timer); fib6_run_gc(0, arg, true); } static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; int err; err = fib6_notifier_init(net); if (err) return err; /* Default to 3-tuple */ net->ipv6.sysctl.multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), GFP_KERNEL); if (!net->ipv6.fib6_main_tbl) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), GFP_KERNEL); if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: kfree(net->ipv6.fib6_main_tbl); #endif out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); out_notifier: fib6_notifier_exit(net); return -ENOMEM; } static void fib6_net_exit(struct net *net) { unsigned int i; del_timer_sync(&net->ipv6.ip6_fib_timer); for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { struct hlist_head *head = &net->ipv6.fib_table_hash[i]; struct hlist_node *tmp; struct fib6_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { hlist_del(&tb->tb6_hlist); fib6_free_table(tb); } } kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, }; static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .dumpit = inet6_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; int __init fib6_init(void) { int ret = -ENOMEM; fib6_node_kmem = KMEM_CACHE(fib6_node, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; ret = register_pernet_subsys(&fib6_net_ops); if (ret) goto out_kmem_cache_create; ret = rtnl_register_many(fib6_rtnl_msg_handlers); if (ret) goto out_unregister_subsys; __fib6_flush_trees = fib6_flush_trees; out: return ret; out_unregister_subsys: unregister_pernet_subsys(&fib6_net_ops); out_kmem_cache_create: kmem_cache_destroy(fib6_node_kmem); goto out; } void fib6_gc_cleanup(void) { unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } #ifdef CONFIG_PROC_FS static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; if (rt->nh) fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } static int ipv6_route_yield(struct fib6_walker *w) { struct ipv6_route_iter *iter = w->args; if (!iter->skip) return 1; do { iter->w.leaf = rcu_dereference_protected( iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; } while (iter->w.leaf); return 0; } static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; iter->w.root = &iter->tbl->tb6_root; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, struct net *net) { unsigned int h; struct hlist_node *node; if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); } static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { int sernum = READ_ONCE(iter->w.root->fn_sernum); if (iter->sernum != sernum) { iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); iter->w.skip = iter->w.count; } } static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; ++(*pos); if (!v) goto iter_table; n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; iter_table: ipv6_route_check_sernum(iter); spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); return NULL; } fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; ipv6_route_seq_setup_walk(iter, net); goto iter_table; } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; if (iter->tbl) { loff_t p = 0; ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } } static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; return w->node && !(w->state == FWS_U && w->node == w->root); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) static int ipv6_route_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__ipv6_route ctx; ctx.meta = meta; ctx.rt = v; return bpf_iter_run_prog(prog, &ctx); } static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct ipv6_route_iter *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return ipv6_route_native_seq_show(seq, v); ret = ipv6_route_prog_seq_show(prog, &meta, v); iter->w.leaf = NULL; return ret; } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)ipv6_route_prog_seq_show(prog, &meta, v); } ipv6_route_native_seq_stop(seq, v); } #else static int ipv6_route_seq_show(struct seq_file *seq, void *v) { return ipv6_route_native_seq_show(seq, v); } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { ipv6_route_native_seq_stop(seq, v); } #endif const struct seq_operations ipv6_route_seq_ops = { .start = ipv6_route_seq_start, .next = ipv6_route_seq_next, .stop = ipv6_route_seq_stop, .show = ipv6_route_seq_show }; #endif /* CONFIG_PROC_FS */ |
| 302 2 312 64 312 312 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(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); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 Address [auto]configuration * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ /* * Changes: * * Janos Farkas : delete timer on ifdown * <chexum@bankinf.banki.hu> * Andi Kleen : kill double kfree on module * unload. * Maciej W. Rozycki : FDDI support * sekiya@USAGI : Don't send too many RS * packets. * yoshfuji@USAGI : Fixed interval between DAD * packets. * YOSHIFUJI Hideaki @USAGI : improved accuracy of * address validation timer. * YOSHIFUJI Hideaki @USAGI : Privacy Extensions (RFC3041) * support. * Yuji SEKIYA @USAGI : Don't assign a same IPv6 * address on a same interface. * YOSHIFUJI Hideaki @USAGI : ARCnet support * YOSHIFUJI Hideaki @USAGI : convert /proc/net/if_inet6 to * seq_file. * YOSHIFUJI Hideaki @USAGI : improved source address * selection; consider scope, * status etc. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/if_arcnet.h> #include <linux/if_infiniband.h> #include <linux/route.h> #include <linux/inetdevice.h> #include <linux/init.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/capability.h> #include <linux/delay.h> #include <linux/notifier.h> #include <linux/string.h> #include <linux/hash.h> #include <net/ip_tunnels.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/6lowpan.h> #include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/tcp.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/l3mdev.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> #include <linux/random.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #include <linux/ioam6.h> #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static inline s32 rfc3315_s14_backoff_init(s32 irt) { /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ u64 tmp = get_random_u32_inclusive(900000, 1100000) * (u64)irt; do_div(tmp, 1000000); return (s32)tmp; } static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) { /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ u64 tmp = get_random_u32_inclusive(1900000, 2100000) * (u64)rt; do_div(tmp, 1000000); if ((s32)tmp > mrt) { /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ tmp = get_random_u32_inclusive(900000, 1100000) * (u64)mrt; do_div(tmp, 1000000); } return (s32)tmp; } #ifdef CONFIG_SYSCTL static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); #else static inline int addrconf_sysctl_register(struct inet6_dev *idev) { return 0; } static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) { } #endif static void ipv6_gen_rnd_iid(struct in6_addr *addr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); #define IN6_ADDR_HSIZE_SHIFT 8 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) static void addrconf_verify(struct net *net); static void addrconf_verify_rtnl(struct net *net); static struct workqueue_struct *addrconf_wq; static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, bool unregister); static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags, bool no_gw); static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, bool send_na); static void addrconf_dad_run(struct inet6_dev *idev, bool restart); static void addrconf_rs_timer(struct timer_list *t); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, .mldv1_unsolicited_report_interval = 10 * HZ, .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 0, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { .initialized = false, }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, .ra_honor_pio_pflag = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, .mldv1_unsolicited_report_interval = 10 * HZ, .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { .initialized = false, }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, .ra_honor_pio_pflag = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ static inline bool addrconf_link_ready(const struct net_device *dev) { return netif_oper_up(dev) && !qdisc_tx_is_noop(dev); } static void addrconf_del_rs_timer(struct inet6_dev *idev) { if (del_timer(&idev->rs_timer)) __in6_dev_put(idev); } static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) { if (cancel_delayed_work(&ifp->dad_work)) __in6_ifa_put(ifp); } static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, unsigned long delay) { in6_ifa_hold(ifp); if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay)) in6_ifa_put(ifp); } static int snmp6_alloc_dev(struct inet6_dev *idev) { int i; idev->stats.ipv6 = alloc_percpu_gfp(struct ipstats_mib, GFP_KERNEL_ACCOUNT); if (!idev->stats.ipv6) goto err_ip; for_each_possible_cpu(i) { struct ipstats_mib *addrconf_stats; addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i); u64_stats_init(&addrconf_stats->syncp); } idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device), GFP_KERNEL); if (!idev->stats.icmpv6dev) goto err_icmp; idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device), GFP_KERNEL_ACCOUNT); if (!idev->stats.icmpv6msgdev) goto err_icmpmsg; return 0; err_icmpmsg: kfree(idev->stats.icmpv6dev); err_icmp: free_percpu(idev->stats.ipv6); err_ip: return -ENOMEM; } static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; int err = -ENOMEM; ASSERT_RTNL(); if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev) return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(*ndev), GFP_KERNEL_ACCOUNT); if (!ndev) return ERR_PTR(err); rwlock_init(&ndev->lock); ndev->dev = dev; INIT_LIST_HEAD(&ndev->addr_list); timer_setup(&ndev->rs_timer, addrconf_rs_timer, 0); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); if (ndev->cnf.stable_secret.initialized) ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; ndev->cnf.mtu6 = dev->mtu; ndev->ra_mtu = 0; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); if (!ndev->nd_parms) { kfree(ndev); return ERR_PTR(err); } if (ndev->cnf.forwarding) dev_disable_lro(dev); /* We refer to the device */ netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL); if (snmp6_alloc_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot allocate memory for statistics\n", __func__); neigh_parms_release(&nd_tbl, ndev->nd_parms); netdev_put(dev, &ndev->dev_tracker); kfree(ndev); return ERR_PTR(err); } if (dev != blackhole_netdev) { if (snmp6_register_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", __func__, dev->name); goto err_release; } } /* One reference from device. */ refcount_set(&ndev->refcnt, 1); if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; #if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { pr_info("%s: Disabled Multicast RS\n", dev->name); ndev->cnf.rtr_solicits = 0; } #endif INIT_LIST_HEAD(&ndev->tempaddr_list); ndev->desync_factor = U32_MAX; if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || dev->type == ARPHRD_TUNNEL6 || dev->type == ARPHRD_SIT || dev->type == ARPHRD_NONE) { ndev->cnf.use_tempaddr = -1; } ndev->token = in6addr_any; if (netif_running(dev) && addrconf_link_ready(dev)) ndev->if_flags |= IF_READY; ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; if (dev != blackhole_netdev) { err = addrconf_sysctl_register(ndev); if (err) { ipv6_mc_destroy_dev(ndev); snmp6_unregister_dev(ndev); goto err_release; } } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); if (dev != blackhole_netdev) { /* Join interface-local all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); /* Join all-router multicast group if forwarding is set */ if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); } return ndev; err_release: neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); return ERR_PTR(err); } static struct inet6_dev *ipv6_find_idev(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) { idev = ipv6_add_dev(dev); if (IS_ERR(idev)) return idev; } if (dev->flags&IFF_UP) ipv6_mc_up(idev); return idev; } static int inet6_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); #ifdef CONFIG_IPV6_MROUTE if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); #endif if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, struct ipv6_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET6; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, READ_ONCE(devconf->forwarding)) < 0) goto nla_put_failure; #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, atomic_read(&devconf->mc_forwarding)) < 0) goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, READ_ONCE(devconf->proxy_ndp)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, READ_ONCE(devconf->ignore_routes_with_linkdown)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err); } static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet6_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int inet6_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; struct inet6_dev *in6_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; struct ipv6_devconf *devconf; int ifindex; int err; err = inet6_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv6.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv6.devconf_dflt; break; default: dev = dev_get_by_index(net, ifindex); if (!dev) return -EINVAL; in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in6_dev) in6_dev_put(in6_dev); dev_put(dev); return err; } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; unsigned int all_default; } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { idev = __in6_dev_get(dev); if (!idev) continue; err = inet6_netconf_fill_devconf(skb, dev->ifindex, &idev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; } if (ctx->all_default == 0) { err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } if (ctx->all_default == 1) { err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } done: rcu_read_unlock(); return err; } #ifdef CONFIG_SYSCTL static void dev_forward_change(struct inet6_dev *idev) { struct net_device *dev; struct inet6_ifaddr *ifa; LIST_HEAD(tmp_addr_list); if (!idev) return; dev = idev->dev; if (idev->cnf.forwarding) dev_disable_lro(dev); if (dev->flags & IFF_MULTICAST) { if (idev->cnf.forwarding) { ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allrouters); ipv6_dev_mc_inc(dev, &in6addr_sitelocal_allrouters); } else { ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); ipv6_dev_mc_dec(dev, &in6addr_interfacelocal_allrouters); ipv6_dev_mc_dec(dev, &in6addr_sitelocal_allrouters); } } read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa->flags&IFA_F_TENTATIVE) continue; list_add_tail(&ifa->if_list_aux, &tmp_addr_list); } read_unlock_bh(&idev->lock); while (!list_empty(&tmp_addr_list)) { ifa = list_first_entry(&tmp_addr_list, struct inet6_ifaddr, if_list_aux); list_del(&ifa->if_list_aux); if (idev->cnf.forwarding) addrconf_join_anycast(ifa); else addrconf_leave_anycast(ifa); } inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &idev->cnf); } static void addrconf_forward_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); WRITE_ONCE(idev->cnf.forwarding, newf); if (changed) dev_forward_change(idev); } } } static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int newf) { struct net *net = (struct net *)table->extra2; int old; if (!rtnl_net_trylock(net)) return restart_syscall(); old = *p; WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->forwarding) { if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); rtnl_net_unlock(net); return 0; } if (p == &net->ipv6.devconf_all->forwarding) { int old_dflt = net->ipv6.devconf_dflt->forwarding; WRITE_ONCE(net->ipv6.devconf_dflt->forwarding, newf); if ((!newf) ^ (!old_dflt)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); addrconf_forward_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); rtnl_net_unlock(net); if (newf) rt6_purge_dflt_routers(net); return 1; } static void addrconf_linkdown_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); WRITE_ONCE(idev->cnf.ignore_routes_with_linkdown, newf); if (changed) inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, dev->ifindex, &idev->cnf); } } } static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int newf) { struct net *net = (struct net *)table->extra2; int old; if (!rtnl_net_trylock(net)) return restart_syscall(); old = *p; WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); rtnl_net_unlock(net); return 0; } if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { WRITE_ONCE(net->ipv6.devconf_dflt->ignore_routes_with_linkdown, newf); addrconf_linkdown_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } rtnl_net_unlock(net); return 1; } #endif /* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG pr_debug("%s\n", __func__); #endif in6_dev_put(ifp->idev); if (cancel_delayed_work(&ifp->dad_work)) pr_notice("delayed DAD work was pending while freeing ifa=%p\n", ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { pr_warn("Freeing alive inet6 address %p\n", ifp); return; } kfree_rcu(ifp, rcu); } static void ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { struct list_head *p; int ifp_scope = ipv6_addr_src_scope(&ifp->addr); /* * Each device address list is sorted in order of scope - * global before linklocal. */ list_for_each(p, &idev->addr_list) { struct inet6_ifaddr *ifa = list_entry(p, struct inet6_ifaddr, if_list); if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) break; } list_add_tail_rcu(&ifp->if_list, p); } static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr) { u32 val = __ipv6_addr_jhash(addr, net_hash_mix(net)); return hash_32(val, IN6_ADDR_HSIZE_SHIFT); } static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev, unsigned int hash) { struct inet6_ifaddr *ifp; hlist_for_each_entry(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev) return true; } } return false; } static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) { struct net *net = dev_net(dev); unsigned int hash = inet6_addr_hash(net, &ifa->addr); int err = 0; spin_lock_bh(&net->ipv6.addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) { netdev_dbg(dev, "ipv6_add_addr: already assigned\n"); err = -EEXIST; } else { hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]); } spin_unlock_bh(&net->ipv6.addrconf_hash_lock); return err; } /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, bool can_block, struct netlink_ext_ack *extack) { gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; int addr_type = ipv6_addr_type(cfg->pfx); struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct fib6_info *f6i = NULL; int err = 0; if (addr_type == IPV6_ADDR_ANY) { NL_SET_ERR_MSG_MOD(extack, "Invalid address"); return ERR_PTR(-EADDRNOTAVAIL); } else if (addr_type & IPV6_ADDR_MULTICAST && !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) { NL_SET_ERR_MSG_MOD(extack, "Cannot assign multicast address without \"IFA_F_MCAUTOJOIN\" flag"); return ERR_PTR(-EADDRNOTAVAIL); } else if (!(idev->dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(idev->dev) && addr_type & IPV6_ADDR_LOOPBACK) { NL_SET_ERR_MSG_MOD(extack, "Cannot assign loopback address on this device"); return ERR_PTR(-EADDRNOTAVAIL); } if (idev->dead) { NL_SET_ERR_MSG_MOD(extack, "device is going away"); err = -ENODEV; goto out; } if (idev->cnf.disable_ipv6) { NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); err = -EACCES; goto out; } /* validator notifier needs to be blocking; * do not call in atomic context */ if (can_block) { struct in6_validator_info i6vi = { .i6vi_addr = *cfg->pfx, .i6vi_dev = idev, .extack = extack, }; err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); err = notifier_to_errno(err); if (err < 0) goto out; } ifa = kzalloc(sizeof(*ifa), gfp_flags | __GFP_ACCOUNT); if (!ifa) { err = -ENOBUFS; goto out; } f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags, extack); if (IS_ERR(f6i)) { err = PTR_ERR(f6i); f6i = NULL; goto out; } neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *cfg->pfx; if (cfg->peer_pfx) ifa->peer_addr = *cfg->peer_pfx; spin_lock_init(&ifa->lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = cfg->scope; ifa->prefix_len = cfg->plen; ifa->rt_priority = cfg->rt_priority; ifa->flags = cfg->ifa_flags; ifa->ifa_proto = cfg->ifa_proto; /* No need to add the TENTATIVE flag for addresses with NODAD */ if (!(cfg->ifa_flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; ifa->valid_lft = cfg->valid_lft; ifa->prefered_lft = cfg->preferred_lft; ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; ifa->rt = f6i; ifa->idev = idev; in6_dev_hold(idev); /* For caller */ refcount_set(&ifa->refcnt, 1); rcu_read_lock(); err = ipv6_add_addr_hash(idev->dev, ifa); if (err < 0) { rcu_read_unlock(); goto out; } write_lock_bh(&idev->lock); /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); if (ifa->flags&IFA_F_TEMPORARY) { list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } in6_ifa_hold(ifa); write_unlock_bh(&idev->lock); rcu_read_unlock(); inet6addr_notifier_call_chain(NETDEV_UP, ifa); out: if (unlikely(err < 0)) { fib6_info_release(f6i); if (ifa) { if (ifa->idev) in6_dev_put(ifa->idev); kfree(ifa); } ifa = ERR_PTR(err); } return ifa; } enum cleanup_prefix_rt_t { CLEANUP_PREFIX_RT_NOP, /* no cleanup action for prefix route */ CLEANUP_PREFIX_RT_DEL, /* delete the prefix route */ CLEANUP_PREFIX_RT_EXPIRE, /* update the lifetime of the prefix route */ }; /* * Check, whether the prefix for ifp would still need a prefix route * after deleting ifp. The function returns one of the CLEANUP_PREFIX_RT_* * constants. * * 1) we don't purge prefix if address was not permanent. * prefix is managed by its own lifetime. * 2) we also don't purge, if the address was IFA_F_NOPREFIXROUTE. * 3) if there are no addresses, delete prefix. * 4) if there are still other permanent address(es), * corresponding prefix is still permanent. * 5) if there are still other addresses with IFA_F_NOPREFIXROUTE, * don't purge the prefix, assume user space is managing it. * 6) otherwise, update prefix lifetime to the * longest valid lifetime among the corresponding * addresses on the device. * Note: subsequent RA will update lifetime. **/ static enum cleanup_prefix_rt_t check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) { struct inet6_ifaddr *ifa; struct inet6_dev *idev = ifp->idev; unsigned long lifetime; enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_DEL; *expires = jiffies; list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; if (ifa->prefix_len != ifp->prefix_len || !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) return CLEANUP_PREFIX_RT_NOP; action = CLEANUP_PREFIX_RT_EXPIRE; spin_lock(&ifa->lock); lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); /* * Note: Because this address is * not permanent, lifetime < * LONG_MAX / HZ here. */ if (time_before(*expires, ifa->tstamp + lifetime * HZ)) *expires = ifa->tstamp + lifetime * HZ; spin_unlock(&ifa->lock); } return action; } static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt, bool del_peer) { struct fib6_table *table; struct fib6_info *f6i; f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (f6i) { if (del_rt) ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); else { if (!(f6i->fib6_flags & RTF_EXPIRES)) { table = f6i->fib6_table; spin_lock_bh(&table->tb6_lock); fib6_set_expires(f6i, expires); fib6_add_gc_list(f6i); spin_unlock_bh(&table->tb6_lock); } fib6_info_release(f6i); } } } /* This function wants to get referenced ifp and releases it before return */ static void ipv6_del_addr(struct inet6_ifaddr *ifp) { enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; struct net *net = dev_net(ifp->idev->dev); unsigned long expires; int state; ASSERT_RTNL(); spin_lock_bh(&ifp->lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; spin_unlock_bh(&ifp->lock); if (state == INET6_IFADDR_STATE_DEAD) goto out; spin_lock_bh(&net->ipv6.addrconf_hash_lock); hlist_del_init_rcu(&ifp->addr_lst); spin_unlock_bh(&net->ipv6.addrconf_hash_lock); write_lock_bh(&ifp->idev->lock); if (ifp->flags&IFA_F_TEMPORARY) { list_del(&ifp->tmp_list); if (ifp->ifpub) { in6_ifa_put(ifp->ifpub); ifp->ifpub = NULL; } __in6_ifa_put(ifp); } if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); addrconf_del_dad_work(ifp); ipv6_ifa_notify(RTM_DELADDR, ifp); inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, expires, action == CLEANUP_PREFIX_RT_DEL, false); } /* clean up prefsrc entries */ rt6_remove_prefsrc(ifp); out: in6_ifa_put(ifp); } static unsigned long ipv6_get_regen_advance(const struct inet6_dev *idev) { return READ_ONCE(idev->cnf.regen_min_advance) + READ_ONCE(idev->cnf.regen_max_retry) * READ_ONCE(idev->cnf.dad_transmits) * max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; } static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) { struct inet6_dev *idev = ifp->idev; unsigned long tmp_tstamp, age; unsigned long regen_advance; unsigned long now = jiffies; u32 if_public_preferred_lft; s32 cnf_temp_preferred_lft; struct inet6_ifaddr *ift; struct ifa6_config cfg; long max_desync_factor; struct in6_addr addr; int ret = 0; write_lock_bh(&idev->lock); retry: in6_dev_hold(idev); if (READ_ONCE(idev->cnf.use_tempaddr) <= 0) { write_unlock_bh(&idev->lock); pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); ret = -1; goto out; } spin_lock_bh(&ifp->lock); if (ifp->regen_count++ >= READ_ONCE(idev->cnf.regen_max_retry)) { WRITE_ONCE(idev->cnf.use_tempaddr, -1); /*XXX*/ spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", __func__); in6_dev_put(idev); ret = -1; goto out; } in6_ifa_hold(ifp); memcpy(addr.s6_addr, ifp->addr.s6_addr, 8); ipv6_gen_rnd_iid(&addr); age = (now - ifp->tstamp) / HZ; regen_advance = ipv6_get_regen_advance(idev); /* recalculate max_desync_factor each time and update * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); max_desync_factor = min_t(long, READ_ONCE(idev->cnf.max_desync_factor), cnf_temp_preferred_lft - regen_advance); if (unlikely(idev->desync_factor > max_desync_factor)) { if (max_desync_factor > 0) { get_random_bytes(&idev->desync_factor, sizeof(idev->desync_factor)); idev->desync_factor %= max_desync_factor; } else { idev->desync_factor = 0; } } if_public_preferred_lft = ifp->prefered_lft; memset(&cfg, 0, sizeof(cfg)); cfg.valid_lft = min_t(__u32, ifp->valid_lft, READ_ONCE(idev->cnf.temp_valid_lft) + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; cfg.preferred_lft = min_t(__u32, if_public_preferred_lft, cfg.preferred_lft); cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); /* From RFC 4941: * * A temporary address is created only if this calculated Preferred * Lifetime is greater than REGEN_ADVANCE time units. In * particular, an implementation must not create a temporary address * with a zero Preferred Lifetime. * * ... * * When creating a temporary address, the lifetime values MUST be * derived from the corresponding prefix as follows: * * ... * * * Its Preferred Lifetime is the lower of the Preferred Lifetime * of the public address or TEMP_PREFERRED_LIFETIME - * DESYNC_FACTOR. * * To comply with the RFC's requirements, clamp the preferred lifetime * to a minimum of regen_advance, unless that would exceed valid_lft or * ifp->prefered_lft. * * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (cfg.preferred_lft <= regen_advance + age) { cfg.preferred_lft = regen_advance + age + 1; if (cfg.preferred_lft > cfg.valid_lft || cfg.preferred_lft > if_public_preferred_lft) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; goto out; } } cfg.ifa_flags = IFA_F_TEMPORARY; /* set in addrconf_prefix_rcv() */ if (ifp->flags & IFA_F_OPTIMISTIC) cfg.ifa_flags |= IFA_F_OPTIMISTIC; cfg.pfx = &addr; cfg.scope = ipv6_addr_scope(cfg.pfx); ift = ipv6_add_addr(idev, &cfg, block, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); write_lock_bh(&idev->lock); goto retry; } spin_lock_bh(&ift->lock); ift->ifpub = ifp; ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); addrconf_dad_start(ift); in6_ifa_put(ift); in6_dev_put(idev); out: return ret; } /* * Choose an appropriate source address (RFC3484) */ enum { IPV6_SADDR_RULE_INIT = 0, IPV6_SADDR_RULE_LOCAL, IPV6_SADDR_RULE_SCOPE, IPV6_SADDR_RULE_PREFERRED, #ifdef CONFIG_IPV6_MIP6 IPV6_SADDR_RULE_HOA, #endif IPV6_SADDR_RULE_OIF, IPV6_SADDR_RULE_LABEL, IPV6_SADDR_RULE_PRIVACY, IPV6_SADDR_RULE_ORCHID, IPV6_SADDR_RULE_PREFIX, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD IPV6_SADDR_RULE_NOT_OPTIMISTIC, #endif IPV6_SADDR_RULE_MAX }; struct ipv6_saddr_score { int rule; int addr_type; struct inet6_ifaddr *ifa; DECLARE_BITMAP(scorebits, IPV6_SADDR_RULE_MAX); int scopedist; int matchlen; }; struct ipv6_saddr_dst { const struct in6_addr *addr; int ifindex; int scope; int label; unsigned int prefs; }; static inline int ipv6_saddr_preferred(int type) { if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|IPV6_ADDR_LOOPBACK)) return 1; return 0; } static bool ipv6_use_optimistic_addr(const struct net *net, const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && !READ_ONCE(idev->cnf.optimistic_dad)) return false; if (!READ_ONCE(net->ipv6.devconf_all->use_optimistic) && !READ_ONCE(idev->cnf.use_optimistic)) return false; return true; #else return false; #endif } static bool ipv6_allow_optimistic_dad(const struct net *net, const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && !READ_ONCE(idev->cnf.optimistic_dad)) return false; return true; #else return false; #endif } static int ipv6_get_saddr_eval(struct net *net, struct ipv6_saddr_score *score, struct ipv6_saddr_dst *dst, int i) { int ret; if (i <= score->rule) { switch (i) { case IPV6_SADDR_RULE_SCOPE: ret = score->scopedist; break; case IPV6_SADDR_RULE_PREFIX: ret = score->matchlen; break; default: ret = !!test_bit(i, score->scorebits); } goto out; } switch (i) { case IPV6_SADDR_RULE_INIT: /* Rule 0: remember if hiscore is not ready yet */ ret = !!score->ifa; break; case IPV6_SADDR_RULE_LOCAL: /* Rule 1: Prefer same address */ ret = ipv6_addr_equal(&score->ifa->addr, dst->addr); break; case IPV6_SADDR_RULE_SCOPE: /* Rule 2: Prefer appropriate scope * * ret * ^ * -1 | d 15 * ---+--+-+---> scope * | * | d is scope of the destination. * B-d | \ * | \ <- smaller scope is better if * B-15 | \ if scope is enough for destination. * | ret = B - scope (-1 <= scope >= d <= 15). * d-C-1 | / * |/ <- greater is better * -C / if scope is not enough for destination. * /| ret = scope - C (-1 <= d < scope <= 15). * * d - C - 1 < B -15 (for all -1 <= d <= 15). * C > d + 14 - B >= 15 + 14 - B = 29 - B. * Assume B = 0 and we get C > 29. */ ret = __ipv6_addr_src_scope(score->addr_type); if (ret >= dst->scope) ret = -ret; else ret -= 128; /* 30 is enough */ score->scopedist = ret; break; case IPV6_SADDR_RULE_PREFERRED: { /* Rule 3: Avoid deprecated and optimistic addresses */ u8 avoid = IFA_F_DEPRECATED; if (!ipv6_use_optimistic_addr(net, score->ifa->idev)) avoid |= IFA_F_OPTIMISTIC; ret = ipv6_saddr_preferred(score->addr_type) || !(score->ifa->flags & avoid); break; } #ifdef CONFIG_IPV6_MIP6 case IPV6_SADDR_RULE_HOA: { /* Rule 4: Prefer home address */ int prefhome = !(dst->prefs & IPV6_PREFER_SRC_COA); ret = !(score->ifa->flags & IFA_F_HOMEADDRESS) ^ prefhome; break; } #endif case IPV6_SADDR_RULE_OIF: /* Rule 5: Prefer outgoing interface */ ret = (!dst->ifindex || dst->ifindex == score->ifa->idev->dev->ifindex); break; case IPV6_SADDR_RULE_LABEL: /* Rule 6: Prefer matching label */ ret = ipv6_addr_label(net, &score->ifa->addr, score->addr_type, score->ifa->idev->dev->ifindex) == dst->label; break; case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address * Note: prefer temporary address if use_tempaddr >= 2 */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : READ_ONCE(score->ifa->idev->cnf.use_tempaddr) >= 2; ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } case IPV6_SADDR_RULE_ORCHID: /* Rule 8-: Prefer ORCHID vs ORCHID or * non-ORCHID vs non-ORCHID */ ret = !(ipv6_addr_orchid(&score->ifa->addr) ^ ipv6_addr_orchid(dst->addr)); break; case IPV6_SADDR_RULE_PREFIX: /* Rule 8: Use longest matching prefix */ ret = ipv6_addr_diff(&score->ifa->addr, dst->addr); if (ret > score->ifa->prefix_len) ret = score->ifa->prefix_len; score->matchlen = ret; break; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD case IPV6_SADDR_RULE_NOT_OPTIMISTIC: /* Optimistic addresses still have lower precedence than other * preferred addresses. */ ret = !(score->ifa->flags & IFA_F_OPTIMISTIC); break; #endif default: ret = 0; } if (ret) __set_bit(i, score->scorebits); score->rule = i; out: return ret; } static int __ipv6_dev_get_saddr(struct net *net, struct ipv6_saddr_dst *dst, struct inet6_dev *idev, struct ipv6_saddr_score *scores, int hiscore_idx) { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* * - Tentative Address (RFC2462 section 5.4) * - A tentative address is not considered * "assigned to an interface" in the traditional * sense, unless it is also flagged as optimistic. * - Candidate Source Address (section 4) * - In any case, anycast addresses, multicast * addresses, and the unspecified address MUST * NOT be included in a candidate set. */ if ((score->ifa->flags & IFA_F_TENTATIVE) && (!(score->ifa->flags & IFA_F_OPTIMISTIC))) continue; score->addr_type = __ipv6_addr_type(&score->ifa->addr); if (unlikely(score->addr_type == IPV6_ADDR_ANY || score->addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", idev->dev->name); continue; } score->rule = -1; bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { int minihiscore, miniscore; minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i); miniscore = ipv6_get_saddr_eval(net, score, dst, i); if (minihiscore > miniscore) { if (i == IPV6_SADDR_RULE_SCOPE && score->scopedist > 0) { /* * special case: * each remaining entry * has too small (not enough) * scope, because ifa entries * are sorted by their scope * values. */ goto out; } break; } else if (minihiscore < miniscore) { swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; /* restore our iterator */ score->ifa = hiscore->ifa; break; } } } out: return hiscore_idx; } static int ipv6_get_saddr_master(struct net *net, const struct net_device *dst_dev, const struct net_device *master, struct ipv6_saddr_dst *dst, struct ipv6_saddr_score *scores, int hiscore_idx) { struct inet6_dev *idev; idev = __in6_dev_get(dst_dev); if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev, scores, hiscore_idx); idev = __in6_dev_get(master); if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev, scores, hiscore_idx); return hiscore_idx; } int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { struct ipv6_saddr_score scores[2], *hiscore; struct ipv6_saddr_dst dst; struct inet6_dev *idev; struct net_device *dev; int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; dst.ifindex = dst_dev ? dst_dev->ifindex : 0; dst.scope = __ipv6_addr_src_scope(dst_type); dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); dst.prefs = prefs; scores[hiscore_idx].rule = -1; scores[hiscore_idx].ifa = NULL; rcu_read_lock(); /* Candidate Source Address (section 4) * - multicast and link-local destination address, * the set of candidate source address MUST only * include addresses assigned to interfaces * belonging to the same link as the outgoing * interface. * (- For site-local destination addresses, the * set of candidate source addresses MUST only * include addresses assigned to interfaces * belonging to the same site as the outgoing * interface.) * - "It is RECOMMENDED that the candidate source addresses * be the set of unicast addresses assigned to the * interface that will be used to send to the destination * (the 'outgoing' interface)." (RFC 6724) */ if (dst_dev) { idev = __in6_dev_get(dst_dev); if ((dst_type & IPV6_ADDR_MULTICAST) || dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || (idev && READ_ONCE(idev->cnf.use_oif_addrs_only))) { use_oif_addr = true; } } if (use_oif_addr) { if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } else { const struct net_device *master; int master_idx = 0; /* if dst_dev exists and is enslaved to an L3 device, then * prefer addresses from dst_dev and then the master over * any other enslaved devices in the L3 domain. */ master = l3mdev_master_dev_rcu(dst_dev); if (master) { master_idx = master->ifindex; hiscore_idx = ipv6_get_saddr_master(net, dst_dev, master, &dst, scores, hiscore_idx); if (scores[hiscore_idx].ifa && scores[hiscore_idx].scopedist >= 0) goto out; } for_each_netdev_rcu(net, dev) { /* only consider addresses on devices in the * same L3 domain */ if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; idev = __in6_dev_get(dev); if (!idev) continue; hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } } out: hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) ret = -EADDRNOTAVAIL; else *saddr = hiscore->ifa->addr; rcu_read_unlock(); return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); static int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags) { struct inet6_ifaddr *ifp; int err = -EADDRNOTAVAIL; list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { if (ifp->scope > IFA_LINK) break; if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { *addr = ifp->addr; err = 0; break; } } return err; } int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags) { struct inet6_dev *idev; int err = -EADDRNOTAVAIL; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } rcu_read_unlock(); return err; } static int ipv6_count_addresses(const struct inet6_dev *idev) { const struct inet6_ifaddr *ifp; int cnt = 0; rcu_read_lock(); list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; rcu_read_unlock(); return cnt; } int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { return ipv6_chk_addr_and_flags(net, addr, dev, !dev, strict, IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_chk_addr); /* device argument is used to find the L3 domain of interest. If * skip_dev_check is set, then the ifp device is not checked against * the passed in dev argument. So the 2 cases for addresses checks are: * 1. does the address exist in the L3 domain that dev is part of * (skip_dev_check = true), or * * 2. does the address exist on the specific device * (skip_dev_check = false) */ static struct net_device * __ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); struct net_device *l3mdev, *ndev; struct inet6_ifaddr *ifp; u32 ifp_flags; rcu_read_lock(); l3mdev = l3mdev_master_dev_rcu(dev); if (skip_dev_check) dev = NULL; hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { ndev = ifp->idev->dev; if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; /* Decouple optimistic from tentative for evaluation here. * Ban optimistic addresses explicitly, when required. */ ifp_flags = (ifp->flags&IFA_F_OPTIMISTIC) ? (ifp->flags&~IFA_F_TENTATIVE) : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && (!dev || ndev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock(); return ndev; } } rcu_read_unlock(); return NULL; } int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags) { return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check, strict, banned_flags) ? 1 : 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); /* Compares an address/prefix_len with addresses on device @dev. * If one is found it returns true. */ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { const struct inet6_ifaddr *ifa; const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { const struct inet6_ifaddr *ifa; const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } } rcu_read_unlock(); return onlink; } EXPORT_SYMBOL(ipv6_chk_prefix); /** * ipv6_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @dev: used to find the L3 domain of interest * * The caller should be protected by RCU, or RTNL. */ struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev) { return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1, IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_dev_find); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp, *result = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { if (in6_ifa_hold_safe(ifp)) { result = ifp; break; } } } } rcu_read_unlock(); return result; } /* Gets referenced address, destroys ifaddr */ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (dad_failed) ifp->flags |= IFA_F_DADFAILED; if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); ifpub = ifp->ifpub; if (ifpub) { in6_ifa_hold(ifpub); spin_unlock_bh(&ifp->lock); ipv6_create_tempaddr(ifpub, true); in6_ifa_put(ifpub); } else { spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) { spin_lock_bh(&ifp->lock); addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; if (dad_failed) ifp->flags &= ~IFA_F_OPTIMISTIC; spin_unlock_bh(&ifp->lock); if (dad_failed) ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); } else { ipv6_del_addr(ifp); } } static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } spin_unlock_bh(&ifp->lock); return err; } void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(idev->dev); int max_addresses; if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); return; } net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n", ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source); spin_lock_bh(&ifp->lock); if (ifp->flags & IFA_F_STABLE_PRIVACY) { struct in6_addr new_addr; struct inet6_ifaddr *ifp2; int retries = ifp->stable_privacy_retry + 1; struct ifa6_config cfg = { .pfx = &new_addr, .plen = ifp->prefix_len, .ifa_flags = ifp->flags, .valid_lft = ifp->valid_lft, .preferred_lft = ifp->prefered_lft, .scope = ifp->scope, }; if (retries > net->ipv6.sysctl.idgen_retries) { net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", ifp->idev->dev->name); goto errdad; } new_addr = ifp->addr; if (ipv6_generate_stable_address(&new_addr, retries, idev)) goto errdad; spin_unlock_bh(&ifp->lock); max_addresses = READ_ONCE(idev->cnf.max_addresses); if (max_addresses && ipv6_count_addresses(idev) >= max_addresses) goto lock_errdad; net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", ifp->idev->dev->name); ifp2 = ipv6_add_addr(idev, &cfg, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; spin_lock_bh(&ifp2->lock); ifp2->stable_privacy_retry = retries; ifp2->state = INET6_IFADDR_STATE_PREDAD; spin_unlock_bh(&ifp2->lock); addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay); in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); } errdad: /* transition from _POSTDAD to _ERRDAD */ ifp->state = INET6_IFADDR_STATE_ERRDAD; spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); in6_ifa_put(ifp); } /* Join to solicited addr multicast group. * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); } /* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; addrconf_addr_solict_mult(addr, &maddr); __ipv6_dev_mc_dec(idev, &maddr); } /* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; __ipv6_dev_ac_inc(ifp->idev, &addr); } /* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; __ipv6_dev_ac_dec(ifp->idev, &addr); } static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev) { switch (dev->addr_len) { case ETH_ALEN: memcpy(eui, dev->dev_addr, 3); eui[3] = 0xFF; eui[4] = 0xFE; memcpy(eui + 5, dev->dev_addr + 3, 3); break; case EUI64_ADDR_LEN: memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN); eui[0] ^= 2; break; default: return -1; } return 0; } static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) { const union fwnet_hwaddr *ha; if (dev->addr_len != FWNET_ALEN) return -1; ha = (const union fwnet_hwaddr *)dev->dev_addr; memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); eui[0] ^= 2; return 0; } static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) { /* XXX: inherit EUI-64 from other interface -- yoshfuji */ if (dev->addr_len != ARCNET_ALEN) return -1; memset(eui, 0, 7); eui[7] = *(u8 *)dev->dev_addr; return 0; } static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) { if (dev->addr_len != INFINIBAND_ALEN) return -1; memcpy(eui, dev->dev_addr + 12, 8); eui[0] |= 2; return 0; } static int __ipv6_isatap_ifid(u8 *eui, __be32 addr) { if (addr == 0) return -1; eui[0] = (ipv4_is_zeronet(addr) || ipv4_is_private_10(addr) || ipv4_is_loopback(addr) || ipv4_is_linklocal_169(addr) || ipv4_is_private_172(addr) || ipv4_is_test_192(addr) || ipv4_is_anycast_6to4(addr) || ipv4_is_private_192(addr) || ipv4_is_test_198(addr) || ipv4_is_multicast(addr) || ipv4_is_lbcast(addr)) ? 0x00 : 0x02; eui[1] = 0; eui[2] = 0x5E; eui[3] = 0xFE; memcpy(eui + 4, &addr, 4); return 0; } static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) { if (dev->priv_flags & IFF_ISATAP) return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); return -1; } static int addrconf_ifid_gre(u8 *eui, struct net_device *dev) { return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); } static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev) { memcpy(eui, dev->perm_addr, 3); memcpy(eui + 5, dev->perm_addr + 3, 3); eui[3] = 0xFF; eui[4] = 0xFE; eui[0] ^= 2; return 0; } static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: return addrconf_ifid_eui48(eui, dev); case ARPHRD_ARCNET: return addrconf_ifid_arcnet(eui, dev); case ARPHRD_INFINIBAND: return addrconf_ifid_infiniband(eui, dev); case ARPHRD_SIT: return addrconf_ifid_sit(eui, dev); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: return addrconf_ifid_gre(eui, dev); case ARPHRD_6LOWPAN: return addrconf_ifid_6lowpan(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); case ARPHRD_TUNNEL6: case ARPHRD_IP6GRE: case ARPHRD_RAWIP: return addrconf_ifid_ip6tnl(eui, dev); } return -1; } static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) { int err = -1; struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { if (ifp->scope > IFA_LINK) break; if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; break; } } read_unlock_bh(&idev->lock); return err; } /* Generation of a randomized Interface Identifier * draft-ietf-6man-rfc4941bis, Section 3.3.1 */ static void ipv6_gen_rnd_iid(struct in6_addr *addr) { regen: get_random_bytes(&addr->s6_addr[8], 8); /* <draft-ietf-6man-rfc4941bis-08.txt>, Section 3.3.1: * check if generated address is not inappropriate: * * - Reserved IPv6 Interface Identifiers * - XXX: already assigned to an address on the device */ /* Subnet-router anycast: 0000:0000:0000:0000 */ if (!(addr->s6_addr32[2] | addr->s6_addr32[3])) goto regen; /* IANA Ethernet block: 0200:5EFF:FE00:0000-0200:5EFF:FE00:5212 * Proxy Mobile IPv6: 0200:5EFF:FE00:5213 * IANA Ethernet block: 0200:5EFF:FE00:5214-0200:5EFF:FEFF:FFFF */ if (ntohl(addr->s6_addr32[2]) == 0x02005eff && (ntohl(addr->s6_addr32[3]) & 0Xff000000) == 0xfe000000) goto regen; /* Reserved subnet anycast addresses */ if (ntohl(addr->s6_addr32[2]) == 0xfdffffff && ntohl(addr->s6_addr32[3]) >= 0Xffffff80) goto regen; } /* * Add prefix route. */ static void addrconf_prefix_route(struct in6_addr *pfx, int plen, u32 metric, struct net_device *dev, unsigned long expires, u32 flags, gfp_t gfp_flags) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, .fc_metric = metric ? : IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, .fc_type = RTN_UNICAST, }; cfg.fc_dst = *pfx; /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ #if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) cfg.fc_flags |= RTF_NONEXTHOP; #endif ip6_route_add(&cfg, gfp_flags, NULL); } static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags, bool no_gw) { struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; table = fib6_get_table(dev_net(dev), tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* prefix routes only use builtin fib6_nh */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != dev->ifindex) continue; if (no_gw && rt->fib6_nh->fib_nh_gw_family) continue; if ((rt->fib6_flags & flags) != flags) continue; if ((rt->fib6_flags & noflags) != 0) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, .fc_type = RTN_MULTICAST, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); ip6_route_add(&cfg, GFP_KERNEL, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) return idev; if (idev->cnf.disable_ipv6) return ERR_PTR(-EACCES); /* Add default multicast route */ if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev)) addrconf_add_mroute(dev); return idev; } static void delete_tempaddrs(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { struct inet6_ifaddr *ift, *tmp; write_lock_bh(&idev->lock); list_for_each_entry_safe(ift, tmp, &idev->tempaddr_list, tmp_list) { if (ift->ifpub != ifp) continue; in6_ifa_hold(ift); write_unlock_bh(&idev->lock); ipv6_del_addr(ift); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); } static void manage_tempaddrs(struct inet6_dev *idev, struct inet6_ifaddr *ifp, __u32 valid_lft, __u32 prefered_lft, bool create, unsigned long now) { u32 flags; struct inet6_ifaddr *ift; read_lock_bh(&idev->lock); /* update all temporary addresses in the list */ list_for_each_entry(ift, &idev->tempaddr_list, tmp_list) { int age, max_valid, max_prefered; if (ifp != ift->ifpub) continue; /* RFC 4941 section 3.3: * If a received option will extend the lifetime of a public * address, the lifetimes of temporary addresses should * be extended, subject to the overall constraint that no * temporary addresses should ever remain "valid" or "preferred" * for a time longer than (TEMP_VALID_LIFETIME) or * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively. */ age = (now - ift->cstamp) / HZ; max_valid = READ_ONCE(idev->cnf.temp_valid_lft) - age; if (max_valid < 0) max_valid = 0; max_prefered = READ_ONCE(idev->cnf.temp_prefered_lft) - idev->desync_factor - age; if (max_prefered < 0) max_prefered = 0; if (valid_lft > max_valid) valid_lft = max_valid; if (prefered_lft > max_prefered) prefered_lft = max_prefered; spin_lock(&ift->lock); flags = ift->flags; ift->valid_lft = valid_lft; ift->prefered_lft = prefered_lft; ift->tstamp = now; if (prefered_lft > 0) ift->flags &= ~IFA_F_DEPRECATED; spin_unlock(&ift->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ift); } /* Also create a temporary address if it's enabled but no temporary * address currently exists. * However, we get called with valid_lft == 0, prefered_lft == 0, create == false * as part of cleanup (ie. deleting the mngtmpaddr). * We don't want that to result in creating a new temporary ip address. */ if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) create = true; if (create && READ_ONCE(idev->cnf.use_tempaddr) > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. */ read_unlock_bh(&idev->lock); ipv6_create_tempaddr(ifp, false); } else { read_unlock_bh(&idev->lock); } } static bool is_addr_mode_generate_stable(struct inet6_dev *idev) { return idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; } int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, const struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); int create = 0, update_lft = 0; if (!ifp && valid_lft) { int max_addresses = READ_ONCE(in6_dev->cnf.max_addresses); struct ifa6_config cfg = { .pfx = addr, .plen = pinfo->prefix_len, .ifa_flags = addr_flags, .valid_lft = valid_lft, .preferred_lft = prefered_lft, .scope = addr_type & IPV6_ADDR_SCOPE_MASK, .ifa_proto = IFAPROT_KERNEL_RA }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((READ_ONCE(net->ipv6.devconf_all->optimistic_dad) || READ_ONCE(in6_dev->cnf.optimistic_dad)) && !net->ipv6.devconf_all->forwarding && sllao) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured * addresses; this would be too easy way to crash kernel. */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) ifp = ipv6_add_addr(in6_dev, &cfg, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; create = 1; spin_lock_bh(&ifp->lock); ifp->flags |= IFA_F_MANAGETEMPADDR; ifp->cstamp = jiffies; ifp->tokenized = tokenized; spin_unlock_bh(&ifp->lock); addrconf_dad_start(ifp); } if (ifp) { u32 flags; unsigned long now; u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; /* RFC4862 Section 5.5.3e: * "Note that the preferred lifetime of the * corresponding address is always reset to * the Preferred Lifetime in the received * Prefix Information option, regardless of * whether the valid lifetime is also reset or * ignored." * * So we should always update prefered_lft here. */ update_lft = !create && stored_lft; if (update_lft && !READ_ONCE(in6_dev->cnf.ra_honor_pio_life)) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); } if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; WRITE_ONCE(ifp->tstamp, now); flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); } else spin_unlock_bh(&ifp->lock); manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, create, now); in6_ifa_put(ifp); addrconf_verify(net); } return 0; } EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr); void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; struct fib6_table *table; __u32 valid_lft; __u32 prefered_lft; int addr_type, err; u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); bool ignore_autoconf = false; pinfo = (struct prefix_info *) opt; if (len < sizeof(struct prefix_info)) { netdev_dbg(dev, "addrconf: prefix option too short\n"); return; } /* * Validation checks ([ADDRCONF], page 19) */ addr_type = ipv6_addr_type(&pinfo->prefix); if (addr_type & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)) return; valid_lft = ntohl(pinfo->valid); prefered_lft = ntohl(pinfo->prefered); if (prefered_lft > valid_lft) { net_warn_ratelimited("addrconf: prefix option has invalid lifetime\n"); return; } in6_dev = in6_dev_get(dev); if (!in6_dev) { net_dbg_ratelimited("addrconf: device %s not configured\n", dev->name); return; } if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) goto put; /* * Two things going on here: * 1) Add routes for on-link prefixes * 2) Configure prefixes with the auto flag set */ if (pinfo->onlink) { struct fib6_info *rt; unsigned long rt_expires; /* Avoid arithmetic overflow. Really, we could * save rt_expires in seconds, likely valid_lft, * but it would require division in fib gc, that it * not good. */ if (HZ > USER_HZ) rt_expires = addrconf_timeout_fixup(valid_lft, HZ); else rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); if (addrconf_finite_timeout(rt_expires)) rt_expires *= HZ; rt = addrconf_get_prefix_route(&pinfo->prefix, pinfo->prefix_len, dev, RTF_ADDRCONF | RTF_PREFIX_RT, RTF_DEFAULT, true); if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { ip6_del_rt(net, rt, false); rt = NULL; } else { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ fib6_set_expires(rt, jiffies + rt_expires); fib6_add_gc_list(rt); } else { fib6_clean_expires(rt); fib6_remove_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); } } else if (valid_lft) { clock_t expires = 0; int flags = RTF_ADDRCONF | RTF_PREFIX_RT; if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ flags |= RTF_EXPIRES; expires = jiffies_to_clock_t(rt_expires); } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, 0, dev, expires, flags, GFP_ATOMIC); } fib6_info_release(rt); } /* Try to figure out our local address for this prefix */ ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd; if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; if (pinfo->prefix_len == 64) { memcpy(&addr, &pinfo->prefix, 8); if (!ipv6_addr_any(&in6_dev->token)) { read_lock_bh(&in6_dev->lock); memcpy(addr.s6_addr + 8, in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; } else if (is_addr_mode_generate_stable(in6_dev) && !ipv6_generate_stable_address(&addr, 0, in6_dev)) { addr_flags |= IFA_F_STABLE_PRIVACY; goto ok; } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { goto put; } else { dev_addr_generated = true; } goto ok; } net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n", pinfo->prefix_len); goto put; ok: err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft); if (err) goto put; /* Ignore error case here because previous prefix add addr was * successful which will be notified. */ ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo); put: in6_dev_put(in6_dev); } static int addrconf_set_sit_dstaddr(struct net *net, struct net_device *dev, struct in6_ifreq *ireq) { struct ip_tunnel_parm_kern p = { }; int err; if (!(ipv6_addr_type(&ireq->ifr6_addr) & IPV6_ADDR_COMPATv4)) return -EADDRNOTAVAIL; p.iph.daddr = ireq->ifr6_addr.s6_addr32[3]; p.iph.version = 4; p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPV6; p.iph.ttl = 64; if (!dev->netdev_ops->ndo_tunnel_ctl) return -EOPNOTSUPP; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, SIOCADDTUNNEL); if (err) return err; dev = __dev_get_by_name(net, p.name); if (!dev) return -ENOBUFS; return dev_open(dev, NULL); } /* * Set destination address. * Special case for SIT interfaces where we create a new "virtual" * device. */ int addrconf_set_dstaddr(struct net *net, void __user *arg) { struct net_device *dev; struct in6_ifreq ireq; int err = -ENODEV; if (!IS_ENABLED(CONFIG_IPV6_SIT)) return -ENODEV; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; rtnl_net_lock(net); dev = __dev_get_by_index(net, ireq.ifr6_ifindex); if (dev && dev->type == ARPHRD_SIT) err = addrconf_set_sit_dstaddr(net, dev, &ireq); rtnl_net_unlock(net); return err; } static int ipv6_mc_config(struct sock *sk, bool join, const struct in6_addr *addr, int ifindex) { int ret; ASSERT_RTNL(); lock_sock(sk); if (join) ret = ipv6_sock_mc_join(sk, ifindex, addr); else ret = ipv6_sock_mc_drop(sk, ifindex, addr); release_sock(sk); return ret; } /* * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, struct net_device *dev, struct ifa6_config *cfg, clock_t expires, u32 flags, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; ASSERT_RTNL_NET(net); if (cfg->plen > 128) { NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length"); return -EINVAL; } if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) { NL_SET_ERR_MSG_MOD(extack, "address with \"mngtmpaddr\" flag must have a prefix length of 64"); return -EINVAL; } idev = addrconf_add_dev(dev); if (IS_ERR(idev)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); return PTR_ERR(idev); } if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, true, cfg->pfx, dev->ifindex); if (ret < 0) { NL_SET_ERR_MSG_MOD(extack, "Multicast auto join failed"); return ret; } } cfg->scope = ipv6_addr_scope(cfg->pfx); ifp = ipv6_add_addr(idev, cfg, true, extack); if (!IS_ERR(ifp)) { if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, dev, expires, flags, GFP_KERNEL); } /* Send a netlink notification if DAD is enabled and * optimistic flag is not set */ if (!(ifp->flags & (IFA_F_OPTIMISTIC | IFA_F_NODAD))) ipv6_ifa_notify(0, ifp); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for * manually configured addresses */ addrconf_dad_start(ifp); if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR) manage_tempaddrs(idev, ifp, cfg->valid_lft, cfg->preferred_lft, true, jiffies); in6_ifa_put(ifp); addrconf_verify_rtnl(net); return 0; } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, cfg->pfx, dev->ifindex); } return PTR_ERR(ifp); } static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, const struct in6_addr *pfx, unsigned int plen, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; if (plen > 128) { NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length"); return -EINVAL; } dev = __dev_get_by_index(net, ifindex); if (!dev) { NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); return -ENODEV; } idev = __in6_dev_get_rtnl_net(dev); if (!idev) { NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); return -ENXIO; } read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->prefix_len == plen && ipv6_addr_equal(pfx, &ifp->addr)) { in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); ipv6_del_addr(ifp); if (!(ifp->flags & IFA_F_TEMPORARY) && (ifp->flags & IFA_F_MANAGETEMPADDR)) delete_tempaddrs(idev, ifp); addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, pfx, dev->ifindex); } return 0; } } read_unlock_bh(&idev->lock); NL_SET_ERR_MSG_MOD(extack, "address not found"); return -EADDRNOTAVAIL; } int addrconf_add_ifaddr(struct net *net, void __user *arg) { struct ifa6_config cfg = { .ifa_flags = IFA_F_PERMANENT, .preferred_lft = INFINITY_LIFE_TIME, .valid_lft = INFINITY_LIFE_TIME, }; struct net_device *dev; struct in6_ifreq ireq; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; cfg.pfx = &ireq.ifr6_addr; cfg.plen = ireq.ifr6_prefixlen; rtnl_net_lock(net); dev = __dev_get_by_index(net, ireq.ifr6_ifindex); if (dev) err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL); else err = -ENODEV; rtnl_net_unlock(net); return err; } int addrconf_del_ifaddr(struct net *net, void __user *arg) { struct in6_ifreq ireq; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; rtnl_net_lock(net); err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr, ireq.ifr6_prefixlen, NULL); rtnl_net_unlock(net); return err; } static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int plen, int scope, u8 proto) { struct inet6_ifaddr *ifp; struct ifa6_config cfg = { .pfx = addr, .plen = plen, .ifa_flags = IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, .scope = scope, .ifa_proto = proto }; ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; spin_unlock_bh(&ifp->lock); rt_genid_bump_ipv6(dev_net(idev->dev)); ipv6_ifa_notify(RTM_NEWADDR, ifp); in6_ifa_put(ifp); } } #if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) static void add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); int scope, plen, offset = 0; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ if (idev->dev->addr_len == sizeof(struct in6_addr)) offset = sizeof(struct in6_addr) - 4; memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { scope = IPV6_ADDR_COMPATv4; plen = 96; pflags |= RTF_NONEXTHOP; } else { if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) return; addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; } if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); return; } for_each_netdev(net, dev) { struct in_device *in_dev = __in_dev_get_rtnl(dev); if (in_dev && (dev->flags & IFF_UP)) { struct in_ifaddr *ifa; int flag = scope; in_dev_for_each_ifa_rtnl(ifa, in_dev) { addr.s6_addr32[3] = ifa->ifa_local; if (ifa->ifa_scope == RT_SCOPE_LINK) continue; if (ifa->ifa_scope >= RT_SCOPE_HOST) { if (idev->dev->flags&IFF_POINTOPOINT) continue; flag |= IFA_HOST; } add_addr(idev, &addr, plen, flag, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); } } } } #endif static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; /* ::1 */ ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFAPROT_KERNEL_LO); } void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags) { struct ifa6_config cfg = { .pfx = addr, .plen = 64, .ifa_flags = flags | IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, .scope = IFA_LINK, .ifa_proto = IFAPROT_KERNEL_LL }; struct inet6_ifaddr *ifp; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad) || READ_ONCE(idev->cnf.optimistic_dad)) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, 0, idev->dev, 0, 0, GFP_ATOMIC); addrconf_dad_start(ifp); in6_ifa_put(ifp); } } EXPORT_SYMBOL_GPL(addrconf_add_linklocal); static bool ipv6_reserved_interfaceid(struct in6_addr address) { if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0) return true; if (address.s6_addr32[2] == htonl(0x02005eff) && ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000))) return true; if (address.s6_addr32[2] == htonl(0xfdffffff) && ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80))) return true; return false; } static int ipv6_generate_stable_address(struct in6_addr *address, u8 dad_count, const struct inet6_dev *idev) { static DEFINE_SPINLOCK(lock); static __u32 digest[SHA1_DIGEST_WORDS]; static __u32 workspace[SHA1_WORKSPACE_WORDS]; static union { char __data[SHA1_BLOCK_SIZE]; struct { struct in6_addr secret; __be32 prefix[2]; unsigned char hwaddr[MAX_ADDR_LEN]; u8 dad_count; } __packed; } data; struct in6_addr secret; struct in6_addr temp; struct net *net = dev_net(idev->dev); BUILD_BUG_ON(sizeof(data.__data) != sizeof(data)); if (idev->cnf.stable_secret.initialized) secret = idev->cnf.stable_secret.secret; else if (net->ipv6.devconf_dflt->stable_secret.initialized) secret = net->ipv6.devconf_dflt->stable_secret.secret; else return -1; retry: spin_lock_bh(&lock); sha1_init(digest); memset(&data, 0, sizeof(data)); memset(workspace, 0, sizeof(workspace)); memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len); data.prefix[0] = address->s6_addr32[0]; data.prefix[1] = address->s6_addr32[1]; data.secret = secret; data.dad_count = dad_count; sha1_transform(digest, data.__data, workspace); temp = *address; temp.s6_addr32[2] = (__force __be32)digest[0]; temp.s6_addr32[3] = (__force __be32)digest[1]; spin_unlock_bh(&lock); if (ipv6_reserved_interfaceid(temp)) { dad_count++; if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries) return -1; goto retry; } *address = temp; return 0; } static void ipv6_gen_mode_random_init(struct inet6_dev *idev) { struct ipv6_stable_secret *s = &idev->cnf.stable_secret; if (s->initialized) return; s = &idev->cnf.stable_secret; get_random_bytes(&s->secret, sizeof(s->secret)); s->initialized = true; } static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; /* no link local addresses on L3 master devices */ if (netif_is_l3_master(idev->dev)) return; /* no link local addresses on devices flagged as slaves */ if (idev->dev->priv_flags & IFF_NO_ADDRCONF) return; ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); switch (idev->cnf.addr_gen_mode) { case IN6_ADDR_GEN_MODE_RANDOM: ipv6_gen_mode_random_init(idev); fallthrough; case IN6_ADDR_GEN_MODE_STABLE_PRIVACY: if (!ipv6_generate_stable_address(&addr, 0, idev)) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) addrconf_prefix_route(&addr, 64, 0, idev->dev, 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. */ if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, 0, idev->dev, 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_NONE: default: /* will not add any link local address */ break; } } static void addrconf_dev_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_FDDI) && (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && (dev->type != ARPHRD_6LOWPAN) && (dev->type != ARPHRD_TUNNEL) && (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ idev = __in6_dev_get(dev); if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) ipv6_mc_up(idev); return; } idev = addrconf_add_dev(dev); if (IS_ERR(idev)) return; /* this device type has no EUI support */ if (dev->type == ARPHRD_NONE && idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) WRITE_ONCE(idev->cnf.addr_gen_mode, IN6_ADDR_GEN_MODE_RANDOM); addrconf_addr_gen(idev, false); } #if IS_ENABLED(CONFIG_IPV6_SIT) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); /* * Configure the tunnel with one of our IPv4 * addresses... we should configure all of * our v4 addrs in the tunnel */ idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } if (dev->priv_flags & IFF_ISATAP) { addrconf_addr_gen(idev, false); return; } add_v4_addrs(idev); if (dev->flags&IFF_POINTOPOINT) addrconf_add_mroute(dev); } #endif #if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } if (dev->type == ARPHRD_ETHER) { addrconf_addr_gen(idev, true); return; } add_v4_addrs(idev); if (dev->flags & IFF_POINTOPOINT) addrconf_add_mroute(dev); } #endif static void addrconf_init_auto_addrs(struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: addrconf_sit_config(dev); break; #endif #if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) case ARPHRD_IP6GRE: case ARPHRD_IPGRE: addrconf_gre_config(dev); break; #endif case ARPHRD_LOOPBACK: init_loopback(dev); break; default: addrconf_dev_config(dev); break; } } static int fixup_permanent_addr(struct net *net, struct inet6_dev *idev, struct inet6_ifaddr *ifp) { /* !fib6_node means the host route was removed from the * FIB, for example, if 'lo' device is taken down. In that * case regenerate the host route. */ if (!ifp->rt || !ifp->rt->fib6_node) { struct fib6_info *f6i, *prev; f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false, GFP_ATOMIC, NULL); if (IS_ERR(f6i)) return PTR_ERR(f6i); /* ifp->rt can be accessed outside of rtnl */ spin_lock(&ifp->lock); prev = ifp->rt; ifp->rt = f6i; spin_unlock(&ifp->lock); fib6_info_release(prev); } if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, idev->dev, 0, 0, GFP_ATOMIC); } if (ifp->state == INET6_IFADDR_STATE_PREDAD) addrconf_dad_start(ifp); return 0; } static void addrconf_permanent_addr(struct net *net, struct net_device *dev) { struct inet6_ifaddr *ifp, *tmp; struct inet6_dev *idev; idev = __in6_dev_get(dev); if (!idev) return; write_lock_bh(&idev->lock); list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { if ((ifp->flags & IFA_F_PERMANENT) && fixup_permanent_addr(net, idev, ifp) < 0) { write_unlock_bh(&idev->lock); in6_ifa_hold(ifp); ipv6_del_addr(ifp); write_lock_bh(&idev->lock); net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", idev->dev->name, &ifp->addr); } } write_unlock_bh(&idev->lock); } static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct netdev_notifier_changeupper_info *info; struct inet6_dev *idev = __in6_dev_get(dev); struct net *net = dev_net(dev); int run_pending = 0; int err; switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); if (IS_ERR(idev)) return notifier_from_errno(PTR_ERR(idev)); } break; case NETDEV_CHANGEMTU: /* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) { addrconf_ifdown(dev, dev != net->loopback_dev); break; } if (idev) { rt6_mtu_change(dev, dev->mtu); WRITE_ONCE(idev->cnf.mtu6, dev->mtu); break; } /* allocate new idev */ idev = ipv6_add_dev(dev); if (IS_ERR(idev)) break; /* device is still not ready */ if (!(idev->if_flags & IF_READY)) break; run_pending = 1; fallthrough; case NETDEV_UP: case NETDEV_CHANGE: if (idev && idev->cnf.disable_ipv6) break; if (dev->priv_flags & IFF_NO_ADDRCONF) { if (event == NETDEV_UP && !IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) ipv6_mc_up(idev); break; } if (event == NETDEV_UP) { /* restore routes for permanent addresses */ addrconf_permanent_addr(net, dev); if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ pr_debug("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); break; } if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); if (!IS_ERR_OR_NULL(idev)) { idev->if_flags |= IF_READY; run_pending = 1; } } else if (event == NETDEV_CHANGE) { if (!addrconf_link_ready(dev)) { /* device is still not ready. */ rt6_sync_down_dev(dev, event); break; } if (!IS_ERR_OR_NULL(idev)) { if (idev->if_flags & IF_READY) { /* device is already configured - * but resend MLD reports, we might * have roamed and need to update * multicast snooping switches */ ipv6_mc_up(idev); change_info = ptr; if (change_info->flags_changed & IFF_NOARP) addrconf_dad_run(idev, true); rt6_sync_up(dev, RTNH_F_LINKDOWN); break; } idev->if_flags |= IF_READY; } pr_debug("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", dev->name); run_pending = 1; } addrconf_init_auto_addrs(dev); if (!IS_ERR_OR_NULL(idev)) { if (run_pending) addrconf_dad_run(idev, false); /* Device has an address by now */ rt6_sync_up(dev, RTNH_F_DEAD); /* * If the MTU changed during the interface down, * when the interface up, the changed MTU must be * reflected in the idev as well as routers. */ if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); WRITE_ONCE(idev->cnf.mtu6, dev->mtu); } WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); /* * If the changed mtu during down is lower than * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) addrconf_ifdown(dev, dev != net->loopback_dev); } break; case NETDEV_DOWN: case NETDEV_UNREGISTER: /* * Remove all addresses from this interface. */ addrconf_ifdown(dev, event != NETDEV_DOWN); break; case NETDEV_CHANGENAME: if (idev) { snmp6_unregister_dev(idev); addrconf_sysctl_unregister(idev); err = addrconf_sysctl_register(idev); if (err) return notifier_from_errno(err); err = snmp6_register_dev(idev); if (err) { addrconf_sysctl_unregister(idev); return notifier_from_errno(err); } } break; case NETDEV_PRE_TYPE_CHANGE: case NETDEV_POST_TYPE_CHANGE: if (idev) addrconf_type_change(dev, event); break; case NETDEV_CHANGEUPPER: info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (info->upper_dev && netif_is_l3_master(info->upper_dev)) addrconf_ifdown(dev, false); } return NOTIFY_OK; } /* * addrconf module should be notified of a device going up */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, .priority = ADDRCONF_NOTIFY_PRIORITY, }; static void addrconf_type_change(struct net_device *dev, unsigned long event) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (event == NETDEV_POST_TYPE_CHANGE) ipv6_mc_remap(idev); else if (event == NETDEV_PRE_TYPE_CHANGE) ipv6_mc_unmap(idev); } static bool addr_is_local(const struct in6_addr *addr) { return ipv6_addr_type(addr) & (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } static int addrconf_ifdown(struct net_device *dev, bool unregister) { unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa; LIST_HEAD(tmp_addr_list); bool keep_addr = false; bool was_ready; int state, i; ASSERT_RTNL(); rt6_disable_ip(dev, event); idev = __in6_dev_get(dev); if (!idev) return -ENODEV; /* * Step 1: remove reference to ipv6 device from parent device. * Do not dev_put! */ if (unregister) { idev->dead = 1; /* protected by rtnl_lock */ RCU_INIT_POINTER(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); } /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ int _keep_addr = READ_ONCE(net->ipv6.devconf_all->keep_addr_on_down); if (!_keep_addr) _keep_addr = READ_ONCE(idev->cnf.keep_addr_on_down); keep_addr = (_keep_addr > 0); } /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &net->ipv6.inet6_addr_lst[i]; spin_lock_bh(&net->ipv6.addrconf_hash_lock); restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { addrconf_del_dad_work(ifa); /* combined flag + permanent flag decide if * address is retained on a down event */ if (!keep_addr || !(ifa->flags & IFA_F_PERMANENT) || addr_is_local(&ifa->addr)) { hlist_del_init_rcu(&ifa->addr_lst); goto restart; } } } spin_unlock_bh(&net->ipv6.addrconf_hash_lock); } write_lock_bh(&idev->lock); addrconf_del_rs_timer(idev); /* Step 2: clear flags for stateless addrconf, repeated down * detection */ was_ready = idev->if_flags & IF_READY; if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 3: clear tempaddr list */ while (!list_empty(&idev->tempaddr_list)) { ifa = list_first_entry(&idev->tempaddr_list, struct inet6_ifaddr, tmp_list); list_del(&ifa->tmp_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); if (ifa->ifpub) { in6_ifa_put(ifa->ifpub); ifa->ifpub = NULL; } spin_unlock_bh(&ifa->lock); in6_ifa_put(ifa); write_lock_bh(&idev->lock); } list_for_each_entry(ifa, &idev->addr_list, if_list) list_add_tail(&ifa->if_list_aux, &tmp_addr_list); write_unlock_bh(&idev->lock); while (!list_empty(&tmp_addr_list)) { struct fib6_info *rt = NULL; bool keep; ifa = list_first_entry(&tmp_addr_list, struct inet6_ifaddr, if_list_aux); list_del(&ifa->if_list_aux); addrconf_del_dad_work(ifa); keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); spin_lock_bh(&ifa->lock); if (keep) { /* set state to skip the notifier below */ state = INET6_IFADDR_STATE_DEAD; ifa->state = INET6_IFADDR_STATE_PREDAD; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; rt = ifa->rt; ifa->rt = NULL; } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; } spin_unlock_bh(&ifa->lock); if (rt) ip6_del_rt(net, rt, false); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } else { if (idev->cnf.forwarding) addrconf_leave_anycast(ifa); addrconf_leave_solict(ifa->idev, &ifa->addr); } if (!keep) { write_lock_bh(&idev->lock); list_del_rcu(&ifa->if_list); write_unlock_bh(&idev->lock); in6_ifa_put(ifa); } } /* Step 5: Discard anycast and multicast list */ if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); } else if (was_ready) { ipv6_mc_down(idev); } WRITE_ONCE(idev->tstamp, jiffies); idev->ra_mtu = 0; /* Last: Shot the device (if unregistered) */ if (unregister) { addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); in6_dev_put(idev); } return 0; } static void addrconf_rs_timer(struct timer_list *t) { struct inet6_dev *idev = from_timer(idev, t, rs_timer); struct net_device *dev = idev->dev; struct in6_addr lladdr; int rtr_solicits; write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) goto out; if (!ipv6_accept_ra(idev)) goto out; /* Announcement received after solicitation was sent */ if (idev->if_flags & IF_RA_RCVD) goto out; rtr_solicits = READ_ONCE(idev->cnf.rtr_solicits); if (idev->rs_probes++ < rtr_solicits || rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); else goto put; write_lock(&idev->lock); idev->rs_interval = rfc3315_s14_backoff_update( idev->rs_interval, READ_ONCE(idev->cnf.rtr_solicit_max_interval)); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == READ_ONCE(idev->cnf.rtr_solicits)) ? READ_ONCE(idev->cnf.rtr_solicit_delay) : idev->rs_interval); } else { /* * Note: we do not support deprecated "all on-link" * assumption any longer. */ pr_debug("%s: no IPv6 routers present\n", idev->dev->name); } out: write_unlock(&idev->lock); put: in6_dev_put(idev); } /* * Duplicate Address Detection */ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; unsigned long rand_num; u64 nonce; if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else rand_num = get_random_u32_below( READ_ONCE(idev->cnf.rtr_solicit_delay) ? : 1); nonce = 0; if (READ_ONCE(idev->cnf.enhanced_dad) || READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad)) { do get_random_bytes(&nonce, 6); while (nonce == 0); } ifp->dad_nonce = nonce; ifp->dad_probes = READ_ONCE(idev->cnf.dad_transmits); addrconf_mod_dad_work(ifp, rand_num); } static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; bool bump_id, notify = false; struct net *net; addrconf_join_solict(dev, &ifp->addr); read_lock_bh(&idev->lock); spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || (READ_ONCE(net->ipv6.devconf_all->accept_dad) < 1 && READ_ONCE(idev->cnf.accept_dad) < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bool send_na = false; if (ifp->flags & IFA_F_TENTATIVE && !(ifp->flags & IFA_F_OPTIMISTIC)) send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); addrconf_dad_completed(ifp, bump_id, send_na); return; } if (!(idev->if_flags & IF_READY)) { spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); /* * If the device is not ready: * - keep it tentative if it is a permanent address. * - otherwise, kill it. */ in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 0); return; } /* * Optimistic nodes can start receiving * Frames right away */ if (ifp->flags & IFA_F_OPTIMISTIC) { ip6_ins_rt(net, ifp->rt); if (ipv6_use_optimistic_addr(net, idev)) { /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ notify = true; } } addrconf_dad_kick(ifp); out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); if (notify) ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) { bool begin_dad = false; spin_lock_bh(&ifp->lock); if (ifp->state != INET6_IFADDR_STATE_DEAD) { ifp->state = INET6_IFADDR_STATE_PREDAD; begin_dad = true; } spin_unlock_bh(&ifp->lock); if (begin_dad) addrconf_mod_dad_work(ifp, 0); } static void addrconf_dad_work(struct work_struct *w) { struct inet6_ifaddr *ifp = container_of(to_delayed_work(w), struct inet6_ifaddr, dad_work); struct inet6_dev *idev = ifp->idev; bool bump_id, disable_ipv6 = false; struct in6_addr mcaddr; struct net *net; enum { DAD_PROCESS, DAD_BEGIN, DAD_ABORT, } action = DAD_PROCESS; net = dev_net(idev->dev); rtnl_net_lock(net); spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; ifp->state = INET6_IFADDR_STATE_DAD; } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; if ((READ_ONCE(net->ipv6.devconf_all->accept_dad) > 1 || READ_ONCE(idev->cnf.accept_dad) > 1) && !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { struct in6_addr addr; addr.s6_addr32[0] = htonl(0xfe800000); addr.s6_addr32[1] = 0; if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && ipv6_addr_equal(&ifp->addr, &addr)) { /* DAD failed for link-local based on MAC */ WRITE_ONCE(idev->cnf.disable_ipv6, 1); pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); disable_ipv6 = true; } } } spin_unlock_bh(&ifp->lock); if (action == DAD_BEGIN) { addrconf_dad_begin(ifp); goto out; } else if (action == DAD_ABORT) { in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); if (disable_ipv6) addrconf_ifdown(idev->dev, false); goto out; } if (!ifp->dad_probes && addrconf_dad_end(ifp)) goto out; write_lock_bh(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { write_unlock_bh(&idev->lock); goto out; } spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); goto out; } if (ifp->dad_probes == 0) { bool send_na = false; /* * DAD was successful */ if (ifp->flags & IFA_F_TENTATIVE && !(ifp->flags & IFA_F_OPTIMISTIC)) send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); addrconf_dad_completed(ifp, bump_id, send_na); goto out; } ifp->dad_probes--; addrconf_mod_dad_work(ifp, max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100)); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, ifp->dad_nonce); out: in6_ifa_put(ifp); rtnl_net_unlock(net); } /* ifp->idev must be at least read locked */ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) { struct inet6_ifaddr *ifpiter; struct inet6_dev *idev = ifp->idev; list_for_each_entry_reverse(ifpiter, &idev->addr_list, if_list) { if (ifpiter->scope > IFA_LINK) break; if (ifp != ifpiter && ifpiter->scope == IFA_LINK && (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE| IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) == IFA_F_PERMANENT) return false; } return true; } static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, bool send_na) { struct net_device *dev = ifp->idev->dev; struct in6_addr lladdr; bool send_rs, send_mld; addrconf_del_dad_work(ifp); /* * Configure the address for reception. Now it is valid. */ ipv6_ifa_notify(RTM_NEWADDR, ifp); /* If added prefix is link local and we are prepared to process router advertisements, start sending router solicitations. */ read_lock_bh(&ifp->idev->lock); send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && READ_ONCE(ifp->idev->cnf.rtr_solicits) != 0 && (dev->flags & IFF_LOOPBACK) == 0 && (dev->type != ARPHRD_TUNNEL) && !netif_is_team_port(dev); read_unlock_bh(&ifp->idev->lock); /* While dad is in progress mld report's source address is in6_addrany. * Resend with proper ll now. */ if (send_mld) ipv6_mc_dad_complete(ifp->idev); /* send unsolicited NA if enabled */ if (send_na && (READ_ONCE(ifp->idev->cnf.ndisc_notify) || READ_ONCE(dev_net(dev)->ipv6.devconf_all->ndisc_notify))) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, /*router=*/ !!ifp->idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } if (send_rs) { /* * If a host as already performed a random delay * [...] as part of DAD [...] there is no need * to delay again before sending the first RS */ if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) return; ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); ifp->idev->rs_interval = rfc3315_s14_backoff_init( READ_ONCE(ifp->idev->cnf.rtr_solicit_interval)); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); spin_unlock(&ifp->lock); write_unlock_bh(&ifp->idev->lock); } if (bump_id) rt_genid_bump_ipv6(dev_net(dev)); /* Make sure that a new temporary address will be created * before this temporary address becomes deprecated. */ if (ifp->flags & IFA_F_TEMPORARY) addrconf_verify_rtnl(dev_net(dev)); } static void addrconf_dad_run(struct inet6_dev *idev, bool restart) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); if ((ifp->flags & IFA_F_TENTATIVE && ifp->state == INET6_IFADDR_STATE_DAD) || restart) { if (restart) ifp->state = INET6_IFADDR_STATE_PREDAD; addrconf_dad_kick(ifp); } spin_unlock(&ifp->lock); } read_unlock_bh(&idev->lock); } #ifdef CONFIG_PROC_FS struct if6_iter_state { struct seq_net_private p; int bucket; int offset; }; static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct inet6_ifaddr *ifa = NULL; int p = 0; /* initial bucket if pos is 0 */ if (pos == 0) { state->bucket = 0; state->offset = 0; } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { /* sync with offset */ if (p < state->offset) { p++; continue; } return ifa; } /* prepare for next bucket */ state->offset = 0; p = 0; } return NULL; } static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); hlist_for_each_entry_continue_rcu(ifa, addr_lst) { state->offset++; return ifa; } state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { return ifa; } } return NULL; } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return if6_get_first(seq, *pos); } static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct inet6_ifaddr *ifa; ifa = if6_get_next(seq, v); ++*pos; return ifa; } static void if6_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } static int if6_seq_show(struct seq_file *seq, void *v) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v; seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n", &ifp->addr, ifp->idev->dev->ifindex, ifp->prefix_len, ifp->scope, (u8) ifp->flags, ifp->idev->dev->name); return 0; } static const struct seq_operations if6_seq_ops = { .start = if6_seq_start, .next = if6_seq_next, .show = if6_seq_show, .stop = if6_seq_stop, }; static int __net_init if6_proc_net_init(struct net *net) { if (!proc_create_net("if_inet6", 0444, net->proc_net, &if6_seq_ops, sizeof(struct if6_iter_state))) return -ENOMEM; return 0; } static void __net_exit if6_proc_net_exit(struct net *net) { remove_proc_entry("if_inet6", net->proc_net); } static struct pernet_operations if6_proc_net_ops = { .init = if6_proc_net_init, .exit = if6_proc_net_exit, }; int __init if6_proc_init(void) { return register_pernet_subsys(&if6_proc_net_ops); } void if6_proc_exit(void) { unregister_pernet_subsys(&if6_proc_net_ops); } #endif /* CONFIG_PROC_FS */ #if IS_ENABLED(CONFIG_IPV6_MIP6) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp = NULL; int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr) && (ifp->flags & IFA_F_HOMEADDRESS)) { ret = 1; break; } } rcu_read_unlock(); return ret; } #endif /* RFC6554 has some algorithm to avoid loops in segment routing by * checking if the segments contains any of a local interface address. * * Quote: * * To detect loops in the SRH, a router MUST determine if the SRH * includes multiple addresses assigned to any interface on that router. * If such addresses appear more than once and are separated by at least * one address not assigned to that router. */ int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, unsigned char nsegs) { const struct in6_addr *addr; int i, ret = 0, found = 0; struct inet6_ifaddr *ifp; bool separated = false; unsigned int hash; bool hash_found; rcu_read_lock(); for (i = 0; i < nsegs; i++) { addr = &segs[i]; hash = inet6_addr_hash(net, addr); hash_found = false; hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { hash_found = true; break; } } if (hash_found) { if (found > 1 && separated) { ret = 1; break; } separated = false; found++; } else { separated = true; } } rcu_read_unlock(); return ret; } /* * Periodic address status verification */ static void addrconf_verify_rtnl(struct net *net) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; int i; ASSERT_RTNL(); rcu_read_lock_bh(); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); cancel_delayed_work(&net->ipv6.addr_chk_work); for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: hlist_for_each_entry_rcu_bh(ifp, &net->ipv6.inet6_addr_lst[i], addr_lst) { unsigned long age; /* When setting preferred_lft to a value not zero or * infinity, while valid_lft is infinity * IFA_F_PERMANENT has a non-infinity life time. */ if ((ifp->flags & IFA_F_PERMANENT) && (ifp->prefered_lft == INFINITY_LIFE_TIME)) continue; spin_lock(&ifp->lock); /* We try to batch several events at once. */ age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE) && ifp->prefered_lft != INFINITY_LIFE_TIME && !ifp->regen_count && ifp->ifpub) { /* This is a non-regenerated temporary addr. */ unsigned long regen_advance = ipv6_get_regen_advance(ifp->idev); if (age + regen_advance >= ifp->prefered_lft) { struct inet6_ifaddr *ifpub = ifp->ifpub; if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ; ifp->regen_count++; in6_ifa_hold(ifp); in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); rcu_read_unlock_bh(); ipv6_create_tempaddr(ifpub, true); in6_ifa_put(ifpub); in6_ifa_put(ifp); rcu_read_lock_bh(); goto restart; } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; } if (ifp->valid_lft != INFINITY_LIFE_TIME && age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); rcu_read_unlock_bh(); ipv6_del_addr(ifp); rcu_read_lock_bh(); goto restart; } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { spin_unlock(&ifp->lock); continue; } else if (age >= ifp->prefered_lft) { /* jiffies - ifp->tstamp > age >= ifp->prefered_lft */ int deprecate = 0; if (!(ifp->flags&IFA_F_DEPRECATED)) { deprecate = 1; ifp->flags |= IFA_F_DEPRECATED; } if ((ifp->valid_lft != INFINITY_LIFE_TIME) && (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))) next = ifp->tstamp + ifp->valid_lft * HZ; spin_unlock(&ifp->lock); if (deprecate) { in6_ifa_hold(ifp); ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); goto restart; } } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ; spin_unlock(&ifp->lock); } } } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; pr_debug("now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", now, next, next_sec, next_sched); mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } static void addrconf_verify_work(struct work_struct *w) { struct net *net = container_of(to_delayed_work(w), struct net, ipv6.addr_chk_work); rtnl_net_lock(net); addrconf_verify_rtnl(net); rtnl_net_unlock(net); } static void addrconf_verify(struct net *net) { mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, 0); } static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, struct in6_addr **peer_pfx) { struct in6_addr *pfx = NULL; *peer_pfx = NULL; if (addr) pfx = nla_data(addr); if (local) { if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) *peer_pfx = pfx; pfx = nla_data(local); } return pfx; } static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) }, [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; static int inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx, *peer_pfx; u32 ifa_flags; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; ifm = nlmsg_data(nlh); pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (!pfx) return -EINVAL; ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); /* We ignore other flags so far. */ ifa_flags &= IFA_F_MANAGETEMPADDR; rtnl_net_lock(net); err = inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, ifm->ifa_prefixlen, extack); rtnl_net_unlock(net); return err; } static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp, unsigned long expires, u32 flags, bool modify_peer) { struct fib6_table *table; struct fib6_info *f6i; u32 prio; f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (!f6i) return -ENOENT; prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF; if (f6i->fib6_metric != prio) { /* delete old one */ ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); /* add new one */ addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); return 0; } if (f6i != net->ipv6.fib6_null_entry) { table = f6i->fib6_table; spin_lock_bh(&table->tb6_lock); if (!(flags & RTF_EXPIRES)) { fib6_clean_expires(f6i); fib6_remove_gc_list(f6i); } else { fib6_set_expires(f6i, expires); fib6_add_gc_list(f6i); } spin_unlock_bh(&table->tb6_lock); } fib6_info_release(f6i); return 0; } static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, struct ifa6_config *cfg, clock_t expires, u32 flags) { bool was_managetempaddr; bool new_peer = false; bool had_prefixroute; ASSERT_RTNL_NET(net); if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) return -EINVAL; if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) cfg->ifa_flags &= ~IFA_F_OPTIMISTIC; if (cfg->peer_pfx && memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { if (!ipv6_addr_any(&ifp->peer_addr)) cleanup_prefix_route(ifp, expires, true, true); new_peer = true; } spin_lock_bh(&ifp->lock); was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; had_prefixroute = ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE); ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; WRITE_ONCE(ifp->tstamp, jiffies); WRITE_ONCE(ifp->valid_lft, cfg->valid_lft); WRITE_ONCE(ifp->prefered_lft, cfg->preferred_lft); WRITE_ONCE(ifp->ifa_proto, cfg->ifa_proto); if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) WRITE_ONCE(ifp->rt_priority, cfg->rt_priority); if (new_peer) ifp->peer_addr = *cfg->peer_pfx; spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { int rc = -ENOENT; if (had_prefixroute) rc = modify_prefix_route(net, ifp, expires, flags, false); /* prefix route could have been deleted; if so restore it */ if (rc == -ENOENT) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr)) rc = modify_prefix_route(net, ifp, expires, flags, true); if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) { addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; write_lock_bh(&ifp->idev->lock); action = check_cleanup_prefix_route(ifp, &rt_expires); write_unlock_bh(&ifp->idev->lock); if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, rt_expires, action == CLEANUP_PREFIX_RT_DEL, false); } } if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) { if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR)) delete_tempaddrs(ifp->idev, ifp); else manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft, cfg->preferred_lft, !was_managetempaddr, jiffies); } addrconf_verify_rtnl(net); return 0; } static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct in6_addr *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; struct inet6_dev *idev; struct ifa6_config cfg; struct ifaddrmsg *ifm; unsigned long timeout; clock_t expires; u32 flags; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; memset(&cfg, 0, sizeof(cfg)); ifm = nlmsg_data(nlh); cfg.pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (!cfg.pfx) return -EINVAL; cfg.peer_pfx = peer_pfx; cfg.plen = ifm->ifa_prefixlen; if (tb[IFA_RT_PRIORITY]) cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) cfg.ifa_proto = nla_get_u8(tb[IFA_PROTO]); cfg.ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); /* We ignore other flags so far. */ cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; cfg.ifa_flags |= IFA_F_PERMANENT; cfg.valid_lft = INFINITY_LIFE_TIME; cfg.preferred_lft = INFINITY_LIFE_TIME; expires = 0; flags = 0; if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); cfg.valid_lft = ci->ifa_valid; cfg.preferred_lft = ci->ifa_prefered; if (!cfg.valid_lft || cfg.preferred_lft > cfg.valid_lft) { NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid"); return -EINVAL; } timeout = addrconf_timeout_fixup(cfg.valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { cfg.ifa_flags &= ~IFA_F_PERMANENT; cfg.valid_lft = timeout; expires = jiffies_to_clock_t(timeout * HZ); flags = RTF_EXPIRES; } timeout = addrconf_timeout_fixup(cfg.preferred_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) cfg.ifa_flags |= IFA_F_DEPRECATED; cfg.preferred_lft = timeout; } } rtnl_net_lock(net); dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) { NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); err = -ENODEV; goto unlock; } idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { err = PTR_ERR(idev); goto unlock; } if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; if (cfg.ifa_flags & IFA_F_NODAD && cfg.ifa_flags & IFA_F_OPTIMISTIC) { NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); err = -EINVAL; goto unlock; } ifa = ipv6_get_ifaddr(net, cfg.pfx, dev, 1); if (!ifa) { /* * It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ err = inet6_addr_add(net, dev, &cfg, expires, flags, extack); goto unlock; } if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "address already assigned"); err = -EEXIST; } else { err = inet6_addr_modify(net, ifa, &cfg, expires, flags); } in6_ifa_put(ifa); unlock: rtnl_net_unlock(net); return err; } static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u32 flags, u8 scope, int ifindex) { struct ifaddrmsg *ifm; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET6; ifm->ifa_prefixlen = prefixlen; ifm->ifa_flags = flags; ifm->ifa_scope = scope; ifm->ifa_index = ifindex; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static inline int rt_scope(int ifa_scope) { if (ifa_scope & IFA_HOST) return RT_SCOPE_HOST; else if (ifa_scope & IFA_LINK) return RT_SCOPE_LINK; else if (ifa_scope & IFA_SITE) return RT_SCOPE_SITE; else return RT_SCOPE_UNIVERSE; } static inline int inet6_ifaddr_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)) + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */; } static int inet6_fill_ifaddr(struct sk_buff *skb, const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { struct nlmsghdr *nlh; u32 preferred, valid; u32 flags, priority; u8 proto; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; flags = READ_ONCE(ifa->flags); put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; preferred = READ_ONCE(ifa->prefered_lft); valid = READ_ONCE(ifa->valid_lft); if (!((flags & IFA_F_PERMANENT) && (preferred == INFINITY_LIFE_TIME))) { if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - READ_ONCE(ifa->tstamp)) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; } else { if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; } priority = READ_ONCE(ifa->rt_priority); if (priority && nla_put_u32(skb, IFA_RT_PRIORITY, priority)) goto error; if (put_cacheinfo(skb, ifa->cstamp, READ_ONCE(ifa->tstamp), preferred, valid) < 0) goto error; if (nla_put_u32(skb, IFA_FLAGS, flags) < 0) goto error; proto = READ_ONCE(ifa->ifa_proto); if (proto && nla_put_u8(skb, IFA_PROTO, proto)) goto error; nlmsg_end(skb, nlh); return 0; error: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } int inet6_fill_ifmcaddr(struct sk_buff *skb, const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { int ifindex = ifmca->idev->dev->ifindex; u8 scope = RT_SCOPE_UNIVERSE; struct nlmsghdr *nlh; if (!args->force_rt_scope_universe && ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } int inet6_fill_ifacaddr(struct sk_buff *skb, const struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; u8 scope = RT_SCOPE_UNIVERSE; struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, READ_ONCE(ifaca->aca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } /* called with rcu_read_lock() */ static int in6_dump_addrs(const struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet6_fill_args *fillargs) { const struct ifmcaddr6 *ifmca; const struct ifacaddr6 *ifaca; int ip_idx = 0; int err = 0; switch (fillargs->type) { case UNICAST_ADDR: { const struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { if (ip_idx < *s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); next: ip_idx++; } break; } case MULTICAST_ADDR: fillargs->event = RTM_GETMULTICAST; /* multicast address */ for (ifmca = rcu_dereference(idev->mc_list); ifmca; ifmca = rcu_dereference(ifmca->next), ip_idx++) { if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ for (ifaca = rcu_dereference(idev->ac_list); ifaca; ifaca = rcu_dereference(ifaca->aca_next), ip_idx++) { if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) break; } break; default: break; } *s_ip_idx = err ? ip_idx : 0; return err; } static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet6_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG_MOD(extack, "Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { struct net *tgt_net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .netnsid = -1, .type = type, .force_rt_scope_universe = false, }; struct { unsigned long ifindex; int ip_idx; } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto done; err = 0; if (fillargs.ifindex) { dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto done; } idev = __in6_dev_get(dev); if (idev) err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, &fillargs); goto done; } } cb->seq = inet6_base_seq(tgt_net); for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { idev = __in6_dev_get(dev); if (!idev) continue; err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, &fillargs); if (err < 0) goto done; } done: rcu_read_unlock(); if (fillargs.netnsid >= 0) put_net(tgt_net); return err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = UNICAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = MULTICAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = ANYCAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) return err; for (i = 0; i <= IFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case IFA_TARGET_NETNSID: case IFA_ADDRESS: case IFA_LOCAL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get address request"); return -EINVAL; } } return 0; } static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *tgt_net = sock_net(in_skb->sk); struct inet6_fill_args fillargs = { .portid = NETLINK_CB(in_skb).portid, .seq = nlh->nlmsg_seq, .event = RTM_NEWADDR, .flags = 0, .netnsid = -1, .force_rt_scope_universe = false, }; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; struct net_device *dev = NULL; struct inet6_ifaddr *ifa; struct sk_buff *skb; int err; err = inet6_rtm_valid_getaddr_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (tb[IFA_TARGET_NETNSID]) { fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk, fillargs.netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (!addr) { err = -EINVAL; goto errout; } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1); if (!ifa) { err = -EADDRNOTAVAIL; goto errout; } skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout_ifa; } err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout_ifa; } err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: dev_put(dev); if (fillargs.netnsid >= 0) put_net(tgt_net); return err; } static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; struct net *net = dev_net(ifa->idev->dev); struct inet6_fill_args fillargs = { .portid = 0, .seq = 0, .event = event, .flags = 0, .netnsid = -1, .force_rt_scope_universe = false, }; int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static void ipv6_store_devconf(const struct ipv6_devconf *cnf, __s32 *array, int bytes) { BUG_ON(bytes < (DEVCONF_MAX * 4)); memset(array, 0, bytes); array[DEVCONF_FORWARDING] = READ_ONCE(cnf->forwarding); array[DEVCONF_HOPLIMIT] = READ_ONCE(cnf->hop_limit); array[DEVCONF_MTU6] = READ_ONCE(cnf->mtu6); array[DEVCONF_ACCEPT_RA] = READ_ONCE(cnf->accept_ra); array[DEVCONF_ACCEPT_REDIRECTS] = READ_ONCE(cnf->accept_redirects); array[DEVCONF_AUTOCONF] = READ_ONCE(cnf->autoconf); array[DEVCONF_DAD_TRANSMITS] = READ_ONCE(cnf->dad_transmits); array[DEVCONF_RTR_SOLICITS] = READ_ONCE(cnf->rtr_solicits); array[DEVCONF_RTR_SOLICIT_INTERVAL] = jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_interval)); array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_max_interval)); array[DEVCONF_RTR_SOLICIT_DELAY] = jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_delay)); array[DEVCONF_FORCE_MLD_VERSION] = READ_ONCE(cnf->force_mld_version); array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = jiffies_to_msecs(READ_ONCE(cnf->mldv1_unsolicited_report_interval)); array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = jiffies_to_msecs(READ_ONCE(cnf->mldv2_unsolicited_report_interval)); array[DEVCONF_USE_TEMPADDR] = READ_ONCE(cnf->use_tempaddr); array[DEVCONF_TEMP_VALID_LFT] = READ_ONCE(cnf->temp_valid_lft); array[DEVCONF_TEMP_PREFERED_LFT] = READ_ONCE(cnf->temp_prefered_lft); array[DEVCONF_REGEN_MAX_RETRY] = READ_ONCE(cnf->regen_max_retry); array[DEVCONF_MAX_DESYNC_FACTOR] = READ_ONCE(cnf->max_desync_factor); array[DEVCONF_MAX_ADDRESSES] = READ_ONCE(cnf->max_addresses); array[DEVCONF_ACCEPT_RA_DEFRTR] = READ_ONCE(cnf->accept_ra_defrtr); array[DEVCONF_RA_DEFRTR_METRIC] = READ_ONCE(cnf->ra_defrtr_metric); array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = READ_ONCE(cnf->accept_ra_min_hop_limit); array[DEVCONF_ACCEPT_RA_PINFO] = READ_ONCE(cnf->accept_ra_pinfo); #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = READ_ONCE(cnf->accept_ra_rtr_pref); array[DEVCONF_RTR_PROBE_INTERVAL] = jiffies_to_msecs(READ_ONCE(cnf->rtr_probe_interval)); #ifdef CONFIG_IPV6_ROUTE_INFO array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = READ_ONCE(cnf->accept_ra_rt_info_min_plen); array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = READ_ONCE(cnf->accept_ra_rt_info_max_plen); #endif #endif array[DEVCONF_PROXY_NDP] = READ_ONCE(cnf->proxy_ndp); array[DEVCONF_ACCEPT_SOURCE_ROUTE] = READ_ONCE(cnf->accept_source_route); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD array[DEVCONF_OPTIMISTIC_DAD] = READ_ONCE(cnf->optimistic_dad); array[DEVCONF_USE_OPTIMISTIC] = READ_ONCE(cnf->use_optimistic); #endif #ifdef CONFIG_IPV6_MROUTE array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif array[DEVCONF_DISABLE_IPV6] = READ_ONCE(cnf->disable_ipv6); array[DEVCONF_ACCEPT_DAD] = READ_ONCE(cnf->accept_dad); array[DEVCONF_FORCE_TLLAO] = READ_ONCE(cnf->force_tllao); array[DEVCONF_NDISC_NOTIFY] = READ_ONCE(cnf->ndisc_notify); array[DEVCONF_SUPPRESS_FRAG_NDISC] = READ_ONCE(cnf->suppress_frag_ndisc); array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = READ_ONCE(cnf->accept_ra_from_local); array[DEVCONF_ACCEPT_RA_MTU] = READ_ONCE(cnf->accept_ra_mtu); array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = READ_ONCE(cnf->ignore_routes_with_linkdown); /* we omit DEVCONF_STABLE_SECRET for now */ array[DEVCONF_USE_OIF_ADDRS_ONLY] = READ_ONCE(cnf->use_oif_addrs_only); array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = READ_ONCE(cnf->drop_unicast_in_l2_multicast); array[DEVCONF_DROP_UNSOLICITED_NA] = READ_ONCE(cnf->drop_unsolicited_na); array[DEVCONF_KEEP_ADDR_ON_DOWN] = READ_ONCE(cnf->keep_addr_on_down); array[DEVCONF_SEG6_ENABLED] = READ_ONCE(cnf->seg6_enabled); #ifdef CONFIG_IPV6_SEG6_HMAC array[DEVCONF_SEG6_REQUIRE_HMAC] = READ_ONCE(cnf->seg6_require_hmac); #endif array[DEVCONF_ENHANCED_DAD] = READ_ONCE(cnf->enhanced_dad); array[DEVCONF_ADDR_GEN_MODE] = READ_ONCE(cnf->addr_gen_mode); array[DEVCONF_DISABLE_POLICY] = READ_ONCE(cnf->disable_policy); array[DEVCONF_NDISC_TCLASS] = READ_ONCE(cnf->ndisc_tclass); array[DEVCONF_RPL_SEG_ENABLED] = READ_ONCE(cnf->rpl_seg_enabled); array[DEVCONF_IOAM6_ENABLED] = READ_ONCE(cnf->ioam6_enabled); array[DEVCONF_IOAM6_ID] = READ_ONCE(cnf->ioam6_id); array[DEVCONF_IOAM6_ID_WIDE] = READ_ONCE(cnf->ioam6_id_wide); array[DEVCONF_NDISC_EVICT_NOCARRIER] = READ_ONCE(cnf->ndisc_evict_nocarrier); array[DEVCONF_ACCEPT_UNTRACKED_NA] = READ_ONCE(cnf->accept_untracked_na); array[DEVCONF_ACCEPT_RA_MIN_LFT] = READ_ONCE(cnf->accept_ra_min_lft); } static inline size_t inet6_ifla6_size(void) { return nla_total_size(4) /* IFLA_INET6_FLAGS */ + nla_total_size(sizeof(struct ifla_cacheinfo)) + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */ + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */ + nla_total_size(4) /* IFLA_INET6_RA_MTU */ + 0; } static inline size_t inet6_if_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ } static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, int bytes) { int i; int pad = bytes - sizeof(u64) * ICMP6_MIB_MAX; BUG_ON(pad < 0); /* Use put_unaligned() because stats may not be aligned for u64. */ put_unaligned(ICMP6_MIB_MAX, &stats[0]); for (i = 1; i < ICMP6_MIB_MAX; i++) put_unaligned(atomic_long_read(&mib[i]), &stats[i]); memset(&stats[ICMP6_MIB_MAX], 0, pad); } static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib, int bytes, size_t syncpoff) { int i, c; u64 buff[IPSTATS_MIB_MAX]; int pad = bytes - sizeof(u64) * IPSTATS_MIB_MAX; BUG_ON(pad < 0); memset(buff, 0, sizeof(buff)); buff[0] = IPSTATS_MIB_MAX; for_each_possible_cpu(c) { for (i = 1; i < IPSTATS_MIB_MAX; i++) buff[i] += snmp_get_cpu_field64(mib, c, i, syncpoff); } memcpy(stats, buff, IPSTATS_MIB_MAX * sizeof(u64)); memset(&stats[IPSTATS_MIB_MAX], 0, pad); } static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, int bytes) { switch (attrtype) { case IFLA_INET6_STATS: __snmp6_fill_stats64(stats, idev->stats.ipv6, bytes, offsetof(struct ipstats_mib, syncp)); break; case IFLA_INET6_ICMP6STATS: __snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, bytes); break; } } static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { struct ifla_cacheinfo ci; struct nlattr *nla; u32 ra_mtu; if (nla_put_u32(skb, IFLA_INET6_FLAGS, READ_ONCE(idev->if_flags))) goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; ci.tstamp = cstamp_delta(READ_ONCE(idev->tstamp)); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); if (!nla) goto nla_put_failure; ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); /* XXX - MC not implemented */ if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) return 0; nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (!nla) goto nla_put_failure; read_lock_bh(&idev->lock); memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, READ_ONCE(idev->cnf.addr_gen_mode))) goto nla_put_failure; ra_mtu = READ_ONCE(idev->ra_mtu); if (ra_mtu && nla_put_u32(skb, IFLA_INET6_RA_MTU, ra_mtu)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static size_t inet6_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { if (!__in6_dev_get(dev)) return 0; return inet6_ifla6_size(); } static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev) return -ENODATA; if (inet6_fill_ifla6_attrs(skb, idev, ext_filter_mask) < 0) return -EMSGSIZE; return 0; } static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct net_device *dev = idev->dev; bool clear_token, update_rs = false; struct in6_addr ll_addr; ASSERT_RTNL(); if (!token) return -EINVAL; if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG_MOD(extack, "Device is loopback"); return -EINVAL; } if (dev->flags & IFF_NOARP) { NL_SET_ERR_MSG_MOD(extack, "Device does not do neighbour discovery"); return -EINVAL; } if (!ipv6_accept_ra(idev)) { NL_SET_ERR_MSG_MOD(extack, "Router advertisement is disabled on device"); return -EINVAL; } if (READ_ONCE(idev->cnf.rtr_solicits) == 0) { NL_SET_ERR_MSG(extack, "Router solicitation is disabled on device"); return -EINVAL; } write_lock_bh(&idev->lock); BUILD_BUG_ON(sizeof(token->s6_addr) != 16); memcpy(idev->token.s6_addr + 8, token->s6_addr + 8, 8); write_unlock_bh(&idev->lock); clear_token = ipv6_addr_any(token); if (clear_token) goto update_lft; if (!idev->dead && (idev->if_flags & IF_READY) && !ipv6_get_lladdr(dev, &ll_addr, IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)) { /* If we're not ready, then normal ifup will take care * of this. Otherwise, we need to request our rs here. */ ndisc_send_rs(dev, &ll_addr, &in6addr_linklocal_allrouters); update_rs = true; } update_lft: write_lock_bh(&idev->lock); if (update_rs) { idev->if_flags |= IF_RS_SENT; idev->rs_interval = rfc3315_s14_backoff_init( READ_ONCE(idev->cnf.rtr_solicit_interval)); idev->rs_probes = 1; addrconf_mod_rs_timer(idev, idev->rs_interval); } /* Well, that's kinda nasty ... */ list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); if (ifp->tokenized) { ifp->valid_lft = 0; ifp->prefered_lft = 0; } spin_unlock(&ifp->lock); } write_unlock_bh(&idev->lock); inet6_ifinfo_notify(RTM_NEWLINK, idev); addrconf_verify_rtnl(dev_net(dev)); return 0; } static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = { [IFLA_INET6_ADDR_GEN_MODE] = { .type = NLA_U8 }, [IFLA_INET6_TOKEN] = { .len = sizeof(struct in6_addr) }, [IFLA_INET6_RA_MTU] = { .type = NLA_REJECT, .reject_message = "IFLA_INET6_RA_MTU can not be set" }, }; static int check_addr_gen_mode(int mode) { if (mode != IN6_ADDR_GEN_MODE_EUI64 && mode != IN6_ADDR_GEN_MODE_NONE && mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && mode != IN6_ADDR_GEN_MODE_RANDOM) return -EINVAL; return 1; } static int check_stable_privacy(struct inet6_dev *idev, struct net *net, int mode) { if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && !idev->cnf.stable_secret.initialized && !net->ipv6.devconf_dflt->stable_secret.initialized) return -EINVAL; return 1; } static int inet6_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_INET6_MAX + 1]; struct inet6_dev *idev = NULL; int err; if (dev) { idev = __in6_dev_get(dev); if (!idev) return -EAFNOSUPPORT; } err = nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, inet6_af_policy, extack); if (err) return err; if (!tb[IFLA_INET6_TOKEN] && !tb[IFLA_INET6_ADDR_GEN_MODE]) return -EINVAL; if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); if (check_addr_gen_mode(mode) < 0) return -EINVAL; if (dev && check_stable_privacy(idev, dev_net(dev), mode) < 0) return -EINVAL; } return 0; } static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); struct nlattr *tb[IFLA_INET6_MAX + 1]; int err; if (!idev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), extack); if (err) return err; } if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); WRITE_ONCE(idev->cnf.addr_gen_mode, mode); } return 0; } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, u32 portid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; int ifindex, iflink; void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_INET6; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; ifindex = READ_ONCE(dev->ifindex); hdr->ifi_index = ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; iflink = dev_get_iflink(dev); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || (ifindex != iflink && nla_put_u32(skb, IFLA_LINK, iflink)) || nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) goto nla_put_failure; if (inet6_fill_ifla6_attrs(skb, idev, 0) < 0) goto nla_put_failure; nla_nest_end(skb, protoinfo); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifinfomsg *ifm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request"); return -EINVAL; } return 0; } static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; int err; /* only requests using strict checking can pass data to * influence the dump */ if (cb->strict_check) { err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); if (err < 0) return err; } err = 0; rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { idev = __in6_dev_get(dev); if (!idev) continue; err = inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); if (err < 0) break; } rcu_read_unlock(); return err; } void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct prefixmsg)) + nla_total_size(sizeof(struct in6_addr)) + nla_total_size(sizeof(struct prefix_cacheinfo)); } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, struct prefix_info *pinfo, u32 portid, u32 seq, int event, unsigned int flags) { struct prefixmsg *pmsg; struct nlmsghdr *nlh; struct prefix_cacheinfo ci; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); if (!nlh) return -EMSGSIZE; pmsg = nlmsg_data(nlh); pmsg->prefix_family = AF_INET6; pmsg->prefix_pad1 = 0; pmsg->prefix_pad2 = 0; pmsg->prefix_ifindex = idev->dev->ifindex; pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; ci.preferred_time = ntohl(pinfo->prefered); ci.valid_time = ntohl(pinfo->valid); if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_prefix_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); if (event) ASSERT_RTNL(); inet6_ifa_notify(event ? : RTM_NEWADDR, ifp); switch (event) { case RTM_NEWADDR: /* * If the address was optimistic we inserted the route at the * start of our DAD process, so we don't need to do it again. * If the device was taken down in the middle of the DAD * cycle there is a race where we could get here without a * host route, so nothing to insert. That will be fixed when * the device is brought up. */ if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) { ip6_ins_rt(net, ifp->rt); } else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) { pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n", &ifp->addr, ifp->idev->dev->name); } if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) addrconf_prefix_route(&ifp->peer_addr, 128, ifp->rt_priority, ifp->idev->dev, 0, 0, GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { struct fib6_info *rt; rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0, false); if (rt) ip6_del_rt(net, rt, false); } if (ifp->rt) { ip6_del_rt(net, ifp->rt, false); ifp->rt = NULL; } rt_genid_bump_ipv6(net); break; } atomic_inc(&net->ipv6.dev_addr_genid); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { if (likely(ifp->idev->dead == 0)) __ipv6_ifa_notify(event, ifp); } #ifdef CONFIG_SYSCTL static int addrconf_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* * ctl->data points to idev->cnf.forwarding, we should * not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int addrconf_sysctl_mtu(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct inet6_dev *idev = ctl->extra1; int min_mtu = IPV6_MIN_MTU; struct ctl_table lctl; lctl = *ctl; lctl.extra1 = &min_mtu; lctl.extra2 = idev ? &idev->dev->mtu : NULL; return proc_dointvec_minmax(&lctl, write, buffer, lenp, ppos); } static void dev_disable_change(struct inet6_dev *idev) { struct netdev_notifier_info info; if (!idev || !idev->dev) return; netdev_notifier_info_init(&info, idev->dev); if (idev->cnf.disable_ipv6) addrconf_notify(NULL, NETDEV_DOWN, &info); else addrconf_notify(NULL, NETDEV_UP, &info); } static void addrconf_disable_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); WRITE_ONCE(idev->cnf.disable_ipv6, newf); if (changed) dev_disable_change(idev); } } } static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf) { struct net *net = (struct net *)table->extra2; int old; if (p == &net->ipv6.devconf_dflt->disable_ipv6) { WRITE_ONCE(*p, newf); return 0; } if (!rtnl_net_trylock(net)) return restart_syscall(); old = *p; WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_all->disable_ipv6) { WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); } else if ((!newf) ^ (!old)) { dev_disable_change((struct inet6_dev *)table->extra1); } rtnl_net_unlock(net); return 0; } static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* * ctl->data points to idev->cnf.disable_ipv6, we should * not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int ret; int old, new; old = *valp; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); new = *valp; if (write && old != new) { struct net *net = ctl->extra2; if (!rtnl_net_trylock(net)) return restart_syscall(); if (valp == &net->ipv6.devconf_dflt->proxy_ndp) { inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); } else if (valp == &net->ipv6.devconf_all->proxy_ndp) { inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } else { struct inet6_dev *idev = ctl->extra1; inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, idev->dev->ifindex, &idev->cnf); } rtnl_net_unlock(net); } return ret; } static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; u32 new_val; struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1; struct net *net = (struct net *)ctl->extra2; struct ctl_table tmp = { .data = &new_val, .maxlen = sizeof(new_val), .mode = ctl->mode, }; if (!rtnl_net_trylock(net)) return restart_syscall(); new_val = *((u32 *)ctl->data); ret = proc_douintvec(&tmp, write, buffer, lenp, ppos); if (ret != 0) goto out; if (write) { if (check_addr_gen_mode(new_val) < 0) { ret = -EINVAL; goto out; } if (idev) { if (check_stable_privacy(idev, net, new_val) < 0) { ret = -EINVAL; goto out; } if (idev->cnf.addr_gen_mode != new_val) { WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; WRITE_ONCE(net->ipv6.devconf_dflt->addr_gen_mode, new_val); for_each_netdev(net, dev) { idev = __in6_dev_get_rtnl_net(dev); if (idev && idev->cnf.addr_gen_mode != new_val) { WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); addrconf_init_auto_addrs(idev->dev); } } } WRITE_ONCE(*((u32 *)ctl->data), new_val); } out: rtnl_net_unlock(net); return ret; } static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; struct in6_addr addr; char str[IPV6_MAX_STRLEN]; struct ctl_table lctl = *ctl; struct net *net = ctl->extra2; struct ipv6_stable_secret *secret = ctl->data; if (&net->ipv6.devconf_all->stable_secret == ctl->data) return -EIO; lctl.maxlen = IPV6_MAX_STRLEN; lctl.data = str; if (!rtnl_net_trylock(net)) return restart_syscall(); if (!write && !secret->initialized) { err = -EIO; goto out; } err = snprintf(str, sizeof(str), "%pI6", &secret->secret); if (err >= sizeof(str)) { err = -EIO; goto out; } err = proc_dostring(&lctl, write, buffer, lenp, ppos); if (err || !write) goto out; if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) { err = -EIO; goto out; } secret->initialized = true; secret->secret = addr; if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) { struct net_device *dev; for_each_netdev(net, dev) { struct inet6_dev *idev = __in6_dev_get_rtnl_net(dev); if (idev) { WRITE_ONCE(idev->cnf.addr_gen_mode, IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } } } else { struct inet6_dev *idev = ctl->extra1; WRITE_ONCE(idev->cnf.addr_gen_mode, IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } out: rtnl_net_unlock(net); return err; } static int addrconf_sysctl_ignore_routes_with_linkdown(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* ctl->data points to idev->cnf.ignore_routes_when_linkdown * we should not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_linkdown(ctl, valp, val); if (ret) *ppos = pos; return ret; } static void addrconf_set_nopolicy(struct rt6_info *rt, int action) { if (rt) { if (action) rt->dst.flags |= DST_NOPOLICY; else rt->dst.flags &= ~DST_NOPOLICY; } } static void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) { struct inet6_ifaddr *ifa; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { spin_lock(&ifa->lock); if (ifa->rt) { /* host routes only use builtin fib6_nh */ struct fib6_nh *nh = ifa->rt->fib6_nh; int cpu; rcu_read_lock(); ifa->rt->dst_nopolicy = val ? true : false; if (nh->rt6i_pcpu) { for_each_possible_cpu(cpu) { struct rt6_info **rtp; rtp = per_cpu_ptr(nh->rt6i_pcpu, cpu); addrconf_set_nopolicy(*rtp, val); } } rcu_read_unlock(); } spin_unlock(&ifa->lock); } read_unlock_bh(&idev->lock); } static int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) { struct net *net = (struct net *)ctl->extra2; struct inet6_dev *idev; if (valp == &net->ipv6.devconf_dflt->disable_policy) { WRITE_ONCE(*valp, val); return 0; } if (!rtnl_net_trylock(net)) return restart_syscall(); WRITE_ONCE(*valp, val); if (valp == &net->ipv6.devconf_all->disable_policy) { struct net_device *dev; for_each_netdev(net, dev) { idev = __in6_dev_get_rtnl_net(dev); if (idev) addrconf_disable_policy_idev(idev, val); } } else { idev = (struct inet6_dev *)ctl->extra1; addrconf_disable_policy_idev(idev, val); } rtnl_net_unlock(net); return 0; } static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write && (*valp != val)) ret = addrconf_disable_policy(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int minus_one = -1; static const int two_five_five = 255; static u32 ioam6_if_id_max = U16_MAX; static const struct ctl_table addrconf_sysctl[] = { { .procname = "forwarding", .data = &ipv6_devconf.forwarding, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_forward, }, { .procname = "hop_limit", .data = &ipv6_devconf.hop_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ONE, .extra2 = (void *)&two_five_five, }, { .procname = "mtu", .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_mtu, }, { .procname = "accept_ra", .data = &ipv6_devconf.accept_ra, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_redirects", .data = &ipv6_devconf.accept_redirects, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "autoconf", .data = &ipv6_devconf.autoconf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "dad_transmits", .data = &ipv6_devconf.dad_transmits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "router_solicitations", .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &minus_one, }, { .procname = "router_solicitation_interval", .data = &ipv6_devconf.rtr_solicit_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "router_solicitation_max_interval", .data = &ipv6_devconf.rtr_solicit_max_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "force_mld_version", .data = &ipv6_devconf.force_mld_version, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mldv1_unsolicited_report_interval", .data = &ipv6_devconf.mldv1_unsolicited_report_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "mldv2_unsolicited_report_interval", .data = &ipv6_devconf.mldv2_unsolicited_report_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "temp_valid_lft", .data = &ipv6_devconf.temp_valid_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "temp_prefered_lft", .data = &ipv6_devconf.temp_prefered_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "regen_min_advance", .data = &ipv6_devconf.regen_min_advance, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_desync_factor", .data = &ipv6_devconf.max_desync_factor, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_defrtr", .data = &ipv6_devconf.accept_ra_defrtr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ra_defrtr_metric", .data = &ipv6_devconf.ra_defrtr_metric, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = (void *)SYSCTL_ONE, }, { .procname = "accept_ra_min_hop_limit", .data = &ipv6_devconf.accept_ra_min_hop_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_min_lft", .data = &ipv6_devconf.accept_ra_min_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ra_honor_pio_life", .data = &ipv6_devconf.ra_honor_pio_life, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ra_honor_pio_pflag", .data = &ipv6_devconf.ra_honor_pio_pflag, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", .data = &ipv6_devconf.accept_ra_rtr_pref, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "router_probe_interval", .data = &ipv6_devconf.rtr_probe_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { .procname = "accept_ra_rt_info_min_plen", .data = &ipv6_devconf.accept_ra_rt_info_min_plen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif #endif { .procname = "proxy_ndp", .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_proxy_ndp, }, { .procname = "accept_source_route", .data = &ipv6_devconf.accept_source_route, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { .procname = "optimistic_dad", .data = &ipv6_devconf.optimistic_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "use_optimistic", .data = &ipv6_devconf.use_optimistic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_IPV6_MROUTE { .procname = "mc_forwarding", .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, #endif { .procname = "disable_ipv6", .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable, }, { .procname = "accept_dad", .data = &ipv6_devconf.accept_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "force_tllao", .data = &ipv6_devconf.force_tllao, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "ndisc_notify", .data = &ipv6_devconf.ndisc_notify, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "suppress_frag_ndisc", .data = &ipv6_devconf.suppress_frag_ndisc, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "accept_ra_from_local", .data = &ipv6_devconf.accept_ra_from_local, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_mtu", .data = &ipv6_devconf.accept_ra_mtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "stable_secret", .data = &ipv6_devconf.stable_secret, .maxlen = IPV6_MAX_STRLEN, .mode = 0600, .proc_handler = addrconf_sysctl_stable_secret, }, { .procname = "use_oif_addrs_only", .data = &ipv6_devconf.use_oif_addrs_only, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ignore_routes_with_linkdown", .data = &ipv6_devconf.ignore_routes_with_linkdown, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown, }, { .procname = "drop_unicast_in_l2_multicast", .data = &ipv6_devconf.drop_unicast_in_l2_multicast, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "drop_unsolicited_na", .data = &ipv6_devconf.drop_unsolicited_na, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "keep_addr_on_down", .data = &ipv6_devconf.keep_addr_on_down, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "seg6_enabled", .data = &ipv6_devconf.seg6_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_SEG6_HMAC { .procname = "seg6_require_hmac", .data = &ipv6_devconf.seg6_require_hmac, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif { .procname = "enhanced_dad", .data = &ipv6_devconf.enhanced_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "addr_gen_mode", .data = &ipv6_devconf.addr_gen_mode, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_addr_gen_mode, }, { .procname = "disable_policy", .data = &ipv6_devconf.disable_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable_policy, }, { .procname = "ndisc_tclass", .data = &ipv6_devconf.ndisc_tclass, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)&two_five_five, }, { .procname = "rpl_seg_enabled", .data = &ipv6_devconf.rpl_seg_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ioam6_enabled", .data = &ipv6_devconf.ioam6_enabled, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)SYSCTL_ONE, }, { .procname = "ioam6_id", .data = &ipv6_devconf.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)&ioam6_if_id_max, }, { .procname = "ioam6_id_wide", .data = &ipv6_devconf.ioam6_id_wide, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec, }, { .procname = "ndisc_evict_nocarrier", .data = &ipv6_devconf.ndisc_evict_nocarrier, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)SYSCTL_ONE, }, { .procname = "accept_untracked_na", .data = &ipv6_devconf.accept_untracked_na, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, struct inet6_dev *idev, struct ipv6_devconf *p) { size_t table_size = ARRAY_SIZE(addrconf_sysctl); int i, ifindex; struct ctl_table *table; char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL_ACCOUNT); if (!table) goto out; for (i = 0; i < table_size; i++) { table[i].data += (char *)p - (char *)&ipv6_devconf; /* If one of these is already set, then it is not safe to * overwrite either of them: this makes proc_dointvec_minmax * usable. */ if (!table[i].extra1 && !table[i].extra2) { table[i].extra1 = idev; /* embedded; no ref */ table[i].extra2 = net; } } snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); p->sysctl_header = register_net_sysctl_sz(net, path, table, table_size); if (!p->sysctl_header) goto free; if (!strcmp(dev_name, "all")) ifindex = NETCONFA_IFINDEX_ALL; else if (!strcmp(dev_name, "default")) ifindex = NETCONFA_IFINDEX_DEFAULT; else ifindex = idev->dev->ifindex; inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(table); out: return -ENOBUFS; } static void __addrconf_sysctl_unregister(struct net *net, struct ipv6_devconf *p, int ifindex) { const struct ctl_table *table; if (!p->sysctl_header) return; table = p->sysctl_header->ctl_table_arg; unregister_net_sysctl_table(p->sysctl_header); p->sysctl_header = NULL; kfree(table); inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int addrconf_sysctl_register(struct inet6_dev *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->nd_parms, &ndisc_ifinfo_sysctl_change); if (err) return err; err = __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev, &idev->cnf); if (err) neigh_sysctl_unregister(idev->nd_parms); return err; } static void addrconf_sysctl_unregister(struct inet6_dev *idev) { __addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->nd_parms); } #endif static int __net_init addrconf_init_net(struct net *net) { int err = -ENOMEM; struct ipv6_devconf *all, *dflt; spin_lock_init(&net->ipv6.addrconf_hash_lock); INIT_DEFERRABLE_WORK(&net->ipv6.addr_chk_work, addrconf_verify_work); net->ipv6.inet6_addr_lst = kcalloc(IN6_ADDR_HSIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!net->ipv6.inet6_addr_lst) goto err_alloc_addr; all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 1: /* copy from init_net */ memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); break; case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv6.devconf_all, sizeof(ipv6_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); break; case 0: case 2: /* use compiled values */ break; } } /* these will be inherited by all namespaces */ dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; dflt->stable_secret.initialized = false; all->stable_secret.initialized = false; net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; #ifdef CONFIG_SYSCTL err = __addrconf_sysctl_register(net, "all", NULL, all); if (err < 0) goto err_reg_all; err = __addrconf_sysctl_register(net, "default", NULL, dflt); if (err < 0) goto err_reg_dflt; #endif return 0; #ifdef CONFIG_SYSCTL err_reg_dflt: __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); net->ipv6.devconf_dflt = NULL; #endif err_alloc_dflt: kfree(all); net->ipv6.devconf_all = NULL; err_alloc_all: kfree(net->ipv6.inet6_addr_lst); err_alloc_addr: return err; } static void __net_exit addrconf_exit_net(struct net *net) { int i; #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __addrconf_sysctl_unregister(net, net->ipv6.devconf_all, NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); net->ipv6.devconf_dflt = NULL; kfree(net->ipv6.devconf_all); net->ipv6.devconf_all = NULL; cancel_delayed_work_sync(&net->ipv6.addr_chk_work); /* * Check hash table, then free it. */ for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&net->ipv6.inet6_addr_lst[i])); kfree(net->ipv6.inet6_addr_lst); net->ipv6.inet6_addr_lst = NULL; } static struct pernet_operations addrconf_ops = { .init = addrconf_init_net, .exit = addrconf_exit_net, }; static struct rtnl_af_ops inet6_ops __read_mostly = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, .get_link_af_size = inet6_get_link_af_size, .validate_link_af = inet6_validate_link_af, .set_link_af = inet6_set_link_af, }; static const struct rtnl_msg_handler addrconf_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETLINK, .dumpit = inet6_dump_ifinfo, .flags = RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWADDR, .doit = inet6_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELADDR, .doit = inet6_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETADDR, .doit = inet6_rtm_getaddr, .dumpit = inet6_dump_ifaddr, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETMULTICAST, .dumpit = inet6_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETANYCAST, .dumpit = inet6_dump_ifacaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETNETCONF, .doit = inet6_netconf_get_devconf, .dumpit = inet6_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; /* * Init / cleanup code */ int __init addrconf_init(void) { struct inet6_dev *idev; int err; err = ipv6_addr_label_init(); if (err < 0) { pr_crit("%s: cannot initialize default policy table: %d\n", __func__, err); goto out; } err = register_pernet_subsys(&addrconf_ops); if (err < 0) goto out_addrlabel; /* All works using addrconf_wq need to lock rtnl. */ addrconf_wq = create_singlethread_workqueue("ipv6_addrconf"); if (!addrconf_wq) { err = -ENOMEM; goto out_nowq; } rtnl_net_lock(&init_net); idev = ipv6_add_dev(blackhole_netdev); rtnl_net_unlock(&init_net); if (IS_ERR(idev)) { err = PTR_ERR(idev); goto errlo; } ip6_route_init_special_entries(); register_netdevice_notifier(&ipv6_dev_notf); addrconf_verify(&init_net); err = rtnl_af_register(&inet6_ops); if (err) goto erraf; err = rtnl_register_many(addrconf_rtnl_msg_handlers); if (err) goto errout; err = ipv6_addr_label_rtnl_register(); if (err < 0) goto errout; return 0; errout: rtnl_unregister_all(PF_INET6); rtnl_af_unregister(&inet6_ops); erraf: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: destroy_workqueue(addrconf_wq); out_nowq: unregister_pernet_subsys(&addrconf_ops); out_addrlabel: ipv6_addr_label_cleanup(); out: return err; } void addrconf_cleanup(void) { struct net_device *dev; unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); ipv6_addr_label_cleanup(); rtnl_af_unregister(&inet6_ops); rtnl_net_lock(&init_net); /* clean dev list */ for_each_netdev(&init_net, dev) { if (!__in6_dev_get_rtnl_net(dev)) continue; addrconf_ifdown(dev, true); } addrconf_ifdown(init_net.loopback_dev, true); rtnl_net_unlock(&init_net); destroy_workqueue(addrconf_wq); } |
| 192 49 883 190 190 190 980 975 883 942 2 190 973 973 976 975 190 12 178 144 51 190 4 4 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 | // 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; } |
| 133 91 95 95 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM_ARM_KVM_ARCH_TIMER_H #define __ASM_ARM_KVM_ARCH_TIMER_H #include <linux/clocksource.h> #include <linux/hrtimer.h> enum kvm_arch_timers { TIMER_PTIMER, TIMER_VTIMER, NR_KVM_EL0_TIMERS, TIMER_HVTIMER = NR_KVM_EL0_TIMERS, TIMER_HPTIMER, NR_KVM_TIMERS }; enum kvm_arch_timer_regs { TIMER_REG_CNT, TIMER_REG_CVAL, TIMER_REG_TVAL, TIMER_REG_CTL, TIMER_REG_VOFF, }; struct arch_timer_offset { /* * If set, pointer to one of the offsets in the kvm's offset * structure. If NULL, assume a zero offset. */ u64 *vm_offset; /* * If set, pointer to one of the offsets in the vcpu's sysreg * array. If NULL, assume a zero offset. */ u64 *vcpu_offset; }; struct arch_timer_vm_data { /* Offset applied to the virtual timer/counter */ u64 voffset; /* Offset applied to the physical timer/counter */ u64 poffset; /* The PPI for each timer, global to the VM */ u8 ppi[NR_KVM_TIMERS]; }; struct arch_timer_context { struct kvm_vcpu *vcpu; /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; u64 ns_frac; /* Offset for this counter/timer */ struct arch_timer_offset offset; /* * We have multiple paths which can save/restore the timer state onto * the hardware, so we need some way of keeping track of where the * latest state is. */ bool loaded; /* Output level of the timer IRQ */ struct { bool level; } irq; /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; }; struct timer_map { struct arch_timer_context *direct_vtimer; struct arch_timer_context *direct_ptimer; struct arch_timer_context *emul_vtimer; struct arch_timer_context *emul_ptimer; }; void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map); struct arch_timer_cpu { struct arch_timer_context timers[NR_KVM_TIMERS]; /* Background timer used when the guest is not running */ struct hrtimer bg_timer; /* Is the timer enabled */ bool enabled; }; int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); void kvm_timer_sync_nested(struct kvm_vcpu *vcpu); void kvm_timer_sync_user(struct kvm_vcpu *vcpu); bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); void kvm_timer_update_run(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); void kvm_timer_init_vm(struct kvm *kvm); u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); void kvm_timer_init_vhe(void); #define vcpu_timer(v) (&(v)->arch.timer_cpu) #define vcpu_get_timer(v,t) (&vcpu_timer(v)->timers[(t)]) #define vcpu_vtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_VTIMER]) #define vcpu_ptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_PTIMER]) #define vcpu_hvtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HVTIMER]) #define vcpu_hptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HPTIMER]) #define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) #define timer_vm_data(ctx) (&(ctx)->vcpu->kvm->arch.timer_data) #define timer_irq(ctx) (timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)]) u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg); void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg, u64 val); /* Needed for tracing */ u32 timer_get_ctl(struct arch_timer_context *ctxt); u64 timer_get_cval(struct arch_timer_context *ctxt); /* CPU HP callbacks */ void kvm_timer_cpu_up(void); void kvm_timer_cpu_down(void); /* CNTKCTL_EL1 valid bits as of DDI0487J.a */ #define CNTKCTL_VALID_BITS (BIT(17) | GENMASK_ULL(9, 0)) DECLARE_STATIC_KEY_FALSE(broken_cntvoff_key); static inline bool has_broken_cntvoff(void) { return static_branch_unlikely(&broken_cntvoff_key); } static inline bool has_cntpoff(void) { return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); } static inline u64 timer_get_offset(struct arch_timer_context *ctxt) { u64 offset = 0; if (!ctxt) return 0; if (ctxt->offset.vm_offset) offset += *ctxt->offset.vm_offset; if (ctxt->offset.vcpu_offset) offset += *ctxt->offset.vcpu_offset; return offset; } #endif |
| 260 261 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entry_range_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset); static inline void unlock_cluster(struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* * Use the second highest bit of inuse_pages counter as the indicator * if one swap device is on the available plist, so the atomic can * still be updated arithmetically while having special data embedded. * * inuse_pages counter is the only thing indicating if a device should * be on avail_lists or not (except swapon / swapoff). By embedding the * off-list bit in the atomic counter, updates no longer need any lock * to check the list status. * * This bit will be set if the device is not on the plist and not * usable, will be cleared if the device is on the plist. */ #define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) #define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) static long swap_usage_in_pages(struct swap_info_struct *si) { return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 /* Reclaim directly, bypass the slot cache and don't touch device lock */ #define TTRS_DIRECT 0x8 static bool swap_is_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct address_space *address_space = swap_address_space(entry); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; folio = filemap_get_folio(address_space, swap_cache_index(entry)); if (IS_ERR(folio)) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* offset could point to the middle of a large folio */ entry = folio->swap; offset = swp_offset(entry); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = lock_cluster(si, offset); need_reclaim = swap_is_has_cache(si, offset, nr_pages); unlock_cluster(ci); if (!need_reclaim) goto out_unlock; if (!(flags & TTRS_DIRECT)) { /* Free through slot cache */ delete_from_swap_cache(folio); folio_set_dirty(folio); ret = nr_pages; goto out_unlock; } xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); folio_ref_sub(folio, nr_pages); folio_set_dirty(folio); ci = lock_cluster(si, offset); swap_entry_range_free(si, ci, entry, nr_pages); unlock_cluster(ci); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; } static inline bool cluster_is_discard(struct swap_cluster_info *info) { return info->flags == CLUSTER_FLAG_DISCARD; } static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) { if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) return false; if (!order) return true; return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si, unsigned long offset) { return &si->cluster_info[offset / SWAPFILE_CLUSTER]; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = offset_to_cluster(si, offset); spin_lock(&ci->lock); return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { spin_unlock(&ci->lock); } static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags) { VM_WARN_ON(ci->flags == new_flags); BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); lockdep_assert_held(&ci->lock); spin_lock(&si->lock); if (ci->flags == CLUSTER_FLAG_NONE) list_add_tail(&ci->list, list); else list_move_tail(&ci->list, list); spin_unlock(&si->lock); if (ci->flags == CLUSTER_FLAG_FRAG) atomic_long_dec(&si->frag_cluster_nr[ci->order]); else if (new_flags == CLUSTER_FLAG_FRAG) atomic_long_inc(&si->frag_cluster_nr[ci->order]); ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { unsigned int idx = cluster_index(si, ci); /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } /* * Isolate and lock the first cluster that is not contented on a list, * clean its flag before taken off-list. Cluster flag must be in sync * with list status, so cluster updaters can always know the cluster * list status without touching si lock. * * Note it's possible that all clusters on a list are contented so * this returns NULL for an non-empty list. */ static struct swap_cluster_info *isolate_lock_cluster( struct swap_info_struct *si, struct list_head *list) { struct swap_cluster_info *ci, *ret = NULL; spin_lock(&si->lock); if (unlikely(!(si->flags & SWP_WRITEOK))) goto out; list_for_each_entry(ci, list, list) { if (!spin_trylock(&ci->lock)) continue; /* We may only isolate and clear flags of following lists */ VM_BUG_ON(!ci->flags); VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && ci->flags != CLUSTER_FLAG_FULL); list_del(&ci->list); ci->flags = CLUSTER_FLAG_NONE; ret = ci; break; } out: spin_unlock(&si->lock); return ret; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. Discard cluster is a bit special as * they don't participate in allocation or reclaim, so clusters marked as * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. */ static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; bool ret = false; unsigned int idx; spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); /* * Delete the cluster from list to prepare for discard, but keep * the CLUSTER_FLAG_DISCARD flag, there could be percpu_cluster * pointing to it, or ran into by relocate_cluster. */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&ci->lock); /* * Discard is done, clear its flags as it's off-list, then * return the cluster to allocation list. */ ci->flags = CLUSTER_FLAG_NONE; memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); __free_cluster(si, ci); spin_unlock(&ci->lock); ret = true; spin_lock(&si->lock); } spin_unlock(&si->lock); return ret; } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); swap_do_scheduled_discard(si); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } /* * Must be called after freeing if ci->count == 0, moves the cluster to free * or discard list. */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * Must be called after freeing if ci->count != 0, moves the cluster to * nonfull list. */ static void partial_free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); lockdep_assert_held(&ci->lock); if (ci->flags != CLUSTER_FLAG_NONFULL) move_cluster(si, ci, &si->nonfull_clusters[ci->order], CLUSTER_FLAG_NONFULL); } /* * Must be called after allocation, moves the cluster to full or frag list. * Note: allocation doesn't acquire si lock, and may drop the ci lock for * reclaim, so the cluster could be any where when called. */ static void relocate_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); /* Discard cluster must remain off-list or on discard list */ if (cluster_is_discard(ci)) return; if (!ci->count) { free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], CLUSTER_FLAG_FRAG); } else { if (ci->flags != CLUSTER_FLAG_FULL) move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL); } } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static void inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = cluster_info + idx; ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset = start; int nr_reclaim; spin_unlock(&ci->lock); do { switch (READ_ONCE(map[offset])) { case 0: offset++; break; case SWAP_HAS_CACHE: nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); if (nr_reclaim > 0) offset += nr_reclaim; else goto out; break; default: goto out; } } while (offset < end); out: spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages, bool *need_reclaim) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; *need_reclaim = true; continue; default: return false; } } return true; } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; lockdep_assert_held(&ci->lock); if (!(si->flags & SWP_WRITEOK)) return false; /* * The first allocation in a cluster makes the * cluster exclusive to this order */ if (cluster_is_empty(ci)) ci->order = order; memset(si->swap_map + start, usage, nr_pages); swap_range_alloc(si, nr_pages); ci->count += nr_pages; return true; } /* Try use a new cluster for current CPU and allocate from it. */ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long offset, unsigned int order, unsigned char usage) { unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; bool need_reclaim, ret; lockdep_assert_held(&ci->lock); if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) goto out; for (end -= nr_pages; offset <= end; offset += nr_pages) { need_reclaim = false; if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* * Reclaim drops ci->lock and cluster could be used * by another order. Not checking flag as off-list * cluster has no flag set, and change of list * won't cause fragmentation. */ if (!cluster_is_usable(ci, order)) goto out; if (cluster_is_empty(ci)) offset = start; /* Reclaim failed but cluster is usable, try next */ if (!ret) continue; } if (!cluster_alloc_range(si, ci, offset, usage, order)) break; found = offset; offset += nr_pages; if (ci->count < SWAPFILE_CLUSTER && offset <= end) next = offset; break; } out: relocate_cluster(si, ci); unlock_cluster(ci); if (si->flags & SWP_SOLIDSTATE) __this_cpu_write(si->percpu_cluster->next[order], next); else si->global_cluster->next[order] = next; return found; } /* Return true if reclaimed a whole cluster */ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; while ((ci = isolate_lock_cluster(si, &si->full_clusters))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } unlock_cluster(ci); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); swap_reclaim_full_clusters(si, true); } /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU * too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct swap_cluster_info *ci; unsigned int offset, found = 0; if (si->flags & SWP_SOLIDSTATE) { /* Fast path using per CPU cluster */ local_lock(&si->percpu_cluster->lock); offset = __this_cpu_read(si->percpu_cluster->next[order]); } else { /* Serialize HDD SWAP allocation for each device. */ spin_lock(&si->global_cluster_lock); offset = si->global_cluster->next[order]; } if (offset) { ci = lock_cluster(si, offset); /* Cluster could have been used by another order */ if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); } else { unlock_cluster(ci); } if (found) goto done; } new_cluster: ci = isolate_lock_cluster(si, &si->free_clusters); if (ci) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; } /* Try reclaim from full clusters if free clusters list is drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { unsigned int frags = 0, frags_existing; while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; /* Clusters failed to allocate are moved to frag_clusters */ frags++; } frags_existing = atomic_long_read(&si->frag_cluster_nr[order]); while (frags < frags_existing && (ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) { atomic_long_dec(&si->frag_cluster_nr[order]); /* * Rotate the frag list to iterate, they were all * failing high order allocation or moved here due to * per-CPU usage, but they could contain newly released * reclaimable (eg. lazy-freed swap cache) slots. */ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; frags++; } } /* * We don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) goto new_cluster; if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) { atomic_long_dec(&si->frag_cluster_nr[o]); found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), 0, usage); if (found) goto done; } while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), 0, usage); if (found) goto done; } } done: if (si->flags & SWP_SOLIDSTATE) local_unlock(&si->percpu_cluster->lock); else spin_unlock(&si->global_cluster_lock); return found; } /* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { int nid; unsigned long pages; spin_lock(&swap_avail_lock); if (swapoff) { /* * Forcefully remove it. Clear the SWP_WRITEOK flags for * swapoff here so it's synchronized by both si->lock and * swap_avail_lock, to ensure the result can be seen by * add_to_avail_list. */ lockdep_assert_held(&si->lock); si->flags &= ~SWP_WRITEOK; atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); } else { /* * If not called by swapoff, take it off-list only if it's * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly * si->inuse_pages == pages), any concurrent slot freeing, * or device already removed from plist by someone else * will make this return false. */ pages = si->pages; if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { int nid; long val; unsigned long pages; spin_lock(&swap_avail_lock); /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ if (swapon) { lockdep_assert_held(&si->lock); si->flags |= SWP_WRITEOK; } else { if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) goto skip; } if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) goto skip; val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); /* * When device is full and device is on the plist, only one updater will * see (inuse_pages == si->pages) and will call del_from_avail_list. If * that updater happen to be here, just skip adding. */ pages = si->pages; if (val == pages) { /* Just like the cmpxchg in del_from_avail_list */ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock * within each cluster, so the total contribution to the global counter should * always be positive and cannot exceed the total number of usable slots. */ static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, * remove it from the plist. */ if (unlikely(val == si->pages)) { del_from_avail_list(si, false); return true; } return false; } static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, * remove it from the plist. */ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) add_to_avail_list(si, false); } static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries) { if (swap_usage_add(si, nr_entries)) { if (vm_swap_full()) schedule_work(&si->reclaim_work); } } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); zswap_invalidate(swp_entry(si->type, offset + i)); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); swap_usage_sub(si, nr_entries); } static int cluster_alloc_swap(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { int n_ret = 0; while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage); if (!offset) break; slots[n_ret++] = swp_entry(si->type, offset); } return n_ret; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { unsigned int nr_pages = 1 << order; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ if (order > 0) { /* * Should not even be attempting large allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP) || nr_pages > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return 0; } /* * Swapfile is not block device so unable * to allocate large entries. */ if (!(si->flags & SWP_BLKDEV)) return 0; } return cluster_alloc_swap(si, usage, nr, slots, order); } static bool get_swap_device_info(struct swap_info_struct *si) { if (!percpu_ref_tryget_live(&si->users)) return false; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is * up to dated. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(), and smp_wmb() in swapoff. */ smp_rmb(); return true; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { int order = swap_entry_order(entry_order); unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); if (get_swap_device_info(si)) { n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries, order); put_swap_device(si); if (n_ret || size > 1) goto check_out; } spin_lock(&swap_avail_lock); /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!get_swap_device_info(si)) goto out; offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster(si, offset); usage = __swap_entry_free_locked(si, offset, 1); if (!usage) swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1); unlock_cluster(ci); return usage; } static bool __swap_entries_free(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); unsigned int type = swp_type(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1) goto fallback; /* cross into another cluster */ if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER) goto fallback; ci = lock_cluster(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { unlock_cluster(ci); goto fallback; } for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); if (!has_cache) swap_entry_range_free(si, ci, entry, nr); unlock_cluster(ci); return has_cache; fallback: for (i = 0; i < nr; i++) { if (data_race(si->swap_map[offset + i])) { count = __swap_entry_free(si, swp_entry(type, offset + i)); if (count == SWAP_HAS_CACHE) has_cache = true; } else { WARN_ON_ONCE(1); } } return has_cache; } /* * Drop the last HAS_CACHE flag of swap entries, caller have to * ensure all entries belong to the same cgroup. */ static void swap_entry_range_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; /* It should never free entries across different clusters */ VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1)); VM_BUG_ON(cluster_is_empty(ci)); VM_BUG_ON(ci->count < nr_pages); ci->count -= nr_pages; do { VM_BUG_ON(*map != SWAP_HAS_CACHE); *map = 0; } while (++map < map_end); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); if (!ci->count) free_cluster(si, ci); else partial_free_cluster(si, ci); } static void cluster_swap_free_nr(struct swap_info_struct *si, unsigned long offset, int nr_pages, unsigned char usage) { struct swap_cluster_info *ci; unsigned long end = offset + nr_pages; ci = lock_cluster(si, offset); do { if (!__swap_entry_free_locked(si, offset, usage)) swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1); } while (++offset < end); unlock_cluster(ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); cluster_swap_free_nr(sis, offset, nr, 1); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster(si, offset); if (swap_is_has_cache(si, offset, size)) swap_entry_range_free(si, ci, entry, size); else { for (int i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) swap_entry_range_free(si, ci, entry, 1); } } unlock_cluster(ci); } void swapcache_free_entries(swp_entry_t *entries, int n) { int i; struct swap_cluster_info *ci; struct swap_info_struct *si = NULL; if (n <= 0) return; for (i = 0; i < n; ++i) { si = _swap_info_get(entries[i]); if (si) { ci = lock_cluster(si, swp_offset(entries[i])); swap_entry_range_free(si, ci, entries[i], 1); unlock_cluster(ci); } } } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster(ci); return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster(ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster(si, offset); if (nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster(ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; if (non_swap_entry(entry)) return; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = __swap_entries_free(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. This is * more efficient for large folios because we will only try to reclaim * the swap once per folio in the common case. If we do * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the * latter will get a reference and lock the folio for every individual * page but will only succeed once the swap slot for every subpage is * zero. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ if (get_swap_device_info(si)) { if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); put_swap_device(si); } fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!swap_usage_in_pages(si)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* Add back to available list */ add_to_avail_list(si, true); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } bool has_usable_swap(void) { bool ret; spin_lock(&swap_lock); ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } /* * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range * see the updated flags, so there will be no more allocations. */ static void wait_for_allocation(struct swap_info_struct *si) { unsigned long offset; unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); struct swap_cluster_info *ci; BUG_ON(si->flags & SWP_WRITEOK); for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = lock_cluster(si, offset); unlock_cluster(ci); offset += SWAPFILE_CLUSTER; } } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p, true); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); spin_unlock(&swap_lock); wait_for_allocation(p); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; kfree(p->global_cluster); p->global_cluster = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages, sector_t *span) { unsigned int nr_good_pages; unsigned long i; int nr_extents; nr_good_pages = maxpages - 1; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; } } if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; si->max = maxpages; si->pages = nr_good_pages; nr_extents = setup_swap_extents(si, span); if (nr_extents < 0) return nr_extents; nr_good_pages = si->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return nr_extents; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); struct swap_cluster_info *cluster_info; unsigned long i, j, k, idx; int cpu, err = -ENOMEM; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); if (si->flags & SWP_SOLIDSTATE) { si->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!si->percpu_cluster) goto err_free; for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(si->percpu_cluster, cpu); for (i = 0; i < SWAP_NR_ORDERS; i++) cluster->next[i] = SWAP_ENTRY_INVALID; local_lock_init(&cluster->lock); } } else { si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL); if (!si->global_cluster) goto err_free; for (i = 0; i < SWAP_NR_ORDERS; i++) si->global_cluster->next[i] = SWAP_ENTRY_INVALID; spin_lock_init(&si->global_cluster_lock); } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map_and_extents(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); for (i = 0; i < swap_header->info.nr_badpages; i++) inc_cluster_info_page(si, cluster_info, swap_header->info.badpages[i]); for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); atomic_long_set(&si->frag_cluster_nr[i], 0); } /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = k % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; ci = cluster_info + idx; if (idx >= nr_clusters) continue; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); continue; } ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: kvfree(cluster_info); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = init_swap_address_space(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(si->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); free_swap_address_space: exit_swap_address_space(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(si->percpu_cluster); si->percpu_cluster = NULL; kfree(si->global_cluster); si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swp_swap_info(entry); offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: unlock_cluster(ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return swp_swap_info(folio->swap)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __folio_swap_cache_index(struct folio *folio) { return swap_cache_index(folio->swap); } EXPORT_SYMBOL_GPL(__folio_swap_cache_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 688 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_PGTABLE_PROT_H #define __ASM_PGTABLE_PROT_H #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <linux/const.h> /* * Software defined PTE bits definition. */ #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_SWP_EXCLUSIVE (_AT(pteval_t, 1) << 2) /* only for swp ptes */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) /* * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be * interpreted according to the HW layout by SW but any attempted HW access to * the address will result in a fault. pte_present() returns true. */ #define PTE_PRESENT_INVALID (PTE_NG) /* only when !PTE_VALID */ #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define PTE_UFFD_WP (_AT(pteval_t, 1) << 58) /* uffd-wp tracking */ #define PTE_SWP_UFFD_WP (_AT(pteval_t, 1) << 3) /* only for swp ptes */ #else #define PTE_UFFD_WP (_AT(pteval_t, 0)) #define PTE_SWP_UFFD_WP (_AT(pteval_t, 0)) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) #define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_NORMAL_TAGGED (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PTE_WRITE | PMD_ATTRINDX(MT_NORMAL)) #define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) #define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) #define _PAGE_KERNEL (PROT_NORMAL) #define _PAGE_KERNEL_RO ((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) #define _PAGE_KERNEL_ROX ((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) #define _PAGE_KERNEL_EXEC (PROT_NORMAL & ~PTE_PXN) #define _PAGE_KERNEL_EXEC_CONT ((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) #define _PAGE_SHARED (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define _PAGE_SHARED_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define _PAGE_READONLY (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) #ifndef __ASSEMBLY__ #include <asm/cpufeature.h> #include <asm/pgtable-types.h> #include <asm/rsi.h> extern bool arm64_use_ng_mappings; extern unsigned long prot_ns_shared; #define PROT_NS_SHARED (is_realm_world() ? prot_ns_shared : 0) #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) #ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S #define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) #else static inline bool __pure lpa2_is_enabled(void) { return read_tcr() & TCR_DS; } #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) #define PHYS_MASK_SHIFT (lpa2_is_enabled() ? CONFIG_ARM64_PA_BITS : 48) #endif /* * Highest possible physical address supported. */ #define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. */ #define PTE_MAYBE_GP (system_supports_bti_kernel() ? PTE_GP : 0) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(_PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_KERNEL_ROX) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL_EXEC) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_KERNEL_EXEC_CONT) #define PAGE_S2_MEMATTR(attr, has_fwb) \ ({ \ u64 __val; \ if (has_fwb) \ __val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr); \ else \ __val = PTE_S2_MEMATTR(MT_S2_ ## attr); \ __val; \ }) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PRESENT_INVALID | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) /* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ #define PAGE_SHARED __pgprot(_PAGE_SHARED) #define PAGE_SHARED_EXEC __pgprot(_PAGE_SHARED_EXEC) #define PAGE_READONLY __pgprot(_PAGE_READONLY) #define PAGE_READONLY_EXEC __pgprot(_PAGE_READONLY_EXEC) #define PAGE_EXECONLY __pgprot(_PAGE_EXECONLY) #endif /* __ASSEMBLY__ */ #define pte_pi_index(pte) ( \ ((pte & BIT(PTE_PI_IDX_3)) >> (PTE_PI_IDX_3 - 3)) | \ ((pte & BIT(PTE_PI_IDX_2)) >> (PTE_PI_IDX_2 - 2)) | \ ((pte & BIT(PTE_PI_IDX_1)) >> (PTE_PI_IDX_1 - 1)) | \ ((pte & BIT(PTE_PI_IDX_0)) >> (PTE_PI_IDX_0 - 0))) /* * Page types used via Permission Indirection Extension (PIE). PIE uses * the USER, DBM, PXN and UXN bits to to generate an index which is used * to look up the actual permission in PIR_ELx and PIRE0_EL1. We define * combinations we use on non-PIE systems with the same encoding, for * convenience these are listed here as comments as are the unallocated * encodings. */ /* 0: PAGE_DEFAULT */ /* 1: PTE_USER */ /* 2: PTE_WRITE */ /* 3: PTE_WRITE | PTE_USER */ /* 4: PAGE_EXECONLY PTE_PXN */ /* 5: PAGE_READONLY_EXEC PTE_PXN | PTE_USER */ /* 6: PTE_PXN | PTE_WRITE */ /* 7: PAGE_SHARED_EXEC PTE_PXN | PTE_WRITE | PTE_USER */ /* 8: PAGE_KERNEL_ROX PTE_UXN */ /* 9: PAGE_GCS_RO PTE_UXN | PTE_USER */ /* a: PAGE_KERNEL_EXEC PTE_UXN | PTE_WRITE */ /* b: PAGE_GCS PTE_UXN | PTE_WRITE | PTE_USER */ /* c: PAGE_KERNEL_RO PTE_UXN | PTE_PXN */ /* d: PAGE_READONLY PTE_UXN | PTE_PXN | PTE_USER */ /* e: PAGE_KERNEL PTE_UXN | PTE_PXN | PTE_WRITE */ /* f: PAGE_SHARED PTE_UXN | PTE_PXN | PTE_WRITE | PTE_USER */ #define _PAGE_GCS (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER) #define _PAGE_GCS_RO (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER) #define PAGE_GCS __pgprot(_PAGE_GCS) #define PAGE_GCS_RO __pgprot(_PAGE_GCS_RO) #define PIE_E0 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_GCS) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW_O)) #define PIE_E1 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_ROX), PIE_RX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_EXEC), PIE_RWX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_RO), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL), PIE_RW)) #endif /* __ASM_PGTABLE_PROT_H */ |
| 143 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/ptrace.h * * Copyright (C) 1996-2003 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PTRACE_H #define __ASM_PTRACE_H #include <asm/cpufeature.h> #include <uapi/asm/ptrace.h> /* Current Exception Level values, as contained in CurrentEL */ #define CurrentEL_EL1 (1 << 2) #define CurrentEL_EL2 (2 << 2) #define INIT_PSTATE_EL1 \ (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL1h) #define INIT_PSTATE_EL2 \ (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL2h) #include <linux/irqchip/arm-gic-v3-prio.h> #define GIC_PRIO_IRQON GICV3_PRIO_UNMASKED #define GIC_PRIO_IRQOFF GICV3_PRIO_IRQ #define GIC_PRIO_PSR_I_SET GICV3_PRIO_PSR_I_SET /* Additional SPSR bits not exposed in the UABI */ #define PSR_MODE_THREAD_BIT (1 << 0) #define PSR_IL_BIT (1 << 20) /* AArch32-specific ptrace requests */ #define COMPAT_PTRACE_GETREGS 12 #define COMPAT_PTRACE_SETREGS 13 #define COMPAT_PTRACE_GET_THREAD_AREA 22 #define COMPAT_PTRACE_SET_SYSCALL 23 #define COMPAT_PTRACE_GETVFPREGS 27 #define COMPAT_PTRACE_SETVFPREGS 28 #define COMPAT_PTRACE_GETHBPREGS 29 #define COMPAT_PTRACE_SETHBPREGS 30 /* SPSR_ELx bits for exceptions taken from AArch32 */ #define PSR_AA32_MODE_MASK 0x0000001f #define PSR_AA32_MODE_USR 0x00000010 #define PSR_AA32_MODE_FIQ 0x00000011 #define PSR_AA32_MODE_IRQ 0x00000012 #define PSR_AA32_MODE_SVC 0x00000013 #define PSR_AA32_MODE_ABT 0x00000017 #define PSR_AA32_MODE_HYP 0x0000001a #define PSR_AA32_MODE_UND 0x0000001b #define PSR_AA32_MODE_SYS 0x0000001f #define PSR_AA32_T_BIT 0x00000020 #define PSR_AA32_F_BIT 0x00000040 #define PSR_AA32_I_BIT 0x00000080 #define PSR_AA32_A_BIT 0x00000100 #define PSR_AA32_E_BIT 0x00000200 #define PSR_AA32_PAN_BIT 0x00400000 #define PSR_AA32_SSBS_BIT 0x00800000 #define PSR_AA32_DIT_BIT 0x01000000 #define PSR_AA32_Q_BIT 0x08000000 #define PSR_AA32_V_BIT 0x10000000 #define PSR_AA32_C_BIT 0x20000000 #define PSR_AA32_Z_BIT 0x40000000 #define PSR_AA32_N_BIT 0x80000000 #define PSR_AA32_IT_MASK 0x0600fc00 /* If-Then execution state mask */ #define PSR_AA32_GE_MASK 0x000f0000 #ifdef CONFIG_CPU_BIG_ENDIAN #define PSR_AA32_ENDSTATE PSR_AA32_E_BIT #else #define PSR_AA32_ENDSTATE 0 #endif /* AArch32 CPSR bits, as seen in AArch32 */ #define COMPAT_PSR_DIT_BIT 0x00200000 /* * These are 'magic' values for PTRACE_PEEKUSR that return info about where a * process is located in memory. */ #define COMPAT_PT_TEXT_ADDR 0x10000 #define COMPAT_PT_DATA_ADDR 0x10004 #define COMPAT_PT_TEXT_END_ADDR 0x10008 /* * If pt_regs.syscallno == NO_SYSCALL, then the thread is not executing * a syscall -- i.e., its most recent entry into the kernel from * userspace was not via SVC, or otherwise a tracer cancelled the syscall. * * This must have the value -1, for ABI compatibility with ptrace etc. */ #define NO_SYSCALL (-1) #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/types.h> #include <asm/stacktrace/frame.h> /* sizeof(struct user) for AArch32 */ #define COMPAT_USER_SZ 296 /* Architecturally defined mapping between AArch32 and AArch64 registers */ #define compat_usr(x) regs[(x)] #define compat_fp regs[11] #define compat_sp regs[13] #define compat_lr regs[14] #define compat_sp_hyp regs[15] #define compat_lr_irq regs[16] #define compat_sp_irq regs[17] #define compat_lr_svc regs[18] #define compat_sp_svc regs[19] #define compat_lr_abt regs[20] #define compat_sp_abt regs[21] #define compat_lr_und regs[22] #define compat_sp_und regs[23] #define compat_r8_fiq regs[24] #define compat_r9_fiq regs[25] #define compat_r10_fiq regs[26] #define compat_r11_fiq regs[27] #define compat_r12_fiq regs[28] #define compat_sp_fiq regs[29] #define compat_lr_fiq regs[30] static inline unsigned long compat_psr_to_pstate(const unsigned long psr) { unsigned long pstate; pstate = psr & ~COMPAT_PSR_DIT_BIT; if (psr & COMPAT_PSR_DIT_BIT) pstate |= PSR_AA32_DIT_BIT; return pstate; } static inline unsigned long pstate_to_compat_psr(const unsigned long pstate) { unsigned long psr; psr = pstate & ~PSR_AA32_DIT_BIT; if (pstate & PSR_AA32_DIT_BIT) psr |= COMPAT_PSR_DIT_BIT; return psr; } /* * This struct defines the way the registers are stored on the stack during an * exception. struct user_pt_regs must form a prefix of struct pt_regs. */ struct pt_regs { union { struct user_pt_regs user_regs; struct { u64 regs[31]; u64 sp; u64 pc; u64 pstate; }; }; u64 orig_x0; s32 syscallno; u32 pmr; u64 sdei_ttbr1; struct frame_record_meta stackframe; /* Only valid for some EL1 exceptions. */ u64 lockdep_hardirqs; u64 exit_rcu; }; /* For correct stack alignment, pt_regs has to be a multiple of 16 bytes. */ static_assert(IS_ALIGNED(sizeof(struct pt_regs), 16)); static inline bool in_syscall(struct pt_regs const *regs) { return regs->syscallno != NO_SYSCALL; } static inline void forget_syscall(struct pt_regs *regs) { regs->syscallno = NO_SYSCALL; } #define MAX_REG_OFFSET offsetof(struct pt_regs, pstate) #define arch_has_single_step() (1) #ifdef CONFIG_COMPAT #define compat_thumb_mode(regs) \ (((regs)->pstate & PSR_AA32_T_BIT)) #else #define compat_thumb_mode(regs) (0) #endif #define user_mode(regs) \ (((regs)->pstate & PSR_MODE_MASK) == PSR_MODE_EL0t) #define compat_user_mode(regs) \ (((regs)->pstate & (PSR_MODE32_BIT | PSR_MODE_MASK)) == \ (PSR_MODE32_BIT | PSR_MODE_EL0t)) #define processor_mode(regs) \ ((regs)->pstate & PSR_MODE_MASK) #define irqs_priority_unmasked(regs) \ (system_uses_irq_prio_masking() ? \ (regs)->pmr == GIC_PRIO_IRQON : \ true) #define interrupts_enabled(regs) \ (!((regs)->pstate & PSR_I_BIT) && irqs_priority_unmasked(regs)) #define fast_interrupts_enabled(regs) \ (!((regs)->pstate & PSR_F_BIT)) static inline unsigned long user_stack_pointer(struct pt_regs *regs) { if (compat_user_mode(regs)) return regs->compat_sp; return regs->sp; } extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten * @offset: offset of the register. * * regs_get_register returns the value of a register whose offset from @regs. * The @offset is the offset of the register in struct pt_regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset) { u64 val = 0; WARN_ON(offset & 7); offset >>= 3; switch (offset) { case 0 ... 30: val = regs->regs[offset]; break; case offsetof(struct pt_regs, sp) >> 3: val = regs->sp; break; case offsetof(struct pt_regs, pc) >> 3: val = regs->pc; break; case offsetof(struct pt_regs, pstate) >> 3: val = regs->pstate; break; default: val = 0; } return val; } /* * Read a register given an architectural register index r. * This handles the common case where 31 means XZR, not SP. */ static inline unsigned long pt_regs_read_reg(const struct pt_regs *regs, int r) { return (r == 31) ? 0 : regs->regs[r]; } /* * Write a register given an architectural register index r. * This handles the common case where 31 means XZR, not SP. */ static inline void pt_regs_write_reg(struct pt_regs *regs, int r, unsigned long val) { if (r != 31) regs->regs[r] = val; } /* Valid only for Kernel mode traps. */ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long regs_return_value(struct pt_regs *regs) { unsigned long val = regs->regs[0]; /* * Audit currently uses regs_return_value() instead of * syscall_get_return_value(). Apply the same sign-extension here until * audit is updated to use syscall_get_return_value(). */ if (compat_user_mode(regs)) val = sign_extend64(val, 31); return val; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->regs[0] = rc; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * * Note that this chooses the most likely register mapping. In very rare * cases this may not return correct data, for example, if one of the * function parameters is 16 bytes or bigger. In such cases, we cannot * get access the parameter correctly and the register assignment of * subsequent parameters will be shifted. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { #define NR_REG_ARGUMENTS 8 if (n < NR_REG_ARGUMENTS) return pt_regs_read_reg(regs, n); return 0; } /* We must avoid circular header include via sched.h */ struct task_struct; int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->pc; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->pc = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->regs[29]; } #define procedure_link_pointer(regs) ((regs)->regs[30]) static inline void procedure_link_pointer_set(struct pt_regs *regs, unsigned long val) { procedure_link_pointer(regs) = val; } extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ #endif |
| 3 6 1 5 1 1 1 4 3 4 5 4 3 4 3 2 3 4 4 1 4 3 5 1 2 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool wake_writer = false, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started reading * and it is no longer full after reading to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) { wake_writer |= pipe_full(head, tail, pipe->max_usage); tail = pipe_update_tail(pipe, buf, tail); } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(wake_writer)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; wake_writer = false; wake_next_reader = true; mutex_lock(&pipe->mutex); } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (wake_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; f->f_pipe = 0; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[0]->f_pipe = 0; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); /* * Disable permission and pre-content events, but enable legacy * inotify events for legacy users. */ file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM); file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_pipe = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_pipe = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole file system mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static const struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PIPE_FS_I_H #define _LINUX_PIPE_FS_I_H #define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ #define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */ #ifdef CONFIG_WATCH_QUEUE #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer * @offset: offset of data inside the @page * @len: length of data inside the @page * @ops: operations associated with this buffer. See @pipe_buf_operations. * @flags: pipe buffer flags. See above. * @private: private data owned by the ops. **/ struct pipe_buffer { struct page *page; unsigned int offset, len; const struct pipe_buf_operations *ops; unsigned int flags; unsigned long private; }; /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; unsigned int head; unsigned int tail; unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; unsigned int r_counter; unsigned int w_counter; bool poll_usage; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; #ifdef CONFIG_WATCH_QUEUE struct watch_queue *watch_queue; #endif }; /* * Note on the nesting of these functions: * * ->confirm() * ->try_steal() * * That is, ->try_steal() must be called on a confirmed buffer. See below for * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); /* * When the contents of this pipe buffer has been completely * consumed by a reader, ->release() is called. */ void (*release)(struct pipe_inode_info *, struct pipe_buffer *); /* * Attempt to take ownership of the pipe buffer and its contents. * ->try_steal() returns %true for success, in which case the contents * of the pipe (the buf->page) is locked and now completely owned by the * caller. The page may then be transferred to a different mapping, the * most often used case is insertion into different file address space * cache. */ bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. */ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_has_watch_queue - Check whether the pipe is a watch_queue, * i.e. it was created with O_NOTIFICATION_PIPE * @pipe: The pipe to check * * Return: true if pipe is a watch queue, false otherwise. */ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) { #ifdef CONFIG_WATCH_QUEUE return pipe->watch_queue != NULL; #else return false; #endif } /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline bool pipe_empty(unsigned int head, unsigned int tail) { return head == tail; } /** * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { return head - tail; } /** * pipe_full - Return true if the pipe is full * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer * @limit: The maximum amount of slots available. */ static inline bool pipe_full(unsigned int head, unsigned int tail, unsigned int limit) { return pipe_occupancy(head, tail) >= limit; } /** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest */ static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, unsigned int slot) { return &pipe->bufs[slot & (pipe->ring_size - 1)]; } /** * pipe_head_buf - Return the pipe buffer at the head of the pipe ring * @pipe: The pipe to access */ static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) { return pipe_buf(pipe, pipe->head); } /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Return: %true if the reference was successfully obtained. */ static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return buf->ops->get(pipe, buf); } /** * pipe_buf_release - put a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to */ static inline void pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { const struct pipe_buf_operations *ops = buf->ops; buf->ops = NULL; ops->release(pipe, buf); } /** * pipe_buf_confirm - verify contents of the pipe buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to confirm */ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->confirm) return 0; return buf->ops->confirm(pipe, buf); } /** * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->try_steal) return false; return buf->ops->try_steal(pipe, buf); } static inline void pipe_discard_from(struct pipe_inode_info *pipe, unsigned int old_head) { unsigned int mask = pipe->ring_size - 1; while (pipe->head > old_head) pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE /* Pipe lock and unlock operations */ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); long pipe_fcntl(struct file *, unsigned int, unsigned int arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned int size); #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILEATTR_H #define _LINUX_FILEATTR_H /* Flags shared betwen flags/xflags */ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ FS_PROJINHERIT_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT) /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ struct fileattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ u32 fsx_extsize; /* extsize field value (get/set)*/ u32 fsx_nextents; /* nextents field value (get) */ u32 fsx_projid; /* project identifier (get/set) */ u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ /* selectors: */ bool flags_valid:1; bool fsx_valid:1; }; int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa); void fileattr_fill_xflags(struct fileattr *fa, u32 xflags); void fileattr_fill_flags(struct fileattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes * @fa: fileattr pointer * * Return: true if any attributes are present that are not represented in * ->flags. */ static inline bool fileattr_has_fsx(const struct fileattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); #endif /* _LINUX_FILEATTR_H */ |
| 156 174 174 174 174 190 190 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. * * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); continue; } /* * If i_count is zero, the inode cannot have any watches and * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. * However, we should have been called /after/ evict_inodes * removed all zero refcount inodes, in any case. Test to * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); fsnotify_inode_delete(inode); iput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return; fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(fsnotify_sb_watched_objects(sb), !atomic_long_read(fsnotify_sb_watched_objects(sb))); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT)); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_PRE_CONTENT)); } void fsnotify_sb_free(struct super_block *sb) { kfree(sb->s_fsnotify_info); } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); hlist_for_each_entry(child, &alias->d_children, d_sib) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_sb->s_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask(mnt_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* Are there any inode/mount/sb objects that watch for these events? */ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | READ_ONCE(inode->i_sb->s_fsnotify_mask); return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } /* Report pre-content event with optional range info */ int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count) { struct file_range range; /* Report page aligned range only when pos is known */ if (!ppos) return fsnotify_path(path, FS_PRE_ACCESS); range.path = path; range.pos = PAGE_ALIGN_DOWN(*ppos); range.count = PAGE_ALIGN(*ppos + count) - range.pos; return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, FSNOTIFY_EVENT_FILE_RANGE); } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); __u32 mnt_mask = path ? READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* Optimize the likely case of nobody watching this path */ if (likely(!parent_watched && !fsnotify_object_watched(inode, mnt_mask, mask))) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt_mask, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if ((!sbinfo || !sbinfo->sb_marks) && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = READ_ONCE(sb->s_fsnotify_mask); if (mnt) marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); if (sbinfo) { iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sbinfo->sb_marks); } if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * At open time we check fsnotify_sb_has_priority_watchers() and set the * FMODE_NONOTIFY_ mode bits accordignly. * Later, fsnotify permission hooks do not check if there are permission event * watches, but that there were permission event watches at open time. */ void file_set_fsnotify_mode_from_watchers(struct file *file) { struct dentry *dentry = file->f_path.dentry, *parent; struct super_block *sb = dentry->d_sb; __u32 mnt_mask, p_mask; /* Is it a file opened by fanotify? */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) return; /* * Permission events is a super set of pre-content events, so if there * are no permission event watchers, there are also no pre-content event * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. */ if (likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT))) { file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return; } /* * If there are permission event watchers but no pre-content event * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. */ if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_PRE_CONTENT))) { file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); return; } /* * OK, there are some pre-content watchers. Check if anybody is * watching for pre-content events on *this* file. */ mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask, FSNOTIFY_PRE_CONTENT_EVENTS))) { /* Enable pre-content events */ file_set_fsnotify_mode(file, 0); return; } /* Is parent watching for pre-content events on this file? */ if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { parent = dget_parent(dentry); p_mask = fsnotify_inode_watches_children(d_inode(parent)); dput(parent); if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) { /* Enable pre-content events */ file_set_fsnotify_mode(file, 0); return; } } /* Nobody watching for pre-content events from this file */ file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); } #endif static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector, SLAB_PANIC); return 0; } core_initcall(fsnotify_init); |
| 24 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ #include <linux/stdarg.h> #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> #include <linux/ratelimit_types.h> #include <linux/once_lite.h> struct console; extern const char linux_banner[]; extern const char linux_proc_banner[]; extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { switch (buffer[1]) { case '0' ... '7': case 'c': /* KERN_CONT */ return buffer[1]; } } return 0; } static inline const char *printk_skip_level(const char *buffer) { if (printk_get_level(buffer)) return buffer + 2; return buffer; } static inline const char *printk_skip_headers(const char *buffer) { while (printk_get_level(buffer)) buffer = printk_skip_level(buffer); return buffer; } /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET int match_devname_and_update_preferred_console(const char *match, const char *name, const short idx); extern int console_printk[]; #define console_loglevel (console_printk[0]) #define default_message_loglevel (console_printk[1]) #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE]; struct ctl_table; extern int suppress_printk; struct va_format { const char *fmt; va_list *va; }; /* * FW_BUG * Add this to a message where you are sure the firmware is buggy or behaves * really stupid or out of spec. Be aware that the responsible BIOS developer * should be able to fix this issue or at least get a concrete idea of the * problem by reading your message without the need of looking at the kernel * code. * * Use it for definite and high priority BIOS bugs. * * FW_WARN * Use it for not that clear (e.g. could the kernel messed up things already?) * and medium priority BIOS bugs. * * FW_INFO * Use this one if you want to tell the user or vendor about something * suspicious, but generally harmless related to the firmware. * * Use it for information or very low priority BIOS bugs. */ #define FW_BUG "[Firmware Bug]: " #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " /* * HW_ERR * Add this to a message for hardware errors, so that user can report * it to hardware vendor instead of LKML or software vendor. */ #define HW_ERR "[Hardware Error]: " /* * DEPRECATED * Add this to a message whenever you want to warn user space about the use * of a deprecated aspect of an API so they can stop using it */ #define DEPRECATED "[Deprecated]: " /* * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format checking. */ #define no_printk(fmt, ...) \ ({ \ if (0) \ _printk(fmt, ##__VA_ARGS__); \ 0; \ }) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif struct dev_printk_info; #ifdef CONFIG_PRINTK asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold int _printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); extern void __printk_deferred_enter(void); extern void __printk_deferred_exit(void); extern void printk_force_console_enter(void); extern void printk_force_console_exit(void); /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ #define printk_deferred_enter() __printk_deferred_enter() #define printk_deferred_exit() __printk_deferred_exit() /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); extern int printk_delay_msec; extern int dmesg_restrict; extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); void console_try_replay_all(void); void printk_legacy_allow_panic_sync(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); void nbcon_atomic_flush_unsafe(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) { return 0; } static inline __printf(1, 2) __cold int _printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold int _printk_deferred(const char *s, ...) { return 0; } static inline void printk_deferred_enter(void) { } static inline void printk_deferred_exit(void) { } static inline void printk_force_console_enter(void) { } static inline void printk_force_console_exit(void) { } static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec) { return false; } static inline void wake_up_klogd(void) { } static inline char *log_buf_addr_get(void) { return NULL; } static inline u32 log_buf_len_get(void) { return 0; } static inline void log_buf_vmcoreinfo_setup(void) { } static inline void setup_log_buf(int early) { } static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } static inline void dump_stack_print_info(const char *log_lvl) { } static inline void show_regs_print_info(const char *log_lvl) { } static inline void dump_stack_lvl(const char *log_lvl) { } static inline void dump_stack(void) { } static inline void printk_trigger_flush(void) { } static inline void console_try_replay_all(void) { } static inline void printk_legacy_allow_panic_sync(void) { } static inline bool nbcon_device_try_acquire(struct console *con) { return false; } static inline void nbcon_device_release(struct console *con) { } static inline void nbcon_atomic_flush_unsafe(void) { } #endif bool this_cpu_in_panic(void); #ifdef CONFIG_SMP extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); extern void __printk_cpu_sync_put(void); #else #define __printk_cpu_sync_try_get() true #define __printk_cpu_sync_wait() #define __printk_cpu_sync_put() #endif /* CONFIG_SMP */ /** * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. * * CAUTION: This function must be used carefully. It does not behave like a * typical lock. Here are important things to watch out for... * * * This function is reentrant on the same CPU. Therefore the calling * code must not assume exclusive access to data if code accessing the * data can run reentrant or within NMI context on the same CPU. * * * If there exists usage of this function from NMI context, it becomes * unsafe to perform any type of locking or spinning to wait for other * CPUs after calling this function from any context. This includes * using spinlocks or any other busy-waiting synchronization methods. */ #define printk_cpu_sync_get_irqsave(flags) \ for (;;) { \ local_irq_save(flags); \ if (__printk_cpu_sync_try_get()) \ break; \ local_irq_restore(flags); \ __printk_cpu_sync_wait(); \ } /** * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning * lock and restore interrupts. * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ #define printk_cpu_sync_put_irqrestore(flags) \ do { \ __printk_cpu_sync_put(); \ local_irq_restore(flags); \ } while (0) extern int kptr_restrict; /** * pr_fmt - used by the pr_*() macros to generate the printk format string * @fmt: format string passed from a pr_*() macro * * This macro can be used to generate a unified format string for pr_*() * macros. A common use is to prefix all pr_*() messages in a file with a common * string. For example, defining this at the top of a source file: * * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt * * would prefix all pr_info, pr_emerg... messages in the file with the module * name. */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif struct module; #ifdef CONFIG_PRINTK_INDEX struct pi_entry { const char *fmt; const char *func; const char *file; unsigned int line; /* * While printk and pr_* have the level stored in the string at compile * time, some subsystems dynamically add it at runtime through the * format string. For these dynamic cases, we allow the subsystem to * tell us the level at compile time. * * NULL indicates that the level, if any, is stored in fmt. */ const char *level; /* * The format string used by various subsystem specific printk() * wrappers to prefix the message. * * Note that the static prefix defined by the pr_fmt() macro is stored * directly in the message format (@fmt), not here. */ const char *subsys_fmt_prefix; } __packed; #define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \ do { \ if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \ /* * We check __builtin_constant_p multiple times here * for the same input because GCC will produce an error * if we try to assign a static variable to fmt if it * is not a constant, even with the outer if statement. */ \ static const struct pi_entry _entry \ __used = { \ .fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \ .func = __func__, \ .file = __FILE__, \ .line = __LINE__, \ .level = __builtin_constant_p(_level) ? (_level) : NULL, \ .subsys_fmt_prefix = _subsys_fmt_prefix,\ }; \ static const struct pi_entry *_entry_ptr \ __used __section(".printk_index") = &_entry; \ } \ } while (0) #else /* !CONFIG_PRINTK_INDEX */ #define __printk_index_emit(...) do {} while (0) #endif /* CONFIG_PRINTK_INDEX */ /* * Some subsystems have their own custom printk that applies a va_format to a * generic format, for example, to include a device number or other metadata * alongside the format supplied by the caller. * * In order to store these in the way they would be emitted by the printk * infrastructure, the subsystem provides us with the start, fixed string, and * any subsequent text in the format string. * * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the * first one. * * subsys_fmt_prefix must be known at compile time, or compilation will fail * (since this is a mistake). If fmt or level is not known at compile time, no * index entry will be made (since this can legitimately happen). */ #define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \ __printk_index_emit(fmt, level, subsys_fmt_prefix) #define printk_index_wrap(_p_func, _fmt, ...) \ ({ \ __printk_index_emit(_fmt, NULL, NULL); \ _p_func(_fmt, ##__VA_ARGS__); \ }) /** * printk - print a kernel message * @fmt: format string * * This is printk(). It can be called from any context. We want it to work. * * If printk indexing is enabled, _printk() is called from printk_index_wrap. * Otherwise, printk is simply #defined to _printk. * * We try to grab the console_lock. If we succeed, it's easy - we log the * output and call the console drivers. If we fail to get the semaphore, we * place the output into the log buffer and return. The current holder of * the console_sem will notice the new output in console_unlock(); and will * send it to the consoles before releasing the lock. * * One effect of this deferred printing is that code which calls printk() and * then changes console_loglevel may break. This is because console_loglevel * is inspected when the actual printing occurs. * * See also: * printf(3) * * See the vsnprintf() documentation for format string extensions over C99. */ #define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) #define printk_deferred(fmt, ...) \ printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__) /** * pr_emerg - Print an emergency-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) /** * pr_alert - Print an alert-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_crit - Print a critical-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_err - Print an error-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) /** * pr_warn - Print a warning-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() * to generate the format string. */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) /** * pr_notice - Print a notice-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) /** * pr_info - Print an info-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /** * pr_cont - Continues a previous log message in the same line. * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CONT loglevel. It should only be * used when continuing a log message with no newline ('\n') enclosed. Otherwise * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) /** * pr_devel - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is * defined. Otherwise it does nothing. * * It uses pr_fmt() to generate the format string. */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include <linux/dynamic_debug.h> /** * pr_debug - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. * * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses * pr_fmt() internally). */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * Print a one-time message (analogous to WARN_ONCE() et al): */ #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_once(fmt, ...) \ printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_once(fmt, ...) \ printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_once(fmt, ...) \ printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_once(fmt, ...) \ printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_once(fmt, ...) \ printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_once(fmt, ...) \ printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) #define pr_debug_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK #define printk_ratelimited(fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else #define printk_ratelimited(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_ratelimited(fmt, ...) \ printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_ratelimited(fmt, ...) \ printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_ratelimited, don't do that... */ #if defined(DEBUG) #define pr_devel_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ __ratelimit(&_rs)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif extern const struct file_operations kmsg_fops; enum { DUMP_PREFIX_NONE, DUMP_PREFIX_ADDRESS, DUMP_PREFIX_OFFSET }; extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize, char *linebuf, size_t linebuflen, bool ascii); #ifdef CONFIG_PRINTK extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); #else static inline void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, const void *buf, size_t len) { } #endif #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #else static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } #endif /** * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) * @buf: data blob to dump * @len: number of bytes in the @buf * * Calls print_hex_dump(), with log level of KERN_DEBUG, * rowsize of 16, groupsize of 1, and ASCII output included. */ #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) #endif |
| 80 | 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-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 KVM_ARMV8_PMU_MAX_COUNTERS 32 #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 { u64 events_host; u64 events_guest; }; struct kvm_pmu { struct irq_work overflow_work; struct kvm_pmu_events events; struct kvm_pmc pmc[KVM_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_implemented_counter_mask(struct kvm_vcpu *vcpu); u64 kvm_pmu_accessible_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_reprogram_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); bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx); void kvm_pmu_nested_transition(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_implemented_counter_mask(struct kvm_vcpu *vcpu) { return 0; } static inline u64 kvm_pmu_accessible_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_reprogram_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; } static inline bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx) { return false; } static inline void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) {} #endif #endif |
| 153 252 252 167 183 252 181 167 167 2 252 2 2 2 2 19 19 12 18 19 18 12 12 19 19 175 175 175 175 175 175 175 175 175 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc/dec() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). * * The INT_MAX overflow condition is either used by the networking * code to reset or detected in the slow path of * static_key_slow_inc_cpuslocked(). */ v = atomic_read(&key->enabled); do { if (v <= 0 || v == INT_MAX) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc/dec() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; guard(mutex)(&jump_label_mutex); /* Try to mark it as 'enabling in progress. */ if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { /* * While holding the mutex this should never observe * anything else than a value >= 1 and succeed */ if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) return false; } return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_dec_not_one(struct static_key *key) { int v; /* * Go into the slow path if key::enabled is less than or equal than * one. One is valid to shut down the key, anything less than one * is an imbalance, which is handled at the call site. * * That includes the special case of '-1' which is set in * static_key_slow_inc_cpuslocked(), but that's harmless as it is * fully serialized in the slow path below. By the time this task * acquires the jump label lock the value is back to one and the * retry under the lock must succeed. */ v = atomic_read(&key->enabled); do { /* * Warn about the '-1' case though; since that means a * decrement is concurrent with a first (0->1) increment. IOW * people are trying to disable something that wasn't yet fully * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); /* * Warn about underflow, and lie about success in an attempt to * not make things worse. */ if (WARN_ON_ONCE(v == 0)) return true; if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); int val; if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); val = atomic_read(&key->enabled); /* * It should be impossible to observe -1 with jump_label_mutex held, * see static_key_slow_inc_cpuslocked(). */ if (WARN_ON_ONCE(val == -1)) return; /* * Cannot already be 0, something went sideways. */ if (WARN_ON_ONCE(val == 0)) return; if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; preempt_disable(); mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; preempt_enable(); if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } preempt_disable(); jlm2->mod = __module_address((unsigned long)key); preempt_enable(); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } preempt_disable(); mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } preempt_enable(); #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 8 8 8 8 8 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/copypage.c * * Copyright (C) 2002 Deep Blue Solutions Ltd, All Rights Reserved. * Copyright (C) 2012 ARM Ltd. */ #include <linux/bitops.h> #include <linux/mm.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/mte.h> void copy_highpage(struct page *to, struct page *from) { void *kto = page_address(to); void *kfrom = page_address(from); struct folio *src = page_folio(from); struct folio *dst = page_folio(to); unsigned int i, nr_pages; copy_page(kto, kfrom); if (kasan_hw_tags_enabled()) page_kasan_tag_reset(to); if (!system_supports_mte()) return; if (folio_test_hugetlb(src)) { if (!folio_test_hugetlb_mte_tagged(src) || from != folio_page(src, 0)) return; WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst)); /* * Populate tags for all subpages. * * Don't assume the first page is head page since * huge page copy may start from any subpage. */ nr_pages = folio_nr_pages(src); for (i = 0; i < nr_pages; i++) { kfrom = page_address(folio_page(src, i)); kto = page_address(folio_page(dst, i)); mte_copy_page_tags(kto, kfrom); } folio_set_hugetlb_mte_tagged(dst); } else if (page_mte_tagged(from)) { /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); set_page_mte_tagged(to); } } EXPORT_SYMBOL(copy_highpage); void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_highpage(to, from); flush_dcache_page(to); } EXPORT_SYMBOL_GPL(copy_user_highpage); |
| 174 194 194 94 174 175 175 101 122 64 103 104 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags)) clear_bit(PG_dcache_clean, &folio->flags); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vrf.c: device driver to encapsulate a VRF space * * Copyright (c) 2015 Cumulus Networks. All rights reserved. * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com> * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> * * Based on dummy, team and ipvlan drivers */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <linux/inetdevice.h> #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> #include <net/sch_generic.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack.h> #include <net/inet_dscp.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.1" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ #define HT_MAP_BITS 4 #define HASH_INITVAL ((u32)0xcafef00d) struct vrf_map { DECLARE_HASHTABLE(ht, HT_MAP_BITS); spinlock_t vmap_lock; /* shared_tables: * count how many distinct tables do not comply with the strict mode * requirement. * shared_tables value must be 0 in order to enable the strict mode. * * example of the evolution of shared_tables: * | time * add vrf0 --> table 100 shared_tables = 0 | t0 * add vrf1 --> table 101 shared_tables = 0 | t1 * add vrf2 --> table 100 shared_tables = 1 | t2 * add vrf3 --> table 100 shared_tables = 1 | t3 * add vrf4 --> table 101 shared_tables = 2 v t4 * * shared_tables is a "step function" (or "staircase function") * and it is increased by one when the second vrf is associated to a * table. * * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1. * * at t3, another dev (vrf3) is bound to the same table 100 but the * value of shared_tables is still 1. * This means that no matter how many new vrfs will register on the * table 100, the shared_tables will not increase (considering only * table 100). * * at t4, vrf4 is bound to table 101, and shared_tables = 2. * * Looking at the value of shared_tables we can immediately know if * the strict_mode can or cannot be enforced. Indeed, strict_mode * can be enforced iff shared_tables = 0. * * Conversely, shared_tables is decreased when a vrf is de-associated * from a table with exactly two associated vrfs. */ u32 shared_tables; bool strict_mode; }; struct vrf_map_elem { struct hlist_node hnode; struct list_head vrf_list; /* VRFs registered to this table */ u32 table_id; int users; int ifindex; }; static unsigned int vrf_net_id; /* per netns vrf data */ struct netns_vrf { /* protected by rtnl lock */ bool add_fib_rules; struct vrf_map vmap; struct ctl_table_header *ctl_hdr; }; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; #if IS_ENABLED(CONFIG_IPV6) struct fib6_table *fib6_table; #endif u32 tb_id; struct list_head me_list; /* entry in vrf_map_elem */ int ifindex; }; static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; kfree_skb(skb); } static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); return &nn_vrf->vmap; } static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev) { return netns_vrf_map(dev_net(dev)); } static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me) { struct list_head *me_head = &me->vrf_list; struct net_vrf *vrf; if (list_empty(me_head)) return -ENODEV; vrf = list_first_entry(me_head, struct net_vrf, me_list); return vrf->ifindex; } static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags) { struct vrf_map_elem *me; me = kmalloc(sizeof(*me), flags); if (!me) return NULL; return me; } static void vrf_map_elem_free(struct vrf_map_elem *me) { kfree(me); } static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id, int ifindex, int users) { me->table_id = table_id; me->ifindex = ifindex; me->users = users; INIT_LIST_HEAD(&me->vrf_list); } static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap, u32 table_id) { struct vrf_map_elem *me; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_for_each_possible(vmap->ht, me, hnode, key) { if (me->table_id == table_id) return me; } return NULL; } static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me) { u32 table_id = me->table_id; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_add(vmap->ht, &me->hnode, key); } static void vrf_map_del_elem(struct vrf_map_elem *me) { hash_del(&me->hnode); } static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock) { spin_lock(&vmap->vmap_lock); } static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) { spin_unlock(&vmap->vmap_lock); } /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); struct vrf_map_elem *new_me, *me; u32 table_id = vrf->tb_id; bool free_new_me = false; int users; int res; /* we pre-allocate elements used in the spin-locked section (so that we * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) return -ENOMEM; vrf_map_elem_init(new_me, table_id, dev->ifindex, 0); vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) { me = new_me; vrf_map_add_elem(vmap, me); goto link_vrf; } /* we already have an entry in the vrf_map, so it means there is (at * least) a vrf registered on the specific table. */ free_new_me = true; if (vmap->strict_mode) { /* vrfs cannot share the same table */ NL_SET_ERR_MSG(extack, "Table is used by another VRF"); res = -EBUSY; goto unlock; } link_vrf: users = ++me->users; if (users == 2) ++vmap->shared_tables; list_add(&vrf->me_list, &me->vrf_list); res = 0; unlock: vrf_map_unlock(vmap); /* clean-up, if needed */ if (free_new_me) vrf_map_elem_free(new_me); return res; } /* called with rtnl lock held */ static void vrf_map_unregister_dev(struct net_device *dev) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); u32 table_id = vrf->tb_id; struct vrf_map_elem *me; int users; vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) goto unlock; list_del(&vrf->me_list); users = --me->users; if (users == 1) { --vmap->shared_tables; } else if (users == 0) { vrf_map_del_elem(me); /* no one will refer to this element anymore */ vrf_map_elem_free(me); } unlock: vrf_map_unlock(vmap); } /* return the vrf device index associated with the table_id */ static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id) { struct vrf_map *vmap = netns_vrf_map(net); struct vrf_map_elem *me; int ifindex; vrf_map_lock(vmap); if (!vmap->strict_mode) { ifindex = -EPERM; goto unlock; } me = vrf_map_lookup_elem(vmap, table_id); if (!me) { ifindex = -ENODEV; goto unlock; } ifindex = vrf_map_elem_get_vrf_ifindex(me); unlock: vrf_map_unlock(vmap); return ifindex; } /* by default VRF devices do not have a qdisc and are expected * to be created with only a single queue. */ static bool qdisc_tx_is_default(const struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; if (dev->num_tx_queues > 1) return false; txq = netdev_get_tx_queue(dev, 0); qdisc = rcu_access_pointer(txq->qdisc); return !qdisc->enqueue; } /* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { unsigned int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) dev_dstats_rx_add(dev, len); else dev_dstats_rx_dropped(dev); return NETDEV_TX_OK; } static void vrf_nf_set_untracked(struct sk_buff *skb) { if (skb_get_nfct(skb) == 0) nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } static void vrf_nf_reset_ct(struct sk_buff *skb) { if (skb_get_nfct(skb) == IP_CT_UNTRACKED) nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) static int vrf_ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) goto err; iph = ipv6_hdr(skb); memset(&fl6, 0, sizeof(fl6)); /* needed to match OIF rule */ fl6.flowi6_l3mdev = dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = iph->nexthdr; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); skb_dst_set(skb, dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; return ret; err: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #endif /* based on ip_local_out; can't use it b/c the dst is switched pointing to us */ static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { struct iphdr *ip4h; int ret = NET_XMIT_DROP; struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); memset(&fl4, 0, sizeof(fl4)); /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)); fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); skb_dst_set(skb, &rt->dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); if (!ip4h->saddr) { ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, RT_SCOPE_LINK); } memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; out: return ret; err: vrf_tx_error(vrf_dev, skb); goto out; } static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) { switch (skb->protocol) { case htons(ETH_P_IP): return vrf_process_v4_outbound(skb, dev); case htons(ETH_P_IPV6): return vrf_process_v6_outbound(skb, dev); default: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } } static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned int len = skb->len; netdev_tx_t ret; ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) dev_dstats_tx_add(dev, len); else dev_dstats_tx_dropped(dev); return ret; } static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; if (!list_empty(&vrf_dev->ptype_all) && likely(skb_headroom(skb) >= ETH_HLEN)) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; rcu_read_lock_bh(); dev_queue_xmit_nit(skb, vrf_dev); rcu_read_unlock_bh(); skb_pull(skb, ETH_HLEN); } vrf_nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) /* modelled after ip6_finish_output2 */ static int vrf_finish_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; const struct in6_addr *nexthop; struct neighbour *neigh; int ret; vrf_nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } /* modelled after ip6_output */ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, vrf_finish_output6, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rt6_info *rt6; rcu_read_lock(); rt6 = rcu_dereference(vrf->rt6); if (likely(rt6)) { dst = &rt6->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output6_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip6_local_out(net, sk, skb); } static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IPV6); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output6_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip6_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert link scope packets */ if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); } /* holding rtnl */ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { struct rt6_info *rt6 = rtnl_dereference(vrf->rt6); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rt6, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rt6) { dst = &rt6->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rt6_create(struct net_device *dev) { int flags = DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct rt6_info *rt6; int rc = -ENOMEM; /* IPv6 can be CONFIG enabled and then disabled runtime */ if (!ipv6_mod_enabled()) return 0; vrf->fib6_table = fib6_new_table(net, vrf->tb_id); if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ rt6 = ip6_dst_alloc(net, dev, flags); if (!rt6) goto out; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; out: return rc; } #else static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { return skb; } static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { } static int vrf_rt6_create(struct net_device *dev) { return 0; } #endif /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; vrf_nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) { dev->stats.tx_errors++; return -ENOMEM; } } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int ret; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return ret; } rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rtable *rth; rcu_read_lock(); rth = rcu_dereference(vrf->rth); if (likely(rth)) { dst = &rth->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip_local_out(net, sk, skb); } static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IP); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert multicast or local broadcast */ if (ipv4_is_multicast(ip_hdr(skb)->daddr) || ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); } /* called with rcu lock held */ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_out(vrf_dev, sk, skb); case AF_INET6: return vrf_ip6_out(vrf_dev, sk, skb); } return skb; } /* holding rtnl */ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) { struct rtable *rth = rtnl_dereference(vrf->rth); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rth, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rth) { dst = &rth->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rtable_create(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; if (!fib_new_table(dev_net(dev), vrf->tb_id)) return -ENOMEM; /* create a dst for routing packets out through a VRF device */ rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1); if (!rth) return -ENOMEM; rth->dst.output = vrf_output; rcu_assign_pointer(vrf->rth, rth); return 0; } /**************************** device handling ********************/ /* cycle interface to flush neighbor cache and move routes across tables */ static void cycle_netdev(struct net_device *dev, struct netlink_ext_ack *extack) { unsigned int flags = dev->flags; int ret; if (!netif_running(dev)) return; ret = dev_change_flags(dev, flags & ~IFF_UP, extack); if (ret >= 0) ret = dev_change_flags(dev, flags, extack); if (ret < 0) { netdev_err(dev, "Failed to cycle device %s; route tables might be wrong!\n", dev->name); } } static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { int ret; /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ if (port_dev == dev_net(dev)->loopback_dev) { NL_SET_ERR_MSG(extack, "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; cycle_netdev(port_dev, extack); return 0; err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave an L3 master device to a VRF"); return -EINVAL; } if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; cycle_netdev(port_dev, NULL); return 0; } static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { return do_vrf_del_slave(dev, port_dev); } static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; dev->flags = IFF_MASTER | IFF_NOARP; /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); return 0; out_rth: vrf_rtable_release(dev, vrf); out_nomem: return -ENOMEM; } static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; static u32 vrf_fib_table(const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return vrf->tb_id; } static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; } static int vrf_prepare_mac_header(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto) { struct ethhdr *eth; int err; /* in general, we do not know if there is enough space in the head of * the packet for hosting the mac header. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev)); if (unlikely(err)) /* no space in the skb head */ return -ENOBUFS; __skb_push(skb, ETH_HLEN); eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. */ ether_addr_copy(eth->h_dest, vrf_dev->dev_addr); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth->h_proto = htons(proto); /* the destination address of the Ethernet frame corresponds to the * address set on the VRF interface; therefore, the packet is intended * to be processed locally. */ skb->protocol = eth->h_proto; skb->pkt_type = PACKET_HOST; skb_postpush_rcsum(skb, skb->data, ETH_HLEN); skb_pull_inline(skb, ETH_HLEN); return 0; } /* prepare and add the mac header to the packet if it was not set previously. * In this way, packet sniffers such as tcpdump can parse the packet correctly. * If the mac header was already set, the original mac header is left * untouched and the function returns immediately. */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto, struct net_device *orig_dev) { if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); } #if IS_ENABLED(CONFIG_IPV6) /* neighbor handling is done with actual device; do not want * to flip skb->dev for those ndisc packets. This really fails * for multiple next protocols (e.g., NEXTHDR_HOP). But it is * a start. */ static bool ipv6_ndisc_frame(const struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); bool rc = false; if (iph->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; struct icmp6hdr _icmph; icmph = skb_header_pointer(skb, sizeof(*iph), sizeof(_icmph), &_icmph); if (!icmph) goto out; switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: rc = true; break; } } out: return rc; } static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, int ifindex) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_iif = ifindex, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), }; struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst)) return; skb_dst_set(skb, &rt6->dst); } static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For non-loopback strict packets, determine the dst using the original * ifindex. */ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; else vrf_ip6_input_dst(skb, vrf_dev, orig_iif); goto out; } /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { struct net_device *orig_dev = skb->dev; dev_dstats_rx_add(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IPV6, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } if (need_strict) vrf_ip6_input_dst(skb, vrf_dev, orig_iif); skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } #else static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { return skb; } #endif static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_device *orig_dev = skb->dev; skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; /* loopback traffic; do not push through packet taps again. * Reset pkt_type for upper layers to process skb */ if (skb->pkt_type == PACKET_LOOPBACK) { skb->pkt_type = PACKET_HOST; goto out; } dev_dstats_rx_add(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } /* called with rcu lock held */ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_rcv(vrf_dev, skb); case AF_INET6: return vrf_ip6_rcv(vrf_dev, skb); } return skb; } #if IS_ENABLED(CONFIG_IPV6) /* send to link-local or multicast address via interface enslaved to * VRF device. Force lookup to VRF table without changing flow struct * Note: Caller to this function must hold rcu_read_lock() and no refcnt * is taken on the dst by this function. */ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, struct flowi6 *fl6) { struct net *net = dev_net(dev); int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF; struct dst_entry *dst = NULL; struct rt6_info *rt; /* VRF device does not have a link-local address and * sending packets to link-local or mcast addresses over * a VRF device does not make sense */ if (fl6->flowi6_oif == dev->ifindex) { dst = &net->ipv6.ip6_null_entry->dst; return dst; } if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; return dst; } #endif static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_l3_rcv = vrf_l3_rcv, .l3mdev_l3_out = vrf_l3_out, #if IS_ENABLED(CONFIG_IPV6) .l3mdev_link_scope_lookup = vrf_link_scope_lookup, #endif }; static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops vrf_ethtool_ops = { .get_drvinfo = vrf_get_drvinfo, }; static inline size_t vrf_fib_rule_nl_size(void) { size_t sz; sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) { struct fib_rule_hdr *frh; struct nlmsghdr *nlh; struct sk_buff *skb; int err; if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) && !ipv6_mod_enabled()) return 0; skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0); if (!nlh) goto nla_put_failure; /* rule only needs to appear once */ nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); frh->family = family; frh->action = FR_ACT_TO_TBL; if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) goto nla_put_failure; if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) goto nla_put_failure; nlmsg_end(skb, nlh); /* fib_nl_{new,del}rule handling looks for net from skb->sk */ skb->sk = dev_net(dev)->rtnl; if (add_it) { err = fib_nl_newrule(skb, nlh, NULL); if (err == -EEXIST) err = 0; } else { err = fib_nl_delrule(skb, nlh, NULL); if (err == -ENOENT) err = 0; } nlmsg_free(skb); return err; nla_put_failure: nlmsg_free(skb); return -EMSGSIZE; } static int vrf_add_fib_rules(const struct net_device *dev) { int err; err = vrf_fib_rule(dev, AF_INET, true); if (err < 0) goto out_err; err = vrf_fib_rule(dev, AF_INET6, true); if (err < 0) goto ipv6_err; #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true); if (err < 0) goto ipmr_err; #endif #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true); if (err < 0) goto ip6mr_err; #endif return 0; #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) ip6mr_err: vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false); #endif #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) ipmr_err: vrf_fib_rule(dev, AF_INET6, false); #endif ipv6_err: vrf_fib_rule(dev, AF_INET, false); out_err: netdev_err(dev, "Failed to add FIB rules.\n"); return err; } static void vrf_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ dev->netns_local = true; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* enable offload features */ dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->hw_features = dev->features; dev->hw_enc_features = dev->features; /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EADDRNOTAVAIL; } } return 0; } static void vrf_dellink(struct net_device *dev, struct list_head *head) { struct net_device *port_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) vrf_del_slave(dev, port_dev); vrf_map_unregister_dev(dev); unregister_netdevice_queue(dev, head); } static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) { NL_SET_ERR_MSG(extack, "VRF table id is missing"); return -EINVAL; } vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); if (vrf->tb_id == RT_TABLE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE], "Invalid VRF table id"); return -EINVAL; } dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err) goto out; /* mapping between table_id and vrf; * note: such binding could not be done in the dev init function * because dev->ifindex id is not available yet. */ vrf->ifindex = dev->ifindex; err = vrf_map_register_dev(dev, extack); if (err) { unregister_netdevice(dev); goto out; } net = dev_net(dev); nn_vrf = net_generic(net, vrf_net_id); add_fib_rules = &nn_vrf->add_fib_rules; if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { vrf_map_unregister_dev(dev); unregister_netdevice(dev); goto out; } *add_fib_rules = false; } out: return err; } static size_t vrf_nl_getsize(const struct net_device *dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ } static int vrf_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); } static size_t vrf_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */ } static int vrf_fill_slave_info(struct sk_buff *skb, const struct net_device *vrf_dev, const struct net_device *slave_dev) { struct net_vrf *vrf = netdev_priv(vrf_dev); if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id)) return -EMSGSIZE; return 0; } static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { [IFLA_VRF_TABLE] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vrf_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct net_vrf), .get_size = vrf_nl_getsize, .policy = vrf_nl_policy, .validate = vrf_validate, .fill_info = vrf_fillinfo, .get_slave_size = vrf_get_slave_size, .fill_slave_info = vrf_fill_slave_info, .newlink = vrf_newlink, .dellink = vrf_dellink, .setup = vrf_setup, .maxtype = IFLA_VRF_MAX, }; static int vrf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); vrf_del_slave(vrf_dev, dev); } out: return NOTIFY_DONE; } static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; static int vrf_map_init(struct vrf_map *vmap) { spin_lock_init(&vmap->vmap_lock); hash_init(vmap->ht); vmap->strict_mode = false; return 0; } #ifdef CONFIG_SYSCTL static bool vrf_strict_mode(struct vrf_map *vmap) { bool strict_mode; vrf_map_lock(vmap); strict_mode = vmap->strict_mode; vrf_map_unlock(vmap); return strict_mode; } static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) { bool *cur_mode; int res = 0; vrf_map_lock(vmap); cur_mode = &vmap->strict_mode; if (*cur_mode == new_mode) goto unlock; if (*cur_mode) { /* disable strict mode */ *cur_mode = false; } else { if (vmap->shared_tables) { /* we cannot allow strict_mode because there are some * vrfs that share one or more tables. */ res = -EBUSY; goto unlock; } /* no tables are shared among vrfs, so we can go back * to 1:1 association between a vrf with its table. */ *cur_mode = true; } unlock: vrf_map_unlock(vmap); return res; } static int vrf_shared_table_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->extra1; struct vrf_map *vmap = netns_vrf_map(net); int proc_strict_mode = 0; struct ctl_table tmp = { .procname = table->procname, .data = &proc_strict_mode, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; int ret; if (!write) proc_strict_mode = vrf_strict_mode(vmap); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode); return ret; } static const struct ctl_table vrf_table[] = { { .procname = "strict_mode", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = vrf_shared_table_handler, /* set by the vrf_netns_init */ .extra1 = NULL, }, }; static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { struct ctl_table *table; table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) return -ENOMEM; /* init the extra1 parameter with the reference to current netns */ table[0].extra1 = net; nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table, ARRAY_SIZE(vrf_table)); if (!nn_vrf->ctl_hdr) { kfree(table); return -ENOMEM; } return 0; } static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); const struct ctl_table *table; table = nn_vrf->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } #else static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { return 0; } static void vrf_netns_exit_sysctl(struct net *net) { } #endif /* Initialize per network namespace state */ static int __net_init vrf_netns_init(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); nn_vrf->add_fib_rules = true; vrf_map_init(&nn_vrf->vmap); return vrf_netns_init_sysctl(net, nn_vrf); } static void __net_exit vrf_netns_exit(struct net *net) { vrf_netns_exit_sysctl(net); } static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .exit = vrf_netns_exit, .id = &vrf_net_id, .size = sizeof(struct netns_vrf), }; static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); if (rc < 0) goto unreg_pernet; rc = rtnl_link_register(&vrf_link_ops); if (rc < 0) goto table_lookup_unreg; return 0; table_lookup_unreg: l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); unreg_pernet: unregister_pernet_subsys(&vrf_net_ops); error: unregister_netdevice_notifier(&vrf_notifier_block); return rc; } module_init(vrf_init_module); MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); MODULE_VERSION(DRV_VERSION); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ static inline void cpu_relax(void) { asm volatile("yield" ::: "memory"); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 91 85 5 2 91 91 91 91 90 91 2 3 3 3 86 76 73 3 3 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Authors: Alex Bennée <alex.bennee@linaro.org> * Oliver Upton <oliver.upton@linux.dev> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { preempt_disable(); /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug registers if the guest doesn't have ownership of them. */ if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; /* Write MDCR_EL2 directly if we're already at EL2 */ if (has_vhe()) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); preempt_enable(); } void kvm_init_host_debug_data(void) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); if (has_vhe()) return; if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) host_data_set_flag(HAS_SPE); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) { /* Force disable trace in protected mode in case of no TRBE */ if (is_protected_kvm_enabled()) host_data_set_flag(EL1_TRACING_CONFIGURED); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) host_data_set_flag(HAS_TRBE); } } /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. * * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. * * - Userspace is using the breakpoint/watchpoint registers to debug the * guest, and MDSCR_EL1.MDE is forced to 1. * * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, * masking all debug exceptions affected by the OS Lock. */ static void setup_external_mdscr(struct kvm_vcpu *vcpu) { /* * Use the guest's MDSCR_EL1 as a starting point, since there are * several other features controlled by MDSCR_EL1 that are not relevant * to the host. * * Clear the bits that KVM may use which also satisfies emulation of * the OS Lock as MDSCR_EL1.MDE is cleared. */ u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | MDSCR_EL1_MDE | MDSCR_EL1_KDE); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) mdscr |= MDSCR_EL1_SS; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; vcpu->arch.external_mdscr_el1 = mdscr; } void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) { u64 mdscr; /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); /* * Determine which of the possible debug states we're in: * * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do * software step or emulate the effects of the OS Lock being enabled. * * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and * the breakpoint/watchpoint registers need to be loaded eagerly. * * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint * context needs to be loaded on the CPU. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; setup_external_mdscr(vcpu); /* * Steal the guest's single-step state machine if userspace wants * single-step the guest. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); else vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; else vcpu->arch.debug_owner = VCPU_DEBUG_FREE; } kvm_arm_setup_mdcr_el2(vcpu); } void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; /* * Save the host's software step state and restore the guest's before * potentially returning to userspace. */ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); else vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; else *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; } /* * Updates ownership of the debug registers after a trapped guest access to a * breakpoint/watchpoint register. Host ownership of the debug registers is of * strictly higher priority, and it is the responsibility of the VMM to emulate * guest debug exceptions in this configuration. */ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) { if (kvm_host_owns_debug_regs(vcpu)) return; vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; kvm_arm_setup_mdcr_el2(vcpu); } void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) { if (val & OSLAR_EL1_OSLK) __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK; else __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK; preempt_disable(); kvm_arch_vcpu_put(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } void kvm_enable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_set_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_enable_trbe); void kvm_disable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_clear_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_disable_trbe); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) { if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; if (has_vhe()) { write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12); return; } *host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest; if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest) host_data_set_flag(EL1_TRACING_CONFIGURED); else host_data_clear_flag(EL1_TRACING_CONFIGURED); } EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration); |
| 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 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 262 262 262 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> #include <linux/rculist.h> #include <linux/nsproxy.h> #include <linux/fs.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> #include <linux/cookie.h> #include <linux/proc_fs.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* * Our network namespace constructor/destructor lists */ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); /* Protects net_namespace_list. Nests iside rtnl_lock() */ DECLARE_RWSEM(net_rwsem); EXPORT_SYMBOL_GPL(net_rwsem); #ifdef CONFIG_KEYS static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif struct net init_net; EXPORT_SYMBOL(init_net); static bool init_net_initialized; /* * pernet_ops_rwsem: protects: pernet_list, net_generic_ids, * init_net_initialized and first_device pointer. * This is internal net namespace object. Please, don't use it * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; DEFINE_COOKIE(net_cookie); static struct net_generic *net_alloc_generic(void) { unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); unsigned int generic_size; struct net_generic *ng; generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) ng->s.len = gen_ptrs; return ng; } static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; } ng = net_alloc_generic(); if (!ng) return -ENOMEM; /* * Some synchronisation notes: * * The net_generic explores the net->gen array inside rcu * read section. Besides once set the net->gen->ptr[x] * pointer never changes (see rules in netns/generic.h). * * That said, we simply duplicate this array and schedule * the old copy for kfree after a grace period. */ memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID], (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *)); ng->ptr[id] = data; rcu_assign_pointer(net->gen, ng); kfree_rcu(old_ng, s.rcu); return 0; } static int ops_init(const struct pernet_operations *ops, struct net *net) { struct net_generic *ng; int err = -ENOMEM; void *data = NULL; if (ops->id) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; err = net_assign_generic(net, *ops->id, data); if (err) goto cleanup; } err = 0; if (ops->init) err = ops->init(net); if (!err) return 0; if (ops->id) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } cleanup: kfree(data); out: return err; } static void ops_pre_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->pre_exit) { list_for_each_entry(net, net_exit_list, exit_list) ops->pre_exit(net); } } static void ops_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->exit) { list_for_each_entry(net, net_exit_list, exit_list) { ops->exit(net); cond_resched(); } } if (ops->exit_batch) ops->exit_batch(net_exit_list); } static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } } /* should be called with nsid_lock held */ static int alloc_netid(struct net *net, struct net *peer, int reqid) { int min = 0, max = 0; if (reqid >= 0) { min = reqid; max = reqid + 1; } return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); } /* This function is used by idr_for_each(). If net is equal to peer, the * function returns the id so that idr_for_each() stops. Because we cannot * returns the id 0 (idr_for_each() will not stop), we return the magic value * NET_ID_ZERO (-1) for it. */ #define NET_ID_ZERO -1 static int net_eq_idr(int id, void *net, void *peer) { if (net_eq(net, peer)) return id ? : NET_ID_ZERO; return 0; } /* Must be called from RCU-critical section or with nsid_lock held */ static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); /* Magic value for id 0. */ if (id == NET_ID_ZERO) return 0; if (id > 0) return id; return NETNSA_NSID_NOT_ASSIGNED; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { int id; if (refcount_read(&net->ns.count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { spin_unlock_bh(&net->nsid_lock); return id; } /* When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) return NETNSA_NSID_NOT_ASSIGNED; rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(const struct net *net, struct net *peer) { int id; rcu_read_lock(); id = __peernet2id(net, peer); rcu_read_unlock(); return id; } EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ bool peernet_has_id(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } struct net *get_net_ns_by_id(const struct net *net, int id) { struct net *peer; if (id < 0) return NULL; rcu_read_lock(); peer = idr_find(&net->netns_ids, id); if (peer) peer = maybe_get_net(peer); rcu_read_unlock(); return peer; } EXPORT_SYMBOL_GPL(get_net_ns_by_id); static __net_init void preinit_net_sysctl(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; /* Limits per socket sk_omem_alloc usage. * TCP zerocopy regular usage needs 128 KB. */ net->core.sysctl_optmem_max = 128 * 1024; net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; net->core.sysctl_tstamp_allow_data = 1; } /* init code that must occur even if setup_net() is not called. */ static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) { refcount_set(&net->passive, 1); refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); spin_lock_init(&net->nsid_lock); mutex_init(&net->ipv4.ra_mutex); #ifdef CONFIG_DEBUG_NET_SMALL_RTNL mutex_init(&net->rtnl_mutex); lock_set_cmp_fn(&net->rtnl_mutex, rtnl_net_lock_cmp_fn, NULL); #endif preinit_net_sysctl(net); } /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); int error = 0; preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) goto out_undo; } down_write(&net_rwsem); list_add_tail_rcu(&net->list, &net_namespace_list); up_write(&net_rwsem); out: return error; out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ list_add(&net->exit_list, &net_exit_list); saved_ops = ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops = saved_ops; rtnl_lock(); list_for_each_entry_continue_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; } #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES); } static void dec_net_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) { struct net *net = NULL; struct net_generic *ng; ng = net_alloc_generic(); if (!ng) goto out; net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); if (!net) goto out_free; #ifdef CONFIG_KEYS net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL); if (!net->key_domain) goto out_free_2; refcount_set(&net->key_domain->usage, 1); #endif rcu_assign_pointer(net->gen, ng); out: return net; #ifdef CONFIG_KEYS out_free_2: kmem_cache_free(net_cachep, net); net = NULL; #endif out_free: kfree(ng); goto out; } static LLIST_HEAD(defer_free_list); static void net_complete_free(void) { struct llist_node *kill_list; struct net *net, *next; /* Get the list of namespaces to free from last round. */ kill_list = llist_del_all(&defer_free_list); llist_for_each_entry_safe(net, next, kill_list, defer_free_list) kmem_cache_free(net_cachep, net); } static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); /* There should not be any trackers left there. */ ref_tracker_dir_exit(&net->notrefcnt_tracker); /* Wait for an extra rcu_barrier() before final free. */ llist_add(&net->defer_free_list, &defer_free_list); } } void net_drop_ns(void *p) { struct net *net = (struct net *)p; if (net) net_free(net); } struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { struct ucounts *ucounts; struct net *net; int rv; if (!(flags & CLONE_NEWNET)) return get_net(old_net); ucounts = inc_net_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); net = net_alloc(); if (!net) { rv = -ENOMEM; goto dec_ucounts; } preinit_net(net, user_ns); net->ucounts = ucounts; get_user_ns(user_ns); rv = down_read_killable(&pernet_ops_rwsem); if (rv < 0) goto put_userns; rv = setup_net(net); up_read(&pernet_ops_rwsem); if (rv < 0) { put_userns: #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); net_free(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; } /** * net_ns_get_ownership - get sysfs ownership data for @net * @net: network namespace in question (can be NULL) * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns the uid/gid pair of root in the user namespace associated with the * given network namespace. */ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { if (net) { kuid_t ns_root_uid = make_kuid(net->user_ns, 0); kgid_t ns_root_gid = make_kgid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } else { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } } EXPORT_SYMBOL_GPL(net_ns_get_ownership); static void unhash_nsid(struct net *net, struct net *last) { struct net *tmp; /* This function is only called from cleanup_net() work, * and this work is the only process, that may delete * a net from net_namespace_list. So, when the below * is executing, the list may only grow. Thus, we do not * use for_each_net_rcu() or net_rwsem. */ for_each_net(tmp) { int id; spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); struct task_struct *cleanup_net_task; static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); cleanup_net_task = current; /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); down_read(&pernet_ops_rwsem); /* Don't let anyone else find us. */ down_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer * to a net from net_kill_list (see peernet2id_alloc()). * So, we skip them in unhash_nsid(). * * Note, that unhash_nsid() does not delete nsid links * between net_kill_list's nets, as they've already * deleted from net_namespace_list. But, this would be * useless anyway, as netns_ids are destroyed there. */ last = list_last_entry(&net_namespace_list, struct net, list); up_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } /* Run all of the network namespace pre_exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); /* * Another CPU might be rcu-iterating the list, wait for it. * This needs to be before calling the exit() notifiers, so * the rcu_barrier() below isn't sufficient alone. * Also the pre_exit() and exit() methods need this barrier. */ synchronize_rcu_expedited(); rtnl_lock(); list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); /* Free the net generic variables */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); up_read(&pernet_ops_rwsem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. */ rcu_barrier(); net_complete_free(); /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); net_free(net); } cleanup_net_task = NULL; } /** * net_ns_barrier - wait until concurrent net_cleanup_work is done * * cleanup_net runs from work queue and will first remove namespaces * from the global list, then run net exit functions. * * Call this in module exit path to make sure that all netns * ->exit ops have been invoked before the function is removed. */ void net_ns_barrier(void) { down_write(&pernet_ops_rwsem); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL(net_ns_barrier); static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { ref_tracker_dir_exit(&net->refcnt_tracker); /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); /** * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { struct net *net; net = maybe_get_net(container_of(ns, struct net, ns)); if (net) return &net->ns; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); struct net *get_net_ns_by_fd(int fd) { CLASS(fd, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); if (proc_ns_file(fd_file(f))) { struct ns_common *ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops == &netns_operations) return get_net(container_of(ns, struct net, ns)); } return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns_by_fd); #endif struct net *get_net_ns_by_pid(pid_t pid) { struct task_struct *tsk; struct net *net; /* Lookup the network namespace */ net = ERR_PTR(-ESRCH); rcu_read_lock(); tsk = find_task_by_vpid(pid); if (tsk) { struct nsproxy *nsproxy; task_lock(tsk); nsproxy = tsk->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(tsk); } rcu_read_unlock(); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); static __net_init int net_ns_net_init(struct net *net) { #ifdef CONFIG_NET_NS net->ns.ops = &netns_operations; #endif return ns_alloc_inum(&net->ns); } static __net_exit void net_ns_net_exit(struct net *net) { ns_free_inum(&net->ns); } static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { [NETNSA_NONE] = { .type = NLA_UNSPEC }, [NETNSA_NSID] = { .type = NLA_S32 }, [NETNSA_PID] = { .type = NLA_U32 }, [NETNSA_FD] = { .type = NLA_U32 }, [NETNSA_TARGET_NSID] = { .type = NLA_S32 }, }; static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct nlattr *nla; struct net *peer; int nsid, err; err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; if (!tb[NETNSA_NSID]) { NL_SET_ERR_MSG(extack, "nsid is missing"); return -EINVAL; } nsid = nla_get_s32(tb[NETNSA_NSID]); if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns already has a nsid assigned"); goto out; } err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); NL_SET_ERR_MSG(extack, "The specified nsid is already used"); } out: put_net(peer); return err; } static int rtnl_net_get_size(void) { return NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(sizeof(s32)) /* NETNSA_NSID */ + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */ ; } struct net_fill_args { u32 portid; u32 seq; int flags; int cmd; int nsid; bool add_ref; int ref_nsid; }; static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args) { struct nlmsghdr *nlh; struct rtgenmsg *rth; nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth), args->flags); if (!nlh) return -EMSGSIZE; rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; if (nla_put_s32(skb, NETNSA_NSID, args->nsid)) goto nla_put_failure; if (args->add_ref && nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int rtnl_net_valid_getid_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETNSA_PID: case NETNSA_FD: case NETNSA_NSID: case NETNSA_TARGET_NSID: break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); return -EINVAL; } } return 0; } static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct net_fill_args fillargs = { .portid = NETLINK_CB(skb).portid, .seq = nlh->nlmsg_seq, .cmd = RTM_NEWNSID, }; struct net *peer, *target = net; struct nlattr *nla; struct sk_buff *msg; int err; err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); if (err < 0) return err; if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else if (tb[NETNSA_NSID]) { peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID])); if (!peer) peer = ERR_PTR(-ENOENT); nla = tb[NETNSA_NSID]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } if (tb[NETNSA_TARGET_NSID]) { int id = nla_get_s32(tb[NETNSA_TARGET_NSID]); target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id); if (IS_ERR(target)) { NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]); NL_SET_ERR_MSG(extack, "Target netns reference is invalid"); err = PTR_ERR(target); goto out; } fillargs.add_ref = true; fillargs.ref_nsid = peernet2id(net, peer); } msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out; } fillargs.nsid = peernet2id(target, peer); err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid); goto out; err_out: nlmsg_free(msg); out: if (fillargs.add_ref) put_net(target); put_net(peer); return err; } struct rtnl_net_dump_cb { struct net *tgt_net; struct net *ref_net; struct sk_buff *skb; struct net_fill_args fillargs; int idx; int s_idx; }; /* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; int ret; if (net_cb->idx < net_cb->s_idx) goto cont; net_cb->fillargs.nsid = id; if (net_cb->fillargs.add_ref) net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer); ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs); if (ret < 0) return ret; cont: net_cb->idx++; return 0; } static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk, struct rtnl_net_dump_cb *net_cb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NETNSA_MAX + 1]; int err, i; err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; if (i == NETNSA_TARGET_NSID) { struct net *net; net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i])); if (IS_ERR(net)) { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Invalid target network namespace id"); return PTR_ERR(net); } net_cb->fillargs.add_ref = true; net_cb->ref_net = net_cb->tgt_net; net_cb->tgt_net = net; } else { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) { struct rtnl_net_dump_cb net_cb = { .tgt_net = sock_net(skb->sk), .skb = skb, .fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .cmd = RTM_NEWNSID, }, .idx = 0, .s_idx = cb->args[0], }; int err = 0; if (cb->strict_check) { err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb); if (err < 0) goto end; } rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); rcu_read_unlock(); cb->args[0] = net_cb.idx; end: if (net_cb.fillargs.add_ref) put_net(net_cb.tgt_net); return err; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; struct sk_buff *msg; int err = -ENOMEM; msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: nlmsg_free(msg); out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } #ifdef CONFIG_NET_NS static void __init netns_ipv4_struct_check(void) { /* TX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_early_retrans); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_win_divisor); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_rtt_log); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_autocorking); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_snd_mss); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_limit_output_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_rtt_wlen); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_wmem); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_ip_fwd_use_pmtu); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); /* TXRX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, sysctl_tcp_moderate_rcvbuf); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); /* RX readonly hotpath cache line */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_ip_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_l3mdev_accept); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_rmem); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 22); } #endif static const struct rtnl_msg_handler net_ns_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNSID, .doit = rtnl_net_newid, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.msgtype = RTM_GETNSID, .doit = rtnl_net_getid, .dumpit = rtnl_net_dumpid, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; void __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS netns_ipv4_struct_check(); net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Create workqueue for cleanup */ netns_wq = create_singlethread_workqueue("netns"); if (!netns_wq) panic("Could not create netns workq"); #endif ng = net_alloc_generic(); if (!ng) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif preinit_net(&init_net, &init_user_ns); down_write(&pernet_ops_rwsem); if (setup_net(&init_net)) panic("Could not setup the initial network namespace"); init_net_initialized = true; up_write(&pernet_ops_rwsem); if (register_pernet_subsys(&net_ns_ops)) panic("Could not register network namespace subsystems"); rtnl_register_many(net_ns_rtnl_msg_handlers); } static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); synchronize_rcu(); if (ops->exit_batch_rtnl) { LIST_HEAD(dev_kill_list); rtnl_lock(); ops->exit_batch_rtnl(net_exit_list, &dev_kill_list); unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } ops_exit_list(ops, net_exit_list); ops_free_list(ops, net_exit_list); } #ifdef CONFIG_NET_NS static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { struct net *net; int error; LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); if (ops->init || ops->id) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { error = ops_init(ops, net); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); } } return 0; out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); free_exit_list(ops, &net_exit_list); return error; } static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; LIST_HEAD(net_exit_list); list_del(&ops->list); /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } #else static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { if (!init_net_initialized) { list_add_tail(&ops->list, list); return 0; } return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) { if (!init_net_initialized) { list_del(&ops->list); } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } } #endif /* CONFIG_NET_NS */ static DEFINE_IDA(net_generic_ids); static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { int error; if (WARN_ON(!!ops->id ^ !!ops->size)) return -EINVAL; if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); if (error < 0) return error; *ops->id = error; /* This does not require READ_ONCE as writers already hold * pernet_ops_rwsem. But WRITE_ONCE is needed to protect * net_alloc_generic. */ WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem * * Register a subsystem which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_subsys(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(first_device, ops); up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); /** * unregister_pernet_subsys - unregister a network namespace subsystem * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_subsys(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem * * Register a device which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_device(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_device(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); #ifdef CONFIG_NET_NS static struct ns_common *netns_get(struct task_struct *task) { struct net *net = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(task); return net ? &net->ns : NULL; } static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } static void netns_put(struct ns_common *ns) { put_net(to_net_ns(ns)); } static int netns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct net *net = to_net_ns(ns); if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_net(nsproxy->net_ns); nsproxy->net_ns = get_net(net); return 0; } static struct user_namespace *netns_owner(struct ns_common *ns) { return to_net_ns(ns)->user_ns; } const struct proc_ns_operations netns_operations = { .name = "net", .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, .owner = netns_owner, }; #endif |
| 5 5 5 | 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 | /* 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> #include <linux/uaccess.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 struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } /* * This does a plain atomic user space read, and the user pointer has * already been verified earlier by get_futex_key() to be both aligned * and actually in user space, just like futex_atomic_cmpxchg_inatomic(). * * We still want to avoid any speculation, and while __get_user() is * the traditional model for this, it's actually slower than doing * this manually these days. * * We could just have a per-architecture special function for it, * the same way we do futex_atomic_cmpxchg_inatomic(), but rather * than force everybody to do that, write it out long-hand using * the low-level user-access infrastructure. * * This looks a bit overkill, but generally just results in a couple * of instructions. */ static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from) { u32 val; if (can_do_masked_user_access()) from = masked_user_access_begin(from); else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(val, from, Efault); user_read_access_end(); *dest = val; return 0; Efault: user_read_access_end(); return -EFAULT; } static inline int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = futex_read_inatomic(dest, from); pagefault_enable(); return ret; } extern void __futex_unqueue(struct futex_q *q); extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task); 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 * @task: Task queueing this futex * * 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). * * Note that @task may be NULL, for async usage of futexes. */ static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) __releases(&hb->lock) { __futex_queue(q, hb, task); 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 */ |
| 1 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Operations on the network namespace */ #ifndef __NET_NET_NAMESPACE_H #define __NET_NET_NAMESPACE_H #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/sysctl.h> #include <linux/uidgid.h> #include <net/flow.h> #include <net/netns/core.h> #include <net/netns/mib.h> #include <net/netns/unix.h> #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> #include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) #include <net/netns/flow_table.h> #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> #include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> #include <linux/notifier.h> #include <linux/xarray.h> struct user_namespace; struct proc_dir_entry; struct net_device; struct sock; struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; struct bpf_prog; #define NETDEV_HASHBITS 8 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { /* First cache line can be often dirtied. * Do not place here read-mostly fields. */ refcount_t passive; /* To decide when the network * namespace should be freed. */ spinlock_t rules_mod_lock; unsigned int dev_base_seq; /* protected by rtnl_mutex */ u32 ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit * methods on dead net ( * pernet_ops_rwsem read locked), * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; struct idr netns_ids; struct ns_common ns; struct ref_tracker_dir refcnt_tracker; struct ref_tracker_dir notrefcnt_tracker; /* tracker for objects not * refcounted against netns */ struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; #ifdef CONFIG_SYSCTL struct ctl_table_set sysctls; #endif struct sock *rtnl; /* rtnetlink socket */ struct sock *genl_sock; struct uevent_sock *uevent_sock; /* uevent socket */ struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; struct xarray dev_by_index; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; struct netns_core core; struct netns_mib mib; struct netns_packet packet; #if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; #endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct netns_ieee802154_lowpan ieee802154_lowpan; #endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif #if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) struct netns_nftables nft; #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) struct netns_ft ft; #endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic __rcu *gen; /* Used to store attached BPF programs */ struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif #if IS_ENABLED(CONFIG_MPLS) struct netns_mpls mpls; #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; #endif #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif #if IS_ENABLED(CONFIG_MCTP) struct netns_mctp mctp; #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif #ifdef CONFIG_DEBUG_NET_SMALL_RTNL /* Move to a better place when the config guard is removed. */ struct mutex rtnl_mutex; #endif } __randomize_layout; #include <linux/seq_file_net.h> /* Init's network namespace */ extern struct net init_net; #ifdef CONFIG_NET_NS struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); extern struct task_struct *cleanup_net_task; #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> static inline struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) return ERR_PTR(-EINVAL); return old_net; } static inline void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } static inline void net_ns_barrier(void) {} static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } static inline struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); #else #define ipx_register_sysctl() #define ipx_unregister_sysctl() #endif #ifdef CONFIG_NET_NS void __put_net(struct net *net); /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); return net; } static inline struct net *maybe_get_net(struct net *net) { /* Used when we know struct net exists but we * aren't guaranteed a previous reference count * exists. If the reference count is zero this * function fails and returns NULL. */ if (!refcount_inc_not_zero(&net->ns.count)) net = NULL; return net; } /* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) __put_net(net); } static inline int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } static inline int check_net(const struct net *net) { return refcount_read(&net->ns.count) != 0; } void net_drop_ns(void *); #else static inline struct net *get_net(struct net *net) { return net; } static inline void put_net(struct net *net) { } static inline struct net *maybe_get_net(struct net *net) { return net; } static inline int net_eq(const struct net *net1, const struct net *net2) { return 1; } static inline int check_net(const struct net *net) { return 1; } #define net_drop_ns NULL #endif /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { return READ_ONCE(net->list.next); } static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, bool refcounted, gfp_t gfp) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_alloc(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker, gfp); #endif } static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, gfp_t gfp) { __netns_tracker_alloc(net, tracker, true, gfp); } static inline void __netns_tracker_free(struct net *net, netns_tracker *tracker, bool refcounted) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_free(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker); #endif } static inline struct net *get_net_track(struct net *net, netns_tracker *tracker, gfp_t gfp) { get_net(net); netns_tracker_alloc(net, tracker, gfp); return net; } static inline void put_net_track(struct net *net, netns_tracker *tracker) { __netns_tracker_free(net, tracker, true); put_net(net); } typedef struct { #ifdef CONFIG_NET_NS struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference_protected(pnet->net, true); #else return &init_net; #endif } static inline struct net *read_pnet_rcu(possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); #else return &init_net; #endif } /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) #define for_each_net_continue_reverse(VAR) \ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit #define __net_initdata #define __net_initconst #else #define __net_init __init #define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(const struct net *net, struct net *peer); bool peernet_has_id(const struct net *net, struct net *peer); struct net *get_net_ns_by_id(const struct net *net, int id); struct pernet_operations { struct list_head list; /* * Below methods are called without any exclusive locks. * More than one net may be constructed and destructed * in parallel on several cpus. Every pernet_operations * have to keep in mind all other pernet_operations and * to introduce a locking, if they share common resources. * * The only time they are called with exclusive lock is * from register_pernet_subsys(), unregister_pernet_subsys() * register_pernet_device() and unregister_pernet_device(). * * Exit methods using blocking RCU primitives, such as * synchronize_rcu(), should be implemented via exit_batch. * Then, destruction of a group of net requires single * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. * * Note that a combination of pre_exit() and exit() can * be used, since a synchronize_rcu() is guaranteed between * the calls. */ int (*init)(struct net *net); void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); unsigned int * const id; const size_t size; }; /* * Use these carefully. If you implement a network device and it * needs per network namespace operations use device pernet operations, * otherwise use pernet subsys operations. * * Network interfaces need to be removed from a dying netns _before_ * subsys notifiers can be called, as most of the network code cleanup * (which is done from subsys notifiers) runs with the assumption that * dev_remove_pack has been called so no new packets will arrive during * and after the cleanup functions have been called. dev_remove_pack * is not per namespace so instead the guarantee of no more packets * arriving in a network namespace is provided by ensuring that all * network devices and all sockets have left the network namespace * before the cleanup methods are called. * * For the longest time the ipv4 icmp code was registered as a pernet * device which caused kernel oops, and panics during network * namespace cleanup. So please don't get this wrong. */ int register_pernet_subsys(struct pernet_operations *); void unregister_pernet_subsys(struct pernet_operations *); int register_pernet_device(struct pernet_operations *); void unregister_pernet_device(struct pernet_operations *); struct ctl_table; #define register_net_sysctl(net, path, table) \ register_net_sysctl_sz(net, path, table, ARRAY_SIZE(table)) #ifdef CONFIG_SYSCTL int net_sysctl_init(void); struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size); void unregister_net_sysctl_table(struct ctl_table_header *header); #else static inline int net_sysctl_init(void) { return 0; } static inline struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { return NULL; } static inline void unregister_net_sysctl_table(struct ctl_table_header *header) { } #endif static inline int rt_genid_ipv4(const struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #if IS_ENABLED(CONFIG_IPV6) static inline int rt_genid_ipv6(const struct net *net) { return atomic_read(&net->ipv6.fib6_sernum); } #endif static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); } extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { if (__fib6_flush_trees) __fib6_flush_trees(net); } #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * net_ieee802154_lowpan(struct net *net) { return &net->ieee802154_lowpan; } #endif /* For callers who don't really care about whether it's IPv4 or IPv6 */ static inline void rt_genid_bump_all(struct net *net) { rt_genid_bump_ipv4(net); rt_genid_bump_ipv6(net); } static inline int fnhe_genid(const struct net *net) { return atomic_read(&net->fnhe_genid); } static inline void fnhe_genid_bump(struct net *net) { atomic_inc(&net->fnhe_genid); } #ifdef CONFIG_NET void net_ns_init(void); #else static inline void net_ns_init(void) {} #endif #endif /* __NET_NET_NAMESPACE_H */ |
| 239 67 67 136 239 57 209 238 239 238 239 210 137 208 209 137 137 209 179 137 209 209 57 209 210 209 138 137 137 137 137 137 210 209 57 57 57 138 138 36 36 272 18 344 345 387 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment on MAX_NR_TIERS */ return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); if (!(flags & BIT(PG_referenced))) return 0; /* * Return the total number of accesses including PG_referenced. Also see * the comment on LRU_REFS_FLAGS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ * | Accessed through page tables and | Accessed through file descriptors | * | promoted by folio_update_gen() | and protected by folio_inc_gen() | * +-----------------------------------+-----------------------------------+ * | PG_active (set while isolated) | | * +-----------------+-----------------+-----------------+-----------------+ * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | * +-----------------------------------+-----------------------------------+ * |<---------- MIN_NR_GENS ---------->| | * |<---------------------------- MAX_NR_GENS ---------------------------->| */ if (folio_test_active(folio)) gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming) gen = MAX_NR_GENS; else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) gen = MIN_NR_GENS; else gen = MAX_NR_GENS - folio_test_workingset(folio); return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * Returns true if an uffd-wp pte was installed, false otherwise. */ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } #endif return false; } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 41 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 49 49 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/ptrace.c * * By Ross Biro 1/23/92 * edited by Linus Torvalds * ARM modifications Copyright (C) 2000 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/audit.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/nospec.h> #include <linux/smp.h> #include <linux/ptrace.h> #include <linux/user.h> #include <linux/seccomp.h> #include <linux/security.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/regset.h> #include <linux/elf.h> #include <linux/rseq.h> #include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/gcs.h> #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> #include <asm/syscall.h> #include <asm/traps.h> #include <asm/system_misc.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> struct pt_regs_offset { const char *name; int offset; }; #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} #define REG_OFFSET_END {.name = NULL, .offset = 0} #define GPR_OFFSET_NAME(r) \ {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])} static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), GPR_OFFSET_NAME(2), GPR_OFFSET_NAME(3), GPR_OFFSET_NAME(4), GPR_OFFSET_NAME(5), GPR_OFFSET_NAME(6), GPR_OFFSET_NAME(7), GPR_OFFSET_NAME(8), GPR_OFFSET_NAME(9), GPR_OFFSET_NAME(10), GPR_OFFSET_NAME(11), GPR_OFFSET_NAME(12), GPR_OFFSET_NAME(13), GPR_OFFSET_NAME(14), GPR_OFFSET_NAME(15), GPR_OFFSET_NAME(16), GPR_OFFSET_NAME(17), GPR_OFFSET_NAME(18), GPR_OFFSET_NAME(19), GPR_OFFSET_NAME(20), GPR_OFFSET_NAME(21), GPR_OFFSET_NAME(22), GPR_OFFSET_NAME(23), GPR_OFFSET_NAME(24), GPR_OFFSET_NAME(25), GPR_OFFSET_NAME(26), GPR_OFFSET_NAME(27), GPR_OFFSET_NAME(28), GPR_OFFSET_NAME(29), GPR_OFFSET_NAME(30), {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])}, REG_OFFSET_NAME(sp), REG_OFFSET_NAME(pc), REG_OFFSET_NAME(pstate), REG_OFFSET_END, }; /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register * * regs_query_register_offset() returns the offset of a register in struct * pt_regs from its name. If the name is invalid, this returns -EINVAL; */ int regs_query_register_offset(const char *name) { const struct pt_regs_offset *roff; for (roff = regoffset_table; roff->name != NULL; roff++) if (!strcmp(roff->name, name)) return roff->offset; return -EINVAL; } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || on_irq_stack(addr, sizeof(unsigned long)); } /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack, * this returns 0. */ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return *addr; else return 0; } /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ /* * Called by kernel/ptrace.c when detaching.. */ void ptrace_disable(struct task_struct *child) { /* * This would be better off in core code, but PTRACE_DETACH has * grown its fair share of arch-specific worts and changing it * is likely to cause regressions on obscure architectures. */ user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Handle hitting a HW-breakpoint. */ static void ptrace_hbptriggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; if (is_compat_task()) { int si_errno = 0; int i; for (i = 0; i < ARM_MAX_BRP; ++i) { if (current->thread.debug.hbp_break[i] == bp) { si_errno = (i << 1) + 1; break; } } for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { si_errno = -((i << 1) + 1); break; } } arm64_force_sig_ptrace_errno_trap(si_errno, bkpt->trigger, desc); return; } arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } /* * Unregister breakpoints from this task and reset the pointers in * the thread_struct. */ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) { int i; struct thread_struct *t = &tsk->thread; for (i = 0; i < ARM_MAX_BRP; i++) { if (t->debug.hbp_break[i]) { unregister_hw_breakpoint(t->debug.hbp_break[i]); t->debug.hbp_break[i] = NULL; } } for (i = 0; i < ARM_MAX_WRP; i++) { if (t->debug.hbp_watch[i]) { unregister_hw_breakpoint(t->debug.hbp_watch[i]); t->debug.hbp_watch[i] = NULL; } } } void ptrace_hw_copy_thread(struct task_struct *tsk) { memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); } static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ERR_PTR(-EINVAL); switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); bp = tsk->thread.debug.hbp_break[idx]; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); bp = tsk->thread.debug.hbp_watch[idx]; break; } out: return bp; } static int ptrace_hbp_set_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx, struct perf_event *bp) { int err = -EINVAL; switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); tsk->thread.debug.hbp_break[idx] = bp; err = 0; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); tsk->thread.debug.hbp_watch[idx] = bp; err = 0; break; } out: return err; } static struct perf_event *ptrace_hbp_create(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp; struct perf_event_attr attr; int err, type; switch (note_type) { case NT_ARM_HW_BREAK: type = HW_BREAKPOINT_X; break; case NT_ARM_HW_WATCH: type = HW_BREAKPOINT_RW; break; default: return ERR_PTR(-EINVAL); } ptrace_breakpoint_init(&attr); /* * Initialise fields to sane defaults * (i.e. values that will pass validation). */ attr.bp_addr = 0; attr.bp_len = HW_BREAKPOINT_LEN_4; attr.bp_type = type; attr.disabled = 1; bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); if (IS_ERR(bp)) return bp; err = ptrace_hbp_set_event(note_type, tsk, idx, bp); if (err) return ERR_PTR(err); return bp; } static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { int err, len, type, offset, disabled = !ctrl.enabled; attr->disabled = disabled; if (disabled) return 0; err = arch_bp_generic_fields(ctrl, &len, &type, &offset); if (err) return err; switch (note_type) { case NT_ARM_HW_BREAK: if ((type & HW_BREAKPOINT_X) != type) return -EINVAL; break; case NT_ARM_HW_WATCH: if ((type & HW_BREAKPOINT_RW) != type) return -EINVAL; break; default: return -EINVAL; } attr->bp_len = len; attr->bp_type = type; attr->bp_addr += offset; return 0; } static int ptrace_hbp_get_resource_info(unsigned int note_type, u32 *info) { u8 num; u32 reg = 0; switch (note_type) { case NT_ARM_HW_BREAK: num = hw_breakpoint_slots(TYPE_INST); break; case NT_ARM_HW_WATCH: num = hw_breakpoint_slots(TYPE_DATA); break; default: return -EINVAL; } reg |= debug_monitors_arch(); reg <<= 8; reg |= num; *info = reg; return 0; } static int ptrace_hbp_get_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 *ctrl) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; return 0; } static int ptrace_hbp_get_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 *addr) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *addr = bp ? counter_arch_bp(bp)->address : 0; return 0; } static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (!bp) bp = ptrace_hbp_create(note_type, tsk, idx); return bp; } static int ptrace_hbp_set_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 uctrl) { int err; struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; decode_ctrl_reg(uctrl, &ctrl); err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); if (err) return err; return modify_user_hw_breakpoint(bp, &attr); } static int ptrace_hbp_set_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 addr) { int err; struct perf_event *bp; struct perf_event_attr attr; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); return err; } #define PTRACE_HBP_ADDR_SZ sizeof(u64) #define PTRACE_HBP_CTRL_SZ sizeof(u32) #define PTRACE_HBP_PAD_SZ sizeof(u32) static int hw_break_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { unsigned int note_type = regset->core_note_type; int ret, idx = 0; u32 info, ctrl; u64 addr; /* Resource info */ ret = ptrace_hbp_get_resource_info(note_type, &info); if (ret) return ret; membuf_write(&to, &info, sizeof(info)); membuf_zero(&to, sizeof(u32)); /* (address, ctrl) registers */ while (to.left) { ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); if (ret) return ret; ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); if (ret) return ret; membuf_store(&to, addr); membuf_store(&to, ctrl); membuf_zero(&to, sizeof(u32)); idx++; } return 0; } static int hw_break_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { unsigned int note_type = regset->core_note_type; int ret, idx = 0, offset, limit; u32 ctrl; u64 addr; /* Resource info and pad */ offset = offsetof(struct user_hwdebug_state, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, ctrl) registers */ limit = regset->n * regset->size; while (count && offset < limit) { if (count < PTRACE_HBP_ADDR_SZ) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, offset, offset + PTRACE_HBP_ADDR_SZ); if (ret) return ret; ret = ptrace_hbp_set_addr(note_type, target, idx, addr); if (ret) return ret; offset += PTRACE_HBP_ADDR_SZ; if (!count) break; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, offset, offset + PTRACE_HBP_CTRL_SZ); if (ret) return ret; ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); if (ret) return ret; offset += PTRACE_HBP_CTRL_SZ; user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, offset, offset + PTRACE_HBP_PAD_SZ); offset += PTRACE_HBP_PAD_SZ; idx++; } return 0; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ static int gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_pt_regs *uregs = &task_pt_regs(target)->user_regs; return membuf_write(&to, uregs, sizeof(*uregs)); } static int gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_pt_regs newregs = task_pt_regs(target)->user_regs; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1); if (ret) return ret; if (!valid_user_regs(&newregs, target)) return -EINVAL; task_pt_regs(target)->user_regs = newregs; return 0; } static int fpr_active(struct task_struct *target, const struct user_regset *regset) { if (!system_supports_fpsimd()) return -ENODEV; return regset->n; } /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ static int __fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; sve_sync_to_fpsimd(target); uregs = &target->thread.uw.fpsimd_state; return membuf_write(&to, uregs, sizeof(*uregs)); } static int fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpsimd()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return __fpr_get(target, regset, to); } static int __fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, unsigned int start_pos) { int ret; struct user_fpsimd_state newstate; /* * Ensure target->thread.uw.fpsimd_state is up to date, so that a * short copyin can't resurrect stale data. */ sve_sync_to_fpsimd(target); newstate = target->thread.uw.fpsimd_state; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, start_pos, start_pos + sizeof(newstate)); if (ret) return ret; target->thread.uw.fpsimd_state = newstate; return ret; } static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_fpsimd()) return -EINVAL; ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; sve_sync_from_fpsimd_zeropad(target); fpsimd_flush_task_state(target); return ret; } static int tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int ret; if (target == current) tls_preserve_current_state(); ret = membuf_store(&to, target->thread.uw.tp_value); if (system_supports_tpidr2()) ret = membuf_store(&to, target->thread.tpidr2_el0); else ret = membuf_zero(&to, sizeof(u64)); return ret; } static int tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long tls[2]; tls[0] = target->thread.uw.tp_value; if (system_supports_tpidr2()) tls[1] = target->thread.tpidr2_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count); if (ret) return ret; target->thread.uw.tp_value = tls[0]; if (system_supports_tpidr2()) target->thread.tpidr2_el0 = tls[1]; return ret; } static int fpmr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpmr()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return membuf_store(&to, target->thread.uw.fpmr); } static int fpmr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long fpmr; if (!system_supports_fpmr()) return -EINVAL; fpmr = target->thread.uw.fpmr; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); if (ret) return ret; target->thread.uw.fpmr = fpmr; fpsimd_flush_task_state(target); return 0; } static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, task_pt_regs(target)->syscallno); } static int system_call_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int syscallno = task_pt_regs(target)->syscallno; int ret; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1); if (ret) return ret; task_pt_regs(target)->syscallno = syscallno; return ret; } #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, struct task_struct *target, enum vec_type type) { unsigned int vq; bool active; enum vec_type task_type; memset(header, 0, sizeof(*header)); /* Check if the requested registers are active for the task */ if (thread_sm_enabled(&target->thread)) task_type = ARM64_VEC_SME; else task_type = ARM64_VEC_SVE; active = (task_type == type); switch (type) { case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; default: WARN_ON_ONCE(1); return; } if (active) { if (target->thread.fp_type == FP_STATE_FPSIMD) { header->flags |= SVE_PT_REGS_FPSIMD; } else { header->flags |= SVE_PT_REGS_SVE; } } header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); } static unsigned int sve_size_from_header(struct user_sve_header const *header) { return ALIGN(header->size, SVE_VQ_BYTES); } static int sve_get_common(struct task_struct *target, const struct user_regset *regset, struct membuf to, enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; /* Header */ sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); if (target == current) fpsimd_preserve_current_state(); BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); switch ((header.flags & SVE_PT_REGS_MASK)) { case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); case SVE_PT_REGS_SVE: start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); membuf_write(&to, target->thread.sve_state, end - start); start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); membuf_zero(&to, end - start); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); start = end; end = sve_size_from_header(&header); return membuf_zero(&to, end - start); default: return 0; } } static int sve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sve()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SVE); } static int sve_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) goto out; /* * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out; /* * Actual VL set may be different from what the user asked * for, or we may have configured the _ONEXEC VL not the * current VL: */ vq = sve_vq_from_vl(task_get_vl(target, type)); /* Enter/exit streaming mode */ if (system_supports_sme()) { u64 old_svcr = target->thread.svcr; switch (type) { case ARM64_VEC_SVE: target->thread.svcr &= ~SVCR_SM_MASK; break; case ARM64_VEC_SME: target->thread.svcr |= SVCR_SM_MASK; /* * Disable traps and ensure there is SME storage but * preserve any currently set values in ZA/ZT. */ sme_alloc(target, false); set_tsk_thread_flag(target, TIF_SME); break; default: WARN_ON_ONCE(1); ret = -EINVAL; goto out; } /* * If we switched then invalidate any existing SVE * state and ensure there's storage. */ if (target->thread.svcr != old_svcr) sve_alloc(target, true); } /* Registers: FPSIMD-only case */ BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) { ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_FPSIMD; goto out; } /* * Otherwise: no registers or full SVE case. For backwards * compatibility reasons we treat empty flags as SVE registers. */ /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (count && vq != sve_vq_from_vl(header.vl)) { ret = -EIO; goto out; } sve_alloc(target, true); if (!target->thread.sve_state) { ret = -ENOMEM; clear_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_FPSIMD; goto out; } /* * Ensure target->thread.sve_state is up to date with target's * FPSIMD regs, so that a short copyin leaves trailing * registers unmodified. Only enable SVE if we are * configuring normal SVE, a system with streaming SVE may not * have normal SVE. */ fpsimd_sync_to_sve(target); if (type == ARM64_VEC_SVE) set_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_SVE; BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sve_state, start, end); if (ret) goto out; start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, start, end); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.uw.fpsimd_state.fpsr, start, end); out: fpsimd_flush_task_state(target); return ret; } static int sve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sve()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SVE); } #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int ssve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SME); } static int ssve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sme()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SME); } static int za_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ memset(&header, 0, sizeof(header)); if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header.flags |= ZA_PT_VL_INHERIT; header.vl = task_get_sme_vl(target); vq = sve_vq_from_vl(header.vl); header.max_vl = sme_max_vl(); header.max_size = ZA_PT_SIZE(vq); /* If ZA is not active there is only the header */ if (thread_za_enabled(&target->thread)) header.size = ZA_PT_SIZE(vq); else header.size = ZA_PT_ZA_OFFSET; membuf_write(&to, &header, sizeof(header)); BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); end = ZA_PT_ZA_OFFSET; if (target == current) fpsimd_preserve_current_state(); /* Any register data to include? */ if (thread_za_enabled(&target->thread)) { start = end; end = ZA_PT_SIZE(vq); membuf_write(&to, target->thread.sme_state, end - start); } /* Zero any trailing padding */ start = end; end = ALIGN(header.size, SVE_VQ_BYTES); return membuf_zero(&to, end - start); } static int za_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) goto out; /* * All current ZA_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for * us: */ ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, ((unsigned long)header.flags) << 16); if (ret) goto out; /* * Actual VL set may be different from what the user asked * for, or we may have configured the _ONEXEC rather than * current VL: */ vq = sve_vq_from_vl(task_get_sme_vl(target)); /* Ensure there is some SVE storage for streaming mode */ if (!target->thread.sve_state) { sve_alloc(target, false); if (!target->thread.sve_state) { ret = -ENOMEM; goto out; } } /* * Only flush the storage if PSTATE.ZA was not already set, * otherwise preserve any existing data. */ sme_alloc(target, !thread_za_enabled(&target->thread)); if (!target->thread.sme_state) return -ENOMEM; /* If there is no data then disable ZA */ if (!count) { target->thread.svcr &= ~SVCR_ZA_MASK; goto out; } /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (vq != sve_vq_from_vl(header.vl)) { ret = -EIO; goto out; } BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); start = ZA_PT_ZA_OFFSET; end = ZA_PT_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sme_state, start, end); if (ret) goto out; /* Mark ZA as active and let userspace use it */ set_tsk_thread_flag(target, TIF_SME); target->thread.svcr |= SVCR_ZA_MASK; out: fpsimd_flush_task_state(target); return ret; } static int zt_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme2()) return -EINVAL; /* * If PSTATE.ZA is not set then ZT will be zeroed when it is * enabled so report the current register value as zero. */ if (thread_za_enabled(&target->thread)) membuf_write(&to, thread_zt_state(&target->thread), ZT_SIG_REG_BYTES); else membuf_zero(&to, ZT_SIG_REG_BYTES); return 0; } static int zt_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_sme2()) return -EINVAL; /* Ensure SVE storage in case this is first use of SME */ sve_alloc(target, false); if (!target->thread.sve_state) return -ENOMEM; if (!thread_za_enabled(&target->thread)) { sme_alloc(target, true); if (!target->thread.sme_state) return -ENOMEM; } ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, thread_zt_state(&target->thread), 0, ZT_SIG_REG_BYTES); if (ret == 0) { target->thread.svcr |= SVCR_ZA_MASK; set_tsk_thread_flag(target, TIF_SME); } fpsimd_flush_task_state(target); return ret; } #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { /* * The PAC bits can differ across data and instruction pointers * depending on TCR_EL1.TBID*, which we may make use of in future, so * we expose separate masks. */ unsigned long mask = ptrauth_user_pac_mask(); struct user_pac_mask uregs = { .data_mask = mask, .insn_mask = mask, }; if (!system_supports_address_auth()) return -EINVAL; return membuf_write(&to, &uregs, sizeof(uregs)); } static int pac_enabled_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; return membuf_write(&to, &enabled_keys, sizeof(enabled_keys)); } static int pac_enabled_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &enabled_keys, 0, sizeof(long)); if (ret) return ret; return ptrauth_set_enabled_keys(target, PR_PAC_ENABLED_KEYS_MASK, enabled_keys); } #ifdef CONFIG_CHECKPOINT_RESTORE static __uint128_t pac_key_to_user(const struct ptrauth_key *key) { return (__uint128_t)key->hi << 64 | key->lo; } static struct ptrauth_key pac_key_from_user(__uint128_t ukey) { struct ptrauth_key key = { .lo = (unsigned long)ukey, .hi = (unsigned long)(ukey >> 64), }; return key; } static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apiakey = pac_key_to_user(&keys->apia); ukeys->apibkey = pac_key_to_user(&keys->apib); ukeys->apdakey = pac_key_to_user(&keys->apda); ukeys->apdbkey = pac_key_to_user(&keys->apdb); } static void pac_address_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_address_keys *ukeys) { keys->apia = pac_key_from_user(ukeys->apiakey); keys->apib = pac_key_from_user(ukeys->apibkey); keys->apda = pac_key_from_user(ukeys->apdakey); keys->apdb = pac_key_from_user(ukeys->apdbkey); } static int pac_address_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_address_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; int ret; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_address_keys_from_user(keys, &user_keys); return 0; } static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apgakey = pac_key_to_user(&keys->apga); } static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_generic_keys *ukeys) { keys->apga = pac_key_from_user(ukeys->apgakey); } static int pac_generic_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_generic_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; int ret; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_generic_keys_from_user(keys, &user_keys); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI static int tagged_addr_ctrl_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long ctrl = get_tagged_addr_ctrl(target); if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) return ctrl; return membuf_write(&to, &ctrl, sizeof(ctrl)); } static int tagged_addr_ctrl_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long ctrl; ctrl = get_tagged_addr_ctrl(target); if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) return ctrl; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; return set_tagged_addr_ctrl(target, ctrl); } #endif #ifdef CONFIG_ARM64_POE static int poe_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_poe()) return -EINVAL; return membuf_write(&to, &target->thread.por_el0, sizeof(target->thread.por_el0)); } static int poe_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long ctrl; if (!system_supports_poe()) return -EINVAL; ctrl = target->thread.por_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; target->thread.por_el0 = ctrl; return 0; } #endif #ifdef CONFIG_ARM64_GCS static void task_gcs_to_user(struct user_gcs *user_gcs, const struct task_struct *target) { user_gcs->features_enabled = target->thread.gcs_el0_mode; user_gcs->features_locked = target->thread.gcs_el0_locked; user_gcs->gcspr_el0 = target->thread.gcspr_el0; } static void task_gcs_from_user(struct task_struct *target, const struct user_gcs *user_gcs) { target->thread.gcs_el0_mode = user_gcs->features_enabled; target->thread.gcs_el0_locked = user_gcs->features_locked; target->thread.gcspr_el0 = user_gcs->gcspr_el0; } static int gcs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_gcs user_gcs; if (!system_supports_gcs()) return -EINVAL; if (target == current) gcs_preserve_current_state(); task_gcs_to_user(&user_gcs, target); return membuf_write(&to, &user_gcs, sizeof(user_gcs)); } static int gcs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_gcs user_gcs; if (!system_supports_gcs()) return -EINVAL; task_gcs_to_user(&user_gcs, target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1); if (ret) return ret; if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) return -EINVAL; task_gcs_from_user(target, &user_gcs); return 0; } #endif enum aarch64_regset { REGSET_GPR, REGSET_FPR, REGSET_TLS, #ifdef CONFIG_HAVE_HW_BREAKPOINT REGSET_HW_BREAK, REGSET_HW_WATCH, #endif REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif #ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, REGSET_ZT, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, #ifdef CONFIG_CHECKPOINT_RESTORE REGSET_PACA_KEYS, REGSET_PACG_KEYS, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif #ifdef CONFIG_ARM64_POE REGSET_POE, #endif #ifdef CONFIG_ARM64_GCS REGSET_GCS, #endif }; static const struct user_regset aarch64_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_pt_regs) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = gpr_get, .set = gpr_set }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_fpsimd_state) / sizeof(u32), /* * We pretend we have 32-bit registers because the fpsr and * fpcr are 32-bits wide. */ .size = sizeof(u32), .align = sizeof(u32), .active = fpr_active, .regset_get = fpr_get, .set = fpr_set }, [REGSET_TLS] = { .core_note_type = NT_ARM_TLS, .n = 2, .size = sizeof(void *), .align = sizeof(void *), .regset_get = tls_get, .set = tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_ARM_HW_BREAK, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { .core_note_type = NT_ARM_HW_WATCH, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { .core_note_type = NT_ARM_SYSTEM_CALL, .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, [REGSET_FPMR] = { .core_note_type = NT_ARM_FPMR, .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = fpmr_get, .set = fpmr_set, }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = sve_get, .set = sve_set, }, #endif #ifdef CONFIG_ARM64_SME [REGSET_SSVE] = { /* Streaming mode SVE */ .core_note_type = NT_ARM_SSVE, .n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = ssve_get, .set = ssve_set, }, [REGSET_ZA] = { /* SME ZA */ .core_note_type = NT_ARM_ZA, /* * ZA is a single register but it's variably sized and * the ptrace core requires that the size of any data * be an exact multiple of the configured register * size so report as though we had SVE_VQ_BYTES * registers. These values aren't exposed to * userspace. */ .n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = za_get, .set = za_set, }, [REGSET_ZT] = { /* SME ZT */ .core_note_type = NT_ARM_ZT, .n = 1, .size = ZT_SIG_REG_BYTES, .align = sizeof(u64), .regset_get = zt_get, .set = zt_set, }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, .n = sizeof(struct user_pac_mask) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = pac_mask_get, /* this cannot be set dynamically */ }, [REGSET_PAC_ENABLED_KEYS] = { .core_note_type = NT_ARM_PAC_ENABLED_KEYS, .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = pac_enabled_keys_get, .set = pac_enabled_keys_set, }, #ifdef CONFIG_CHECKPOINT_RESTORE [REGSET_PACA_KEYS] = { .core_note_type = NT_ARM_PACA_KEYS, .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_address_keys_get, .set = pac_address_keys_set, }, [REGSET_PACG_KEYS] = { .core_note_type = NT_ARM_PACG_KEYS, .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_generic_keys_get, .set = pac_generic_keys_set, }, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI [REGSET_TAGGED_ADDR_CTRL] = { .core_note_type = NT_ARM_TAGGED_ADDR_CTRL, .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = tagged_addr_ctrl_get, .set = tagged_addr_ctrl_set, }, #endif #ifdef CONFIG_ARM64_POE [REGSET_POE] = { .core_note_type = NT_ARM_POE, .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = poe_get, .set = poe_set, }, #endif #ifdef CONFIG_ARM64_GCS [REGSET_GCS] = { .core_note_type = NT_ARM_GCS, .n = sizeof(struct user_gcs) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = gcs_get, .set = gcs_set, }, #endif }; static const struct user_regset_view user_aarch64_view = { .name = "aarch64", .e_machine = EM_AARCH64, .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, }; static inline compat_ulong_t compat_get_user_reg(struct task_struct *task, int idx) { struct pt_regs *regs = task_pt_regs(task); switch (idx) { case 15: return regs->pc; case 16: return pstate_to_compat_psr(regs->pstate); case 17: return regs->orig_x0; default: return regs->regs[idx]; } } static int compat_gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int i = 0; while (to.left) membuf_store(&to, compat_get_user_reg(target, i++)); return 0; } static int compat_gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct pt_regs newregs; int ret = 0; unsigned int i, start, num_regs; /* Calculate the number of AArch32 registers contained in count */ num_regs = count / regset->size; /* Convert pos into an register number */ start = pos / regset->size; if (start + num_regs > regset->n) return -EIO; newregs = *task_pt_regs(target); for (i = 0; i < num_regs; ++i) { unsigned int idx = start + i; compat_ulong_t reg; if (kbuf) { memcpy(®, kbuf, sizeof(reg)); kbuf += sizeof(reg); } else { ret = copy_from_user(®, ubuf, sizeof(reg)); if (ret) { ret = -EFAULT; break; } ubuf += sizeof(reg); } switch (idx) { case 15: newregs.pc = reg; break; case 16: reg = compat_psr_to_pstate(reg); newregs.pstate = reg; break; case 17: newregs.orig_x0 = reg; break; default: newregs.regs[idx] = reg; } } if (valid_user_regs(&newregs.user_regs, target)) *task_pt_regs(target) = newregs; else ret = -EINVAL; return ret; } static int compat_vfp_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; if (target == current) fpsimd_preserve_current_state(); /* * The VFP registers are packed into the fpsimd_state, so they all sit * nicely together for us. We just need to create the fpscr separately. */ membuf_write(&to, uregs, VFP_STATE_SIZE - sizeof(compat_ulong_t)); fpscr = (uregs->fpsr & VFP_FPSCR_STAT_MASK) | (uregs->fpcr & VFP_FPSCR_CTRL_MASK); return membuf_store(&to, fpscr); } static int compat_vfp_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; int ret, vregs_end_pos; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, vregs_end_pos); if (count && !ret) { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpscr, vregs_end_pos, VFP_STATE_SIZE); if (!ret) { uregs->fpsr = fpscr & VFP_FPSCR_STAT_MASK; uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK; } } fpsimd_flush_task_state(target); return ret; } static int compat_tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, (compat_ulong_t)target->thread.uw.tp_value); } static int compat_tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; compat_ulong_t tls = target->thread.uw.tp_value; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) return ret; target->thread.uw.tp_value = tls; return ret; } static const struct user_regset aarch32_regsets[] = { [REGSET_COMPAT_GPR] = { .core_note_type = NT_PRSTATUS, .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_COMPAT_VFP] = { .core_note_type = NT_ARM_VFP, .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .active = fpr_active, .regset_get = compat_vfp_get, .set = compat_vfp_set }, }; static const struct user_regset_view user_aarch32_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets) }; static const struct user_regset aarch32_ptrace_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_FPR] = { .core_note_type = NT_ARM_VFP, .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_vfp_get, .set = compat_vfp_set }, [REGSET_TLS] = { .core_note_type = NT_ARM_TLS, .n = 1, .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_tls_get, .set = compat_tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_ARM_HW_BREAK, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { .core_note_type = NT_ARM_HW_WATCH, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { .core_note_type = NT_ARM_SYSTEM_CALL, .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, }; static const struct user_regset_view user_aarch32_ptrace_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; #ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { compat_ulong_t tmp; if (off & 3) return -EIO; if (off == COMPAT_PT_TEXT_ADDR) tmp = tsk->mm->start_code; else if (off == COMPAT_PT_DATA_ADDR) tmp = tsk->mm->start_data; else if (off == COMPAT_PT_TEXT_END_ADDR) tmp = tsk->mm->end_code; else if (off < sizeof(compat_elf_gregset_t)) tmp = compat_get_user_reg(tsk, off >> 2); else if (off >= COMPAT_USER_SZ) return -EIO; else tmp = 0; return put_user(tmp, ret); } static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t val) { struct pt_regs newregs = *task_pt_regs(tsk); unsigned int idx = off / 4; if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; if (off >= sizeof(compat_elf_gregset_t)) return 0; switch (idx) { case 15: newregs.pc = val; break; case 16: newregs.pstate = compat_psr_to_pstate(val); break; case 17: newregs.orig_x0 = val; break; default: newregs.regs[idx] = val; } if (!valid_user_regs(&newregs.user_regs, tsk)) return -EINVAL; *task_pt_regs(tsk) = newregs; return 0; } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Convert a virtual register number into an index for a thread_info * breakpoint array. Breakpoints are identified using positive numbers * whilst watchpoints are negative. The registers are laid out as pairs * of (address, control), each pair mapping to a unique hw_breakpoint struct. * Register 0 is reserved for describing resource information. */ static int compat_ptrace_hbp_num_to_idx(compat_long_t num) { return (abs(num) - 1) >> 1; } static int compat_ptrace_hbp_get_resource_info(u32 *kdata) { u8 num_brps, num_wrps, debug_arch, wp_len; u32 reg = 0; num_brps = hw_breakpoint_slots(TYPE_INST); num_wrps = hw_breakpoint_slots(TYPE_DATA); debug_arch = debug_monitors_arch(); wp_len = 8; reg |= debug_arch; reg <<= 8; reg |= wp_len; reg <<= 8; reg |= num_wrps; reg <<= 8; reg |= num_brps; *kdata = reg; return 0; } static int compat_ptrace_hbp_get(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr = 0; u32 ctrl = 0; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr); *kdata = (u32)addr; } else { err = ptrace_hbp_get_ctrl(note_type, tsk, idx, &ctrl); *kdata = ctrl; } return err; } static int compat_ptrace_hbp_set(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr; u32 ctrl; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { addr = *kdata; err = ptrace_hbp_set_addr(note_type, tsk, idx, addr); } else { ctrl = *kdata; err = ptrace_hbp_set_ctrl(note_type, tsk, idx, ctrl); } return err; } static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata; /* Watchpoint */ if (num < 0) { ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata); /* Resource info */ } else if (num == 0) { ret = compat_ptrace_hbp_get_resource_info(&kdata); /* Breakpoint */ } else { ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata); } if (!ret) ret = put_user(kdata, data); return ret; } static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata = 0; if (num == 0) return 0; ret = get_user(kdata, data); if (ret) return ret; if (num < 0) ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata); else ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata); return ret; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; switch (request) { case PTRACE_PEEKUSR: ret = compat_ptrace_read_user(child, addr, datap); break; case PTRACE_POKEUSR: ret = compat_ptrace_write_user(child, addr, data); break; case COMPAT_PTRACE_GETREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_SETREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_GET_THREAD_AREA: ret = put_user((compat_ulong_t)child->thread.uw.tp_value, (compat_ulong_t __user *)datap); break; case COMPAT_PTRACE_SET_SYSCALL: task_pt_regs(child)->syscallno = data; ret = 0; break; case COMPAT_PTRACE_GETVFPREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; case COMPAT_PTRACE_SETVFPREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; #ifdef CONFIG_HAVE_HW_BREAKPOINT case COMPAT_PTRACE_GETHBPREGS: ret = compat_ptrace_gethbpregs(child, addr, datap); break; case COMPAT_PTRACE_SETHBPREGS: ret = compat_ptrace_sethbpregs(child, addr, datap); break; #endif default: ret = compat_ptrace_request(child, request, addr, data); break; } return ret; } #endif /* CONFIG_COMPAT */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on * 32-bit children use an extended user_aarch32_ptrace_view to allow * access to the TLS register. */ if (is_compat_task()) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; return &user_aarch64_view; } long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { switch (request) { case PTRACE_PEEKMTETAGS: case PTRACE_POKEMTETAGS: return mte_ptrace_copy_tags(child, request, addr, data); } return ptrace_request(child, request, addr, data); } enum ptrace_syscall_dir { PTRACE_SYSCALL_ENTER = 0, PTRACE_SYSCALL_EXIT, }; static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) { int regno; unsigned long saved_reg; /* * We have some ABI weirdness here in the way that we handle syscall * exit stops because we indicate whether or not the stop has been * signalled from syscall entry or syscall exit by clobbering a general * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee * and restoring its old value after the stop. This means that: * * - Any writes by the tracer to this register during the stop are * ignored/discarded. * * - The actual value of the register is not available during the stop, * so the tracer cannot save it and restore it later. * * - Syscall stops behave differently to seccomp and pseudo-step traps * (the latter do not nobble any registers). */ regno = (is_compat_task() ? 12 : 7); saved_reg = regs->regs[regno]; regs->regs[regno] = dir; if (dir == PTRACE_SYSCALL_ENTER) { if (ptrace_report_syscall_entry(regs)) forget_syscall(regs); regs->regs[regno] = saved_reg; } else if (!test_thread_flag(TIF_SINGLESTEP)) { ptrace_report_syscall_exit(regs, 0); regs->regs[regno] = saved_reg; } else { regs->regs[regno] = saved_reg; /* * Signal a pseudo-step exception since we are stepping but * tracer modifications to the registers may have rewound the * state machine. */ ptrace_report_syscall_exit(regs, 1); } } int syscall_trace_enter(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { report_syscall(regs, PTRACE_SYSCALL_ENTER); if (flags & _TIF_SYSCALL_EMU) return NO_SYSCALL; } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing() == -1) return NO_SYSCALL; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]); return regs->syscallno; } void syscall_trace_exit(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); audit_syscall_exit(regs); if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, syscall_get_return_value(current, regs)); if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); } /* * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is * not described in ARM DDI 0487D.a. * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | \ GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS; if (!system_supports_mixed_endian_el0()) { if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) regs->pstate |= PSR_AA32_E_BIT; else regs->pstate &= ~PSR_AA32_E_BIT; } if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_AA32_A_BIT) == 0 && (regs->pstate & PSR_AA32_I_BIT) == 0 && (regs->pstate & PSR_AA32_F_BIT) == 0) { return 1; } /* * Force PSR to a valid 32-bit EL0t, preserving the same bits as * arch/arm. */ regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT | PSR_AA32_C_BIT | PSR_AA32_V_BIT | PSR_AA32_Q_BIT | PSR_AA32_IT_MASK | PSR_AA32_GE_MASK | PSR_AA32_E_BIT | PSR_AA32_T_BIT; regs->pstate |= PSR_MODE32_BIT; return 0; } static int valid_native_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS; if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_D_BIT) == 0 && (regs->pstate & PSR_A_BIT) == 0 && (regs->pstate & PSR_I_BIT) == 0 && (regs->pstate & PSR_F_BIT) == 0) { return 1; } /* Force PSR to a valid 64-bit EL0t */ regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; return 0; } /* * Are the current registers suitable for user mode? (used to maintain * security in signal handlers) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); else return valid_native_regs(regs); } |
| 85 73 227 93 93 8 85 1 93 93 1 92 232 217 232 272 272 181 181 181 105 181 272 345 343 232 72 193 215 232 344 345 72 72 72 72 2 175 175 144 144 144 57 93 225 225 195 195 235 261 197 197 196 196 197 3 194 195 197 196 224 225 225 225 225 225 121 121 121 121 121 121 73 73 73 | 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 | /* * 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) * 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 <linux/oom.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(const 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(const 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 */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibililty to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { 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; } /* KSM folios don't reach here because of the !page__anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 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; } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_likely_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (lru_gen_enabled() && pvmw.pte) { if (lru_gen_look_around(&pvmw)) referenced++; } else if (pvmw.pte) { 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 = 0, 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(&folio->_mapcount); break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; 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(const struct folio *folio, const 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_pgoff(folio, 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); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } 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 = 0, 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, &folio->_mapcount); break; } atomic_sub(nr_pages, &folio->_large_mapcount); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; 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 < nr_pmdmapped; break; } /* * 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 (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio)) deferred_split_folio(folio, true); __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(const 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 */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/gfp_types.h> #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> #include <linux/sched.h> struct vm_area_struct; struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * gfp flag masking for nested internal allocations. * * For code that needs to do allocations inside the public allocation API (e.g. * memory allocation tracking code) the allocations need to obey the caller * allocation context constrains to prevent allocation context mismatches (e.g. * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock * situations. * * It is also assumed that these nested allocations are for internal kernel * object storage purposes only and are not going to be used for DMA, etc. Hence * we strip out all the zone information and leave just the context information * intact. * * Further, internal allocations must fail before the higher level allocation * can fail, so we must make them fail faster and fail silently. We also don't * want them to deplete emergency reserves. Hence nested allocations must be * prepared for these allocations to fail. */ static inline gfp_t gfp_nested_mask(gfp_t flags) { return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the case of non-NUMA systems the NODE_DATA() gets optimized to * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); #define alloc_pages_bulk_mempolicy(...) \ alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ #define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array) static inline unsigned long alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array); } #define alloc_pages_bulk_node(...) \ alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) return; if (node_online(this_node)) return; pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); dump_stack(); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } #define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) static inline struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); return __folio_alloc_noprof(gfp, order, nid, NULL); } #define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node_noprof(nid, gfp_mask, order); } #define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node_noprof(gfp, order, numa_node_id()); } static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return folio_alloc_noprof(gfp, order); } #define vma_alloc_folio_noprof(gfp, order, vma, addr) \ folio_alloc_noprof(gfp, order) #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); #define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); #define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) void free_pages_exact(void *virt, size_t size); __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define alloc_pages_exact_nid(...) \ alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); static inline bool gfp_has_io_fs(gfp_t gfp) { return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); #define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); #ifdef CONFIG_CONTIG_ALLOC static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, int nid, nodemask_t *node) { struct page *page; if (WARN_ON(!order || !(gfp & __GFP_COMP))) return NULL; page = alloc_contig_pages_noprof(1 << order, gfp, nid, node); return page ? page_folio(page) : NULL; } #else static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, int nid, nodemask_t *node) { return NULL; } #endif /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) #endif /* __LINUX_GFP_H */ |
| 254 21 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 391 390 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM__VIRT_H #define __ASM__VIRT_H /* * The arm64 hcall implementation uses x0 to specify the hcall * number. A value less than HVC_STUB_HCALL_NR indicates a special * hcall, such as set vector. Any other value is handled in a * hypervisor specific way. * * The hypercall is allowed to clobber any of the caller-saved * registers (x0-x18), so it is advisable to use it through the * indirection of a function call (as implemented in hyp-stub.S). */ /* * HVC_SET_VECTORS - Set the value of the vbar_el2 register. * * @x1: Physical address of the new vector table. */ #define HVC_SET_VECTORS 0 /* * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine. */ #define HVC_SOFT_RESTART 1 /* * HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs */ #define HVC_RESET_VECTORS 2 /* * HVC_FINALISE_EL2 - Upgrade the CPU from EL1 to EL2, if possible */ #define HVC_FINALISE_EL2 3 /* Max number of HYP stub hypercalls */ #define HVC_STUB_HCALL_NR 4 /* Error returned when an invalid stub number is passed into x0 */ #define HVC_STUB_ERR 0xbadca11 #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) /* * Flags returned together with the boot mode, but not preserved in * __boot_cpu_mode. Used by the idreg override code to work out the * boot state. */ #define BOOT_CPU_FLAG_E2H BIT_ULL(32) #ifndef __ASSEMBLY__ #include <asm/ptrace.h> #include <asm/sections.h> #include <asm/sysreg.h> #include <asm/cpufeature.h> /* * __boot_cpu_mode records what mode CPUs were booted in. * A correctly-implemented bootloader must start all CPUs in the same mode: * In this case, both 32bit halves of __boot_cpu_mode will contain the * same value (either 0 if booted in EL1, BOOT_CPU_MODE_EL2 if booted in EL2). * * Should the bootloader fail to do this, the two values will be different. * This allows the kernel to flag an error when the secondaries have come up. */ extern u32 __boot_cpu_mode[2]; #define ARM64_VECTOR_TABLE_LEN SZ_2K void __hyp_set_vectors(phys_addr_t phys_vector_base); void __hyp_reset_vectors(void); bool is_kvm_arm_initialised(void); DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); static inline bool is_pkvm_initialized(void) { return IS_ENABLED(CONFIG_KVM) && static_branch_likely(&kvm_protected_mode_initialized); } /* Reports the availability of HYP mode */ static inline bool is_hyp_mode_available(void) { /* * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ if (is_pkvm_initialized()) return true; return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 && __boot_cpu_mode[1] == BOOT_CPU_MODE_EL2); } /* Check if the bootloader has booted CPUs in different modes */ static inline bool is_hyp_mode_mismatched(void) { /* * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ if (is_pkvm_initialized()) return false; return __boot_cpu_mode[0] != __boot_cpu_mode[1]; } static __always_inline bool is_kernel_in_hyp_mode(void) { BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__) || __is_defined(__KVM_VHE_HYPERVISOR__)); return read_sysreg(CurrentEL) == CurrentEL_EL2; } static __always_inline bool has_vhe(void) { /* * Code only run in VHE/NVHE hyp context can assume VHE is present or * absent. Otherwise fall back to caps. * This allows the compiler to discard VHE-specific code from the * nVHE object, reducing the number of external symbol references * needed to link. */ if (is_vhe_hyp_code()) return true; else if (is_nvhe_hyp_code()) return false; else return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN); } static __always_inline bool is_protected_kvm_enabled(void) { if (is_vhe_hyp_code()) return false; else return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE); } static __always_inline bool has_hvhe(void) { if (is_vhe_hyp_code()) return false; return cpus_have_final_cap(ARM64_KVM_HVHE); } static inline bool is_hyp_nvhe(void) { return is_hyp_mode_available() && !is_kernel_in_hyp_mode(); } #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_H */ |
| 252 41 41 40 4 2 40 2 40 40 34 34 34 29 29 29 29 29 29 50 46 6 23 34 34 32 2 34 34 34 23 33 4 17 19 9 5 5 3 9 19 19 19 17 4 54 53 1 54 1 54 52 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/uaccess.h> #include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include "vgic.h" /* * Initialization rules: there are multiple stages to the vgic * initialization, both for the distributor and the CPU interfaces. The basic * idea is that even though the VGIC is not functional or not requested from * user space, the critical path of the run loop can still call VGIC functions * that just won't do anything, without them having to check additional * initialization flags to ensure they don't look at uninitialized data * structures. * * Distributor: * * - kvm_vgic_early_init(): initialization of static data that doesn't * depend on any sizing information or emulation type. No allocation * is allowed there. * * - vgic_init(): allocation and initialization of the generic data * structures that depend on sizing information (number of CPUs, * number of interrupts). Also initializes the vcpu specific data * structures. Can be executed lazily for GICv2. * * CPU Interface: * * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend * on any sizing information. Private interrupts are allocated if not * already allocated at vgic-creation time. */ /* EARLY INIT */ /** * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures * @kvm: The VM whose VGIC districutor should be initialized * * Only do initialization of static structures that don't require any * allocation or sizing information from userspace. vgic_init() called * kvm_vgic_dist_init() which takes care of the rest. */ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ); } /* CREATION */ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); /** * kvm_vgic_create: triggered by the instantiation of the VGIC device by * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) * or through the generic KVM_CREATE_DEVICE API ioctl. * irqchip_in_kernel() tells you if this function succeeded or not. * @kvm: kvm struct pointer * @type: KVM_DEV_TYPE_ARM_VGIC_V[23] */ int kvm_vgic_create(struct kvm *kvm, u32 type) { struct kvm_vcpu *vcpu; unsigned long i; int ret; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, * which had no chance yet to check the availability of the GICv2 * emulation. So check this here again. KVM_CREATE_DEVICE does * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; /* Must be held to avoid race with vCPU creation */ lockdep_assert_held(&kvm->lock); ret = -EBUSY; if (!lock_all_vcpus(kvm)) return ret; mutex_lock(&kvm->arch.config_lock); if (irqchip_in_kernel(kvm)) { ret = -EEXIST; goto out_unlock; } kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_has_run_once(vcpu)) goto out_unlock; } ret = 0; if (type == KVM_DEV_TYPE_ARM_VGIC_V2) kvm->max_vcpus = VGIC_V2_MAX_CPUS; else kvm->max_vcpus = VGIC_V3_MAX_CPUS; if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) { ret = -E2BIG; goto out_unlock; } kvm_for_each_vcpu(i, vcpu, kvm) { ret = vgic_allocate_private_irqs_locked(vcpu, type); if (ret) break; } if (ret) { kvm_for_each_vcpu(i, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; kfree(vgic_cpu->private_irqs); vgic_cpu->private_irqs = NULL; } goto out_unlock; } kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; if (type == KVM_DEV_TYPE_ARM_VGIC_V2) kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; else INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); return ret; } /* INIT/DESTROY */ /** * kvm_vgic_dist_init: initialize the dist data structures * @kvm: kvm struct pointer * @nr_spis: number of spis, frozen by caller */ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0); int i; dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!dist->spis) return -ENOMEM; /* * In the following code we do not take the irq struct lock since * no other action on irq structs can happen while the VGIC is * not initialized yet: * If someone wants to inject an interrupt or does a MMIO access, we * require prior initialization in case of a virtual GICv3 or trigger * initialization when using a virtual GICv2. */ for (i = 0; i < nr_spis; i++) { struct vgic_irq *irq = &dist->spis[i]; irq->intid = i + VGIC_NR_PRIVATE_IRQS; INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; kref_init(&irq->refcount); switch (dist->vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V2: irq->targets = 0; irq->group = 0; break; case KVM_DEV_TYPE_ARM_VGIC_V3: irq->mpidr = 0; irq->group = 1; break; default: kfree(dist->spis); dist->spis = NULL; return -EINVAL; } } return 0; } static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; int i; lockdep_assert_held(&vcpu->kvm->arch.config_lock); if (vgic_cpu->private_irqs) return 0; vgic_cpu->private_irqs = kcalloc(VGIC_NR_PRIVATE_IRQS, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!vgic_cpu->private_irqs) return -ENOMEM; /* * Enable and configure all SGIs to be edge-triggered and * configure all PPIs as level-triggered. */ for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; kref_init(&irq->refcount); if (vgic_irq_is_sgi(i)) { /* SGIs */ irq->enabled = 1; irq->config = VGIC_CONFIG_EDGE; } else { /* PPIs */ irq->config = VGIC_CONFIG_LEVEL; } switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V3: irq->group = 1; irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); break; case KVM_DEV_TYPE_ARM_VGIC_V2: irq->group = 0; irq->targets = BIT(vcpu->vcpu_id); break; } } return 0; } static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type) { int ret; mutex_lock(&vcpu->kvm->arch.config_lock); ret = vgic_allocate_private_irqs_locked(vcpu, type); mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; } /** * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data * structures and register VCPU-specific KVM iodevs * * @vcpu: pointer to the VCPU being created and initialized * * Only do initialization, but do not actually enable the * VGIC CPU interface */ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; int ret = 0; vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); if (!irqchip_in_kernel(vcpu->kvm)) return 0; ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model); if (ret) return ret; /* * If we are creating a VCPU with a GICv3 we must also register the * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { mutex_lock(&vcpu->kvm->slots_lock); ret = vgic_register_redist_iodev(vcpu); mutex_unlock(&vcpu->kvm->slots_lock); } return ret; } static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_enable(vcpu); else vgic_v3_enable(vcpu); } /* * vgic_init: allocates and initializes dist and vcpu data structures * depending on two dimensioning parameters: * - the number of spis * - the number of vcpus * The function is generally called when nr_spis has been explicitly set * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. * vgic_initialized() returns true when this function has succeeded. */ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; unsigned long idx; lockdep_assert_held(&kvm->arch.config_lock); if (vgic_initialized(kvm)) return 0; /* Are we also in the middle of creating a VCPU? */ if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) return -EBUSY; /* freeze the number of spis */ if (!dist->nr_spis) dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; ret = kvm_vgic_dist_init(kvm, dist->nr_spis); if (ret) goto out; /* * If we have GICv4.1 enabled, unconditionally request enable the * v4 support so that we get HW-accelerated vSGIs. Otherwise, only * enable it if we present a virtual ITS to the guest. */ if (vgic_supports_direct_msis(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; } kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); if (ret) goto out; vgic_debug_init(kvm); /* * If userspace didn't set the GIC implementation revision, * default to the latest and greatest. You know want it. */ if (!dist->implementation_rev) dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST; dist->initialized = true; out: return ret; } static void kvm_vgic_dist_destroy(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_redist_region *rdreg, *next; dist->ready = false; dist->initialized = false; kfree(dist->spis); dist->spis = NULL; dist->nr_spis = 0; dist->vgic_dist_base = VGIC_ADDR_UNDEF; if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; } if (vgic_supports_direct_msis(kvm)) vgic_v4_teardown(kvm); xa_destroy(&dist->lpi_xa); } static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; /* * Retire all pending LPIs on this vcpu anyway as we're * going to destroy it. */ vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); kfree(vgic_cpu->private_irqs); vgic_cpu->private_irqs = NULL; if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { /* * If this vCPU is being destroyed because of a failed creation * then unregister the redistributor to avoid leaving behind a * dangling pointer to the vCPU struct. * * vCPUs that have been successfully created (i.e. added to * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as * this function gets called while holding kvm->arch.config_lock * in the VM teardown path and would otherwise introduce a lock * inversion w.r.t. kvm->srcu. * * vCPUs that failed creation are torn down outside of the * kvm->arch.config_lock and do not get unregistered in * kvm_vgic_destroy(), meaning it is both safe and necessary to * do so here. */ if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu) vgic_unregister_redist_iodev(vcpu); vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; } } void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; mutex_lock(&kvm->slots_lock); __kvm_vgic_vcpu_destroy(vcpu); mutex_unlock(&kvm->slots_lock); } void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) __kvm_vgic_vcpu_destroy(vcpu); kvm_vgic_dist_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) kvm_for_each_vcpu(i, vcpu, kvm) vgic_unregister_redist_iodev(vcpu); mutex_unlock(&kvm->slots_lock); } /** * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest * is a GICv2. A GICv3 must be explicitly initialized by userspace using the * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. * @kvm: kvm struct pointer */ int vgic_lazy_init(struct kvm *kvm) { int ret = 0; if (unlikely(!vgic_initialized(kvm))) { /* * We only provide the automatic initialization of the VGIC * for the legacy case of a GICv2. Any other type must * be explicitly initialized once setup with the respective * KVM device call. */ if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; mutex_lock(&kvm->arch.config_lock); ret = vgic_init(kvm); mutex_unlock(&kvm->arch.config_lock); } return ret; } /* RESOURCE MAPPING */ /** * kvm_vgic_map_resources - map the MMIO regions * @kvm: kvm struct pointer * * Map the MMIO regions depending on the VGIC model exposed to the guest * called on the first VCPU run. * Also map the virtual CPU interface into the VM. * v2 calls vgic_init() if not already done. * v3 and derivatives return an error if the VGIC is not initialized. * vgic_ready() returns true if this function has succeeded. */ int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; enum vgic_type type; gpa_t dist_base; int ret = 0; if (likely(vgic_ready(kvm))) return 0; mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); if (vgic_ready(kvm)) goto out; if (!irqchip_in_kernel(kvm)) goto out; if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { ret = vgic_v2_map_resources(kvm); type = VGIC_V2; } else { ret = vgic_v3_map_resources(kvm); type = VGIC_V3; } if (ret) goto out; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); if (ret) { kvm_err("Unable to register VGIC dist MMIO regions\n"); goto out_slots; } /* * kvm_io_bus_register_dev() guarantees all readers see the new MMIO * registration before returning through synchronize_srcu(), which also * implies a full memory barrier. As such, marking the distributor as * 'ready' here is guaranteed to be ordered after all vCPUs having seen * a completely configured distributor. */ dist->ready = true; goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); out_slots: if (ret) kvm_vm_dead(kvm); mutex_unlock(&kvm->slots_lock); return ret; } /* GENERIC PROBE */ void kvm_vgic_cpu_up(void) { enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); } void kvm_vgic_cpu_down(void) { disable_percpu_irq(kvm_vgic_global_state.maint_irq); } static irqreturn_t vgic_maintenance_handler(int irq, void *data) { /* * We cannot rely on the vgic maintenance interrupt to be * delivered synchronously. This means we can only use it to * exit the VM, and we perform the handling of EOIed * interrupts on the exit path (see vgic_fold_lr_state). */ return IRQ_HANDLED; } static struct gic_kvm_info *gic_kvm_info; void __init vgic_set_kvm_info(const struct gic_kvm_info *info) { BUG_ON(gic_kvm_info != NULL); gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL); if (gic_kvm_info) *gic_kvm_info = *info; } /** * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware * * For a specific CPU, initialize the GIC VE hardware. */ void kvm_vgic_init_cpu_hardware(void) { BUG_ON(preemptible()); /* * We want to make sure the list registers start out clear so that we * only have the program the used registers. */ if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_init_lrs(); else kvm_call_hyp(__vgic_v3_init_lrs); } /** * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable * according to the host GIC model. Accordingly calls either * vgic_v2/v3_probe which registers the KVM_DEVICE that can be * instantiated by a guest later on . */ int kvm_vgic_hyp_init(void) { bool has_mask; int ret; if (!gic_kvm_info) return -ENODEV; has_mask = !gic_kvm_info->no_maint_irq_mask; if (has_mask && !gic_kvm_info->maint_irq) { kvm_err("No vgic maintenance irq\n"); return -ENXIO; } /* * If we get one of these oddball non-GICs, taint the kernel, * as we have no idea of how they *really* behave. */ if (gic_kvm_info->no_hw_deactivation) { kvm_info("Non-architectural vgic, tainting kernel\n"); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); kvm_vgic_global_state.no_hw_deactivation = true; } switch (gic_kvm_info->type) { case GIC_V2: ret = vgic_v2_probe(gic_kvm_info); break; case GIC_V3: ret = vgic_v3_probe(gic_kvm_info); if (!ret) { static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif); kvm_info("GIC system register CPU interface enabled\n"); } break; default: ret = -ENODEV; } kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq; kfree(gic_kvm_info); gic_kvm_info = NULL; if (ret) return ret; if (!has_mask && !kvm_vgic_global_state.maint_irq) return 0; ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, vgic_maintenance_handler, "vgic", kvm_get_running_vcpus()); if (ret) { kvm_err("Cannot register interrupt %d\n", kvm_vgic_global_state.maint_irq); return ret; } kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); return 0; } |
| 174 174 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #include "internal.h" #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } /* * Allocate an file->f_owner struct if it doesn't exist, handling racing * allocations correctly. */ int file_f_owner_allocate(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) return 0; f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); if (!f_owner) return -ENOMEM; rwlock_init(&f_owner->lock); f_owner->file = file; /* If someone else raced us, drop our allocation. */ if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) kfree(f_owner); return 0; } EXPORT_SYMBOL(file_f_owner_allocate); void file_f_owner_release(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) { put_pid(f_owner->pid); kfree(f_owner); } } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (WARN_ON_ONCE(!f_owner)) return; write_lock_irq(&f_owner->lock); if (force || !f_owner->pid) { put_pid(f_owner->pid); f_owner->pid = get_pid(pid); f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); f_owner->uid = cred->uid; f_owner->euid = cred->euid; } } write_unlock_irq(&f_owner->lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; might_sleep(); type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (!f_owner) return pid; read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) { pid = pid_vnr(f_owner->pid); if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&f_owner->lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; struct fown_struct *f_owner; enum pid_type pid_type = PIDTYPE_PID; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) owner.pid = pid_vnr(f_owner->pid); rcu_read_unlock(); pid_type = f_owner->pid_type; } switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } if (f_owner) read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; uid_t src[2] = {0, 0}; int err; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); src[0] = from_kuid(user_ns, f_owner->uid); src[1] = from_kuid(user_ns, f_owner->euid); read_unlock_irq(&f_owner->lock); } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return fd_file(f) == filp; } /* Let the caller figure out whether a given file was just created. */ static long f_created_query(const struct file *filp) { return !!(filp->f_mode & FMODE_CREATED); } static int f_owner_sig(struct file *filp, int signum, bool setsig) { int ret = 0; struct fown_struct *f_owner; might_sleep(); if (setsig) { if (!valid_signal(signum)) return -EINVAL; ret = file_f_owner_allocate(filp); if (ret) return ret; } f_owner = file_f_owner(filp); if (setsig) f_owner->signum = signum; else if (f_owner) ret = f_owner->signum; return ret; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_CREATED_QUERY: err = f_created_query(filp); break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = f_owner_sig(filp, 0, false); break; case F_SETSIG: err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, cmd, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd_raw, f)(fd); long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, fd_file(f)); return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; CLASS(fd_raw, f)(fd); struct flock64 flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { CLASS(fd_raw, f)(fd); struct flock flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct file *file) { struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; fown = file_f_owner(file); if (!fown) return 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = file_f_owner(fa->fa_file); if (!fown) goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 12 12 12 5 5 1 5 1 4 10 5 5 3 3 2 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 | // 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 <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_nested.h> #include <asm/esr.h> static void pend_sync_exception(struct kvm_vcpu *vcpu) { /* If not nesting, EL1 is the only possible exception target */ if (likely(!vcpu_has_nv(vcpu))) { kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); return; } /* * With NV, we need to pick between EL1 and EL2. Note that we * never deal with a nesting exception here, hence never * changing context, and the exception itself can be delayed * until the next entry. */ switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) { case PSR_MODE_EL2h: case PSR_MODE_EL2t: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); break; case PSR_MODE_EL1h: case PSR_MODE_EL1t: kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); break; case PSR_MODE_EL0t: if (vcpu_el2_tge_is_set(vcpu)) kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); else kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); break; default: BUG(); } } static bool match_target_el(struct kvm_vcpu *vcpu, unsigned long target) { return (vcpu_get_flag(vcpu, EXCEPT_MASK) == target); } static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u64 esr = 0; pend_sync_exception(vcpu); /* * Build an {i,d}abort, depending on the level and the * instruction set. Report an external synchronous abort. */ if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; /* * Here, the guest runs in AArch64 mode when in EL1. If we get * an AArch32 fault, it means we managed to trap an EL0 fault. */ if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t) esr |= (ESR_ELx_EC_IABT_LOW << ESR_ELx_EC_SHIFT); else esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT); if (!is_iabt) esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; esr |= ESR_ELx_FSC_EXTABT; if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) { vcpu_write_sys_reg(vcpu, addr, FAR_EL1); vcpu_write_sys_reg(vcpu, esr, ESR_EL1); } else { vcpu_write_sys_reg(vcpu, addr, FAR_EL2); vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } } static void inject_undef64(struct kvm_vcpu *vcpu) { u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); pend_sync_exception(vcpu); /* * Build an unknown exception, depending on the instruction * set. */ if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) vcpu_write_sys_reg(vcpu, esr, ESR_EL1); else vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } #define DFSR_FSC_EXTABT_LPAE 0x10 #define DFSR_FSC_EXTABT_nLPAE 0x08 #define DFSR_LPAE BIT(9) #define TTBCR_EAE BIT(31) static void inject_undef32(struct kvm_vcpu *vcpu) { kvm_pend_exception(vcpu, EXCEPT_AA32_UND); } /* * Modelled after TakeDataAbortException() and TakePrefetchAbortException * pseudocode. */ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr) { u64 far; u32 fsr; /* Give the guest an IMPLEMENTATION DEFINED exception */ if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) { fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; } else { /* no need to shuffle FS[4] into DFSR[10] as it's 0 */ fsr = DFSR_FSC_EXTABT_nLPAE; } far = vcpu_read_sys_reg(vcpu, FAR_EL1); if (is_pabt) { kvm_pend_exception(vcpu, EXCEPT_AA32_IABT); far &= GENMASK(31, 0); far |= (u64)addr << 32; vcpu_write_sys_reg(vcpu, fsr, IFSR32_EL2); } else { /* !iabt */ kvm_pend_exception(vcpu, EXCEPT_AA32_DABT); far &= GENMASK(63, 32); far |= addr; vcpu_write_sys_reg(vcpu, fsr, ESR_EL1); } vcpu_write_sys_reg(vcpu, far, FAR_EL1); } /** * kvm_inject_dabt - inject a data abort into the guest * @vcpu: The VCPU to receive the data abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) inject_abt32(vcpu, false, addr); else inject_abt64(vcpu, false, addr); } /** * kvm_inject_pabt - inject a prefetch abort into the guest * @vcpu: The VCPU to receive the prefetch abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) inject_abt32(vcpu, true, addr); else inject_abt64(vcpu, true, addr); } void kvm_inject_size_fault(struct kvm_vcpu *vcpu) { unsigned long addr, esr; addr = kvm_vcpu_get_fault_ipa(vcpu); addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); if (kvm_vcpu_trap_is_iabt(vcpu)) kvm_inject_pabt(vcpu, addr); else kvm_inject_dabt(vcpu, addr); /* * If AArch64 or LPAE, set FSC to 0 to indicate an Address * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) return; esr = vcpu_read_sys_reg(vcpu, ESR_EL1); esr &= ~GENMASK_ULL(5, 0); vcpu_write_sys_reg(vcpu, esr, ESR_EL1); } /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) inject_undef32(vcpu); else inject_undef64(vcpu); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 esr) { vcpu_set_vsesr(vcpu, esr & ESR_ELx_ISS_MASK); *vcpu_hcr(vcpu) |= HCR_VSE; } /** * kvm_inject_vabt - inject an async abort / SError into the guest * @vcpu: The VCPU to receive the exception * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. * * Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with * the remaining ISS all-zeros so that this error is not interpreted as an * uncategorized RAS error. Without the RAS Extensions we can't specify an ESR * value, so the CPU generates an imp-def value. */ void kvm_inject_vabt(struct kvm_vcpu *vcpu) { kvm_set_sei_esr(vcpu, ESR_ELx_ISV); } |
| 993 998 994 994 49 998 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ 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 error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ 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)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc(sizeof(*ee), GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* * Get symlink's pathname of program, but fallback to realpath if * symlink's pathname does not exist or symlink's pathname refers * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ). */ exename.name = tomoyo_realpath_nofollow(original_name); if (exename.name && !strncmp(exename.name, "proc:/", 6)) { kfree(exename.name); exename.name = NULL; } if (!exename.name) { exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new proceess * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; /* * Maybe kmap()/kunmap() should be used here. * But remove_arg_zero() uses kmap_atomic()/kunmap_atomic(). * So do I. */ char *kaddr = kmap_atomic(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_atomic(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 254 21 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 4 4 4 4 4 4 4 4 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Netlink attributes * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/netlink.h> /* For these data types, attribute length should be exactly the given * size. However, to maintain compatibility with broken commands, if the * attribute length does not match the expected size a warning is emitted * to the user that the command is sending invalid data and needs to be fixed. */ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_MSECS] = sizeof(u64), [NLA_NESTED] = NLA_HDRLEN, [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; /* * Nested policies might refer back to the original * policy in some cases, and userspace could try to * abuse that and recurse by nesting in the right * ways. Limit recursion to avoid this problem. */ #define MAX_POLICY_RECURSION_DEPTH 10 static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth); static int validate_nla_bitfield32(const struct nlattr *nla, const u32 valid_flags_mask) { const struct nla_bitfield32 *bf = nla_data(nla); if (!valid_flags_mask) return -EINVAL; /*disallow invalid bit selector */ if (bf->selector & ~valid_flags_mask) return -EINVAL; /*disallow invalid bit values */ if (bf->value & ~valid_flags_mask) return -EINVAL; /*disallow valid bit values that are not selected*/ if (bf->value & ~bf->selector) return -EINVAL; return 0; } static int nla_validate_array(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack, unsigned int validate, unsigned int depth) { const struct nlattr *entry; int rem; nla_for_each_attr(entry, head, len, rem) { int ret; if (nla_len(entry) == 0) continue; if (nla_len(entry) < NLA_HDRLEN) { NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy, "Array element too short"); return -ERANGE; } ret = __nla_validate_parse(nla_data(entry), nla_len(entry), maxtype, policy, validate, extack, NULL, depth + 1); if (ret < 0) return ret; } return 0; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range) { WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR && (pt->min < 0 || pt->max < 0)); range->min = 0; switch (pt->type) { case NLA_U8: range->max = U8_MAX; break; case NLA_U16: case NLA_BE16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: case NLA_BE32: range->max = U32_MAX; break; case NLA_U64: case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { struct netlink_range_validation range; u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_MSECS: value = nla_get_u64(nla); break; case NLA_BINARY: value = nla_len(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && pt->type == NLA_BINARY && value > range.max) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, pt->type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } /* this assumes min <= max (don't validate against min) */ return 0; } if (value < range.min || value > range.max) { bool binary = pt->type == NLA_BINARY; if (binary) NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "binary attribute size out of range"); else NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range) { switch (pt->type) { case NLA_S8: range->min = S8_MIN; range->max = S8_MAX; break; case NLA_S16: range->min = S16_MIN; range->max = S16_MAX; break; case NLA_S32: range->min = S32_MIN; range->max = S32_MAX; break; case NLA_S64: case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range_signed; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_int_range_signed(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct netlink_range_validation_signed range; s64 value; switch (pt->type) { case NLA_S8: value = nla_get_s8(nla); break; case NLA_S16: value = nla_get_s16(nla); break; case NLA_S32: value = nla_get_s32(nla); break; case NLA_S64: value = nla_get_s64(nla); break; case NLA_SINT: value = nla_get_sint(nla); break; default: return -EINVAL; } nla_get_range_signed(pt, &range); if (value < range.min || value > range.max) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { switch (pt->type) { case NLA_U8: case NLA_U16: case NLA_U32: case NLA_U64: case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: case NLA_BE32: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: case NLA_S64: case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); return -EINVAL; } } static int nla_validate_mask(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } if (value & ~(u64)pt->mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set"); return -EINVAL; } return 0; } static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, unsigned int depth) { u16 strict_start_type = policy[0].strict_start_type; const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); int err = -ERANGE; if (strict_start_type && type >= strict_start_type) validate |= NL_VALIDATE_STRICT; if (type <= 0 || type > maxtype) return 0; type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } } if (validate & NL_VALIDATE_NESTED) { if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) && !(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED is missing"); return -EINVAL; } if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY && pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED not expected"); return -EINVAL; } } switch (pt->type) { case NLA_REJECT: if (extack && pt->reject_message) { NL_SET_BAD_ATTR(extack, nla); extack->_msg = pt->reject_message; return -EINVAL; } err = -EINVAL; goto out_err; case NLA_FLAG: if (attrlen > 0) goto out_err; break; case NLA_SINT: case NLA_UINT: if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } break; case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; err = validate_nla_bitfield32(nla, pt->bitfield32_valid); if (err) goto out_err; break; case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); else minlen = attrlen; if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) { err = -EINVAL; goto out_err; } fallthrough; case NLA_STRING: if (attrlen < 1) goto out_err; if (pt->len) { char *buf = nla_data(nla); if (buf[attrlen - 1] == '\0') attrlen--; if (attrlen > pt->len) goto out_err; } break; case NLA_BINARY: if (pt->len && attrlen > pt->len) goto out_err; break; case NLA_NESTED: /* a nested attributes is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { err = __nla_validate_parse(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, validate, extack, NULL, depth + 1); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_NESTED_ARRAY: /* a nested array attribute is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { int err; err = nla_validate_array(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, extack, validate, depth); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_UNSPEC: if (validate & NL_VALIDATE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unsupported attribute"); return -EINVAL; } if (attrlen < pt->len) goto out_err; break; default: if (pt->len) minlen = pt->len; else minlen = nla_attr_minlen[pt->type]; if (attrlen < minlen) goto out_err; } /* further validation */ switch (pt->validation_type) { case NLA_VALIDATE_NONE: /* nothing to do */ break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; case NLA_VALIDATE_MASK: err = nla_validate_mask(pt, nla, extack); if (err) return err; break; case NLA_VALIDATE_FUNCTION: if (pt->validate) { err = pt->validate(nla, extack); if (err) return err; } break; } return 0; out_err: NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "Attribute failed policy validation"); return err; } static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth) { const struct nlattr *nla; int rem; if (depth >= MAX_POLICY_RECURSION_DEPTH) { NL_SET_ERR_MSG(extack, "allowed policy recursion depth exceeded"); return -EINVAL; } if (tb) memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); nla_for_each_attr(nla, head, len, rem) { u16 type = nla_type(nla); if (type == 0 || type > maxtype) { if (validate & NL_VALIDATE_MAXTYPE) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute type"); return -EINVAL; } continue; } type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); if (err < 0) return err; } if (tb) tb[type] = (struct nlattr *)nla; } if (unlikely(rem > 0)) { pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", rem, current->comm); NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes"); if (validate & NL_VALIDATE_TRAILING) return -EINVAL; } return 0; } /** * __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 * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation depends on the validate flags passed, see * &enum netlink_validation for more details on that. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, NULL, 0); } EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy * @p: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used * to allocated Netlink buffers roughly the size of the actual * message. * * Returns 0 on success or a negative error code. */ int nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_len[p->type]) len += nla_total_size(nla_attr_len[p->type]); else if (nla_attr_minlen[p->type]) len += nla_total_size(nla_attr_minlen[p->type]); } return len; } EXPORT_SYMBOL(nla_policy_len); /** * __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 * @validate: validation strictness * @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. * Validation is controlled by the @validate parameter. * * Returns 0 on success or a negative error code. */ 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) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, tb, 0); } EXPORT_SYMBOL(__nla_parse); /** * nla_find - Find a specific attribute in a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @attrtype: type of attribute to look for * * Returns the first attribute in the stream matching the specified type. */ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype) { const struct nlattr *nla; int rem; nla_for_each_attr(nla, head, len, rem) if (nla_type(nla) == attrtype) return (struct nlattr *)nla; return NULL; } EXPORT_SYMBOL(nla_find); /** * nla_strscpy - Copy string attribute payload into a sized buffer * @dst: Where to copy the string to. * @nla: Attribute to copy the string from. * @dstsize: Size of destination buffer. * * Copies at most dstsize - 1 bytes into the destination buffer. * Unlike strscpy() the destination buffer is always padded out. * * Return: * * srclen - Returns @nla length (not including the trailing %NUL). * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater * than @dstsize. */ ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize) { size_t srclen = nla_len(nla); char *src = nla_data(nla); ssize_t ret; size_t len; if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX)) return -E2BIG; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; if (srclen >= dstsize) { len = dstsize - 1; ret = -E2BIG; } else { len = srclen; ret = len; } memcpy(dst, src, len); /* Zero pad end of dst. */ memset(dst + len, 0, dstsize - len); return ret; } EXPORT_SYMBOL(nla_strscpy); /** * nla_strdup - Copy string attribute payload into a newly allocated buffer * @nla: attribute to copy the string from * @flags: the type of memory to allocate (see kmalloc). * * Returns a pointer to the allocated buffer or NULL on error. */ char *nla_strdup(const struct nlattr *nla, gfp_t flags) { size_t srclen = nla_len(nla); char *src = nla_data(nla), *dst; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; dst = kmalloc(srclen + 1, flags); if (dst != NULL) { memcpy(dst, src, srclen); dst[srclen] = '\0'; } return dst; } EXPORT_SYMBOL(nla_strdup); /** * nla_memcpy - Copy a netlink attribute into another memory area * @dest: where to copy to memcpy * @src: netlink attribute to copy from * @count: size of the destination area * * Note: The number of bytes copied is limited by the length of * attribute's payload. memcpy * * Returns the number of bytes copied. */ int nla_memcpy(void *dest, const struct nlattr *src, int count) { int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); if (count > minlen) memset(dest + minlen, 0, count - minlen); return minlen; } EXPORT_SYMBOL(nla_memcpy); /** * nla_memcmp - Compare an attribute with sized memory area * @nla: netlink attribute * @data: memory area * @size: size of memory area */ int nla_memcmp(const struct nlattr *nla, const void *data, size_t size) { int d = nla_len(nla) - size; if (d == 0) d = memcmp(nla_data(nla), data, size); return d; } EXPORT_SYMBOL(nla_memcmp); /** * nla_strcmp - Compare a string attribute against a string * @nla: netlink string attribute * @str: another string */ int nla_strcmp(const struct nlattr *nla, const char *str) { int len = strlen(str); char *buf = nla_data(nla); int attrlen = nla_len(nla); int d; while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); return d; } EXPORT_SYMBOL(nla_strcmp); #ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); return nla; } EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(__nla_reserve_64bit); /** * __nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * The caller is responsible to ensure that the skb provides enough * tailroom for the payload. */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return NULL; return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return NULL; return __nla_reserve_64bit(skb, attrtype, attrlen, padattr); } EXPORT_SYMBOL(nla_reserve_64bit); /** * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute payload. */ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return NULL; return __nla_reserve_nohdr(skb, attrlen); } EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { struct nlattr *nla; nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put); /** * __nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { struct nlattr *nla; nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put_64bit); /** * __nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute payload. */ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { void *start; start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put); /** * nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return -EMSGSIZE; __nla_put_64bit(skb, attrtype, attrlen, data, padattr); return 0; } EXPORT_SYMBOL(nla_put_64bit); /** * nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); #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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NETFILTER_NETDEV_H_ #define _NETFILTER_NETDEV_H_ #include <linux/netfilter.h> #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif return rcu_access_pointer(skb->dev->nf_hooks_ingress); } /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. */ if (unlikely(!e)) return 0; nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; return ret; } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { return 0; } static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } #endif /* CONFIG_NETFILTER_INGRESS */ #ifdef CONFIG_NETFILTER_EGRESS static inline bool nf_hook_egress_active(void) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) return false; #endif return true; } /** * nf_hook_egress - classify packets before transmission * @skb: packet to be classified * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. * On egress, the order is reversed for symmetry. Conceptually, tc and * netfilter can be thought of as layers, with netfilter layered above tc: * When tc redirects a packet to another interface, netfilter is not applied * because the packet is on the tc layer. * * The nf_skip_egress flag controls whether netfilter is applied on egress. * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the * packet passes through tc and netfilter. Because __dev_queue_xmit() may be * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. * * Returns: @skb on success or %NULL if the packet was consumed or filtered. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { struct nf_hook_entries *e; struct nf_hook_state state; int ret; #ifdef CONFIG_NETFILTER_SKIP_EGRESS if (skb->nf_skip_egress) return skb; #endif e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); rcu_read_unlock(); if (ret == 1) { return skb; } else if (ret < 0) { *rc = NET_XMIT_DROP; return NULL; } else { /* ret == 0 */ *rc = NET_XMIT_SUCCESS; return NULL; } } #else /* CONFIG_NETFILTER_EGRESS */ static inline bool nf_hook_egress_active(void) { return false; } static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { return skb; } #endif /* CONFIG_NETFILTER_EGRESS */ static inline void nf_skip_egress(struct sk_buff *skb, bool skip) { #ifdef CONFIG_NETFILTER_SKIP_EGRESS skb->nf_skip_egress = skip; #endif } static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif #ifdef CONFIG_NETFILTER_EGRESS RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); #endif } #endif /* _NETFILTER_NETDEV_H_ */ |
| 88 88 87 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H #include <linux/context_tracking_state.h> #include <linux/sched.h> /* * Common vtime APIs */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING extern void vtime_account_kernel(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); extern void vtime_account_softirq(struct task_struct *tsk); extern void vtime_account_hardirq(struct task_struct *tsk); extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } static inline void vtime_account_softirq(struct task_struct *tsk) { } static inline void vtime_account_hardirq(struct task_struct *tsk) { } static inline void vtime_flush(struct task_struct *tsk) { } #endif /* * vtime_accounting_enabled_this_cpu() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); static __always_inline void vtime_account_guest_enter(void) { vtime_account_kernel(current); current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { vtime_account_kernel(current); current->flags &= ~PF_VCPU; } #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. * For now vtime state is tied to context tracking. We might want to decouple * those later if necessary. */ static inline bool vtime_accounting_enabled(void) { return context_tracking_enabled(); } static inline bool vtime_accounting_enabled_cpu(int cpu) { return context_tracking_enabled_cpu(cpu); } static inline bool vtime_accounting_enabled_this_cpu(void) { return context_tracking_enabled_this_cpu(); } extern void vtime_task_switch_generic(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { if (vtime_accounting_enabled_this_cpu()) vtime_task_switch_generic(prev); } static __always_inline void vtime_account_guest_enter(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; } #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } static __always_inline void vtime_account_guest_enter(void) { current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { current->flags &= ~PF_VCPU; } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset); #else static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { } #endif static inline void account_softirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, SOFTIRQ_OFFSET); irqtime_account_irq(tsk, SOFTIRQ_OFFSET); } static inline void account_softirq_exit(struct task_struct *tsk) { vtime_account_softirq(tsk); irqtime_account_irq(tsk, 0); } static inline void account_hardirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, HARDIRQ_OFFSET); irqtime_account_irq(tsk, HARDIRQ_OFFSET); } static inline void account_hardirq_exit(struct task_struct *tsk) { vtime_account_hardirq(tsk); irqtime_account_irq(tsk, 0); } #endif /* _LINUX_KERNEL_VTIME_H */ |
| 214 215 206 8 2 206 206 215 206 205 206 204 197 274 420 420 5 1 5 5 419 274 420 54 420 420 54 419 419 165 194 195 1 206 206 206 206 204 206 206 205 206 206 204 203 6 4 1 1 204 204 204 204 1 204 204 1 1 179 179 6 176 176 179 178 3 177 177 176 177 2 177 177 2 39 2 2 2 2 2 2 2 175 176 176 9 178 2 2 3 1 274 2 182 8 178 1 276 276 275 1 2 203 181 181 3 178 178 6 2 3 3 9 1 176 2 8 993 994 869 18 204 10 177 3 203 39 176 203 201 3 204 176 1 176 206 205 2 206 206 177 39 39 39 3 3 39 8 1 10 10 4 9 8 5 3 274 274 274 274 274 274 274 252 252 2 252 252 252 29 189 165 1 165 31 189 188 4 4 4 29 4 32 33 4 3 29 30 2 3 29 29 32 30 2 2 28 28 30 158 1 41 171 1 161 13 2 196 172 3 3 3 27 2 31 30 3 33 2 6 28 31 30 3 2 30 2 6 28 173 171 2 28 170 28 171 155 41 1 39 190 28 165 4 1 189 187 4 188 188 4 2 2 8 5 5 206 2 8 9 196 191 24 193 206 206 206 2 204 206 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/wordpart.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags) { struct filename *result; char *kname; int len; result = audit_reusename(filename); if (result) return result; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); /* * Handle both empty path and copy failure in one go. */ if (unlikely(len <= 0)) { if (unlikely(len < 0)) { __putname(result); return ERR_PTR(len); } /* The empty path is special. */ if (!(flags & LOOKUP_EMPTY)) { __putname(result); return ERR_PTR(-ENOENT); } } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; /* * size is chosen that way we to guarantee that * result->iname[0] is within the same object and that * kname can't be equal to result->iname, no matter what. */ result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); kfree(result); return ERR_PTR(len); } /* The empty path is special. */ if (unlikely(!len) && !(flags & LOOKUP_EMPTY)) { __putname(kname); kfree(result); return ERR_PTR(-ENOENT); } if (unlikely(len == PATH_MAX)) { __putname(kname); kfree(result); return ERR_PTR(-ENAMETOOLONG); } } atomic_set(&result->refcnt, 1); result->uptr = filename; result->aname = NULL; audit_getname(result); return result; } struct filename *getname_uflags(const char __user *filename, int uflags) { int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return getname_flags(filename, flags); } struct filename *getname(const char __user * filename) { return getname_flags(filename, 0); } struct filename *__getname_maybe_null(const char __user *pathname) { struct filename *name; char c; /* try to save on allocations; loss on um, though */ if (get_user(c, pathname)) return ERR_PTR(-EFAULT); if (!c) return NULL; name = getname_flags(pathname, LOOKUP_EMPTY); if (!IS_ERR(name) && !(name->name[0])) { putname(name); name = NULL; } return name; } struct filename *getname_kernel(const char * filename) { struct filename *result; int len = strlen(filename) + 1; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { result->name = (char *)result->iname; } else if (len <= PATH_MAX) { const size_t size = offsetof(struct filename, iname[1]); struct filename *tmp; tmp = kmalloc(size, GFP_KERNEL); if (unlikely(!tmp)) { __putname(result); return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; result = tmp; } else { __putname(result); return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; atomic_set(&result->refcnt, 1); audit_getname(result); return result; } EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { if (IS_ERR_OR_NULL(name)) return; if (WARN_ON_ONCE(!atomic_read(&name->refcnt))) return; if (!atomic_dec_and_test(&name->refcnt)) return; if (name->name != name->iname) { __putname(name->name); kfree(name); } else __putname(name); } EXPORT_SYMBOL(putname); /** * check_acl - perform ACL permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the ACL permission checking. Since this function * retrieve POSIX acls it needs to know whether it is called from a blocking or * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * 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. */ static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_inode_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(idmap, inode, acl, mask); } acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(idmap, inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * Very quick optimistic "we know we have no ACL's" check. * * Note that this is purely for ACL_TYPE_ACCESS, and purely * for the "we have cached that there are no ACLs" case. * * If this returns true, we know there are no ACLs. But if * it returns false, we might still not have ACLs (it could * be the is_uncached_acl() case). */ static inline bool no_acl_inode(struct inode *inode) { #ifdef CONFIG_FS_POSIX_ACL return likely(!READ_ONCE(inode->i_acl)); #else return true; #endif } /** * acl_permission_check - perform basic UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the basic UNIX permission checking. Since this * function may retrieve POSIX acls it needs to know whether it is called from a * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * 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. */ static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) { unsigned int mode = inode->i_mode; vfsuid_t vfsuid; /* * Common cheap case: everybody has the requested * rights, and there are no ACLs to check. No need * to do any owner/group checks in that case. * * - 'mask&7' is the requested permission bit set * - multiplying by 0111 spreads them out to all of ugo * - '& ~mode' looks for missing inode permission bits * - the '!' is for "no missing permissions" * * After that, we just need to check that there are no * ACL's on the inode - do the 'IS_POSIXACL()' check last * because it will dereference the ->i_sb pointer and we * want to avoid that if at all possible. */ if (!((mask & 7) * 0111 & ~mode)) { if (no_acl_inode(inode)) return 0; if (!IS_POSIXACL(inode)) return 0; } /* Are we the owner? If so, ACL's don't matter */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(idmap, inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @idmap: idmap of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. * * 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. */ int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(idmap, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /** * do_inode_permission - UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(idmap, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(idmap, inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @idmap: idmap of the mount the inode was found from * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ if (IS_IMMUTABLE(inode)) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (HAS_UNMAPPED_ID(idmap, inode)) return -EACCES; } retval = do_inode_permission(idmap, inode, mask); if (retval) return retval; retval = devcgroup_inode_permission(inode, mask); if (retval) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags, state; unsigned seq, next_seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; const char *pathname; struct nameidata *saved; unsigned root_seq; int dfd; vfsuid_t dir_vfsuid; umode_t dir_mode; } __randomize_layout; #define ND_ROOT_PRESET 1 #define ND_ROOT_GRABBED 2 #define ND_JUMPED 4 static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->depth = 0; p->dfd = dfd; p->name = name; p->pathname = likely(name) ? name->name : ""; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name, const struct path *root) { __set_nameidata(p, dfd, name); p->state = 0; if (unlikely(root)) { p->state = ND_ROOT_PRESET; p->root = *root; } } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * @mnt: The mountpoint to check. * @dentry: The dentry to check. * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void leave_rcu(struct nameidata *nd) { nd->flags &= ~LOOKUP_RCU; nd->seq = nd->next_seq = 0; rcu_read_unlock(); } static void terminate_walk(struct nameidata *nd) { drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->state & ND_ROOT_GRABBED) { path_put(&nd->root); nd->state &= ~ND_ROOT_GRABBED; } } else { leave_rcu(nd); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; return false; } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET)) return true; nd->state |= ND_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; leave_rcu(nd); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: leave_rcu(nd); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * Returns: true on success, false on failure * * Similar to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) { int res; BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(!legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); if (unlikely(res)) { if (res > 0) goto out2; goto out1; } if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; leave_rcu(nd); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: leave_rcu(nd); return false; out_dput: leave_rcu(nd); dput(dentry); return false; } static inline int d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dir, name, dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (!(nd->state & ND_ROOT_PRESET)) if (!(nd->flags & LOOKUP_IS_SCOPED)) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->state & ND_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->state |= ND_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (error) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (read_seqcount_retry(&d->d_seq, nd->seq)) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->state |= ND_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(const struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->state |= ND_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } static int sysctl_protected_symlinks __read_mostly; static int sysctl_protected_hardlinks __read_mostly; static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_hardlinks", .data = &sysctl_protected_hardlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_fifos", .data = &sysctl_protected_fifos, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "protected_regular", .data = &sysctl_protected_regular, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __init init_fs_namei_sysctls(void) { register_sysctl_init("fs", namei_sysctls); return 0; } fs_initcall(init_fs_namei_sysctls); #endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * @inode: Used for idmapping. * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { struct mnt_idmap *idmap; vfsuid_t vfsuid; if (!sysctl_protected_symlinks) return 0; idmap = mnt_idmap(nd->path.mnt); vfsuid = i_uid_into_vfsuid(idmap, inode); /* Allowed if owner and follower match. */ if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (vfsuid_valid(nd->dir_vfsuid) && vfsuid_eq(nd->dir_vfsuid, vfsuid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @idmap: idmap of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(idmap, inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @idmap: idmap of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * 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. * * Returns 0 if successful, -ve on error. */ int may_linkat(struct mnt_idmap *idmap, const struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(idmap, inode) || inode_owner_or_capable(idmap, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @idmap: idmap of the mount the inode was found from * @nd: nameidata pathwalk data * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * 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. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd, struct inode *const inode) { umode_t dir_mode = nd->dir_mode; vfsuid_t dir_vfsuid = nd->dir_vfsuid, i_vfsuid; if (likely(!(dir_mode & S_ISVTX))) return 0; if (S_ISREG(inode->i_mode) && !sysctl_protected_regular) return 0; if (S_ISFIFO(inode->i_mode) && !sysctl_protected_fifos) return 0; i_vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq(i_vfsuid, dir_vfsuid)) return 0; if (vfsuid_eq_kuid(i_vfsuid, current_fsuid())) return 0; if (likely(dir_mode & 0002)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create"); return -EACCES; } if (dir_mode & 0020) { if (sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_fifo"); return -EACCES; } if (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_regular"); return -EACCES; } } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path, unsigned int flags) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, flags); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (likely(!(flags & DCACHE_MANAGED_DENTRY))) return true; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->state |= ND_JUMPED; nd->next_seq = read_seqcount_begin(&dentry->d_seq); flags = dentry->d_flags; // makes sure that non-RCU pathwalk could reach // this state. if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = nd->next_seq; if (likely(__follow_mount_rcu(nd, path))) return 0; // *path and nd->next_seq might've been clobbered path->mnt = nd->path.mnt; path->dentry = dentry; nd->next_seq = seq; if (!try_to_unlazy_next(nd, dentry)) return -ECHILD; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) ret = -EXDEV; else nd->state |= ND_JUMPED; } if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; struct inode *dir = base->d_inode; if (dentry) return dentry; /* Don't create child dentry for a dead directory. */ if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } return dentry; } EXPORT_SYMBOL(lookup_one_qstr_excl); /** * lookup_fast - do fast lockless (but racy) lookup of a dentry * @nd: current nameidata * * Do a fast, but racy lookup in the dcache for the given dentry, and * revalidate it. Returns a valid dentry pointer or NULL if one wasn't * found. On error, an ERR_PTR will be returned. * * If this function returns a valid dentry and the walk is no longer * lazy, the dentry will carry a reference that must later be put. If * RCU mode is still in force, then this is not the case and the dentry * must be legitimized before use. If this returns NULL, then the walk * will no longer be in RCU mode. */ static struct dentry *lookup_fast(struct nameidata *nd) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. */ if (read_seqcount_retry(&parent->d_seq, nd->seq)) return ERR_PTR(-ECHILD); status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry)) return ERR_PTR(-ECHILD); if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct mnt_idmap *idmap, struct nameidata *restrict nd) { int err, mask; mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0; err = inode_permission(idmap, nd->inode, mask | MAY_EXEC); if (likely(!err)) return 0; // If we failed, and we weren't in LOOKUP_RCU, it's final if (!(nd->flags & LOOKUP_RCU)) return err; // Drop out of RCU mode to make sure it wasn't transient if (!try_to_unlazy(nd)) return -ECHILD; // redo it all non-lazy if (err != -ECHILD) // hard error return err; return inode_permission(idmap, nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, nd->next_seq); if (!try_to_unlazy(nd) || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, int flags) { struct saved *last; const char *res; int error = reserve_stack(nd, link); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = nd->next_seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. * * NOTE: dentry must be what nd->next_seq had been sampled from. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry) { struct path path; struct inode *inode; int err = handle_mounts(nd, dentry, &path); if (err < 0) return ERR_PTR(err); inode = path.dentry->d_inode; if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (nd->flags & LOOKUP_RCU) { if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); if (unlikely(!inode)) return ERR_PTR(-ENOENT); } else { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = nd->next_seq; return NULL; } if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink above matches inode */ if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); } else { if (path.mnt == nd->path.mnt) mntget(path.mnt); } return pick_link(nd, &path, inode, flags); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; // makes sure that non-RCU pathwalk could reach this state if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; nd->next_seq = read_seqcount_begin(&parent->d_seq); // makes sure that non-RCU pathwalk could reach this state if (read_seqcount_retry(&old->d_seq, nd->seq)) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); nd->next_seq = nd->seq; return nd->path.dentry; } static struct dentry *follow_dotdot(struct nameidata *nd) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); return dget(nd->path.dentry); } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (error) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd); else parent = follow_dotdot(nd); if (IS_ERR(parent)) return ERR_CAST(parent); error = step_into(nd, WALK_NOFOLLOW, parent); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)) return ERR_PTR(-EAGAIN); if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)) return ERR_PTR(-EAGAIN); } } return NULL; } static const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return step_into(nd, flags, dentry); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * Calculate the length and hash of the path component, and * return the length as the result. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long a, b, x, y = (unsigned long)nd->path.dentry; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; /* * The first iteration is special, because it can result in * '.' and '..' and has no mixing other than the final fold. */ a = load_unaligned_zeropad(name); b = a ^ REPEAT_BYTE('/'); if (has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)) { adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); *lastword = a; len = find_zero(mask); nd->last.hash = fold_hash(a, y); nd->last.len = len; return name + len; } len = 0; x = 0; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); x ^= a; len += find_zero(mask); *lastword = 0; // Multi-word components cannot be DOT or DOTDOT nd->last.hash = fold_hash(x, y); nd->last.len = len; return name + len; } /* * Note that the 'last' word is always zero-masked, but * was loaded as a possibly big-endian word. */ #ifdef __BIG_ENDIAN #define LAST_WORD_IS_DOT (0x2eul << (BITS_PER_LONG-8)) #define LAST_WORD_IS_DOTDOT (0x2e2eul << (BITS_PER_LONG-16)) #endif #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long hash = init_name_hash(nd->path.dentry); unsigned long len = 0, c, last = 0; c = (unsigned char)*name; do { last = (last << 8) + c; len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); // This is reliable for DOT or DOTDOT, since the component // cannot contain NUL characters - top bits being zero means // we cannot have had any other pathnames. *lastword = last; nd->last.hash = end_name_hash(hash); nd->last.len = len; return name + len; } #endif #ifndef LAST_WORD_IS_DOT #define LAST_WORD_IS_DOT 0x2e #define LAST_WORD_IS_DOTDOT 0x2e2e #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; if (!*name) { nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; } /* At this point we know we have a real path component. */ for(;;) { struct mnt_idmap *idmap; const char *link; unsigned long lastword; idmap = mnt_idmap(nd->path.mnt); err = may_lookup(idmap, nd); if (err) return err; nd->last.name = name; name = hash_name(nd, name, &lastword); switch(lastword) { case LAST_WORD_IS_DOTDOT: nd->last_type = LAST_DOTDOT; nd->state |= ND_JUMPED; break; case LAST_WORD_IS_DOT: nd->last_type = LAST_DOT; break; default: nd->last_type = LAST_NORM; nd->state &= ~ND_JUMPED; struct dentry *parent = nd->path.dentry; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { err = parent->d_op->d_hash(parent, &nd->last); if (err < 0) return err; } } if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (!depth) { nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->pathname; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) return ERR_PTR(-EAGAIN); if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); else nd->seq = nd->next_seq = 0; nd->flags = flags; nd->state |= ND_JUMPED; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (nd->state & ND_ROOT_PRESET) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ CLASS(fd_raw, f)(nd->dfd); struct dentry *dentry; if (fd_empty(f)) return ERR_PTR(-EBADF); if (flags & LOOKUP_LINKAT_EMPTY) { if (fd_file(f)->f_cred != current_cred() && !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH)) return ERR_PTR(-ENOENT); } dentry = fd_file(f)->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) return ERR_PTR(-ENOTDIR); nd->path = fd_file(f)->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->state |= ND_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); nd->next_seq = nd->seq; return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry)); } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); return retval; } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } /* Note: this does not consume "name" */ static int __filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } restore_nameidata(); return retval; } static int filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { return __filename_parentat(dfd, name, flags, parent, last, type, NULL); } /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path) { struct dentry *d; struct qstr last; int type, error; error = filename_parentat(dfd, name, 0, path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) { path_put(path); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); d = lookup_one_qstr_excl(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); } return d; } struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename = getname_kernel(name); struct dentry *res = __kern_path_locked(AT_FDCWD, filename, path); putname(filename); return res; } struct dentry *user_path_locked_at(int dfd, const char __user *name, struct path *path) { struct filename *filename = getname(name); struct dentry *res = __kern_path_locked(dfd, filename, path); putname(filename); return res; } EXPORT_SYMBOL(user_path_locked_at); int kern_path(const char *name, unsigned int flags, struct path *path) { struct filename *filename = getname_kernel(name); int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL); putname(filename); return ret; } EXPORT_SYMBOL(kern_path); /** * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair * @filename: filename structure * @flags: lookup flags * @parent: pointer to struct path to fill * @last: last component * @type: type of the last component * @root: pointer to struct path of the base directory */ int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { return __filename_parentat(AT_FDCWD, filename, flags, parent, last, type, root); } EXPORT_SYMBOL(vfs_path_parent_lookup); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { struct filename *filename; struct path root = {.mnt = mnt, .dentry = dentry}; int ret; filename = getname_kernel(name); /* the first argument of filename_lookup() is ignored with root */ ret = filename_lookup(AT_FDCWD, filename, flags, path, &root); putname(filename); return ret; } EXPORT_SYMBOL(vfs_path_lookup); static int lookup_one_common(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len, struct qstr *this) { this->name = name; this->len = len; this->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (is_dot_dotdot(name, len)) return -EACCES; while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, this); if (err < 0) return err; } return inode_permission(idmap, base->d_inode, MAY_EXEC); } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); if (err) return ERR_PTR(err); return lookup_dcache(&this, base, 0); } EXPORT_SYMBOL(try_lookup_one_len); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one_len); /** * lookup_one - filesystem helper to lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_common(idmap, name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one); /** * lookup_one_unlocked - filesystem helper to lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { struct qstr this; int err; struct dentry *ret; err = lookup_one_common(idmap, name, base, len, &this); if (err) return ERR_PTR(err); ret = lookup_dcache(&this, base, 0); if (!ret) ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_unlocked); /** * lookup_one_positive_unlocked - filesystem helper to lookup single * pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The helper should be called without i_mutex held. */ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { struct dentry *ret = lookup_one_unlocked(idmap, name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_one_positive_unlocked); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { return lookup_one_unlocked(&nop_mnt_idmap, name, base, len); } EXPORT_SYMBOL(lookup_one_len_unlocked); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { return lookup_one_positive_unlocked(&nop_mnt_idmap, name, base, len); } EXPORT_SYMBOL(lookup_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path, 0); return 0; } #endif int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { struct filename *filename = getname_flags(name, flags); int ret = filename_lookup(dfd, filename, flags, path, NULL); putname(filename); return ret; } EXPORT_SYMBOL(user_path_at); int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), fsuid)) return 0; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, dir), fsuid)) return 0; return !capable_wrt_inode_uidgid(idmap, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(idmap, dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } // p1 != p2, both are on the same filesystem, ->s_vfs_rename_mutex is held static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) { struct dentry *p = p1, *q = p2, *r; while ((r = p->d_parent) != p2 && r != p) p = r; if (r == p2) { // p is a child of p2 and an ancestor of p1 or p1 itself inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } // p is the root of connected component that contains p1 // p2 does not occur on the path from p to p1 while ((r = q->d_parent) != p1 && r != p && r != q) q = r; if (r == p1) { // q is a child of p1 and an ancestor of p2 or p2 itself inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return q; } else if (likely(r == p)) { // both p2 and p1 are descendents of p inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return NULL; } else { // no common ancestor at the time we'd been called mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); return ERR_PTR(-EXDEV); } } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); return lock_two_directories(p1, p2); } EXPORT_SYMBOL(lock_rename); /* * c1 and p2 should be on the same fs. */ struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) { if (READ_ONCE(c1->d_parent) == p2) { /* * hopefully won't need to touch ->s_vfs_rename_mutex at all. */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); /* * now that p2 is locked, nobody can move in or out of it, * so the test below is safe. */ if (likely(c1->d_parent == p2)) return NULL; /* * c1 got moved out of p2 while we'd been taking locks; * unlock and fall back to slow case. */ inode_unlock(p2->d_inode); } mutex_lock(&c1->d_sb->s_vfs_rename_mutex); /* * nobody can move out of any directories on this fs. */ if (likely(c1->d_parent != p2)) return lock_two_directories(c1->d_parent, p2); /* * c1 got moved into p2 while we were taking locks; * we need p2 locked and ->s_vfs_rename_mutex unlocked, * for consistency with lock_rename(). */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); return NULL; } EXPORT_SYMBOL(lock_rename_child); void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(idmap, dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } /** * vfs_create - create new file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child file * @mode: mode of the child file * @want_excl: whether the file must not yet exist * * Create a new 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. */ int vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { int error; error = may_create(idmap, dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = dir->i_op->create(idmap, dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create(&nop_mnt_idmap, dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(struct mnt_idmap *idmap, const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; } error = inode_permission(idmap, inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(idmap, inode)) return -EPERM; return 0; } static int handle_truncate(struct mnt_idmap *idmap, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; error = security_file_truncate(filp); if (!error) { error = do_truncate(idmap, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(struct mnt_idmap *idmap, const struct path *dir, struct dentry *dentry, umode_t mode) { int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap)) return -EOVERFLOW; error = inode_permission(idmap, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { struct mnt_idmap *idmap; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } if (open_flag & O_CREAT) audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(idmap, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(idmap, &nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static inline bool trailing_slashes(struct nameidata *nd) { return (bool)nd->last.name[nd->last.len]; } static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag) { struct dentry *dentry; if (open_flag & O_CREAT) { if (trailing_slashes(nd)) return ERR_PTR(-EISDIR); /* Don't bother on an O_EXCL create */ if (open_flag & O_EXCL) return NULL; } if (trailing_slashes(nd)) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; dentry = lookup_fast(nd); if (IS_ERR_OR_NULL(dentry)) return dentry; if (open_flag & O_CREAT) { /* Discard negative dentries. Need inode_lock to do the create */ if (!dentry->d_inode) { if (!(nd->flags & LOOKUP_RCU)) dput(dentry); dentry = NULL; } } return dentry; } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } /* We _can_ be in RCU mode here */ dentry = lookup_fast_for_open(nd, open_flag); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; if (!(open_flag & O_CREAT)) { if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) return ERR_PTR(-ECHILD); } else { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry)) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); } if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct mnt_idmap *idmap; int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(idmap, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(idmap, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = security_file_post_open(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(idmap, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } /** * vfs_tmpfile - create tmpfile * @idmap: idmap of the mount the inode was found from * @parentpath: pointer to the path of the base directory * @file: file descriptor of the new tmpfile * @mode: mode of the new tmpfile * * Create a temporary 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. */ int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode) { struct dentry *child; struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; int open_flag = file->f_flags; /* we want directory to be writable */ error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (!dir->i_op->tmpfile) return -EOPNOTSUPP; child = d_alloc(parentpath->dentry, &slash_name); if (unlikely(!child)) return -ENOMEM; file->f_path.mnt = parentpath->mnt; file->f_path.dentry = child; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = dir->i_op->tmpfile(idmap, dir, file, mode); dput(child); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); if (error) return error; /* Don't check for other permissions, the inode was just created */ error = may_open(idmap, &file->f_path, 0, file->f_flags); if (error) return error; inode = file_inode(file); if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } security_inode_post_create_tmpfile(idmap, inode); return 0; } /** * kernel_tmpfile_open - open a tmpfile for kernel internal use * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile * @open_flag: flags * @cred: credentials for open * * Create and open a temporary file. The file is not accounted in nr_files, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred) { struct file *file; int error; file = alloc_empty_file_noaccount(open_flag, cred); if (IS_ERR(file)) return file; error = vfs_tmpfile(idmap, parentpath, file, mode); if (error) { fput(file); file = ERR_PTR(error); } return file; } EXPORT_SYMBOL(kernel_tmpfile_open); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; error = vfs_tmpfile(mnt_idmap(path.mnt), &path, file, op->mode); if (error) goto out2; audit_inode(nd->name, file->f_path.dentry, 0); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; set_nameidata(&nd, dfd, pathname, NULL); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(const struct path *root, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; int flags = op->lookup_flags; if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename, root); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); putname(filename); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; bool want_dir = lookup_flags & LOOKUP_DIRECTORY; unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* * Do the final lookup. Suppress 'create' if there is a trailing * '/', and a directory wasn't requested. */ if (last.name[last.len] && !want_dir) create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); dentry = lookup_one_qstr_excl(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; error = -EEXIST; if (d_is_positive(dentry)) goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } if (unlikely(err2)) { error = err2; goto fail; } return dentry; fail: dput(dentry); dentry = ERR_PTR(error); unlock: inode_unlock(path->dentry->d_inode); if (!err2) mnt_drop_write(path->mnt); out: path_put(path); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { struct filename *filename = getname_kernel(pathname); struct dentry *res = filename_create(dfd, filename, path, lookup_flags); putname(filename); return res; } EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { struct filename *filename = getname(pathname); struct dentry *res = filename_create(dfd, filename, path, lookup_flags); putname(filename); return res; } EXPORT_SYMBOL(user_path_create); /** * vfs_mknod - create device node or file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child device node * @mode: mode of the child device node * @dev: device number of device to create * * Create a device node or 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. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(idmap, dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = dir->i_op->mknod(idmap, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } static int do_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { struct mnt_idmap *idmap; struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) goto out1; retry: dentry = filename_create(dfd, name, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out1; error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2; idmap = mnt_idmap(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(idmap, path.dentry->d_inode, dentry, mode, true); if (!error) security_path_post_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, 0); break; } out2: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out1: putname(name); return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { return do_mknodat(dfd, getname(filename), mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { return do_mknodat(AT_FDCWD, getname(filename), mode, dev); } /** * vfs_mkdir - create directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @mode: mode of the child directory * * Create a directory. * * 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. */ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int error; unsigned max_links = dir->i_sb->s_max_links; error = may_create(idmap, dir, dentry); if (error) return error; if (!dir->i_op->mkdir) return -EPERM; mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; if (max_links && dir->i_nlink >= max_links) return -EMLINK; error = dir->i_op->mkdir(idmap, dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); int do_mkdirat(int dfd, struct filename *name, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: dentry = filename_create(dfd, name, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode); } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out_putname: putname(name); return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { return do_mkdirat(dfd, getname(pathname), mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { return do_mkdirat(AT_FDCWD, getname(pathname), mode); } /** * vfs_rmdir - remove directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * * Remove a directory. * * 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. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { int error = may_delete(idmap, dir, dentry, 1); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry) || (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); int do_rmdir(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) goto exit1; switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit2; case LAST_DOT: error = -EINVAL; goto exit2; case LAST_ROOT: error = -EBUSY; goto exit2; } error = mnt_want_write(path.mnt); if (error) goto exit2; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; if (!dentry->d_inode) { error = -ENOENT; goto exit4; } error = security_path_rmdir(&path, dentry); if (error) goto exit4; error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry); exit4: dput(dentry); exit3: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit2: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } exit1: putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object * @idmap: idmap of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * 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. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(idmap, dir, dentry, 0); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (IS_SWAPFILE(target)) error = -EPERM; else if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ int do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode = NULL; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) goto exit1; error = -EISDIR; if (type != LAST_NORM) goto exit2; error = mnt_want_write(path.mnt); if (error) goto exit2; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ if (last.name[last.len] || d_is_negative(dentry)) goto slashes; inode = dentry->d_inode; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit3; error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, &delegated_inode); exit3: dput(dentry); } inode_unlock(path.dentry->d_inode); if (inode) iput(inode); /* truncate the inode here */ inode = NULL; if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path.mnt); exit2: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; inode = NULL; goto retry; } exit1: putname(name); return error; slashes: if (d_is_negative(dentry)) error = -ENOENT; else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; goto exit3; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; if (flag & AT_REMOVEDIR) return do_rmdir(dfd, getname(pathname)); return do_unlinkat(dfd, getname(pathname)); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { return do_unlinkat(AT_FDCWD, getname(pathname)); } /** * vfs_symlink - create symlink * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child symlink file * @oldname: name of the file to link to * * Create a symlink. * * 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. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname) { int error; error = may_create(idmap, dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = dir->i_op->symlink(idmap, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); int do_symlinkat(struct filename *from, int newdfd, struct filename *to) { int error; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; if (IS_ERR(from)) { error = PTR_ERR(from); goto out_putnames; } retry: dentry = filename_create(newdfd, to, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putnames; error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out_putnames: putname(to); putname(from); return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_symlinkat(getname(oldname), newdfd, getname(newname)); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { return do_symlinkat(getname(oldname), AT_FDCWD, getname(newname)); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @idmap: idmap of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_mutex * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * 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. */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create(idmap, dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count will likely cause i_uid and i_gid to * be writen back improperly if their true value is unknown to * the vfs. */ if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode->i_state & I_LINKABLE)) { spin_lock(&inode->i_lock); inode->i_state &= ~I_LINKABLE; spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags) { struct mnt_idmap *idmap; struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) { error = -EINVAL; goto out_putnames; } /* * To use null names we require CAP_DAC_READ_SEARCH or * that the open-time creds of the dfd matches current. * This ensures that not everyone will be able to create * a hardlink using the passed file descriptor. */ if (flags & AT_EMPTY_PATH) how |= LOOKUP_LINKAT_EMPTY; if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) goto out_putnames; new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out_putpath; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; idmap = mnt_idmap(new_path.mnt); error = may_linkat(idmap, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out_putpath: path_put(&old_path); out_putnames: putname(old); putname(new); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { return do_linkat(olddfd, getname_uflags(oldname, flags), newdfd, getname(newname), flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { return do_linkat(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } /** * vfs_rename - rename a filesystem object * @rd: pointer to &struct renamedata info * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { int error; struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; struct inode **delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete(rd->old_mnt_idmap, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create(rd->new_mnt_idmap, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete(rd->new_mnt_idmap, new_dir, new_dentry, is_dir); else error = may_delete(rd->new_mnt_idmap, new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(rd->old_mnt_idmap, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(rd->new_mnt_idmap, target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) goto out; error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(rd->new_mnt_idmap, old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) goto put_names; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) goto put_names; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: error = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (error) goto put_names; error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (error) goto exit1; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); if (IS_ERR(trap)) { error = PTR_ERR(trap); goto exit_lock_rename; } old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry, lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; /* source must exist */ error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; error = -EEXIST; if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) goto exit5; if (flags & RENAME_EXCHANGE) { error = -ENOENT; if (d_is_negative(new_dentry)) goto exit5; if (!d_is_dir(new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit5; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit5; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) goto exit5; /* target should not be an ancestor of source */ if (!(flags & RENAME_EXCHANGE)) error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&old_path, old_dentry, &new_path, new_dentry, flags); if (error) goto exit5; rd.old_dir = old_path.dentry->d_inode; rd.old_dentry = old_dentry; rd.old_mnt_idmap = mnt_idmap(old_path.mnt); rd.new_dir = new_path.dentry->d_inode; rd.new_dentry = new_dentry; rd.new_mnt_idmap = mnt_idmap(new_path.mnt); rd.delegated_inode = &delegated_inode; rd.flags = flags; error = vfs_rename(&rd); exit5: dput(new_dentry); exit4: dput(old_dentry); exit3: unlock_rename(new_path.dentry, old_path.dentry); exit_lock_rename: if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } put_names: putname(from); putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen) { int copylen; copylen = linklen; if (unlikely(copylen > (unsigned) buflen)) copylen = buflen; if (copy_to_user(buffer, link, copylen)) copylen = -EFAULT; return copylen; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (inode->i_opflags & IOP_CACHED_LINK) return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen); if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr; struct page *page; struct address_space *mapping = inode->i_mapping; if (!dentry) { page = find_get_page(mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) return (char*)page; } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); kaddr = page_address(page); nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); void page_put_link(void *arg) { put_page(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { const char *link; int res; DEFINE_DELAYED_CALL(done); link = page_get_link(dentry, d_inode(dentry), &done); res = PTR_ERR(link); if (!IS_ERR(link)) res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); int page_symlink(struct inode *inode, const char *symname, int len) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); struct folio *folio; void *fsdata = NULL; int err; unsigned int flags; retry: if (nofs) flags = memalloc_nofs_save(); err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata); if (nofs) memalloc_nofs_restore(flags); if (err) goto fail; memcpy(folio_address(folio), symname, len - 1); err = aops->write_end(NULL, mapping, 0, len - 1, len - 1, folio, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 436 3 149 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timestamp #if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMESTAMP_H #include <linux/tracepoint.h> #include <linux/fs.h> #define CTIME_QUERIED_FLAGS \ { I_CTIME_QUERIED, "Q" } DECLARE_EVENT_CLASS(ctime, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(time64_t, ctime_s) __field(u32, ctime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; ), TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns ) ); DEFINE_EVENT(ctime, inode_set_ctime_to_ts, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); DEFINE_EVENT(ctime, ctime_xchg_skip, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); TRACE_EVENT(ctime_ns_xchg, TP_PROTO(struct inode *inode, u32 old, u32 new, u32 cur), TP_ARGS(inode, old, new, cur), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(u32, gen) __field(u32, old) __field(u32, new) __field(u32, cur) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->old = old; __entry->new = new; __entry->cur = cur; ), TP_printk("ino=%d:%d:%ld:%u old=%u:%s new=%u cur=%u:%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->old & ~I_CTIME_QUERIED, __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), __entry->new, __entry->cur & ~I_CTIME_QUERIED, __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) ) ); TRACE_EVENT(fill_mg_cmtime, TP_PROTO(struct inode *inode, struct timespec64 *ctime, struct timespec64 *mtime), TP_ARGS(inode, ctime, mtime), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(time64_t, ctime_s) __field(time64_t, mtime_s) __field(u32, ctime_ns) __field(u32, mtime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->mtime_s = mtime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; __entry->mtime_ns = mtime->tv_nsec; ), TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u mtime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns, __entry->mtime_s, __entry->mtime_ns ) ); #endif /* _TRACE_TIMESTAMP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.pf != NFPROTO_NETDEV || hook->ops.hooknum != NF_NETDEV_INGRESS) return false; dev = hook->ops.dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct net_device *dev; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { dev = hook->ops.dev; if (this_dev && this_dev != dev) continue; err = nft_chain_offload_cmd(basechain, dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { if (i-- <= 0) break; dev = hook->ops.dev; nft_chain_offload_cmd(basechain, dev, FLOW_BLOCK_UNBIND); } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 413 90 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_FIND_H_ #define __LINUX_FIND_H_ #ifndef __LINUX_BITMAP_H #error only <linux/bitmap.h> can be included directly #endif #include <linux/bitops.h> unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); #endif #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, size, offset); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_and_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_andnot_bit /** * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits * in *addr2 * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_or_bit /** * find_next_or_bit - find the next set bit in either memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = (*addr1 | *addr2) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_or_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit(addr, size, offset); } #endif #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif /** * find_nth_bit - find N'th set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * The following is semantically equivalent: * idx = find_nth_bit(addr, size, 0); * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_bit(addr, size, n); } /** * find_nth_and_bit - find N'th set bit in 2 memory regions * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_bit(addr1, addr2, size, n); } /** * find_nth_andnot_bit - find N'th set bit in 2 memory regions, * flipping bits in 2nd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_andnot_bit(addr1, addr2, size, n); } /** * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, * excluding those set in 3rd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @addr3: The 3rd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); } #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_bit(addr1, addr2, size); } #endif /** * find_first_and_and_bit - find the first set bit in 3 memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @addr3: The third address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_and_bit(addr1, addr2, addr3, size); } #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_and_bit_wrap - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); return bit < offset ? bit : size; } /** * find_next_bit_wrap - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { unsigned long bit = find_next_bit(addr, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); return bit < offset ? bit : size; } /* * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { unsigned long bit; /* If not wrapped around */ if (n > start) { /* and have a bit, just return it. */ bit = find_next_bit(bitmap, size, n); if (bit < size) return bit; /* Otherwise, wrap around and ... */ n = 0; } /* Search the other part. */ bit = find_next_bit(bitmap, start, n); return bit < start ? bit : size; } /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #if defined(__LITTLE_ENDIAN) static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit_le(addr, size, offset); } #endif #ifndef find_first_zero_bit_le static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit_le(addr, size); } #endif #ifndef find_next_bit_le static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit_le(addr, size, offset); } #endif #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_andnot_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_or_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ for ((bit) = 0; \ (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit) * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_bit((addr), (size), b), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_bit((addr), (size), (b)), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit) * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and * wrapping around the end of bitmap. * @bit: offset for current iteration * @addr: bitmap address to base the search on * @size: bitmap size in number of bits * @start: Starting bit for bitmap traversing, wrapping around the bitmap end */ #define for_each_set_bit_wrap(bit, addr, size, start) \ for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ (bit) < (size); \ (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset * @clump: location to store copy of current 8-bit clump * @bits: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_clump8(start, clump, bits, size) \ for ((start) = find_first_clump8(&(clump), (bits), (size)); \ (start) < (size); \ (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) #endif /*__LINUX_FIND_H_ */ |
| 174 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(!READ_ONCE(file->f_ep))) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_release(struct file *file) {} #endif #if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) /* ARM OABI has an incompatible struct layout and needs a special handler */ extern struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent); #else static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { if (__put_user(revents, &uevent->events) || __put_user(data, &uevent->data)) return NULL; return uevent+1; } #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 261 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ }; #define SWAP_CLUSTER_MAX 32UL #define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The flags field determines if a cluster is free. This is * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * other than list, and swap_info_struct->swap_map * elements corresponding to the swap cluster. */ u16 count; u8 flags; u8 order; struct list_head list; }; /* All on-list cluster must have a non-zero flag. */ enum swap_cluster_flags { CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ CLUSTER_FLAG_FREE, CLUSTER_FLAG_NONFULL, CLUSTER_FLAG_FRAG, /* Clusters with flags above are allocatable */ CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, CLUSTER_FLAG_FULL, CLUSTER_FLAG_DISCARD, CLUSTER_FLAG_MAX, }; /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate an entry is not valid. */ #define SWAP_ENTRY_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { local_lock_t lock; /* Protect the percpu_cluster above */ unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ struct list_head full_clusters; /* full clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ atomic_long_t inuse_pages; /* number of those currently in use */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */ spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) #define MIN_SWAPPINESS 0 #define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_page_and_swap_cache(struct page *); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } static inline void free_swap_cache(struct folio *folio) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline int swapcache_prepare(swp_entry_t swp, int nr) { return 0; } static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); } static inline void swap_free(swp_entry_t entry) { swap_free_nr(entry, 1); } #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #include <linux/bits.h> #include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif /* * Generic definitions for bit operations, should not be used in regular code * directly. */ /** * generic___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic and may be reordered. * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ static __always_inline void generic___set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p |= mask; } static __always_inline void generic___clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p &= ~mask; } /** * generic___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic and may be reordered. * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ static __always_inline void generic___change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p ^= mask; } /** * generic___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old | mask; return (old & mask) != 0; } /** * generic___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old & ~mask; return (old & mask) != 0; } /* WARNING: non atomic and it can be reordered! */ static __always_inline bool generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old ^ mask; return (old & mask) != 0; } /** * generic_test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool generic_test_bit(unsigned long nr, const volatile unsigned long *addr) { /* * Unlike the bitops with the '__' prefix above, this one *is* atomic, * so `volatile` must always stay here with no cast-aways. See * `Documentation/atomic_bitops.txt` for the details. */ return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } /** * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1))); } /* * const_*() definitions provide good compile-time optimizations when * the passed arguments can be resolved at compile time. */ #define const___set_bit generic___set_bit #define const___clear_bit generic___clear_bit #define const___change_bit generic___change_bit #define const___test_and_set_bit generic___test_and_set_bit #define const___test_and_clear_bit generic___test_and_clear_bit #define const___test_and_change_bit generic___test_and_change_bit #define const_test_bit_acquire generic_test_bit_acquire /** * const_test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from * * A version of generic_test_bit() which discards the `volatile` qualifier to * allow a compiler to optimize code harder. Non-atomic and to be called only * for testing compile-time constants, e.g. by the corresponding macros, not * directly from "regular" code. */ static __always_inline bool const_test_bit(unsigned long nr, const volatile unsigned long *addr) { const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr); unsigned long mask = BIT_MASK(nr); unsigned long val = *p; return !!(val & mask); } #endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_SCHED_GENERIC_H #define __NET_SCHED_GENERIC_H #include <linux/netdevice.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/pkt_sched.h> #include <linux/pkt_cls.h> #include <linux/percpu.h> #include <linux/dynamic_queue_limits.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/hashtable.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> #include <linux/xarray.h> struct Qdisc_ops; struct qdisc_walker; struct tcf_walker; struct module; struct bpf_flow_keys; struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; struct qdisc_rate_table *next; int refcnt; }; enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, __QDISC_STATE_DRAINING, }; enum qdisc_state2_t { /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. * Use qdisc_run_begin/end() or qdisc_is_running() instead. */ __QDISC_STATE2_RUNNING, }; #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) #define QDISC_STATE_NON_EMPTY (QDISC_STATE_MISSED | \ QDISC_STATE_DRAINING) struct qdisc_size_table { struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; u16 data[]; }; /* similar to sk_buff_head, but skb->prev pointer is undefined. */ struct qdisc_skb_head { struct sk_buff *head; struct sk_buff *tail; __u32 qlen; spinlock_t lock; }; struct Qdisc { int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *sch); unsigned int flags; #define TCQ_F_BUILTIN 1 #define TCQ_F_INGRESS 2 #define TCQ_F_CAN_BYPASS 4 #define TCQ_F_MQROOT 8 #define TCQ_F_ONETXQUEUE 0x10 /* dequeue_skb() can assume all skbs are for * q->dev_queue : It can test * netif_xmit_frozen_or_stopped() before * dequeueing next packet. * Its true for MQ/MQPRIO slaves, or non * multiqueue device. */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : * qdisc_tree_decrease_qlen() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ #define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ #define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; struct hlist_node hash; u32 handle; u32 parent; struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; /* * For performance sake on SMP, we put highly modified fields at the end */ struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; struct rcu_head rcu; netdevice_tracker dev_tracker; struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; refcount_inc(&qdisc->refcnt); } static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return true; return refcount_dec_if_one(&qdisc->refcnt); } /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return qdisc; if (refcount_inc_not_zero(&qdisc->refcnt)) return qdisc; return NULL; } /* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc * root_lock section, or provide their own memory barriers -- ordering * against qdisc_run_begin/end() atomic bit operations. */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) { return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY); } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; } static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) return nolock_qdisc_is_empty(qdisc); return !READ_ONCE(qdisc->q.qlen); } /* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with * the qdisc root lock acquired. */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (spin_trylock(&qdisc->seqlock)) return true; /* No need to insist if the MISSED flag was already set. * Note that test_and_set_bit() also gives us memory ordering * guarantees wrt potential earlier enqueue() and below * spin_trylock(), both of which are necessary to prevent races */ if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state)) return false; /* Try to take the lock again to make sure that we will either * grab it or the CPU that still has it will see MISSED set * when testing it in qdisc_run_end() */ return spin_trylock(&qdisc->seqlock); } return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline void qdisc_run_end(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); /* spin_unlock() only has store-release semantic. The unlock * and test_bit() ordering is a store-load ordering, so a full * memory barrier is needed here. */ smp_mb(); if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); } else { __clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) { return qdisc->flags & TCQ_F_ONETXQUEUE; } static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { unsigned int flags; /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, struct Qdisc *, struct Qdisc **, struct netlink_ext_ack *extack); struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl); void (*qlen_notify)(struct Qdisc *, unsigned long); /* Class manipulation routines */ unsigned long (*find)(struct Qdisc *, u32 classid); int (*change)(struct Qdisc *, u32, u32, struct nlattr **, unsigned long *, struct netlink_ext_ack *); int (*delete)(struct Qdisc *, unsigned long, struct netlink_ext_ack *); void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ struct tcf_block * (*tcf_block)(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); /* rtnetlink specific */ int (*dump)(struct Qdisc *, unsigned long, struct sk_buff *skb, struct tcmsg*); int (*dump_stats)(struct Qdisc *, unsigned long, struct gnet_dump *); }; /* Qdisc_class_ops flag values */ /* Implements API that doesn't require rtnl lock */ enum qdisc_class_ops_flags { QDISC_CLASS_OPS_DOIT_UNLOCKED = 1, }; struct Qdisc_ops { struct Qdisc_ops *next; const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; int priv_size; unsigned int static_flags; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); int (*init)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*reset)(struct Qdisc *); void (*destroy)(struct Qdisc *); int (*change)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*attach)(struct Qdisc *sch); int (*change_tx_queue_len)(struct Qdisc *, unsigned int); void (*change_real_num_tx)(struct Qdisc *sch, unsigned int new_real_tx); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); void (*ingress_block_set)(struct Qdisc *sch, u32 block_index); void (*egress_block_set)(struct Qdisc *sch, u32 block_index); u32 (*ingress_block_get)(struct Qdisc *sch); u32 (*egress_block_get)(struct Qdisc *sch); struct module *owner; }; struct tcf_result { union { struct { unsigned long class; u32 classid; }; const struct tcf_proto *goto_tp; }; }; struct tcf_chain; struct tcf_proto_ops { struct list_head head; char kind[IFNAMSIZ]; int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); void (*destroy)(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack); void* (*get)(struct tcf_proto*, u32 handle); void (*put)(struct tcf_proto *tp, void *f); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, void **, u32, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*hw_add)(struct tcf_proto *tp, void *type_data); void (*hw_del)(struct tcf_proto *tp, void *type_data); void (*bind_class)(void *, u32, unsigned long, void *, unsigned long); void * (*tmplt_create)(struct net *net, struct tcf_chain *chain, struct nlattr **tca, struct netlink_ext_ack *extack); void (*tmplt_destroy)(void *tmplt_priv); void (*tmplt_reoffload)(struct tcf_chain *chain, bool add, flow_setup_cb_t *cb, void *cb_priv); struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, u32 handle); /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, bool); int (*terse_dump)(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t, bool rtnl_held); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); struct module *owner; int flags; }; /* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags * are expected to implement tcf_proto_ops->delete_empty(), otherwise race * conditions can occur when filters are inserted/deleted simultaneously. */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; struct tcf_proto { /* Fast access part */ struct tcf_proto __rcu *next; void __rcu *root; /* called under RCU BH lock*/ int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); __be16 protocol; /* All the rest */ u32 prio; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; /* Lock protects tcf_proto shared state and can be used by unlocked * classifiers to protect their private data. */ spinlock_t lock; bool deleting; bool counted; bool usesw; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; }; struct qdisc_skb_cb { struct { unsigned int pkt_len; u16 slave_dev_queue_mapping; u16 tc_classid; }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { /* Protects filter_chain. */ struct mutex filter_chain_lock; struct tcf_proto __rcu *filter_chain; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; unsigned int action_refcnt; bool explicitly_created; bool flushing; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; struct rcu_head rcu; }; struct tcf_block { struct xarray ports; /* datapath accessible */ /* Lock protects tcf_block and lifetime-management data of chains * attached to the block (refcnt, action_refcnt, explicitly_created). */ struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; struct rw_semaphore cb_lock; /* protects cb_list and offload counters */ struct flow_block flow_block; struct list_head owner_list; bool keep_dst; atomic_t useswcnt; atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ struct { struct tcf_chain *chain; struct list_head filter_chain_list; } chain0; struct rcu_head rcu; DECLARE_HASHTABLE(proto_destroy_ht, 7); struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index); static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) { return lockdep_is_held(&chain->filter_chain_lock); } static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp) { return lockdep_is_held(&tp->lock); } #define tcf_chain_dereference(p, chain) \ rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain)) #define tcf_proto_dereference(p, tp) \ rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp)) static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb)); BUILD_BUG_ON(sizeof(qcb->data) < sz); } static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; } static inline int qdisc_qlen_sum(const struct Qdisc *q) { __u32 qlen = q->qstats.qlen; int i; if (qdisc_is_percpu_stats(q)) { for_each_possible_cpu(i) qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; } else { qlen += q->q.qlen; } return qlen; } static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) { return (struct qdisc_skb_cb *)skb->cb; } static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc) { return &qdisc->q.lock; } static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) { struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc); return q; } static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) { return rcu_dereference_bh(qdisc->dev_queue->qdisc); } static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) { struct Qdisc *root = qdisc_root_sleeping(qdisc); ASSERT_RTNL(); return qdisc_lock(root); } static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; } static inline void sch_tree_lock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_lock_bh(qdisc_lock(q)); else spin_lock_bh(qdisc_root_sleeping_lock(q)); } static inline void sch_tree_unlock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_unlock_bh(qdisc_lock(q)); else spin_unlock_bh(qdisc_root_sleeping_lock(q)); } extern struct Qdisc noop_qdisc; extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; extern const u8 sch_default_prio2band[TC_PRIO_MAX + 1]; extern struct Qdisc_ops mq_qdisc_ops; extern struct Qdisc_ops noqueue_qdisc_ops; extern const struct Qdisc_ops *default_qdisc_ops; static inline const struct Qdisc_ops * get_default_qdisc_ops(const struct net_device *dev, int ntx) { return ntx < dev->real_num_tx_queues ? default_qdisc_ops : &pfifo_fast_ops; } struct Qdisc_class_common { u32 classid; unsigned int filter_cnt; struct hlist_node hnode; }; struct Qdisc_class_hash { struct hlist_head *hash; unsigned int hashsize; unsigned int hashmask; unsigned int hashelems; }; static inline unsigned int qdisc_class_hash(u32 id, u32 mask) { id ^= id >> 8; id ^= id >> 4; return id & mask; } static inline struct Qdisc_class_common * qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) { struct Qdisc_class_common *cl; unsigned int h; if (!id) return NULL; h = qdisc_class_hash(id, hash->hashmask); hlist_for_each_entry(cl, &hash->hash[h], hnode) { if (cl->classid == id) return cl; } return NULL; } static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl) { return cl->filter_cnt > 0; } static inline void qdisc_class_get(struct Qdisc_class_common *cl) { unsigned int res; if (check_add_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class overflow"); cl->filter_cnt = res; } static inline void qdisc_class_put(struct Qdisc_class_common *cl) { unsigned int res; if (check_sub_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class underflow"); cl->filter_cnt = res; } static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid) { u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY; return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL; } int qdisc_class_hash_init(struct Qdisc_class_hash *); void qdisc_class_hash_insert(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_remove(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); int dev_qdisc_change_tx_queue_len(struct net_device *dev); void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); void dev_deactivate(struct net_device *dev); void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack); #else static inline int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data) { q->flags &= ~TCQ_F_OFFLOADED; return 0; } static inline void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack) { } #endif void qdisc_offload_query_caps(struct net_device *dev, enum tc_setup_type type, void *caps, size_t caps_len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); int skb_do_redirect(struct sk_buff *); static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_XGRESS return skb->tc_at_ingress; #else return false; #endif } static inline bool skb_skip_tc_classify(struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT if (skb->tc_skip_classify) { skb->tc_skip_classify = 0; return true; } #endif return false; } /* Reset all TX qdiscs greater than index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } } } /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { unsigned int i; rcu_read_lock(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); const struct Qdisc *q = rcu_dereference(txq->qdisc); if (!qdisc_is_empty(q)) { rcu_read_unlock(); return false; } } rcu_read_unlock(); return true; } /* Are any of the TX qdiscs changing? */ static inline bool qdisc_tx_changing(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; } /* Is the device using the noop qdisc on all queues? */ static inline bool qdisc_tx_is_noop(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != &noop_qdisc) return false; } return true; } static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) { return qdisc_skb_cb(skb)->pkt_len; } /* additional qdisc xmit flags (NET_XMIT_MASK in linux/netdevice.h) */ enum net_xmit_qdisc_t { __NET_XMIT_STOLEN = 0x00010000, __NET_XMIT_BYPASS = 0x00020000, }; #ifdef CONFIG_NET_CLS_ACT #define net_xmit_drop_count(e) ((e) & __NET_XMIT_STOLEN ? 0 : 1) #else #define net_xmit_drop_count(e) (1) #endif static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); if (stab) __qdisc_calculate_pkt_len(skb, stab); #endif } static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { return sch->enqueue(skb, sch, to_free); } static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u64 packets) { u64_stats_update_begin(&bstats->syncp); u64_stats_add(&bstats->bytes, bytes); u64_stats_add(&bstats->packets, packets); u64_stats_update_end(&bstats->syncp); } static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, qdisc_pkt_len(skb), skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); } static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(&sch->bstats, skb); } static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog += qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch) { this_cpu_dec(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->requeues); } static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) { sch->qstats.drops += count; } static inline void qstats_drop_inc(struct gnet_stats_queue *qstats) { qstats->drops++; } static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats) { qstats->overlimits++; } static inline void qdisc_qstats_drop(struct Qdisc *sch) { qstats_drop_inc(&sch->qstats); } static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->drops); } static inline void qdisc_qstats_overlimit(struct Qdisc *sch) { sch->qstats.overlimits++; } static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch) { __u32 qlen = qdisc_qlen_sum(sch); return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen); } static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } static inline void qdisc_tree_flush_backlog(struct Qdisc *sch) { __u32 qlen, backlog; qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); qdisc_tree_reduce_backlog(sch, qlen, backlog); } static inline void qdisc_purge_queue(struct Qdisc *sch) { __u32 qlen, backlog; qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); qdisc_reset(sch); qdisc_tree_reduce_backlog(sch, qlen, backlog); } static inline void __qdisc_enqueue_tail(struct sk_buff *skb, struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; if (last) { skb->next = NULL; last->next = skb; qh->tail = skb; } else { qh->tail = skb; qh->head = skb; } qh->qlen++; } static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) { __qdisc_enqueue_tail(skb, &sch->q); qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } static inline void __qdisc_enqueue_head(struct sk_buff *skb, struct qdisc_skb_head *qh) { skb->next = qh->head; if (!qh->head) qh->tail = skb; qh->head = skb; qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) { struct sk_buff *skb = qh->head; if (likely(skb != NULL)) { qh->head = skb->next; qh->qlen--; if (qh->head == NULL) qh->tail = NULL; skb->next = NULL; } return skb; } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (likely(skb != NULL)) { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); } return skb; } struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u32 drop_reason; u16 zone; /* Only valid if post_ct = true */ u16 mru; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) { struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); return cb; } static inline enum skb_drop_reason tcf_get_drop_reason(const struct sk_buff *skb) { return tc_skb_cb(skb)->drop_reason; } static inline void tcf_set_drop_reason(const struct sk_buff *skb, enum skb_drop_reason reason) { tc_skb_cb(skb)->drop_reason = reason; } /* Instead of calling kfree_skb() while root qdisc lock is held, * queue the skb for future freeing at end of __dev_xmit_skb() */ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) { skb->next = *to_free; *to_free = skb; } static inline void __qdisc_drop_all(struct sk_buff *skb, struct sk_buff **to_free) { if (skb->prev) skb->prev->next = *to_free; else skb->next = *to_free; *to_free = skb; } static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) { struct sk_buff *skb = __qdisc_dequeue_head(qh); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); __qdisc_drop(skb, to_free); return len; } return 0; } static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; return qh->head; } /* generic pseudo peek method for non-work-conserving qdisc */ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); /* we can reuse ->gso_skb because peek isn't called for root qdiscs */ if (!skb) { skb = sch->dequeue(sch); if (skb) { __skb_queue_head(&sch->gso_skb, skb); /* it's still part of the queue */ qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; } } return skb; } static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch, struct sk_buff *skb) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_bstats_cpu_update(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); sch->q.qlen--; } } static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch, unsigned int pkt_len) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_qlen_inc(sch); this_cpu_add(sch->cpu_qstats->backlog, pkt_len); } else { sch->qstats.backlog += pkt_len; sch->q.qlen++; } } /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); if (skb) { skb = __skb_dequeue(&sch->gso_skb); if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } } else { skb = sch->dequeue(sch); } return skb; } static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ ASSERT_RTNL(); if (qh->qlen) { rtnl_kfree_skbs(qh->head, qh->tail); qh->head = NULL; qh->tail = NULL; qh->qlen = 0; } } static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, struct Qdisc **pold) { struct Qdisc *old; sch_tree_lock(sch); old = *pold; *pold = new; if (old != NULL) qdisc_purge_queue(old); sch_tree_unlock(sch); return old; } static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { rtnl_kfree_skbs(skb, skb); qdisc_qstats_drop(sch); } static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_cpu_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free, enum skb_drop_reason reason) { tcf_set_drop_reason(skb, reason); return qdisc_drop(skb, sch, to_free); } static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop_all(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } struct psched_ratecfg { u64 rate_bytes_ps; /* bytes per second */ u32 mult; u16 overhead; u16 mpu; u8 linklayer; u8 shift; }; static inline u64 psched_l2t_ns(const struct psched_ratecfg *r, unsigned int len) { len += r->overhead; if (len < r->mpu) len = r->mpu; if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift; return ((u64)len * r->mult) >> r->shift; } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64); static inline void psched_ratecfg_getrate(struct tc_ratespec *res, const struct psched_ratecfg *r) { memset(res, 0, sizeof(*res)); /* legacy struct tc_ratespec has a 32bit @rate field * Qdisc using 64bit rate should add new attributes * in order to maintain compatibility. */ res->rate = min_t(u64, r->rate_bytes_ps, ~0U); res->overhead = r->overhead; res->mpu = r->mpu; res->linklayer = (r->linklayer & TC_LINKLAYER_MASK); } struct psched_pktrate { u64 rate_pkts_ps; /* packets per second */ u32 mult; u8 shift; }; static inline u64 psched_pkt2t_ns(const struct psched_pktrate *r, unsigned int pkt_num) { return ((u64)pkt_num * r->mult) >> r->shift; } void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); /* Mini Qdisc serves for specific needs of ingress/clsact Qdisc. * The fast path only needs to access filter list and to update stats */ struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; unsigned long rcu_state; }; static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) { this_cpu_inc(miniq->cpu_qstats->drops); } struct mini_Qdisc_pair { struct mini_Qdisc miniq1; struct mini_Qdisc miniq2; struct mini_Qdisc __rcu **p_miniq; }; void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); /* Make sure qdisc is no longer in SCHED state. */ static inline void qdisc_synchronize(const struct Qdisc *q) { while (test_bit(__QDISC_STATE_SCHED, &q->state)) msleep(1); } #endif |
| 190 190 5 191 191 178 4 5 5 5 178 5 207 5 178 207 206 207 207 206 48 190 190 5 5 5 48 47 48 4 4 4 48 48 48 4 48 4 48 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" #include "services.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[] __counted_by(len); }; #define index_to_sid(index) ((index) + SECINITSID_NUM + 1) #define sid_to_index(sid) ((sid) - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_equal(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { unsigned int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; unsigned int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc( SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ convert = s->convert; if (convert) { struct sidtab *target = convert->target; rc = -ENOMEM; dst_convert = sidtab_do_lookup(target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = services_convert_context(convert->args, context, &dst_convert->context, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); target->count = count + 1; hash_add_rcu(target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = services_convert_context( convert->args, &esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #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) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(struct_size(cache, str, str_len), GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 158 159 22 21 2 2 2 2 2 21 39 40 40 40 37 37 1 36 37 37 1 36 36 36 36 67 30 22 40 37 1 67 180 137 67 180 22 22 22 22 22 22 22 26 26 26 26 26 26 29 29 29 29 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mlock.c * * (C) Copyright 1995 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig */ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> #include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/secretmem.h> #include "internal.h" struct mlock_fbatch { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { .lock = INIT_LOCAL_LOCK(lock), }; bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; } EXPORT_SYMBOL(can_do_mlock); /* * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it * will be ostensibly placed on the LRU "unevictable" list (actually no such * list exists), rather than the [in]active lists. PG_unevictable is set to * indicate the unevictable state. */ static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { /* There is nothing more we can do while it's off LRU */ if (!folio_test_clear_lru(folio)) return lruvec; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (unlikely(folio_evictable(folio))) { /* * This is a little surprising, but quite possible: PG_mlocked * must have got cleared already by another CPU. Could this * folio be unevictable? I'm not sure, but move it now if so. */ if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, folio_nr_pages(folio)); } goto out; } if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++; goto out; } lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: folio_set_lru(folio); return lruvec; } static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); lruvec = folio_lruvec_relock_irq(folio, lruvec); /* As above, this is a little surprising, but possible */ if (unlikely(folio_evictable(folio))) goto out; folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: lruvec_add_folio(lruvec, folio); folio_set_lru(folio); return lruvec; } static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) { int nr_pages = folio_nr_pages(folio); bool isolated = false; if (!folio_test_clear_lru(folio)) goto munlock; isolated = true; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_test_unevictable(folio)) { /* Then mlock_count is maintained, but might undercount */ if (folio->mlock_count) folio->mlock_count--; if (folio->mlock_count) goto out; } /* else assume that was the last mlock: reclaim will fix it if not */ munlock: if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio)) __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); else __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } /* folio_evictable() has to be checked *after* clearing Mlocked */ if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } out: if (isolated) folio_set_lru(folio); return lruvec; } /* * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ #define LRU_FOLIO 0x1 #define NEW_FOLIO 0x2 static inline struct folio *mlock_lru(struct folio *folio) { return (struct folio *)((unsigned long)folio + LRU_FOLIO); } static inline struct folio *mlock_new(struct folio *folio) { return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can * make use of such folio pointer flags in future, but for now just keep it for * mlock. We could use three separate folio batches instead, but one feels * better (munlocking a full folio batch does not need to drain mlocking folio * batches first). */ static void mlock_folio_batch(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; unsigned long mlock; struct folio *folio; int i; for (i = 0; i < folio_batch_count(fbatch); i++) { folio = fbatch->folios[i]; mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); folio = (struct folio *)((unsigned long)folio - mlock); fbatch->folios[i] = folio; if (mlock & LRU_FOLIO) lruvec = __mlock_folio(folio, lruvec); else if (mlock & NEW_FOLIO) lruvec = __mlock_new_folio(folio, lruvec); else lruvec = __munlock_folio(folio, lruvec); } if (lruvec) unlock_page_lruvec_irq(lruvec); folios_put(fbatch); } void mlock_drain_local(void) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } void mlock_drain_remote(int cpu) { struct folio_batch *fbatch; WARN_ON_ONCE(cpu_online(cpu)); fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); } bool need_mlock_drain(int cpu) { return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); } /** * mlock_folio - mlock a folio already on (or temporarily off) LRU * @folio: folio to be mlocked. */ void mlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * mlock_new_folio - mlock a newly allocated folio not yet on LRU * @folio: folio to be mlocked, either normal or a THP head. */ void mlock_new_folio(struct folio *folio) { struct folio_batch *fbatch; int nr_pages = folio_nr_pages(folio); local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * munlock_folio - munlock a folio * @folio: folio to be munlocked, either normal or a THP head. */ void munlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), * which will check whether the folio is multiply mlocked. */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } static inline unsigned int folio_mlock_step(struct folio *folio, pte_t *pte, unsigned long addr, unsigned long end) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; unsigned int count = (end - addr) >> PAGE_SHIFT; pte_t ptent = ptep_get(pte); if (!folio_test_large(folio)) return 1; return folio_pte_batch(folio, addr, pte, ptent, count, fpb_flags, NULL, NULL, NULL); } static inline bool allow_mlock_munlock(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned int step) { /* * For unlock, allow munlock large folio which is partially * mapped to VMA. As it's possible that large folio is * mlocked and VMA is split later. * * During memory pressure, such kind of large folio can * be split. And the pages are not in VM_LOCKed VMA * can be reclaimed. */ if (!(vma->vm_flags & VM_LOCKED)) return true; /* folio_within_range() cannot take KSM, but any small folio is OK */ if (!folio_test_large(folio)) return true; /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; /* folio is not fully mapped, skip mlock */ if (step != folio_nr_pages(folio)) return false; return true; } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; unsigned int step = 1; unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (!pmd_present(*pmd)) goto out; if (is_huge_zero_pmd(*pmd)) goto out; folio = pmd_folio(*pmd); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); goto out; } start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) { walk->action = ACTION_AGAIN; return 0; } for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; step = folio_mlock_step(folio, pte, addr, end); if (!allow_mlock_munlock(folio, vma, start, end, step)) goto next_entry; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); next_entry: pte += step - 1; addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: spin_unlock(ptl); cond_resched(); return 0; } /* * mlock_vma_pages_range() - mlock any pages already in the range, * or munlock all pages in the range. * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range * @end - end of range in @vma * @newflags - the new set of flags for @vma. * * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ static void mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, vm_flags_t newflags) { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* * There is a slight chance that concurrent page migration, * or page reclaim finding a page of this now-VM_LOCKED vma, * will call mlock_vma_folio() and raise page's mlock_count: * double counting, leaving the page unevictable indefinitely. * Communicate this danger to mlock_vma_folio() with VM_IO, * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. * mmap_lock is held in write mode here, so this weird * combination should not be visible to other mmap_lock users; * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. */ if (newflags & VM_LOCKED) newflags |= VM_IO; vma_start_write(vma); vm_flags_reset_once(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); lru_add_drain(); if (newflags & VM_IO) { newflags &= ~VM_IO; vm_flags_reset_once(vma, newflags); } } /* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!(newflags & VM_LOCKED)) nr_pages = -nr_pages; else if (oldflags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { /* No work to do, and mlocking twice would be wrong */ vma_start_write(vma); vm_flags_reset(vma, newflags); } else { mlock_vma_pages_range(vma, start, end, newflags); } out: *prev = vma; return ret; } static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { int error; vm_flags_t newflags; if (vma->vm_start != tmp) return -ENOMEM; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) return error; tmp = vma_iter_end(&vmi); nstart = tmp; } if (tmp < end) return -ENOMEM; return 0; } /* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; unsigned long count = 0; unsigned long end; VMA_ITERATOR(vmi, mm, start); /* Don't overflow past ULONG_MAX */ if (unlikely(ULONG_MAX - len < start)) end = ULONG_MAX; else end = start + len; for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (end < vma->vm_end) { count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; } /* * convert get_user_pages() return value to posix mlock() error */ static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; } static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; start = untagged_addr(start); if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); mmap_write_unlock(current->mm); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; } SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; start = untagged_addr(start); len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); mmap_write_unlock(current->mm); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */ static int apply_mlockall_flags(int flags) { VMA_ITERATOR(vmi, current->mm, 0); struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for_each_vma(vmi, vma) { int error; vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, newflags); /* Ignore errors, but prev needs fixing up. */ if (error) prev = vma; cond_resched(); } out: return 0; } SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); mmap_write_unlock(current->mm); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock); int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit != RLIM_INFINITY) lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; } if (!get_ucounts(ucounts)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); allowed = 0; goto out; } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); put_ucounts(ucounts); } |
| 1131 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PREEMPT_H #define __LINUX_PREEMPT_H /* * include/linux/preempt.h - macros for accessing and manipulating * preempt_count (used for kernel preemption, interrupt count, etc.) */ #include <linux/linkage.h> #include <linux/cleanup.h> #include <linux/types.h> /* * We put the hardirq and softirq counter into the preemption * counter. The bitmask has the following meaning: * * - bits 0-7 are the preemption count (max preemption depth: 256) * - bits 8-15 are the softirq count (max # of softirqs: 256) * * The hardirq count could in theory be the same as the number of * interrupts in the system, but we run all interrupt handlers with * interrupts disabled, so we cannot have nesting interrupts. Though * there are a few palaeontologic drivers which reenable interrupts in * the handler, so we need more than one bit here. * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 #define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) #define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) #define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) #define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) #define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) #define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* * Disable preemption until the scheduler is running -- use an unconditional * value so that it also works on !PREEMPT_COUNT kernels. * * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). */ #define INIT_PREEMPT_COUNT PREEMPT_OFFSET /* * Initial preempt_count value; reflects the preempt_count schedule invariant * which states that during context switches: * * preempt_count() == 2*PREEMPT_DISABLE_OFFSET * * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. * Note: See finish_task_switch(). */ #define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> /** * interrupt_context_level - return interrupt context level * * Returns the current interrupt context level. * 0 - normal context * 1 - softirq context * 2 - hardirq context * 3 - NMI context */ static __always_inline unsigned char interrupt_context_level(void) { unsigned long pc = preempt_count(); unsigned char level = 0; level += !!(pc & (NMI_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); return level; } /* * These macro definitions avoid redundant invocations of preempt_count() * because such invocations would result in redundant loads given that * preempt_count() is commonly implemented with READ_ONCE(). */ #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) # define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) #else # define softirq_count() (preempt_count() & SOFTIRQ_MASK) # define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) #endif /* * Macros to retrieve the current execution context: * * in_nmi() - We're in NMI context * in_hardirq() - We're in hard IRQ context * in_serving_softirq() - We're in softirq context * in_task() - We're in task context */ #define in_nmi() (nmi_count()) #define in_hardirq() (hardirq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) #ifdef CONFIG_PREEMPT_RT # define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq())) #else # define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) #endif /* * The following macros are deprecated and should not be used in new code: * in_irq() - Obsolete version of in_hardirq() * in_softirq() - We have BH disabled, or are processing softirqs * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) /* * The preempt_count offset after preempt_disable(); */ #if defined(CONFIG_PREEMPT_COUNT) # define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET #else # define PREEMPT_DISABLE_OFFSET 0 #endif /* * The preempt_count offset after spin_lock() */ #if !defined(CONFIG_PREEMPT_RT) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET #else /* Locks on RT do not disable preemption */ #define PREEMPT_LOCK_OFFSET 0 #endif /* * The preempt_count offset needed for things like: * * spin_lock_bh() * * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and * softirqs, such that unlock sequences of: * * spin_unlock(); * local_bh_enable(); * * Work as expected. */ #define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET) /* * Are we running in atomic context? WARNING: this macro cannot * always detect atomic context; in particular, it cannot know about * held spinlocks in non-preemptible kernels. Thus it should not be * used in the general case to determine whether sleeping is possible. * Do not use in_atomic() in driver code. */ #define in_atomic() (preempt_count() != 0) /* * Check whether we were atomic before we did preempt_disable(): * (used by the scheduler) */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); #define preempt_count_dec_and_test() \ ({ preempt_count_sub(1); should_resched(0); }) #else #define preempt_count_add(val) __preempt_count_add(val) #define preempt_count_sub(val) __preempt_count_sub(val) #define preempt_count_dec_and_test() __preempt_count_dec_and_test() #endif #define __preempt_count_inc() __preempt_count_add(1) #define __preempt_count_dec() __preempt_count_sub(1) #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ do { \ preempt_count_inc(); \ barrier(); \ } while (0) #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_no_resched() sched_preempt_enable_no_resched() #define preemptible() (preempt_count() == 0 && !irqs_disabled()) #ifdef CONFIG_PREEMPTION #define preempt_enable() \ do { \ barrier(); \ if (unlikely(preempt_count_dec_and_test())) \ __preempt_schedule(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ if (unlikely(__preempt_count_dec_and_test())) \ __preempt_schedule_notrace(); \ } while (0) #define preempt_check_resched() \ do { \ if (should_resched(0)) \ __preempt_schedule(); \ } while (0) #else /* !CONFIG_PREEMPTION */ #define preempt_enable() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #define preempt_check_resched() do { } while (0) #endif /* CONFIG_PREEMPTION */ #define preempt_disable_notrace() \ do { \ __preempt_count_inc(); \ barrier(); \ } while (0) #define preempt_enable_no_resched_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ /* * Even if we don't have any preemption, we need preempt disable/enable * to be barriers, so that we don't have things like get_user/put_user * that can cause faults and scheduling migrate into our preempt-protected * region. */ #define preempt_disable() barrier() #define sched_preempt_enable_no_resched() barrier() #define preempt_enable_no_resched() barrier() #define preempt_enable() barrier() #define preempt_check_resched() do { } while (0) #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() #define preemptible() 0 #endif /* CONFIG_PREEMPT_COUNT */ #ifdef MODULE /* * Modules have no business playing preemption tricks. */ #undef sched_preempt_enable_no_resched #undef preempt_enable_no_resched #undef preempt_enable_no_resched_notrace #undef preempt_check_resched #endif #define preempt_set_need_resched() \ do { \ set_preempt_need_resched(); \ } while (0) #define preempt_fold_need_resched() \ do { \ if (tif_need_resched()) \ set_preempt_need_resched(); \ } while (0) #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; /** * preempt_ops - notifiers called when a task is preempted and rescheduled * @sched_in: we're about to be rescheduled: * notifier: struct preempt_notifier for the task being scheduled * cpu: cpu we're scheduled on * @sched_out: we've just been preempted * notifier: struct preempt_notifier for the task being preempted * next: the task that's kicking us out * * Please note that sched_in and out are called under different * contexts. sched_out is called with rq lock held and irq disabled * while sched_in is called without rq lock and irq enabled. This * difference is intentional and depended upon by its users. */ struct preempt_ops { void (*sched_in)(struct preempt_notifier *notifier, int cpu); void (*sched_out)(struct preempt_notifier *notifier, struct task_struct *next); }; /** * preempt_notifier - key for installing preemption notifiers * @link: internal use * @ops: defines the notifier functions to be called * * Usually used in conjunction with container_of(). */ struct preempt_notifier { struct hlist_node link; struct preempt_ops *ops; }; void preempt_notifier_inc(void); void preempt_notifier_dec(void); void preempt_notifier_register(struct preempt_notifier *notifier); void preempt_notifier_unregister(struct preempt_notifier *notifier); static inline void preempt_notifier_init(struct preempt_notifier *notifier, struct preempt_ops *ops) { /* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */ notifier->link.next = NULL; notifier->link.pprev = NULL; notifier->ops = ops; } #endif #ifdef CONFIG_SMP /* * Migrate-Disable and why it is undesired. * * When a preempted task becomes elegible to run under the ideal model (IOW it * becomes one of the M highest priority tasks), it might still have to wait * for the preemptee's migrate_disable() section to complete. Thereby suffering * a reduction in bandwidth in the exact duration of the migrate_disable() * section. * * Per this argument, the change from preempt_disable() to migrate_disable() * gets us: * * - a higher priority tasks gains reduced wake-up latency; with preempt_disable() * it would have had to wait for the lower priority task. * * - a lower priority tasks; which under preempt_disable() could've instantly * migrated away when another CPU becomes available, is now constrained * by the ability to push the higher priority task away, which might itself be * in a migrate_disable() section, reducing it's available bandwidth. * * IOW it trades latency / moves the interference term, but it stays in the * system, and as long as it remains unbounded, the system is not fully * deterministic. * * * The reason we have it anyway. * * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a * number of primitives into becoming preemptible, they would also allow * migration. This turns out to break a bunch of per-cpu usage. To this end, * all these primitives employ migirate_disable() to restore this implicit * assumption. * * This is a 'temporary' work-around at best. The correct solution is getting * rid of the above assumptions and reworking the code to employ explicit * per-cpu locking or short preempt-disable regions. * * The end goal must be to get rid of migrate_disable(), alternatively we need * a schedulability theory that does not depend on abritrary migration. * * * Notes on the implementation. * * The implementation is particularly tricky since existing code patterns * dictate neither migrate_disable() nor migrate_enable() is allowed to block. * This means that it cannot use cpus_read_lock() to serialize against hotplug, * nor can it easily migrate itself into a pending affinity mask change on * migrate_enable(). * * * Note: even non-work-conserving schedulers like semi-partitioned depends on * migration, so migrate_disable() is not only a problem for * work-conserving schedulers. * */ extern void migrate_disable(void); extern void migrate_enable(void); #else static inline void migrate_disable(void) { } static inline void migrate_enable(void) { } #endif /* CONFIG_SMP */ /** * preempt_disable_nested - Disable preemption inside a normally preempt disabled section * * Use for code which requires preemption protection inside a critical * section which has preemption disabled implicitly on non-PREEMPT_RT * enabled kernels, by e.g.: * - holding a spinlock/rwlock * - soft interrupt context * - regular interrupt handlers * * On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft * interrupt context and regular interrupt handlers are preemptible and * only prevent migration. preempt_disable_nested() ensures that preemption * is disabled for cases which require CPU local serialization even on * PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP. * * The use cases are code sequences which are not serialized by a * particular lock instance, e.g.: * - seqcount write side critical sections where the seqcount is not * associated to a particular lock and therefore the automatic * protection mechanism does not work. This prevents a live lock * against a preempting high priority reader. * - RMW per CPU variable updates like vmstat. */ /* Macro to avoid header recursion hell vs. lockdep */ #define preempt_disable_nested() \ do { \ if (IS_ENABLED(CONFIG_PREEMPT_RT)) \ preempt_disable(); \ else \ lockdep_assert_preemption_disabled(); \ } while (0) /** * preempt_enable_nested - Undo the effect of preempt_disable_nested() */ static __always_inline void preempt_enable_nested(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) #ifdef CONFIG_PREEMPT_DYNAMIC extern bool preempt_model_none(void); extern bool preempt_model_voluntary(void); extern bool preempt_model_full(void); extern bool preempt_model_lazy(void); #else static inline bool preempt_model_none(void) { return IS_ENABLED(CONFIG_PREEMPT_NONE); } static inline bool preempt_model_voluntary(void) { return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); } static inline bool preempt_model_full(void) { return IS_ENABLED(CONFIG_PREEMPT); } static inline bool preempt_model_lazy(void) { return IS_ENABLED(CONFIG_PREEMPT_LAZY); } #endif static inline bool preempt_model_rt(void) { return IS_ENABLED(CONFIG_PREEMPT_RT); } /* * Does the preemption model allow non-cooperative preemption? * * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the * PREEMPT_NONE model. */ static inline bool preempt_model_preemptible(void) { return preempt_model_full() || preempt_model_lazy() || preempt_model_rt(); } #endif /* __LINUX_PREEMPT_H */ |
| 846 846 175 846 846 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/cleanup.h> #include <linux/kernel.h> #include <linux/bitmap.h> #include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); if (n != -1) cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, * since there is only one valid option. */ if (wrap && n >= 0) return nr_cpumask_bits; return cpumask_first(mask); } #else unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); #endif /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) { unsigned int i; cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_assign_cpu - assign a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer * @bool: the value to assign */ static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 7 191 179 191 191 191 7 6 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003 Tresys Technology, LLC * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep __ro_after_init; static struct kmem_cache *avtab_xperms_cachep __ro_after_init; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline u32 avtab_hash(const struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) \ do { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } while (0) mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node *avtab_insert_node(struct avtab *h, struct avtab_node **dst, const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } newnode->next = *dst; *dst = newnode; h->nel++; return newnode; } static int avtab_node_cmp(const struct avtab_key *key1, const struct avtab_key *key2) { u16 specified = key1->specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class == key2->target_class && (specified & key2->specified)) return 0; if (key1->source_type < key2->source_type) return -1; if (key1->source_type == key2->source_type && key1->target_type < key2->target_type) return -1; if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class < key2->target_class) return -1; return 1; } static int avtab_insert(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur, *newnode; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); /* extended perms may not be unique */ if (cmp == 0 && !(key->specified & AVTAB_XPERMS)) return -EEXIST; if (cmp <= 0) break; } newnode = avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp <= 0) break; } return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node *avtab_search_node(struct avtab *h, const struct avtab_key *key) { u32 hvalue; struct avtab_node *cur; int cmp; if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } struct avtab_node *avtab_search_node_next(struct avtab_node *node, u16 specified) { struct avtab_key tmp_key; struct avtab_node *cur; int cmp; if (!node) return NULL; tmp_key = node->key; tmp_key.specified = specified; for (cur = node->next; cur; cur = cur->next) { cmp = avtab_node_cmp(&tmp_key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } void avtab_destroy(struct avtab *h) { u32 i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { nslot = nrules > 3 ? rounddown_pow_of_two(nrules / 2) : 2; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } #ifdef CONFIG_SECURITY_SELINUX_DEBUG void avtab_hash_eval(struct avtab *h, const char *tag) { u32 i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += (unsigned long long)chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d, sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } #endif /* CONFIG_SECURITY_SELINUX_DEBUG */ /* clang-format off */ static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; /* clang-format on */ int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), void *p, bool conditional) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, i; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int rc; unsigned int set, vers = pol->policyvers; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32) * items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16) * 4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = hweight16(key.specified & (AVTAB_XPERMS | AVTAB_TYPE | AVTAB_AV)); if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if ((vers < POLICYDB_VERSION_COND_XPERMS) && (key.specified & AVTAB_XPERMS) && conditional) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules in conditional " "policies and one was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32) * ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL, false); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, const struct avtab_node *cur, struct policy_file *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp) { u32 i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = KMEM_CACHE(avtab_node, SLAB_PANIC); avtab_xperms_cachep = KMEM_CACHE(avtab_extended_perms, SLAB_PANIC); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux IPv6 multicast routing support for BSD pim6sd * Based on net/ipv4/ipmr.c. * * (c) 2004 Mickael Hoerdt, <hoerdt@clarinet.u-strasbg.fr> * LSIIT Laboratory, Strasbourg, France * (c) 2004 Jean-Philippe Andriot, <jean-philippe.andriot@6WIND.com> * 6WIND, Paris, France * Copyright (C)2007,2008 USAGI/WIDE Project * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <linux/mroute6.h> #include <linux/pim.h> #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> #include <linux/export.h> #include <net/ip6_checksum.h> #include <linux/netconf.h> #include <net/ip_tunnels.h> #include <linux/nospec.h> struct ip6mr_rule { struct fib_rule common; }; struct ip6mr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved entries is changed only in process context and protected with weak lock mrt_lock. Queue of unresolved entries is protected with strong spinlock mfc_unres_lock. In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr_table *mrt); static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv6.mr6_tables)) static bool ip6mr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv6.mr6_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv6.mr6_tables) return NULL; return ret; } static struct mr_table *__ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ip6mr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { int err; struct ip6mr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi6_to_flowi(flp6)); err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flowi6_to_flowi(flp6), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ip6mr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ip6mr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) { return 1; } static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .family = RTNL_FAMILY_IP6MR, .rule_size = sizeof(struct ip6mr_rule), .addr_size = sizeof(struct in6_addr), .action = ip6mr_rule_action, .match = ip6mr_rule_match, .configure = ip6mr_rule_configure, .compare = ip6mr_rule_compare, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, }; static int __net_init ip6mr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ip6mr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv6.mr6_tables); mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT); if (err < 0) goto err2; net->ipv6.mr6_rules_ops = ops; return 0; err2: rtnl_lock(); ip6mr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } fib_rules_unregister(net->ipv6.mr6_rules_ops); } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack); } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR); } bool ip6mr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL && rule->table == RT6_TABLE_DFLT && !rule->l3mdev; } EXPORT_SYMBOL(ip6mr_rule_default); #else #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) static bool ip6mr_can_free_table(struct net *net) { return !check_net(net); } static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv6.mrt6; return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { return net->ipv6.mrt6; } #define __ip6mr_get_table ip6mr_get_table static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { *mrt = net->ipv6.mrt6; return 0; } static int __net_init ip6mr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv6.mrt6 = mrt; return 0; } static void __net_exit ip6mr_rules_exit(struct net *net) { ASSERT_RTNL(); ip6mr_free_table(net->ipv6.mrt6); net->ipv6.mrt6 = NULL; } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return 0; } #endif static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc6_cache_cmp_arg *cmparg = arg->key; struct mfc6_cache *c = (struct mfc6_cache *)ptr; return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) || !ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin); } static const struct rhashtable_params ip6mr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc6_cache, cmparg), .key_len = sizeof(struct mfc6_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ip6mr_hash_cmp, .automatic_shrinking = true, }; static void ip6mr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); #endif } static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = { .mf6c_origin = IN6ADDR_ANY_INIT, .mf6c_mcastgrp = IN6ADDR_ANY_INIT, }; static struct mr_table_ops ip6mr_mr_table_ops = { .rht_params = &ip6mr_rht_params, .cmparg_any = &ip6mr_mr_table_ops_cmparg_any, }; static struct mr_table *ip6mr_new_table(struct net *net, u32 id) { struct mr_table *mrt; mrt = __ip6mr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ip6mr_mr_table_ops, ipmr_expire_process, ip6mr_new_table_set); } static void ip6mr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!ip6mr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC | MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing * /proc/ip6_mr_cache /proc/ip6_mr_vif */ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); } return 0; } static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, .next = mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, .show = ip6mr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group " "Origin " "Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc6_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", atomic_long_read(&mfc->_c.mfc_un.res.pkt), atomic_long_read(&mfc->_c.mfc_un.res.bytes), atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IPV6_PIMSM_V2 static int pim6_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) || (pim->flags & PIM_NULL_REGISTER) || (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, sizeof(*pim), IPPROTO_PIM, csum_partial((void *)pim, sizeof(*pim), 0)) && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; /* check if the inner packet is destined to mcast group */ encap = (struct ipv6hdr *)(skb_transport_header(skb) + sizeof(*pim)); if (!ipv6_addr_is_multicast(&encap->daddr) || encap->payload_len == 0 || ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto drop; /* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */ reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (reg_vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]); if (!reg_dev) goto drop; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return 0; drop: kfree_skb(skb); return 0; } static const struct inet6_protocol pim6_protocol = { .handler = pim6_rcv, }; /* Service routines creating virtual interfaces: PIMREG */ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; if (!pskb_inet_may_pull(skb)) goto tx_err; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto tx_err; DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), MRT6MSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_local = true; } static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT6_TABLE_DFLT) sprintf(name, "pim6reg"); else sprintf(name, "pim6reg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } #endif static int call_ip6mr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, mifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv6.ipmr_seq); } static int call_ip6mr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc6_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type, &mfc->_c, tb_id, &net->ipv6.ipmr_seq); } /* Delete a VIF entry */ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct vif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); spin_lock(&mrt_lock); RCU_INIT_POINTER(v->dev, NULL); #ifdef CONFIG_IPV6_PIMSM_V2 if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } #endif if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_dec(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static inline void ip6mr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c); } static inline void ip6mr_cache_free(struct mfc6_cache *c) { call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT; rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else kfree_skb(skb); } ip6mr_cache_free(c); } /* Timer process for all the unresolved queue. */ static void ipmr_do_expire_process(struct mr_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; struct mr_mfc *c, *next; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } if (!list_empty(&mrt->mfc_unres_queue)) ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ip6mr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int mif6_add(struct net *net, struct mr_table *mrt, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { #ifdef CONFIG_IPV6_PIMSM_V2 case MIFF_REGISTER: /* * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; #endif case 0: dev = dev_get_by_index(net, vifc->mif6c_pifi); if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_inc(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0), MIFF_REGISTER); /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); #endif if (vifi + 1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt, struct in6_addr *mcastgrp, mifi_t mifi) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = in6addr_any, .mf6c_mcastgrp = *mcastgrp, }; if (ipv6_addr_any(mcastgrp)) return mr_mfc_find_any_parent(mrt, mifi); return mr_mfc_find_any(mrt, mifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc6_cache * ip6mr_cache_find_parent(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp, int parent) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXMIFS; c->_c.free = ip6mr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); return c; } static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (!c) return NULL; skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; return c; } /* * A cache entry has gone into a resolved state from queued */ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; /* * Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE; } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip6_mr_forward(net, mrt, skb->dev, skb, c); rcu_read_unlock(); } } } /* * Bounce a cache query up to pim6sd and netlink. * * Called under rcu_read_lock() */ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { struct sock *mroute6_sk; struct sk_buff *skb; struct mrt6msg *msg; int ret; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt) +sizeof(*msg)); else #endif skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC); if (!skb) return -ENOBUFS; /* I suppose that internal messages * do not require checksums */ skb->ip_summed = CHECKSUM_UNNECESSARY; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) { /* Ugly, but we have no choice with this interface. Duplicate old header, fix length etc. And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; if (assert == MRT6MSG_WRMIFWHOLE) msg->im6_mif = mifi; else msg->im6_mif = READ_ONCE(mrt->mroute_reg_vif_num); msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb->ip_summed = CHECKSUM_UNNECESSARY; } else #endif { /* * Copy the IP header */ skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr)); /* * Add our header */ skb_put(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; msg->im6_mif = mifi; msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; } mroute6_sk = rcu_dereference(mrt->mroute_sk); if (!mroute6_sk) { kfree_skb(skb); return -EINVAL; } mrt6msg_netlink_event(mrt, skb); /* Deliver to user space multicast routing algorithms */ ret = sock_queue_rcv_skb(mroute6_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, struct sk_buff *skb, struct net_device *dev) { struct mfc6_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; break; } } if (!found) { /* * Create a new entry if allowable */ c = ip6mr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mf6c_origin = ipv6_hdr(skb)->saddr; c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; /* * Reflect first query at pim6sd */ err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ip6mr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* * MFC6 cache manipulation by user space */ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, int parent) { struct mfc6_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); list_del_rcu(&c->_c.list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, c, mrt->id); mr6_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ip6mr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) mif6_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static unsigned int ip6mr_seq_read(const struct net *net) { return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net); } static int ip6mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, ip6mr_mr_table_iter, extack); } static struct notifier_block ip6_mr_notifier = { .notifier_call = ip6mr_device_event }; static const struct fib_notifier_ops ip6mr_notifier_ops_template = { .family = RTNL_FAMILY_IP6MR, .fib_seq_read = ip6mr_seq_read, .fib_dump = ip6mr_dump, .owner = THIS_MODULE, }; static int __net_init ip6mr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv6.ipmr_seq = 0; ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv6.ip6mr_notifier_ops = ops; return 0; } static void __net_exit ip6mr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops); net->ipv6.ip6mr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ip6mr_net_init(struct net *net) { int err; err = ip6mr_notifier_init(net); if (err) return err; err = ip6mr_rules_init(net); if (err < 0) goto ip6mr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip6_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ip6mr_rules_exit(net); rtnl_unlock(); #endif ip6mr_rules_fail: ip6mr_notifier_exit(net); return err; } static void __net_exit ip6mr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip6_mr_cache", net->proc_net); remove_proc_entry("ip6_mr_vif", net->proc_net); #endif ip6mr_notifier_exit(net); } static void __net_exit ip6mr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip6mr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, .exit_batch = ip6mr_net_exit_batch, }; static const struct rtnl_msg_handler ip6mr_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = RTNL_FAMILY_IP6MR, .msgtype = RTM_GETROUTE, .doit = ip6mr_rtm_getroute, .dumpit = ip6mr_rtm_dumproute}, }; int __init ip6_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); if (!mrt_cachep) return -ENOMEM; err = register_pernet_subsys(&ip6mr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IPV6_PIMSM_V2 if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif err = rtnl_register_many(ip6mr_rtnl_msg_handlers); if (!err) return 0; #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } void __init ip6_mr_cleanup(void) { rtnl_unregister_many(ip6mr_rtnl_msg_handlers); #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); #endif unregister_netdevice_notifier(&ip6_mr_notifier); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, struct mf6cctl *mfc, int mrtsock, int parent) { unsigned char ttls[MAXMIFS]; struct mfc6_cache *uc, *c; struct mr_mfc *_uc; bool found; int i, err; if (mfc->mf6cc_parent >= MAXMIFS) return -ENFILE; memset(ttls, 255, MAXMIFS); for (i = 0; i < MAXMIFS; i++) { if (IF_ISSET(i, &mfc->mf6cc_ifset)) ttls[i] = 1; } /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; c = ip6mr_cache_alloc(); if (!c) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ip6mr_rht_params); if (err) { pr_err("ip6mr: rhtable insert error %d\n", err); ip6mr_cache_free(c); return err; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc6_cache *)_uc; if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* * Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct mr_mfc *c, *tmp; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS))) continue; mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT6_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } spin_unlock_bh(&mfc_unres_lock); } } } static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); spin_lock(&mrt_lock); if (rtnl_dereference(mrt->mroute_sk)) { err = -EADDRINUSE; } else { rcu_assign_pointer(mrt->mroute_sk, sk); sock_set_flag(sk, SOCK_RCU_FREE); atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } spin_unlock(&mrt_lock); if (!err) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); rtnl_unlock(); return err; } int ip6mr_sk_done(struct sock *sk) { struct net *net = sock_net(sk); struct ipv6_devconf *devconf; struct mr_table *mrt; int err = -EACCES; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return err; devconf = net->ipv6.devconf_all; if (!devconf || !atomic_read(&devconf->mc_forwarding)) return err; rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { spin_lock(&mrt_lock); RCU_INIT_POINTER(mrt->mroute_sk, NULL); /* Note that mroute_sk had SOCK_RCU_FREE set, * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ atomic_dec(&devconf->mc_forwarding); spin_unlock(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MFC); err = 0; break; } } rtnl_unlock(); return err; } bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; return rcu_access_pointer(mrt->mroute_sk); } EXPORT_SYMBOL(mroute6_is_socket); /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; if (optname != MRT6_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } switch (optname) { case MRT6_INIT: if (optlen < sizeof(int)) return -EINVAL; return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); case MRT6_ADD_MIF: if (optlen < sizeof(vif)) return -EINVAL; if (copy_from_sockptr(&vif, optval, sizeof(vif))) return -EFAULT; if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); ret = mif6_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; case MRT6_DEL_MIF: if (optlen < sizeof(mifi_t)) return -EINVAL; if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; /* * Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; fallthrough; case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) return -EFAULT; if (parent == 0) parent = mfc.mf6cc_parent; rtnl_lock(); if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) ret = ip6mr_mfc_delete(mrt, &mfc, parent); else ret = ip6mr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); rtnl_unlock(); return ret; case MRT6_FLUSH: { int flags; if (optlen != sizeof(flags)) return -EINVAL; if (copy_from_sockptr(&flags, optval, sizeof(flags))) return -EFAULT; rtnl_lock(); mroute_clean_tables(mrt, flags); rtnl_unlock(); return 0; } /* * Control PIM assert (to activate pim will activate assert) */ case MRT6_ASSERT: { int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; mrt->mroute_do_assert = v; return 0; } #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { bool do_wrmifwhole; int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; do_wrmifwhole = (v == MRT6MSG_WRMIFWHOLE); v = !!v; rtnl_lock(); ret = 0; if (v != mrt->mroute_do_pim) { mrt->mroute_do_pim = v; mrt->mroute_do_assert = v; mrt->mroute_do_wrvifwhole = do_wrmifwhole; } rtnl_unlock(); return ret; } #endif #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES case MRT6_TABLE: { u32 v; if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) return -EINVAL; if (sk == rcu_access_pointer(mrt->mroute_sk)) return -EBUSY; rtnl_lock(); ret = 0; mrt = ip6mr_new_table(net, v); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw6_sk(sk)->ip6mr_table = v; rtnl_unlock(); return ret; } #endif /* * Spurious command, or MRT6_VERSION which you cannot * set. */ default: return -ENOPROTOOPT; } } /* * Getsock opt support for the multicast routing system. */ int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (optname) { case MRT6_VERSION: val = 0x0305; break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; olr = min_t(int, olr, sizeof(int)); if (olr < 0) return -EINVAL; if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* * The IP multicast ioctl support routines. */ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) { struct sioc_sg_req6 *sr; struct sioc_mif_req6 *vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: vr = (struct sioc_mif_req6 *)arg; if (vr->mifi >= mrt->maxvif) return -EINVAL; vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->mifi]; if (VIF_EXISTS(mrt, vr->mifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: sr = (struct sioc_sg_req6 *)arg; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, &sr->grp.sin6_addr); if (c) { sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req6 { struct sockaddr_in6 src; struct sockaddr_in6 grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_mif_req6 { mifi_t mifi; compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req6 sr; struct compat_sioc_mif_req6 vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); return dst_output(net, sk, skb); } /* * Processing handlers for ip6mr_forward */ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct ipv6hdr *ipv6h; struct dst_entry *dst; struct flowi6 fl6; vif_dev = vif_dev_read(vif); if (!vif_dev) goto out_free; #ifdef CONFIG_IPV6_PIMSM_V2 if (vif->flags & MIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } #endif ipv6h = ipv6_hdr(skb); fl6 = (struct flowi6) { .flowi6_oif = vif->link, .daddr = ipv6h->daddr, }; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); goto out_free; } skb_dst_drop(skb); skb_dst_set(skb, dst); /* * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ skb->dev = vif_dev; WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); /* We are about to write */ /* XXX: extension headers? */ if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev))) goto out_free; ipv6h = ipv6_hdr(skb); ipv6h->hop_limit--; IP6CB(skb)->flags |= IP6SKB_FORWARDED; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, vif_dev, ip6mr_forward2_finish); out_free: kfree_skb(skb); return 0; } /* Called with rcu_read_lock() */ static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in mif6_delete()/mif6_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* Called under rcu_read_lock() */ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int vif, ct; int true_vifi = ip6mr_find_vif(mrt, dev); vif = c->_c.mfc_parent; atomic_long_inc(&c->_c.mfc_un.res.pkt); atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); if (mrt->mroute_do_wrvifwhole) ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRMIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* * Forward the frame */ if (ipv6_addr_any(&c->mf6c_origin) && ipv6_addr_any(&c->mf6c_mcastgrp)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ip6mr_forward2(net, mrt, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, psend); return; } dont_forward: kfree_skb(skb); } /* * Multicast packets for forwarding arrive here */ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; int err; struct net_device *dev; /* skb->dev passed in is the master dev for vrfs. * Get the proper interface that does have a vif associated with it. */ dev = skb->dev; if (netif_is_l3_master(skb->dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) { kfree_skb(skb); return err; } cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); if (!cache) { int vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &ipv6_hdr(skb)->daddr, vif); } /* * No usable cache entry */ if (!cache) { int vif; vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) { int err = ip6mr_cache_unresolved(mrt, vif, skb, dev); return err; } kfree_skb(skb); return -ENODEV; } ip6_mr_forward(net, mrt, dev, skb, cache); return 0; } int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { int err; struct mr_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache && skb->dev) { int vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, vif); } if (!cache) { struct sk_buff *skb2; struct ipv6hdr *iph; struct net_device *dev; int vif; dev = skb->dev; if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) { rcu_read_unlock(); return -ENODEV; } /* really correct? */ skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_reset_transport_header(skb2); skb_put(skb2, sizeof(struct ipv6hdr)); skb_reset_network_header(skb2); iph = ipv6_hdr(skb2); iph->version = 0; iph->priority = 0; iph->flow_lbl[0] = 0; iph->flow_lbl[1] = 0; iph->flow_lbl[2] = 0; iph->payload_len = 0; iph->nexthdr = IPPROTO_NONE; iph->hop_limit = 0; iph->saddr = rt->rt6i_src.addr; iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc6_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IP6MR; rtm->rtm_dst_len = 128; rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c, cmd, flags); } static int mr6_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */ /* IP6MRA_CREPORT_SRC_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_DST_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct mrt6msg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct mrt6msg); msg = (struct mrt6msg *)skb_transport_header(pkt); skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IP6MR; if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) || nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) || nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR, &msg->im6_src) || nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR, &msg->im6_dst)) goto nla_put_failure; nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); } static const struct nla_policy ip6mr_getroute_policy[RTA_MAX + 1] = { [RTA_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_TABLE] = { .type = NLA_U32 }, }; static int ip6mr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, ip6mr_getroute_policy, extack); if (err) return err; rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for multicast route get request"); return -EINVAL; } if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } return 0; } static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct in6_addr src = {}, grp = {}; struct nlattr *tb[RTA_MAX + 1]; struct mfc6_cache *cache; struct mr_table *mrt; struct sk_buff *skb; u32 tableid; int err; err = ip6mr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (tb[RTA_SRC]) src = nla_get_in6_addr(tb[RTA_SRC]); if (tb[RTA_DST]) grp = nla_get_in6_addr(tb[RTA_DST]); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT); if (!mrt) { NL_SET_ERR_MSG_MOD(extack, "MR table does not exist"); return -ENOENT; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ip6mr_cache_find(mrt, &src, &grp); rcu_read_unlock(); if (!cache) { NL_SET_ERR_MSG_MOD(extack, "MR cache entry not found"); return -ENOENT; } skb = nlmsg_new(mr6_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) return -ENOBUFS; err = ip6mr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) { kfree_skb(skb); return err; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR) return skb->len; NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); } |
| 9 9 9 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM net #if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NET_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> TRACE_EVENT(net_dev_start_xmit, TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), TP_ARGS(skb, dev), TP_STRUCT__entry( __string( name, dev->name ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( int, network_offset ) __field( bool, transport_offset_valid) __field( int, transport_offset) __field( u8, tx_flags ) __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->network_offset = skb_network_offset(skb); __entry->transport_offset_valid = skb_transport_header_was_set(skb); __entry->transport_offset = skb_transport_header_was_set(skb) ? skb_transport_offset(skb) : 0; __entry->tx_flags = skb_shinfo(skb)->tx_flags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, __entry->gso_size, __entry->gso_segs, __entry->gso_type) ); TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, int rc, struct net_device *dev, unsigned int skb_len), TP_ARGS(skb, rc, dev, skb_len), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u rc=%d", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) ); TRACE_EVENT(net_dev_xmit_timeout, TP_PROTO(struct net_device *dev, int queue_index), TP_ARGS(dev, queue_index), TP_STRUCT__entry( __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) ), TP_fast_assign( __assign_str(name); __assign_str(driver); __entry->queue_index = queue_index; ), TP_printk("dev=%s driver=%s queue=%d", __get_str(name), __get_str(driver), __entry->queue_index) ); DECLARE_EVENT_CLASS(net_dev_template, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) DEFINE_EVENT(net_dev_template, net_dev_queue, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_receive_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_rx, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __string( name, skb->dev->name ) __field( unsigned int, napi_id ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( u32, hash ) __field( bool, l4_hash ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( unsigned int, truesize ) __field( bool, mac_header_valid) __field( int, mac_header ) __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); #ifdef CONFIG_NET_RX_BUSY_POLL __entry->napi_id = skb->napi_id; #else __entry->napi_id = 0; #endif __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->hash = skb->hash; __entry->l4_hash = skb->l4_hash; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->truesize = skb->truesize; __entry->mac_header_valid = skb_mac_header_was_set(skb); __entry->mac_header = skb_mac_header(skb) - skb->data; __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, __entry->nr_frags, __entry->gso_size, __entry->gso_type) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field(int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), TP_ARGS(ret) ); #endif /* _TRACE_NET_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 254 302 3 274 31 299 28 28 19 19 19 19 19 19 19 19 19 19 19 19 284 284 19 19 93 93 93 93 486 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/iversion.h> #include <linux/writeback.h> #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/pidfs.h> #include <linux/uaccess.h> #include "internal.h" int simple_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); const struct dentry_operations simple_dentry_operations = { .d_delete = always_delete_dentry, }; EXPORT_SYMBOL(simple_dentry_operations); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_sb->s_d_op) d_set_d_op(dentry, &simple_dentry_operations); if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) return NULL; d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while (*p) { struct dentry *d = hlist_entry(*p, struct dentry, d_sib); p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { if (!hlist_unhashed(&cursor->d_sib)) __hlist_del(&cursor->d_sib); hlist_add_behind(&cursor->d_sib, &d->d_sib); p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (to) hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct dentry *next = NULL; struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = &dentry->d_children.first; else p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; p = &next->d_sib.next; } spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (next) hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); /* simple_offset_add() never assigns these to a dentry */ enum { DIR_OFFSET_FIRST = 2, /* Find first real entry */ DIR_OFFSET_EOD = S32_MAX, }; /* simple_offset_add() allocation range */ enum { DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; static void offset_set(struct dentry *dentry, long offset) { dentry->d_fsdata = (void *)offset; } static long dentry2offset(struct dentry *dentry) { return (long)dentry->d_fsdata; } static struct lock_class_key simple_offset_lock_class; /** * simple_offset_init - initialize an offset_ctx * @octx: directory offset map to be initialized * */ void simple_offset_init(struct offset_ctx *octx) { mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE); lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class); octx->next_offset = DIR_OFFSET_MIN; } /** * simple_offset_add - Add an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: new dentry being added * * Returns zero on success. @octx and the dentry's offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { unsigned long offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, DIR_OFFSET_MAX, &octx->next_offset, GFP_KERNEL); if (unlikely(ret < 0)) return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; } static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry, long offset) { int ret; ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL); if (ret) return ret; offset_set(dentry, offset); return 0; } /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: dentry being removed * */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { long offset; offset = dentry2offset(dentry); if (offset == 0) return; mtree_erase(&octx->mt, offset); offset_set(dentry, 0); } /** * simple_offset_rename - handle directory offsets for rename * @old_dir: parent directory of source entry * @old_dentry: dentry of source entry * @new_dir: parent_directory of destination entry * @new_dentry: dentry of destination * * Caller provides appropriate serialization. * * User space expects the directory offset value of the replaced * (new) directory entry to be unchanged after a rename. * * Returns zero on success, a negative errno value on failure. */ int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long new_offset = dentry2offset(new_dentry); simple_offset_remove(old_ctx, old_dentry); if (new_offset) { offset_set(new_dentry, 0); return simple_offset_replace(new_ctx, old_dentry, new_offset); } return simple_offset_add(new_ctx, old_dentry); } /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved * @old_dentry: dentry being moved * @new_dir: destination parent * @new_dentry: destination dentry * * This API preserves the directory offset values. Caller provides * appropriate serialization. * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long old_index = dentry2offset(old_dentry); long new_index = dentry2offset(new_dentry); int ret; simple_offset_remove(old_ctx, old_dentry); simple_offset_remove(new_ctx, new_dentry); ret = simple_offset_replace(new_ctx, old_dentry, new_index); if (ret) goto out_restore; ret = simple_offset_replace(old_ctx, new_dentry, old_index); if (ret) { simple_offset_remove(new_ctx, old_dentry); goto out_restore; } ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (ret) { simple_offset_remove(new_ctx, old_dentry); simple_offset_remove(old_ctx, new_dentry); goto out_restore; } return 0; out_restore: (void)simple_offset_replace(old_ctx, old_dentry, old_index); (void)simple_offset_replace(new_ctx, new_dentry, new_index); return ret; } /** * simple_offset_destroy - Release offset map * @octx: directory offset ctx that is about to be destroyed * * During fs teardown (eg. umount), a directory's offset map might still * contain entries. xa_destroy() cleans out anything that remains. */ void simple_offset_destroy(struct offset_ctx *octx) { mtree_destroy(&octx->mt); } /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated * @offset: a byte offset * @whence: enumerator describing the starting position for this update * * SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories. * * Returns the updated read position if successful; otherwise a * negative errno is returned and the read position remains unchanged. */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_CUR: offset += file->f_pos; fallthrough; case SEEK_SET: if (offset >= 0) break; fallthrough; default: return -EINVAL; } return vfs_setpos(file, offset, LONG_MAX); } static struct dentry *find_positive_dentry(struct dentry *parent, struct dentry *dentry, bool next) { struct dentry *found = NULL; spin_lock(&parent->d_lock); if (next) dentry = d_next_sibling(dentry); else if (!dentry) dentry = d_first_child(parent); hlist_for_each_entry_from(dentry, d_sib) { if (!simple_positive(dentry)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(dentry)) found = dget_dlock(dentry); spin_unlock(&dentry->d_lock); if (likely(found)) break; } spin_unlock(&parent->d_lock); return found; } static noinline_for_stack struct dentry * offset_dir_lookup(struct dentry *parent, loff_t offset) { struct inode *inode = d_inode(parent); struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; MA_STATE(mas, &octx->mt, offset, offset); if (offset == DIR_OFFSET_FIRST) found = find_positive_dentry(parent, NULL, false); else { rcu_read_lock(); child = mas_find(&mas, DIR_OFFSET_MAX); found = find_positive_dentry(parent, child, false); rcu_read_unlock(); } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; struct dentry *dentry; dentry = offset_dir_lookup(dir, ctx->pos); if (!dentry) goto out_eod; while (true) { struct dentry *next; ctx->pos = dentry2offset(dentry); if (!offset_dir_emit(ctx, dentry)) break; next = find_positive_dentry(dir, dentry, true); dput(dentry); if (!next) goto out_eod; dentry = next; } dput(dentry); return; out_eod: ctx->pos = DIR_OFFSET_EOD; } /** * offset_readdir - Emit entries starting at offset @ctx->pos * @file: an open directory to iterate over * @ctx: directory iteration context * * Caller must hold @file's i_rwsem to prevent insertion or removal of * entries during this call. * * On entry, @ctx->pos contains an offset that represents the first entry * to be read from the directory. * * The operation continues until there are no more entries to read, or * until the ctx->actor indicates there is no more space in the caller's * output buffer. * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. * Caller places this value in the d_off field of the last entry in the * user's buffer. * * Return values: * %0 - Complete */ static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos != DIR_OFFSET_EOD) offset_iterate_dir(file, ctx); return 0; } const struct file_operations simple_offset_dir_operations = { .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, .fsync = noop_fsync, }; static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); d = prev ? d_next_sibling(prev) : d_first_child(parent); hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock(inode); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode_set_ctime_current(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; inode_lock(inode); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (d_is_dir(victim)) fsnotify_rmdir(inode, victim); else fsnotify_unlink(inode, victim); if (callback) callback(victim); dput(victim); // unpin it } if (victim == dentry) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } EXPORT_SYMBOL(simple_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; s->s_d_op = ctx->dops; return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock); hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); goto out; } spin_unlock(&child->d_lock); } ret = 1; out: spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(simple_empty); int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); dput(dentry); return 0; } EXPORT_SYMBOL(simple_unlink); int simple_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); simple_unlink(dir, dentry); drop_nlink(dir); return 0; } EXPORT_SYMBOL(simple_rmdir); /** * simple_rename_timestamp - update the various inode timestamps for rename * @old_dir: old parent directory * @old_dentry: dentry that is being renamed * @new_dir: new parent directory * @new_dentry: target for rename * * POSIX mandates that the old and new parent directories have their ctime and * mtime updated, and that inodes of @old_dentry and @new_dentry (if any), have * their ctime updated. */ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode *newino = d_inode(new_dentry); inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); } EXPORT_SYMBOL_GPL(simple_rename_timestamp); int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL_GPL(simple_rename_exchange); int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int they_are_dirs = d_is_dir(old_dentry); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; if (flags & RENAME_EXCHANGE) return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (d_really_is_positive(new_dentry)) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem * @idmap: idmap of the target mount * @dentry: dentry * @iattr: iattr structure * * Returns 0 on success, -error on failure. * * simple_setattr is a simple ->setattr implementation without a proper * implementation of size changes. * * It can either be used for in-memory filesystems or special files * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; error = setattr_prepare(idmap, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); setattr_copy(idmap, inode, iattr); mark_inode_dirty(inode); return 0; } EXPORT_SYMBOL(simple_setattr); static int simple_read_folio(struct file *file, struct folio *folio) { folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); folio_unlock(folio); return 0; } int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct folio *folio; folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); *foliop = folio; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); folio_zero_segments(folio, 0, from, from + len, folio_size(folio)); } return 0; } EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " * @copied: " * @folio: " * @fsdata: " * * simple_write_end does the minimum needed for updating a folio after * writing is done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_mutex is assumed to be held. * Block based filesystems should use generic_write_end(). * NOTE: Even though i_size might get updated by this function, mark_inode_dirty * is not called, so a filesystem that actually does store data in .write_inode * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * * Use *ONLY* with simple_read_folio() */ static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; /* zero the stale part of the folio if we did a short copy */ if (!folio_test_uptodate(folio)) { if (copied < len) { size_t from = offset_in_folio(folio, pos); folio_zero_range(folio, from + copied, len - copied); } folio_mark_uptodate(folio); } /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold the i_mutex. */ if (last_pos > inode->i_size) i_size_write(inode, last_pos); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } /* * Provides ramfs-style behavior: data in the pagecache, but no writeback. */ const struct address_space_operations ram_aops = { .read_folio = simple_read_folio, .write_begin = simple_write_begin, .write_end = simple_write_end, .dirty_folio = noop_dirty_folio, }; EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate * unique inode values later for this filesystem, then you must take care * to pass it an appropriate max_reserved value to avoid collisions. */ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; struct dentry *dentry; int i; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; inode = new_inode(s); if (!inode) return -ENOMEM; /* * because the root inode is 1, the files array must not contain an * entry at index 1 */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); s->s_root = d_make_root(inode); if (!s->s_root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) continue; /* warn if it tries to conflict with the root inode */ if (unlikely(i == 1)) printk(KERN_WARNING "%s: %s passed in a files array" "with an index of 1!\n", __func__, s->s_type->name); dentry = d_alloc_name(s->s_root, files->name); if (!dentry) return -ENOMEM; inode = new_inode(s); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_mode = S_IFREG | files->mode; simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); } return 0; } EXPORT_SYMBOL(simple_fill_super); static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; } mntget(*mount); ++*count; spin_unlock(&pin_fs_lock); mntput(mnt); return 0; } EXPORT_SYMBOL(simple_pin_fs); void simple_release_fs(struct vfsmount **mount, int *count) { struct vfsmount *mnt; spin_lock(&pin_fs_lock); mnt = *mount; if (!--*count) *mount = NULL; spin_unlock(&pin_fs_lock); mntput(mnt); } EXPORT_SYMBOL(simple_release_fs); /** * simple_read_from_buffer - copy data from the buffer to user space * @to: the user space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The simple_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the user space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; size_t ret; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; ret = copy_to_user(to, from + pos, count); if (ret == count) return -EFAULT; count -= ret; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_read_from_buffer); /** * simple_write_to_buffer - copy data from user space to the buffer * @to: the buffer to write to * @available: the size of the buffer * @ppos: the current position in the buffer * @from: the user space buffer to read from * @count: the maximum number of bytes to read * * The simple_write_to_buffer() function reads up to @count bytes from the user * space address starting at @from into the buffer @to at offset @ppos. * * On success, the number of bytes written is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count) { loff_t pos = *ppos; size_t res; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; res = copy_from_user(to + pos, from, count); if (res == count) return -EFAULT; count -= res; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_write_to_buffer); /** * memory_read_from_buffer - copy data from the buffer * @to: the kernel space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The memory_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the kernel space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; if (pos < 0) return -EINVAL; if (pos >= available) return 0; if (count > available - pos) count = available - pos; memcpy(to, from + pos, count); *ppos = pos + count; return count; } EXPORT_SYMBOL(memory_read_from_buffer); /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then * possibly a read which collects the result - which is stored in a * file-local buffer. */ void simple_transaction_set(struct file *file, size_t n) { struct simple_transaction_argresp *ar = file->private_data; BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); /* * The barrier ensures that ar->size will really remain zero until * ar->data is ready for reading. */ smp_mb(); ar->size = n; } EXPORT_SYMBOL(simple_transaction_set); char *simple_transaction_get(struct file *file, const char __user *buf, size_t size) { struct simple_transaction_argresp *ar; static DEFINE_SPINLOCK(simple_transaction_lock); if (size > SIMPLE_TRANSACTION_LIMIT - 1) return ERR_PTR(-EFBIG); ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL); if (!ar) return ERR_PTR(-ENOMEM); spin_lock(&simple_transaction_lock); /* only one write allowed per open */ if (file->private_data) { spin_unlock(&simple_transaction_lock); free_page((unsigned long)ar); return ERR_PTR(-EBUSY); } file->private_data = ar; spin_unlock(&simple_transaction_lock); if (copy_from_user(ar->data, buf, size)) return ERR_PTR(-EFAULT); return ar->data; } EXPORT_SYMBOL(simple_transaction_get); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { struct simple_transaction_argresp *ar = file->private_data; if (!ar) return 0; return simple_read_from_buffer(buf, size, pos, ar->data, ar->size); } EXPORT_SYMBOL(simple_transaction_read); int simple_transaction_release(struct inode *inode, struct file *file) { free_page((unsigned long)file->private_data); return 0; } EXPORT_SYMBOL(simple_transaction_release); /* Simple attribute files */ struct simple_attr { int (*get)(void *, u64 *); int (*set)(void *, u64); char get_buf[24]; /* enough to store a u64 and "\n\0" */ char set_buf[24]; void *data; const char *fmt; /* format for read operation */ struct mutex mutex; /* protects access to these buffers */ }; /* simple_attr_open is called by an actual attribute open file operation * to set the attribute specific access operations. */ int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { struct simple_attr *attr; attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) return -ENOMEM; attr->get = get; attr->set = set; attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); file->private_data = attr; return nonseekable_open(inode, file); } EXPORT_SYMBOL_GPL(simple_attr_open); int simple_attr_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */ /* read from the buffer that is filled with the get function */ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; size_t size; ssize_t ret; attr = file->private_data; if (!attr->get) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; if (*ppos && attr->get_buf[0]) { /* continued read */ size = strlen(attr->get_buf); } else { /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) goto out; size = scnprintf(attr->get_buf, sizeof(attr->get_buf), attr->fmt, (unsigned long long)val); } ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size); out: mutex_unlock(&attr->mutex); return ret; } EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; size_t size; ssize_t ret; attr = file->private_data; if (!attr->set) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; ret = -EFAULT; size = min(sizeof(attr->set_buf) - 1, len); if (copy_from_user(attr->set_buf, buf, size)) goto out; attr->set_buf[size] = '\0'; if (is_signed) ret = kstrtoll(attr->set_buf, 0, &val); else ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ out: mutex_unlock(&attr->mutex); return ret; } ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(simple_attr_write); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(simple_attr_write_signed); /** * generic_encode_ino32_fh - generic export_operations->encode_fh function * @inode: the object to encode * @fh: where to store the file handle fragment * @max_len: maximum length to store there (in 4 byte units) * @parent: parent directory inode, if wanted * * This generic encode_fh function assumes that the 32 inode number * is suitable for locating an inode, and that the generation number * can be used to check that it is still valid. It places them in the * filehandle fragment where export_decode_fh expects to find them. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent) { struct fid *fid = (void *)fh; int len = *max_len; int type = FILEID_INO32_GEN; if (parent && (len < 4)) { *max_len = 4; return FILEID_INVALID; } else if (len < 2) { *max_len = 2; return FILEID_INVALID; } len = 2; fid->i32.ino = inode->i_ino; fid->i32.gen = inode->i_generation; if (parent) { fid->i32.parent_ino = parent->i_ino; fid->i32.parent_gen = parent->i_generation; len = 4; type = FILEID_INO32_GEN_PARENT; } *max_len = len; return type; } EXPORT_SYMBOL_GPL(generic_encode_ino32_fh); /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the object specified in the file handle. */ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.ino, fid->i32.gen); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); /** * generic_fh_to_parent - generic helper for the fh_to_parent export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the _parent_ object specified in the file handle if it * is specified in the file handle, or NULL otherwise. */ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len <= 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.parent_ino, (fh_len > 3 ? fid->i32.parent_gen : 0)); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** * __generic_file_fsync - generic fsync implementation for simple filesystems * * @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_file_fsync(struct file *file, loff_t start, loff_t end, int 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; inode_lock(inode); 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: inode_unlock(inode); /* 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_file_fsync); /** * generic_file_fsync - generic fsync implementation for simple filesystems * with flush * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * */ int generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; err = __generic_file_fsync(file, start, end, datasync); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev); } EXPORT_SYMBOL(generic_file_fsync); /** * generic_check_addressable - Check addressability of file system * @blocksize_bits: log of file system block size * @num_blocks: number of blocks in file system * * Determine whether a file system with @num_blocks blocks (and a * block size of 2**@blocksize_bits) is addressable by the sector_t * and page cache of the system. Return 0 if so and -EFBIG otherwise. */ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page = last_fs_block >> (PAGE_SHIFT - blocksize_bits); if (unlikely(num_blocks == 0)) return 0; if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT)) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { return -EFBIG; } return 0; } EXPORT_SYMBOL(generic_check_addressable); /* * No-op implementation of ->fsync for in-memory filesystems. */ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return 0; } EXPORT_SYMBOL(noop_fsync); ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* * iomap based filesystems support direct I/O without need for * this callback. However, it still needs to be set in * inode->a_ops so that open/fcntl know that direct I/O is * generally supported. */ return -EINVAL; } EXPORT_SYMBOL_GPL(noop_direct_IO); /* Because kfree isn't assignment-compatible with void(void*) ;-/ */ void kfree_link(void *p) { kfree(p); } EXPORT_SYMBOL(kfree_link); struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { .dirty_folio = noop_dirty_folio, }; struct inode *inode = new_inode_pseudo(s); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &anon_aops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); /** * simple_nosetlease - generic helper for prohibiting leases * @filp: file pointer * @arg: type of lease to obtain * @flp: new lease supplied for insertion * @priv: private data for lm_setup operation * * Generic helper for filesystems that do not wish to allow leases to be set. * All arguments are ignored and it just returns -EINVAL. */ int simple_nosetlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } EXPORT_SYMBOL(simple_nosetlease); /** * simple_get_link - generic helper to get the target of "fast" symlinks * @dentry: not used here * @inode: the symlink inode * @done: not used here * * Generic helper for filesystems to use for symlink inodes where a pointer to * the symlink target is stored in ->i_link. NOTE: this isn't normally called, * since as an optimization the path lookup code uses any non-NULL ->i_link * directly, without calling ->get_link(). But ->get_link() still must be set, * to mark the inode_operations as being for a symlink. * * Return: the symlink target */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return inode->i_link; } EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { .get_link = simple_get_link, }; EXPORT_SYMBOL(simple_symlink_inode_operations); /* * Operations for a permanently empty directory. */ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-ENOENT); } static int empty_dir_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EPERM; } static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) { return -EOPNOTSUPP; } static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, .setattr = empty_dir_setattr, .listxattr = empty_dir_listxattr, }; static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) { /* An empty directory has two entries . and .. at offsets 0 and 1 */ return generic_file_llseek_size(file, offset, whence, 2, 2); } static int empty_dir_readdir(struct file *file, struct dir_context *ctx) { dir_emit_dots(file, ctx); return 0; } static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; void make_empty_dir_inode(struct inode *inode) { set_nlink(inode, 2); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; inode->i_op = &empty_dir_inode_operations; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &empty_dir_operations; } bool is_empty_dir_inode(struct inode *inode) { return (inode->i_fop == &empty_dir_operations) && (inode->i_op == &empty_dir_inode_operations); } #if IS_ENABLED(CONFIG_UNICODE) /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against * @len: len of name of dentry * @str: str pointer to name of dentry * @name: Name to compare against * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const struct dentry *parent; const struct inode *dir; union shortname_store strbuf; struct qstr qstr; /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. * * This comparison is safe under RCU because the caller * guarantees the consistency between str and len. See * __d_lookup_rcu_op_compare() for details. */ if (len == name->len && !memcmp(str, name->name, len)) return 0; parent = READ_ONCE(dentry->d_parent); dir = READ_ONCE(parent->d_inode); if (!dir || !IS_CASEFOLDED(dir)) return 1; qstr.len = len; qstr.name = str; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. * As above, len is guaranteed to match str, so the shortname case * is exactly when str points to ->d_shortname. */ if (qstr.name == dentry->d_shortname.string) { strbuf = dentry->d_shortname; // NUL is guaranteed to be in there qstr.name = strbuf.string; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } EXPORT_SYMBOL(generic_ci_d_compare); /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems * @dentry: dentry of the parent directory * @str: qstr of name whose hash we should fill in * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; int ret; if (!dir || !IS_CASEFOLDED(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); if (ret < 0 && sb_has_strict_encoding(sb)) return -EINVAL; return 0; } EXPORT_SYMBOL(generic_ci_d_hash); static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, #ifdef CONFIG_FS_ENCRYPTION .d_revalidate = fscrypt_d_revalidate, #endif }; /** * generic_ci_match() - Match a name (case-insensitively) with a dirent. * This is a filesystem helper for comparison with directory entries. * generic_ci_d_compare should be used in VFS' ->d_compare instead. * * @parent: Inode of the parent of the dirent under comparison * @name: name under lookup. * @folded_name: Optional pre-folded name under lookup * @de_name: Dirent name. * @de_name_len: dirent name length. * * Test whether a case-insensitive directory entry matches the filename * being searched. If @folded_name is provided, it is used instead of * recalculating the casefold of @name. * * Return: > 0 if the directory entry matches, 0 if it doesn't match, or * < 0 on error. */ int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len) { const struct super_block *sb = parent->i_sb; const struct unicode_map *um = sb->s_encoding; struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); struct qstr dirent = QSTR_INIT(de_name, de_name_len); int res = 0; if (IS_ENCRYPTED(parent)) { const struct fscrypt_str encrypted_name = FSTR_INIT((u8 *) de_name, de_name_len); if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent))) return -EINVAL; decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); if (!decrypted_name.name) return -ENOMEM; res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name, &decrypted_name); if (res < 0) { kfree(decrypted_name.name); return res; } dirent.name = decrypted_name.name; dirent.len = decrypted_name.len; } /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. */ if (dirent.len == name->len && !memcmp(name->name, dirent.name, dirent.len)) goto out; if (folded_name->name) res = utf8_strncasecmp_folded(um, folded_name, &dirent); else res = utf8_strncasecmp(um, name, &dirent); out: kfree(decrypted_name.name); if (res < 0 && sb_has_strict_encoding(sb)) { pr_err_ratelimited("Directory contains filename that is invalid UTF-8"); return 0; } return !res; } EXPORT_SYMBOL(generic_ci_match); #endif #ifdef CONFIG_FS_ENCRYPTION static const struct dentry_operations generic_encrypted_dentry_ops = { .d_revalidate = fscrypt_d_revalidate, }; #endif /** * generic_set_sb_d_ops - helper for choosing the set of * filesystem-wide dentry operations for the enabled features * @sb: superblock to be configured * * Filesystems supporting casefolding and/or fscrypt can call this * helper at mount-time to configure sb->s_d_op to best set of dentry * operations required for the enabled features. The helper must be * called after these have been configured, but before the root dentry * is created. */ void generic_set_sb_d_ops(struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) if (sb->s_encoding) { sb->s_d_op = &generic_ci_dentry_ops; return; } #endif #ifdef CONFIG_FS_ENCRYPTION if (sb->s_cop) { sb->s_d_op = &generic_encrypted_dentry_ops; return; } #endif } EXPORT_SYMBOL(generic_set_sb_d_ops); /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * We add a full memory barrier to ensure that any de facto ordering * with other state is preserved (either implicitly coming from cmpxchg * or explicitly from smp_mb if we don't know upfront if we will execute * the former). * * These barriers pair with inode_query_iversion(). */ cur = inode_peek_iversion_raw(inode); if (!force && !(cur & I_VERSION_QUERIED)) { smp_mb(); cur = inode_peek_iversion_raw(inode); } do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ u64 inode_query_iversion(struct inode *inode) { u64 cur, new; bool fenced = false; /* * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with * inode_maybe_inc_iversion(), see that routine for more details. */ cur = inode_peek_iversion_raw(inode); do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { if (!fenced) smp_mb(); break; } fenced = true; new = cur | I_VERSION_QUERIED; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } EXPORT_SYMBOL(inode_query_iversion); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos - buffered_written; loff_t end = iocb->ki_pos - 1; int err; /* * If the buffered write fallback returned an error, we want to return * the number of bytes which were written by direct I/O, or the error * code if that was zero. * * Note that this differs from normal direct-io semantics, which will * return -EFOO even if some bytes were written. */ if (unlikely(buffered_written < 0)) { if (direct_written) return direct_written; return buffered_written; } /* * We need to ensure that the page cache pages are written to disk and * invalidated to preserve the expected O_DIRECT semantics. */ err = filemap_write_and_wait_range(mapping, pos, end); if (err < 0) { /* * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; } invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); /** * simple_inode_init_ts - initialize the timestamps for a new inode * @inode: inode to be initialized * * When a new inode is created, most filesystems set the timestamps to the * current time. Add a helper to do this. */ struct timespec64 simple_inode_init_ts(struct inode *inode) { struct timespec64 ts = inode_set_ctime_current(inode); inode_set_atime_to_ts(inode, ts); inode_set_mtime_to_ts(inode, ts); return ts; } EXPORT_SYMBOL(simple_inode_init_ts); static inline struct dentry *get_stashed_dentry(struct dentry **stashed) { struct dentry *dentry; guard(rcu)(); dentry = rcu_dereference(*stashed); if (!dentry) return NULL; if (!lockref_get_not_dead(&dentry->d_lockref)) return NULL; return dentry; } static struct dentry *prepare_anon_dentry(struct dentry **stashed, struct super_block *sb, void *data) { struct dentry *dentry; struct inode *inode; const struct stashed_operations *sops = sb->s_fs_info; int ret; inode = new_inode_pseudo(sb); if (!inode) { sops->put_data(data); return ERR_PTR(-ENOMEM); } inode->i_flags |= S_IMMUTABLE; inode->i_mode = S_IFREG; simple_inode_init_ts(inode); ret = sops->init_inode(inode, data); if (ret < 0) { iput(inode); return ERR_PTR(ret); } /* Notice when this is changed. */ WARN_ON_ONCE(!S_ISREG(inode->i_mode)); WARN_ON_ONCE(!IS_IMMUTABLE(inode)); dentry = d_alloc_anon(sb); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); } /* Store address of location where dentry's supposed to be stashed. */ dentry->d_fsdata = stashed; /* @data is now owned by the fs */ d_instantiate(dentry, inode); return dentry; } static struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry) { guard(rcu)(); for (;;) { struct dentry *old; /* Assume any old dentry was cleared out. */ old = cmpxchg(stashed, NULL, dentry); if (likely(!old)) return dentry; /* Check if somebody else installed a reusable dentry. */ if (lockref_get_not_dead(&old->d_lockref)) return old; /* There's an old dead dentry there, try to take it over. */ if (likely(try_cmpxchg(stashed, &old, dentry))) return dentry; } } /** * path_from_stashed - create path from stashed or new dentry * @stashed: where to retrieve or stash dentry * @mnt: mnt of the filesystems to use * @data: data to store in inode->i_private * @path: path to create * * The function tries to retrieve a stashed dentry from @stashed. If the dentry * is still valid then it will be reused. If the dentry isn't able the function * will allocate a new dentry and inode. It will then check again whether it * can reuse an existing dentry in case one has been added in the meantime or * update @stashed with the newly added dentry. * * Special-purpose helper for nsfs and pidfs. * * Return: On success zero and on failure a negative error is returned. */ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path) { struct dentry *dentry; const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info; /* See if dentry can be reused. */ path->dentry = get_stashed_dentry(stashed); if (path->dentry) { sops->put_data(data); goto out_path; } /* Allocate a new dentry. */ dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data); if (IS_ERR(dentry)) return PTR_ERR(dentry); /* Added a new dentry. @data is now owned by the filesystem. */ path->dentry = stash_dentry(stashed, dentry); if (path->dentry != dentry) dput(dentry); out_path: WARN_ON_ONCE(path->dentry->d_fsdata != stashed); WARN_ON_ONCE(d_inode(path->dentry)->i_private != data); path->mnt = mntget(mnt); return 0; } void stashed_dentry_prune(struct dentry *dentry) { struct dentry **stashed = dentry->d_fsdata; struct inode *inode = d_inode(dentry); if (WARN_ON_ONCE(!stashed)) return; if (!inode) return; /* * Only replace our own @dentry as someone else might've * already cleared out @dentry and stashed their own * dentry in there. */ cmpxchg(stashed, dentry, NULL); } |
| 2 408 408 264 6 263 264 304 305 305 304 304 992 2 2 2 2 2 20 20 20 513 514 16 513 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_CLOCK_WAS_SET (1 << 1) #define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; /* * The most important data for readout fits into a single 64 byte * cache line. */ struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; struct timekeeper shadow_timekeeper; raw_spinlock_t lock; } ____cacheline_aligned; static struct tk_data tk_core; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; unsigned long timekeeper_lock_irqsave(void) { unsigned long flags; raw_spin_lock_irqsave(&tk_core.lock, flags); return flags; } void timekeeper_unlock_irqrestore(unsigned long flags) { raw_spin_unlock_irqrestore(&tk_core.lock, flags); } /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is * earlier than that value. * * mg_floor represents the latest fine-grained time that has been handed out as * a file timestamp on the system. This is tracked as a monotonic ktime_t, and * converted to a realtime clock value on an as-needed basis. * * Maintaining mg_floor ensures the multigrain interfaces never issue a * timestamp earlier than one that has been previously issued. * * The exception to this rule is when there is a backward realtime clock jump. If * such an event occurs, a timestamp can appear to be earlier than a previous one. */ static __cacheline_aligned_in_smp atomic64_t mg_floor; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ write_seqcount_latch_begin(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); write_seqcount_latch_end(&tkf->seq); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; int ret; guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { guard(raw_spinlock_irqsave)(&tk_core.lock); return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Leap state update for both shadow and the real timekeeper * Separate to spare a full memcpy() of the timekeeper. */ static void tk_update_leap_state_all(struct tk_data *tkd) { write_seqcount_begin(&tkd->seq); tk_update_leap_state(&tkd->shadow_timekeeper); tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; write_seqcount_end(&tkd->seq); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* * Restore the shadow timekeeper from the real timekeeper. */ static void timekeeping_restore_shadow(struct tk_data *tkd) { lockdep_assert_held(&tkd->lock); memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); } static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { struct timekeeper *tk = &tk_core.shadow_timekeeper; lockdep_assert_held(&tkd->lock); /* * Block out readers before running the updates below because that * updates VDSO and other time related infrastructure. Not blocking * the readers might let a reader see time going backwards when * reading from the VDSO after the VDSO update and then reading in * the kernel from the timekeeper before that got updated. */ write_seqcount_begin(&tkd->seq); if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * Update the real timekeeper. * * We could avoid this memcpy() by switching pointers, but that has * the downside that the reader side does not longer benefit from * the cacheline optimized data layout of the timekeeper and requires * another indirection. */ memcpy(&tkd->timekeeper, tk, sizeof(*tk)); write_seqcount_end(&tkd->seq); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; if (IS_ENABLED(CONFIG_64BIT)) { /* * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and * tk_update_sleep_time(). */ return ktime_add(tmono, READ_ONCE(*offset)); } do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_boot = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } static bool convert_clock(u64 *val, u32 numerator, u32 denominator) { u64 rem, res; if (!numerator || !denominator) return false; res = div64_u64_rem(*val, denominator, &rem) * numerator; *val = res + div_u64(rem * numerator, denominator); return true; } static bool convert_base_to_cs(struct system_counterval_t *scv) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; u32 num, den; /* The timestamp was taken from the time keeper clock source */ if (cs->id == scv->cs_id) return true; /* * Check whether cs_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != scv->cs_id) return false; num = scv->use_nsecs ? cs->freq_khz : base->numerator; den = scv->use_nsecs ? USEC_PER_SEC : base->denominator; if (!convert_clock(&scv->cycles, num, den)) return false; scv->cycles += base->offset; return true; } static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; /* * Check whether base_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != base_id) return false; *cycles -= base->offset; if (!convert_clock(cycles, base->denominator, base->numerator)) return false; return true; } static bool convert_ns_to_cs(u64 *delta) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta)) return false; *delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult); return true; } /** * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp * @treal: CLOCK_REALTIME timestamp to convert * @base_id: base clocksource id * @cycles: pointer to store the converted base clock timestamp * * Converts a supplied, future realtime clock value to the corresponding base clock value. * * Return: true if the conversion is successful, false otherwise. */ bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 delta; do { seq = read_seqcount_begin(&tk_core.seq); if ((u64)treal < tk->tkr_mono.base_real) return false; delta = (u64)treal - tk->tkr_mono.base_real; if (!convert_ns_to_cs(&delta)) return false; *cycles = tk->tkr_mono.cycle_last + delta; if (!convert_cs_to_base(cycles, base_id)) return false; } while (read_seqcount_retry(&tk_core.seq, seq)); return true; } EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || !convert_base_to_cs(&system_counterval)) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * timekeeping_clocksource_has_base - Check whether the current clocksource * is based on given a base clock * @id: base clocksource ID * * Note: The return value is a snapshot which can become invalid right * after the function returns. * * Return: true if the timekeeper clocksource has a base clock with @id, * false otherwise */ bool timekeeping_clocksource_has_base(enum clocksource_ids id) { /* * This is a snapshot, so no point in using the sequence * count. Just prevent the compiler from re-evaluating @base as the * clocksource might change concurrently. */ struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base); return base ? base->id == id : false; } EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timespec64 ts_delta, xt; if (!timespec64_valid_settod(ts)) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); xt = tk_xtime(tks); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); tk_set_xtime(tks, ts); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); return 0; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 tmp; timekeeping_forward_now(tks); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tks), *ts); if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_xtime_add(tks, ts); tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return 0; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct clocksource *new = data, *old = NULL; /* * If the clocksource is in a module, get a module reference. * Succeeds for built-in code (owner == NULL) as well. Abort if the * reference can't be acquired. */ if (!try_module_get(new->owner)) return 0; /* Abort if the device can't be enabled */ if (new->enable && new->enable(new) != 0) { module_put(new->owner); return 0; } scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); old = tks->tkr_mono.clock; tk_setup_internals(tks, new); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } static __init void tkd_basic_setup(struct tk_data *tkd) { raw_spin_lock_init(&tkd->lock); seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; tkd_basic_setup(&tk_core); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); guard(raw_spinlock_irqsave)(&tk_core.lock); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tks, clock); tk_set_xtime(tks, &wall_time); tks->raw_sec = 0; tk_set_wall_to_mono(tks, wall_to_mono); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; suspend_timing_needed = false; timekeeping_forward_now(tks); __timekeeping_inject_sleeptime(tks, delta); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; bool inject_sleeptime = false; u64 cycle_now, nsec; unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ tks->tkr_mono.cycle_last = cycle_now; tks->tkr_raw.cycle_last = cycle_now; tks->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&tk_core.lock, flags); timekeeping_forward_now(tks); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tks->tkr_mono.clock; cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update_from_shadow(&tk_core, 0); halt_fast_timekeeper(tks); raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u64 ntp_tl = ntp_tick_length(); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; u64 offset; guard(raw_spinlock_irqsave)(&tk_core.lock); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); /** * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor * @ts: timespec64 to be filled * * Fetch the global mg_floor value, convert it to realtime and compare it * to the current coarse-grained time. Fill @ts with whichever is * latest. Note that this is a filesystem-specific interface and should be * avoided outside of that context. */ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 floor = atomic64_read(&mg_floor); ktime_t f_real, offset, coarse; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); coarse = timespec64_to_ktime(*ts); f_real = ktime_add(floor, offset); if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real); } /** * ktime_get_real_ts64_mg - attempt to update floor value and return result * @ts: pointer to the timespec to be set * * Get a monotonic fine-grained time value and attempt to swap it into * mg_floor. If that succeeds then accept the new floor value. If it fails * then another task raced in during the interim time and updated the * floor. Since any update to the floor must be later than the previous * floor, either outcome is acceptable. * * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), * and determining that the resulting coarse-grained timestamp did not effect * a change in ctime. Any more recent floor value would effect a change to * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. * * @ts will be filled with the latest floor value, regardless of the outcome of * the cmpxchg. Note that this is a filesystem specific interface and should be * avoided outside of that context. */ void ktime_get_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t old = atomic64_read(&mg_floor); ktime_t offset, mono; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; mono = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); mono = ktime_add_ns(mono, nsecs); /* * Attempt to update the floor with the new time value. As any * update must be later then the existing floor, and would effect * a change to ctime from the perspective of the current task, * accept the resulting floor value regardless of the outcome of * the swap. */ if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. * "old" has been updated with the latest value of "mg_floor". * That value is newer than the previous floor value, which * is enough to effect a change to ctime. Accept it. */ *ts = ktime_to_timespec64(ktime_add(old, offset)); } } void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function * @txc: Pointer to kernel_timex structure containing NTP parameters */ int do_adjtimex(struct __kernel_timex *txc) { struct audit_ntp_data ad; bool offset_set = false; bool clock_set = false; struct timespec64 ts; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; offset_set = delta.tv_sec != 0; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; s32 orig_tai, tai; orig_tai = tai = tks->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tks, tai); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); clock_set = true; } else { tk_update_leap_state_all(&tk_core); } } audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(offset_set); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function * @phase_ts: Pointer to timespec64 structure representing phase timestamp * @raw_ts: Pointer to timespec64 structure representing raw timestamp */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. */ #ifndef IB_VERBS_H #define IB_VERBS_H #include <linux/ethtool.h> #include <linux/types.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/refcount.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/dim.h> #include <uapi/rdma/ib_user_verbs.h> #include <rdma/rdma_counter.h> #include <rdma/restrack.h> #include <rdma/signature.h> #include <uapi/rdma/rdma_user_ioctl.h> #include <uapi/rdma/ib_user_ioctl_verbs.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN struct ib_umem_odp; struct ib_uqp_object; struct ib_usrq_object; struct ib_uwq_object; struct rdma_cm_id; struct ib_port; struct hw_stats_device_data; extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_alert(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_crit(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_err(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_warn(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else __printf(2, 3) __cold static inline void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {} #endif #define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ ibdev_level(ibdev, fmt, ##__VA_ARGS__); \ } while (0) #define ibdev_emerg_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__) #define ibdev_alert_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__) #define ibdev_crit_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__) #define ibdev_err_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__) #define ibdev_warn_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__) #define ibdev_notice_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__) #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \ __dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \ ##__VA_ARGS__); \ } while (0) #else __printf(2, 3) __cold static inline void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {} #endif union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { struct net_device __rcu *ndev; struct ib_device *device; union ib_gid gid; enum ib_gid_type gid_type; u16 index; u32 port_num; }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP, RDMA_TRANSPORT_UNSPECIFIED, }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; else if (network_type == RDMA_NETWORK_ROCE_V1) return IB_GID_TYPE_ROCE; else return IB_GID_TYPE_IB; } static inline enum rdma_network_type rdma_gid_attr_network_type(const struct ib_gid_attr *attr) { if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (attr->gid_type == IB_GID_TYPE_ROCE) return RDMA_NETWORK_ROCE_V1; if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, /* Placement type attributes */ IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL, IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT, IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE, }; enum ib_kernel_cap_flags { /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IBK_LOCAL_DMA_LKEY = 1 << 0, /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ IBK_INTEGRITY_HANDOVER = 1 << 1, /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ IBK_ON_DEMAND_PAGING = 1 << 2, /* IB_MR_TYPE_SG_GAPS is supported */ IBK_SG_GAPS_REG = 1 << 3, /* Driver supports RDMA_NLDEV_CMD_DELLINK */ IBK_ALLOW_USER_UNREG = 1 << 4, /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ IBK_UD_TSO = 1 << 6, /* iopib will use the device ops: * get_vf_config * get_vf_guid * get_vf_stats * set_vf_guid * set_vf_link_state */ IBK_VIRTUAL_FUNCTION = 1 << 7, /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ IBK_RDMA_NETDEV_OPA = 1 << 8, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = 1 << 0, IB_ODP_SUPPORT_IMPLICIT = 1 << 1, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = 1 << 0, IB_ODP_SUPPORT_RECV = 1 << 1, IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, IB_ODP_SUPPORT_SRQ_RECV = 1 << 5, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; uint32_t xrc_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching with rendezvous offload for RC transport */ IB_TM_CAP_RNDV_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; enum ib_cq_attr_mask { IB_CQ_MODERATE = 1 << 0, }; struct ib_cq_caps { u16 max_cq_moderation_count; u16 max_cq_moderation_period; }; struct ib_dm_mr_attr { u64 length; u64 offset; u32 access_flags; }; struct ib_dm_alloc_attr { u64 length; u32 alignment; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; unsigned int max_pi_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; /* Max entries for sgl for optimized performance per READ */ u32 max_sgl_rd; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; enum opa_mtu { OPA_MTU_8192 = 6, OPA_MTU_10240 = 7 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) { switch (mtu) { case OPA_MTU_8192: return 8192; case OPA_MTU_10240: return 10240; default: return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); } } static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) { if (mtu >= 10240) return OPA_MTU_10240; else if (mtu >= 8192) return OPA_MTU_8192; else return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, IB_PORT_PHYS_STATE_DISABLED = 3, IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4, IB_PORT_PHYS_STATE_LINK_UP = 5, IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6, IB_PORT_PHYS_STATE_PHY_TEST = 7, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_2X = 16, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_2X: return 2; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64, IB_SPEED_NDR = 128, IB_SPEED_XDR = 256, }; enum ib_stat_flag { IB_STAT_FLAG_OPTIONAL = 1 << 0, }; /** * struct rdma_stat_desc * @name - The name of the counter * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL * @priv - Driver private information; Core code should not use */ struct rdma_stat_desc { const char *name; unsigned int flags; const void *priv; }; /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @descs - Array of pointers to static descriptors used for the counters * in directory. * @is_disabled - A bitmap to indicate each counter is currently disabled * or not. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { struct mutex lock; /* Protect lifespan and values[] */ unsigned long timestamp; unsigned long lifespan; const struct rdma_stat_desc *descs; unsigned long *is_disabled; int num_counters; u64 value[] __counted_by(num_counters); }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan); void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats); /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 #define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \ | RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP) #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u32 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { const struct ib_gid_attr *sgid_attr; union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18, IB_RATE_28_GBPS = 19, IB_RATE_50_GBPS = 20, IB_RATE_400_GBPS = 21, IB_RATE_600_GBPS = 22, IB_RATE_800_GBPS = 23, }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) * @IB_MR_TYPE_DM: memory region that is used for device * memory registration * @IB_MR_TYPE_USER: memory region that is used for the user-space * application * @IB_MR_TYPE_DMA: memory region that is used for DMA operations * without address translations (VA=PA) * @IB_MR_TYPE_INTEGRITY: memory region that is used for * data integrity operations */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SG_GAPS, IB_MR_TYPE_DM, IB_MR_TYPE_USER, IB_MR_TYPE_DMA, IB_MR_TYPE_INTEGRITY, }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); struct rdma_ah_init_attr { struct rdma_ah_attr *ah_attr; u32 flags; struct net_device *xmit_slave; }; enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u32 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND = IB_UVERBS_WC_SEND, IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, IB_WC_FLUSH = IB_UVERBS_WC_FLUSH, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u32 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of needed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC = IB_UVERBS_QPT_RC, IB_QPT_UC = IB_UVERBS_QPT_UC, IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, IB_QP_CREATE_NETDEV_USE = 1 << 7, IB_QP_CREATE_SCATTER_FCS = IB_UVERBS_QP_CREATE_SCATTER_FCS, IB_QP_CREATE_CVLAN_STRIPPING = IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, IB_QP_CREATE_PCI_WRITE_END_PADDING = IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u32 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u32 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u32 alt_port_num; u8 alt_timeout; u32 rate_limit; struct net_device *xmit_slave; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, IB_WR_FLUSH = IB_UVERBS_WR_FLUSH, IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_MR_INTEGRITY, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u32 port_num; /* valid for DR SMPs on switch only */ }; static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE, IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE, IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ, IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC, IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND, IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED, IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND, IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB, IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING, IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL, IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT, IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE, IB_ACCESS_SUPPORTED = ((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL, }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_umem; enum rdma_remove_reason { /* * Userspace requested uobject deletion or initial try * to remove uobject via cleanup. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, /* The driver failed to destroy the uobject and is being disconnected */ RDMA_REMOVE_DRIVER_FAILURE, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; struct xarray mmap_xa; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ /* ufile & ucontext owning this object */ struct ib_uverbs_file *ufile; /* FIXME, save memory: ufile->context == context */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_api_object *uapi_object; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; struct rdma_restrack_entry res; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct rw_semaphore tgt_qps_rwsem; struct xarray tgt_qps; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; const struct ib_gid_attr *sgid_attr; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { struct ib_device *device; struct ib_ucq_object *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; struct dim *dim; /* updated only by trace points */ ktime_t timestamp; u8 interrupt:1; u8 shared:1; unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_usrq_object *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; enum ib_raw_packet_caps { /* * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, /* * Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, /* * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uwq_object *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, IB_WQ_FLAGS_PCI_WRITE_END_PADDING = IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u32 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct completion srq_completion; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uqp_object *uobject; void (*event_handler)(struct ib_event *, void *); void (*registered_event_handler)(struct ib_event *, void *); void *qp_context; /* sgid_attrs associated with the AV's */ const struct ib_gid_attr *av_sgid_attr; const struct ib_gid_attr *alt_path_sgid_attr; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u32 port; bool integrity_en; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; /* The counter the qp is bind to */ struct rdma_counter *counter; }; struct ib_dm { struct ib_device *device; u32 length; u32 flags; struct ib_uobject *uobject; atomic_t usecnt; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; enum ib_mr_type type; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; struct ib_dm *dm; struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */ /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, IB_FLOW_SPEC_ESP = 0x34, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_GRE = 0x51, IB_FLOW_SPEC_MPLS = 0x60, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, IB_FLOW_SPEC_ACTION_COUNT = 0x1003, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; } __packed; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_esp_filter { __be32 spi; __be32 seq; }; struct ib_flow_spec_esp { u32 type; u16 size; struct ib_flow_esp_filter val; struct ib_flow_esp_filter mask; }; struct ib_flow_gre_filter { __be16 c_ks_res0_ver; __be16 protocol; __be32 key; }; struct ib_flow_spec_gre { u32 type; u16 size; struct ib_flow_gre_filter val; struct ib_flow_gre_filter mask; }; struct ib_flow_mpls_filter { __be32 tag; }; struct ib_flow_spec_mpls { u32 type; u16 size; struct ib_flow_mpls_filter val; struct ib_flow_mpls_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; struct ib_flow_spec_action_handle { enum ib_flow_spec_type type; u16 size; struct ib_flow_action *act; }; enum ib_counters_description { IB_COUNTER_PACKETS, IB_COUNTER_BYTES, }; struct ib_flow_spec_action_count { enum ib_flow_spec_type type; u16 size; struct ib_counters *counters; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_esp esp; struct ib_flow_spec_gre gre; struct ib_flow_spec_mpls mpls; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; struct ib_flow_spec_action_handle action; struct ib_flow_spec_action_count flow_count; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u32 port; union ib_flow_spec flows[]; }; struct ib_flow { struct ib_qp *qp; struct ib_device *device; struct ib_uobject *uobject; }; enum ib_flow_action_type { IB_FLOW_ACTION_UNSPECIFIED, IB_FLOW_ACTION_ESP = 1, }; struct ib_flow_action_attrs_esp_keymats { enum ib_uverbs_flow_action_esp_keymat protocol; union { struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm; } keymat; }; struct ib_flow_action_attrs_esp_replays { enum ib_uverbs_flow_action_esp_replay protocol; union { struct ib_uverbs_flow_action_esp_replay_bmp bmp; } replay; }; enum ib_flow_action_attrs_esp_flags { /* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags * This is done in order to share the same flags between user-space and * kernel and spare an unnecessary translation. */ /* Kernel flags */ IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32, IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33, }; struct ib_flow_spec_list { struct ib_flow_spec_list *next; union ib_flow_spec spec; }; struct ib_flow_action_attrs_esp { struct ib_flow_action_attrs_esp_keymats *keymat; struct ib_flow_action_attrs_esp_replays *replay; struct ib_flow_spec_list *encap; /* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled. * Value of 0 is a valid value. */ u32 esn; u32 spi; u32 seq; u32 tfc_pad; /* Use enum ib_flow_action_attrs_esp_flags */ u64 flags; u64 hard_limit_pkts; }; struct ib_flow_action { struct ib_device *device; struct ib_uobject *uobject; enum ib_flow_action_type type; atomic_t usecnt; }; struct ib_mad; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; enum ib_port_state last_port_state; }; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; struct ib_port_data { struct ib_device *ib_dev; struct ib_port_immutable immutable; spinlock_t pkey_list_lock; spinlock_t netdev_lock; struct list_head pkey_list; struct ib_port_cache cache; struct net_device __rcu *netdev; netdevice_tracker netdev_tracker; struct hlist_node ndev_hash_link; struct rdma_port_counter port_counter; struct ib_port *sysfs; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u32 port_num; int mtu; /* * cleanup function must be specified. * FIXME: This is only used for OPA_VNIC and that usage should be * removed too. */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); /* timeout */ void (*tx_timeout)(struct net_device *dev, unsigned int txqueue); }; struct rdma_netdev_alloc_params { size_t sizeof_priv; unsigned int txqs; unsigned int rxqs; void *param; int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num, struct net_device *netdev, void *param); }; struct ib_odp_counters { atomic64_t faults; atomic64_t faults_handled; atomic64_t invalidations; atomic64_t invalidations_handled; atomic64_t prefetch; }; struct ib_counters { struct ib_device *device; struct ib_uobject *uobject; /* num of objects attached */ atomic_t usecnt; }; struct ib_counters_read_attr { u64 *counters_buff; u32 ncounters; u32 flags; /* use enum ib_read_counters_flags */ }; struct uverbs_attr_bundle; struct iw_cm_id; struct iw_cm_conn_param; #define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \ .size_##ib_struct = \ (sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \ BUILD_BUG_ON_ZERO( \ !__same_type(((struct drv_struct *)NULL)->member, \ struct ib_struct))) #define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ gfp, false)) #define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ GFP_KERNEL, true)) #define rdma_zalloc_drv_obj(ib_dev, ib_type) \ rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL) #define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct struct rdma_user_mmap_entry { struct kref ref; struct ib_ucontext *ucontext; unsigned long start_pgoff; size_t npages; bool driver_removed; }; /* Return the offset (in bytes) the user should pass to libc's mmap() */ static inline u64 rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry) { return (u64)entry->start_pgoff << PAGE_SHIFT; } /** * struct ib_device_ops - InfiniBand device operations * This structure defines all the InfiniBand device operations, providers will * need to define the supported operations, otherwise they will be set to null. */ struct ib_device_ops { struct module *owner; enum rdma_driver_id driver_id; u32 uverbs_abi_ver; unsigned int uverbs_no_driver_id_binding:1; /* * NOTE: New drivers should not make use of device_group; instead new * device parameter should be exposed via netlink command. This * mechanism exists only for existing drivers. */ const struct attribute_group *device_group; const struct attribute_group **port_groups; int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*post_srq_recv)(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int (*process_mad)(struct ib_device *device, int process_mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); void (*get_dev_fw_str)(struct ib_device *device, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); int (*query_port)(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); int (*modify_port)(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *device, u32 port_num, struct ib_port_immutable *immutable); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u32 port_num); /** * When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device has finished * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u32 port_num); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, struct rdma_netdev_alloc_params *params); /** * query_gid should be return GID value for @device, when @port_num * link layer is either IB or iWarp. It is no-op if @port_num port * is RoCE link layer. */ int (*query_gid)(struct ib_device *device, u32 port_num, int index, union ib_gid *gid); /** * When calling add_gid, the HW vendor's driver should add the gid * of device of port at gid index available at @attr. Meta-info of * that gid (for example, the network device related to this gid) is * available at @attr. @context allows the HW vendor driver to store * extra information together with a GID entry. The HW vendor driver may * allocate memory to contain this information and store it in @context * when a new GID entry is written to. Params are consistent until the * next call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called when * roce_gid_table is used. */ int (*add_gid)(const struct ib_gid_attr *attr, void **context); /** * When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index gid_index of port port_num * available in @attr. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int (*alloc_ucontext)(struct ib_ucontext *context, struct ib_udata *udata); void (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); /** * This will be called once refcount of an entry in mmap_xa reaches * zero. The type of the memory that was mapped may differ between * entries and is opaque to the rdma_user_mmap interface. * Therefore needs to be implemented by the driver in mmap_free. */ void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata); int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct uverbs_attr_bundle *attrs); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, u64 length, u64 virt_addr, int fd, int mr_access_flags, struct uverbs_attr_bundle *attrs); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata); struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); int (*advise_mr)(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); /* * Kernel users should universally support relaxed ordering (RO), as * they are designed to read data only after observing the CQE and use * the DMA API correctly. * * Some drivers implicitly enable RO if platform supports it. */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); int (*destroy_flow_action)(struct ib_flow_action *action); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int (*get_vf_guid)(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid, int type); struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, struct ib_dm_alloc_attr *attr, struct uverbs_attr_bundle *attrs); int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs); struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, struct ib_dm_mr_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset); /** * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and * fill in the driver initialized data. The struct is kfree()'ed by * the sysfs core when the device is removed. A lifespan of -1 in the * return struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device); struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device, u32 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u32 port, int index); /** * modify_hw_stat - Modify the counter configuration * @enable: true/false when enable/disable a counter * Return codes - 0 on success or error code otherwise. */ int (*modify_hw_stat)(struct ib_device *device, u32 port, unsigned int counter_index, bool enable); /** * Allows rdma drivers to add their own restrack attributes. */ int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); /* Device lifecycle callbacks */ /* * Called after the device becomes registered, before clients are * attached */ int (*enable_driver)(struct ib_device *dev); /* * This is called as part of ib_dealloc_device(). */ void (*dealloc_driver)(struct ib_device *dev); /* iWarp CM callbacks */ void (*iw_add_ref)(struct ib_qp *qp); void (*iw_rem_ref)(struct ib_qp *qp); struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn); int (*iw_connect)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_accept)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog); int (*iw_destroy_listen)(struct iw_cm_id *cm_id); /** * counter_bind_qp - Bind a QP to a counter. * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ int (*counter_unbind_qp)(struct ib_qp *qp); /** * counter_dealloc -De-allocate the hw counter */ int (*counter_dealloc)(struct rdma_counter *counter); /** * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in * the driver initialized data. */ struct rdma_hw_stats *(*counter_alloc_stats)( struct rdma_counter *counter); /** * counter_update_stats - Query the stats value of this counter */ int (*counter_update_stats)(struct rdma_counter *counter); /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. */ int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); /* query driver for its ucontext properties */ int (*query_ucontext)(struct ib_ucontext *context, struct uverbs_attr_bundle *attrs); /* * Provide NUMA node. This API exists for rdmavt/hfi1 only. * Everyone else relies on Linux memory management model. */ int (*get_numa_node)(struct ib_device *dev); /** * add_sub_dev - Add a sub IB device */ struct ib_device *(*add_sub_dev)(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** * del_sub_dev - Delete a sub IB device */ void (*del_sub_dev)(struct ib_device *sub_dev); /** * ufile_cleanup - Attempt to cleanup ubojects HW resources inside * the ufile. */ void (*ufile_hw_cleanup)(struct ib_uverbs_file *ufile); /** * report_port_event - Drivers need to implement this if they have * some private stuff to handle when link status changes. */ void (*report_port_event)(struct ib_device *ibdev, struct net_device *ndev, unsigned long event); DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_qp); DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); }; struct ib_core_device { /* device must be the first element in structure until, * union of ib_core_device and device exists in ib_device. */ struct device dev; possible_net_t rdma_net; struct kobject *ports_kobj; struct list_head port_list; struct ib_device *owner; /* reach back to owner ib_device */ }; struct rdma_restrack_root; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; struct ib_device_ops ops; char name[IB_DEVICE_NAME_MAX]; struct rcu_head rcu_head; struct list_head event_handler_list; /* Protects event_handler_list */ struct rw_semaphore event_handler_rwsem; /* Protects QP's event_handler calls and open_qp list */ spinlock_t qp_open_list_lock; struct rw_semaphore client_data_rwsem; struct xarray client_data; struct mutex unregistration_lock; /* Synchronize GID, Pkey cache entries, subnet prefix, LMC */ rwlock_t cache_lock; /** * port_data is indexed by port number */ struct ib_port_data *port_data; int num_comp_vectors; union { struct device dev; struct ib_core_device coredev; }; /* First group is for device attributes, * Second group is for driver provided attributes (optional). * Third group is for the hw_stats * It is a NULL terminated array. */ const struct attribute_group *groups[4]; u64 uverbs_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; /* Indicates kernel verbs support, should not be used in drivers */ u16 kverbs_provider:1; /* CQ adaptive moderation (RDMA DIM) */ u16 use_cq_dim:1; u8 node_type; u32 phys_port_cnt; struct ib_device_attr attrs; struct hw_stats_device_data *hw_stats_data; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; spinlock_t cq_pools_lock; struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; struct rdma_restrack_root *res; const struct uapi_definition *driver_def; /* * Positive refcount indicates that the device is currently * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; struct work_struct unregistration_work; const struct rdma_link_ops *link_ops; /* Protects compat_devs xarray modifications */ struct mutex compat_devs_mutex; /* Maintains compat devices for each net namespace */ struct xarray compat_devs; /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; u32 lag_flags; /* A parent device has a list of sub-devices */ struct mutex subdev_lock; struct list_head subdev_list_head; /* A sub device has a type and a parent */ enum rdma_nl_dev_type type; struct ib_device *parent; struct list_head subdev_list; enum rdma_nl_name_assign_type name_assign_type; }; static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size, gfp_t gfp, bool is_numa_aware) { if (is_numa_aware && dev->ops.get_numa_node) return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev)); return kzalloc(size, gfp); } struct ib_client_nl_info; struct ib_client { const char *name; int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res); int (*get_global_nl_info)(struct ib_client_nl_info *res); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*get_net_dev_by_params)( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); refcount_t uses; struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ u8 no_kverbs_req:1; }; /* * IB block DMA iterator * * Iterates the DMA-mapped SGL in contiguous memory blocks aligned * to a HW supported page size. */ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ }; struct ib_device *_ib_alloc_device(size_t size); #define ib_alloc_device(drv_struct, member) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member))), \ struct drv_struct, member) void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); void ib_unregister_device_queued(struct ib_device *ib_dev); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz); bool __rdma_block_iter_next(struct ib_block_iter *biter); /** * rdma_block_iter_dma_address - get the aligned dma address of the current * block held by the block iterator. * @biter: block iterator holding the memory block */ static inline dma_addr_t rdma_block_iter_dma_address(struct ib_block_iter *biter) { return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); } /** * rdma_for_each_block - iterate over contiguous memory blocks of the sg list * @sglist: sglist to iterate over * @biter: block iterator holding the memory block * @nents: maximum number of sg entries to iterate over * @pgsz: best HW supported page size to use * * Callers may use rdma_block_iter_dma_address() to get each * blocks aligned DMA address. */ #define rdma_for_each_block(sglist, biter, nents, pgsz) \ for (__rdma_block_iter_start(biter, sglist, nents, \ pgsz); \ __rdma_block_iter_next(biter);) /** * ib_get_client_data - Get IB client context * @device:Device to get context for * @client:Client to get context for * * ib_get_client_data() returns the client context data set with * ib_set_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ static inline void *ib_get_client_data(struct ib_device *device, struct ib_client *client) { return xa_load(&device->client_data, client->client_id); } void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); void ib_set_device_ops(struct ib_device *device, const struct ib_device_ops *ops); int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma, unsigned long pfn, unsigned long size, pgprot_t prot, struct rdma_user_mmap_entry *entry); int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length); int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 min_pgoff, u32 max_pgoff); #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) void rdma_user_mmap_disassociate(struct ib_device *device); #else static inline void rdma_user_mmap_disassociate(struct ib_device *device) { } #endif static inline int rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 pgoff) { return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff, pgoff); } struct rdma_user_mmap_entry * rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext, unsigned long pgoff); struct rdma_user_mmap_entry * rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, struct vm_area_struct *vma); void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry); void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_buffer_cleared(const void __user *p, size_t len) { bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { return ib_is_buffer_cleared(udata->inbuf + offset, len); } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(const struct ib_event *event); int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u32 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_for_each_port - Iterate over all valid port numbers of the IB device * @device - The struct ib_device * to iterate over * @iter - The unsigned int to store the port number */ #define rdma_for_each_port(device, iter) \ for (iter = rdma_start_port(device + \ BUILD_BUG_ON_ZERO(!__same_type(u32, \ iter))); \ iter <= rdma_end_port(device); iter++) /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u32 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_is_grh_required(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_IB_GRH_REQUIRED; } static inline bool rdma_protocol_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u32 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u32 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u32 port_num) { return rdma_protocol_roce(device, port_num) && device->ops.add_gid && device->ops.del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device * @port_num: 1 based Port number * * Return true if port is an Intel OPA port , false if not */ static inline bool rdma_core_cap_opa_port(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; } /** * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. * @device: Device * @port_num: Port number * @mtu: enum value of MTU * * Return the MTU size supported by the port as an integer value. Will return * -1 if enum value of mtu is not supported. */ static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port, int mtu) { if (rdma_core_cap_opa_port(device, port)) return opa_mtu_enum_to_int((enum opa_mtu)mtu); else return ib_mtu_enum_to_int((enum ib_mtu)mtu); } /** * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. * @device: Device * @port_num: Port number * @attr: port attribute * * Return the MTU size supported by the port as an integer value. */ static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port, struct ib_port_attr *attr) { if (rdma_core_cap_opa_port(device, port)) return attr->phys_mtu; else return ib_mtu_enum_to_int(attr->max_mtu); } int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD * @pd: The protection domain * * NOTE: for user PD use ib_dealloc_pd_user with valid udata! */ static inline void ib_dealloc_pd(struct ib_pd *pd) { int ret = ib_dealloc_pd_user(pd, NULL); WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { /* In a sleepable context */ RDMA_CREATE_AH_SLEEPABLE = BIT(0), }; /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags); /** * rdma_create_user_ah - Creates an address handle for the given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. * When ib_init_ah_attr_from_wc() returns success, * (a) for IB link layer it optionally contains a reference to SGID attribute * when GRH is present for IB link layer. * (b) for RoCE link layer it contains a reference to SGID attribute. * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID * attributes which are initialized using ib_init_ah_attr_from_wc(). * */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); enum rdma_destroy_ah_flags { /* In a sleepable context */ RDMA_DESTROY_AH_SLEEPABLE = BIT(0), }; /** * rdma_destroy_ah_user - Destroys an address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * @udata: Valid user data or NULL for kernel objects */ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); /** * rdma_destroy_ah - Destroys an kernel address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { int ret = rdma_destroy_ah_user(ah, flags, NULL); WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata); static inline struct ib_srq * ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) { if (!pd->device->ops.create_srq) return ERR_PTR(-EOPNOTSUPP); return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); } /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq_user - Destroys the specified SRQ. * @srq: The SRQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); /** * ib_destroy_srq - Destroys the specified kernel SRQ. * @srq: The SRQ to destroy. * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ static inline void ib_destroy_srq(struct ib_srq *srq) { int ret = ib_destroy_srq_user(srq, NULL); WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return srq->device->ops.post_srq_recv(srq, recv_wr, bad_recv_wr ? : &dummy); } struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller); /** * ib_create_qp - Creates a kernel QP associated with the specific protection * domain. * @pd: The protection domain associated with the QP. * @init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ static inline struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr) { return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME); } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. * @udata: Valid udata or NULL for kernel objects */ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata); /** * ib_destroy_qp - Destroys the specified kernel QP. * @qp: The QP to destroy. * * NOTE: for user qp use ib_destroy_qp_user with valid udata! */ static inline int ib_destroy_qp(struct ib_qp *qp) { return ib_destroy_qp_user(qp, NULL); } /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr) { const struct ib_send_wr *dummy; return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller); /** * ib_alloc_cq_any: Allocate kernel CQ * @dev: The IB device * @private: Private data attached to the CQE * @nr_cqe: Number of CQEs in the CQ * @poll_ctx: Context used for polling the CQ */ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx) { return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx, KBUILD_MODNAME); } void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller); #define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * rdma_set_cq_moderation - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq_user - Destroys the specified CQ. * @cq: The CQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); /** * ib_destroy_cq - Destroys the specified kernel CQ. * @cq: The CQ to destroy. * * NOTE: for user cq use ib_destroy_cq_user with valid udata! */ static inline void ib_destroy_cq(struct ib_cq *cq) { int ret = ib_destroy_cq_user(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->ops.poll_cq(cq, num_entries, wc); } /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->ops.req_notify_cq(cq, flags); } struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx); void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); /* * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to * NULL. This causes the ib_dma* helpers to just stash the kernel virtual * address into the dma address. */ static inline bool ib_uses_virt_dma(struct ib_device *dev) { return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; } /* * Check if a IB device's underlying DMA mapping supports P2PDMA transfers. */ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return false; return dma_pci_p2pdma_supported(dev->dma_device); } /** * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after * going through the dma_addr marshalling. */ static inline void *ib_virt_dma_to_ptr(u64 dma_addr) { /* virt_dma mode maps the kvs's directly into the dma addr */ return (void *)(uintptr_t)dma_addr; } /** * ib_virt_dma_to_page - Convert a dma_addr to a struct page * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() device to get back to the struct page after going * through the dma_addr marshalling. */ static inline struct page *ib_virt_dma_to_page(u64 dma_addr) { return virt_to_page(ib_virt_dma_to_ptr(dma_addr)); } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (ib_uses_virt_dma(dev)) return 0; return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_page(dev->dma_device, addr, size, direction); } int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (ib_uses_virt_dma(dev)) return ib_dma_virt_map_sg(dev, sg, nents); return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The sg_table object describing the buffer * @direction: The direction of the DMA * @attrs: Optional DMA attributes for the map operation */ static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { int nents; if (ib_uses_virt_dma(dev)) { nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); if (!nents) return -EIO; sgt->nents = nents; return 0; } return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); } static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer * @dev: The device to query * * The returned value represents a size in bytes. */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /* ib_reg_user_mr - register a memory region for virtual addresses from kernel * space. This function should be called when 'current' is the owning MM. */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags); /* ib_advise_mr - give an advice about an address range in a memory region */ int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge); /** * ib_dereg_mr_user - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * @udata: Valid user data or NULL for kernel object * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata); /** * ib_dereg_mr - Deregisters a kernel memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. * * NOTE: for user mr use ib_dereg_mr_user with valid udata! */ static inline int ib_dereg_mr(struct ib_mr *mr) { return ib_dereg_mr_user(mr, NULL); } struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata); int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata); static inline int ib_check_mr_access(struct ib_device *ib_dev, unsigned int flags) { u64 device_cap = ib_dev->attrs.device_cap_flags; /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; if (flags & ~IB_ACCESS_SUPPORTED) return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EOPNOTSUPP; if ((flags & IB_ACCESS_FLUSH_GLOBAL && !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) || (flags & IB_ACCESS_FLUSH_PERSISTENT && !(device_cap & IB_DEVICE_FLUSH_PERSISTENT))) return -EOPNOTSUPP; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); /** * ib_device_try_get: Hold a registration lock * device: The device to lock * * A device under an active registration lock cannot become unregistered. It * is only possible to obtain a registration lock on a device that is fully * registered, otherwise this function returns false. * * The registration lock is only necessary for actions which require the * device to still be registered. Uses that only require the device pointer to * be valid should use get_device(&ibdev->dev) to hold the memory. * */ static inline bool ib_device_try_get(struct ib_device *dev) { return refcount_inc_not_zero(&dev->refcount); } void ib_device_put(struct ib_device *device); struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id); struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, u32 *port); static inline enum ib_port_state ib_get_curr_port_state(struct net_device *net_dev) { return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; } void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num) { attr->port_num = port_num; } static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; grh->sgid_attr = NULL; } void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr); void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr); void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src); void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new); void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src); /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } if (dev->type == RDMA_DEVICE_TYPE_SMI) return RDMA_AH_ATTR_TYPE_IB; return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->ops.get_vector_affinity) return NULL; return device->ops.get_vector_affinity(device, comp_vector); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @device: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ibdev); void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port); void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev); /** * rdma_device_to_ibdev - Get ib_device pointer from device pointer * * @device: device pointer for which ib_device pointer to retrieve * * rdma_device_to_ibdev() retrieves ib_device pointer from device. * */ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) { struct ib_core_device *coredev = container_of(device, struct ib_core_device, dev); return coredev->owner; } /** * ibdev_to_node - return the NUMA node for a given ib_device * @dev: device to get the NUMA node for. */ static inline int ibdev_to_node(struct ib_device *ibdev) { struct device *parent = ibdev->dev.parent; if (!parent) return NUMA_NO_NODE; return dev_to_node(parent); } /** * rdma_device_to_drv_device - Helper macro to reach back to driver's * ib_device holder structure from device pointer. * * NOTE: New drivers should not make use of this API; This API is only for * existing drivers who have exposed sysfs entries using * ops->device_group. */ #define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) #define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based * on the flow_label * * This function will convert the 20 bit flow_label input to a valid RoCE v2 * UDP src port 14 bit value. All RoCE V2 drivers should use this same * convention. */ static inline u16 rdma_flow_label_to_udp_sport(u32 fl) { u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; fl_low ^= fl_high >> 14; return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); } /** * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on * local and remote qpn values * * This function folded the multiplication results of two qpns, 24 bit each, * fields, and converts it to a 20 bit results. * * This function will create symmetric flow_label value based on the local * and remote qpn values. this will allow both the requester and responder * to calculate the same flow_label for a given connection. * * This helper function should be used by driver in case the upper layer * provide a zero flow_label value. This is to improve entropy of RDMA * traffic in the network. */ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) { u64 v = (u64)lqpn * rqpn; v ^= v >> 20; v ^= v >> 40; return (u32)(v & IB_GRH_FLOWLABEL_MASK); } /** * rdma_get_udp_sport - Calculate and set UDP source port based on the flow * label. If flow label is not defined in GRH then * calculate it based on lqpn/rqpn. * * @fl: flow label from GRH * @lqpn: local qp number * @rqpn: remote qp number */ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn) { if (!fl) fl = rdma_calc_flow_label(lqpn, rqpn); return rdma_flow_label_to_udp_sport(fl); } const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port); /** ib_add_sub_device - Add a sub IB device on an existing one * * @parent: The IB device that needs to add a sub device * @type: The type of the new sub device * @name: The name of the new sub device * * * Return 0 on success, an error code otherwise */ int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get' * * @sub: The sub device that is going to be deleted * * Return 0 on success, an error code otherwise */ int ib_del_sub_device_and_put(struct ib_device *sub); static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev) { ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER; } #endif /* IB_VERBS_H */ |
| 355 356 344 | 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_MAPLE_TREE_H #define _LINUX_MAPLE_TREE_H /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> * Matthew Wilcox <willy@infradead.org> */ #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> /* #define CONFIG_MAPLE_RCU_DISABLED */ /* * Allocated nodes are mutable until they have been inserted into the tree, * at which time they cannot change their type until they have been removed * from the tree and an RCU grace period has passed. * * Removed nodes have their ->parent set to point to themselves. RCU readers * check ->parent before relying on the value that they loaded from the * slots array. This lets us reuse the slots array for the RCU head. * * Nodes in the tree point to their parent unless bit 0 is set. */ #if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) /* 64bit sizes */ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ #define MAPLE_NODE_MASK 255UL /* * The node->parent of the root node has bit 0 set and the rest of the pointer * is a pointer to the tree itself. No more bits are available in this pointer * (on m68k, the data structure may only be 2-byte aligned). * * Internal non-root nodes can only have maple_range_* nodes as parents. The * parent pointer is 256B aligned like all other tree nodes. When storing a 32 * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an * extra bit to store the offset. This extra bit comes from a reuse of the last * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * * Once the type is decided, the decision of an allocation range type or a * range type is done by examining the immutable tree flag for the * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and location in the parent pointer: * type : slot location * 0x??1 : Root * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 * 0x010 : 32 bit values, type in 0-2, slot in 3-6 * 0x110 : 64 bit values, type in 0-2, slot in 3-6 */ /* * This metadata is used to optimize the gap updating code and in reverse * searching for gaps or any other code that needs to find the end of the data. */ struct maple_metadata { unsigned char end; unsigned char gap; }; /* * Leaf nodes do not store pointers to nodes, they store user data. Users may * store almost any bit pattern. As noted above, the optimisation of storing an * entry at 0 in the root pointer cannot be done for data which have the bottom * two bits set to '10'. We also reserve values with the bottom two bits set to * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs * return errnos as a negative errno shifted right by two bits and the bottom * two bits set to '10', and while choosing to store these values in the array * is not an error, it may lead to confusion if you're testing for an error with * mas_is_err(). * * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges, Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. */ struct maple_range_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; union { void __rcu *slot[MAPLE_RANGE64_SLOTS]; struct { void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; struct maple_metadata meta; }; }; }; /* * At tree creation time, the user can specify that they're willing to trade off * storing fewer entries in a tree in return for storing more information in * each node. * * The maple tree supports recording the largest range of NULL entries available * in this node, also called gaps. This optimises the tree for allocating a * range. */ struct maple_arange_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; void __rcu *slot[MAPLE_ARANGE64_SLOTS]; unsigned long gap[MAPLE_ARANGE64_SLOTS]; struct maple_metadata meta; }; struct maple_alloc { unsigned long total; unsigned char node_count; unsigned int request_count; struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; }; struct maple_topiary { struct maple_pnode *parent; struct maple_enode *next; /* Overlaps the pivot */ }; enum maple_type { maple_dense, maple_leaf_64, maple_range_64, maple_arange_64, }; enum store_type { wr_invalid, wr_new_root, wr_store_root, wr_exact_fit, wr_spanning_store, wr_split_store, wr_rebalance, wr_append, wr_node_store, wr_slot_store, }; /** * DOC: Maple tree flags * * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree * * MT_FLAGS_USE_RCU - Operate in RCU mode * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value * * MT_FLAGS_LOCK_MASK - How the mt_lock is used * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe * * MT_FLAGS_LOCK_BH - Acquired bh-safe * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used * * MAPLE_HEIGHT_MAX The largest height that can be stored */ #define MT_FLAGS_ALLOC_RANGE 0x01 #define MT_FLAGS_USE_RCU 0x02 #define MT_FLAGS_HEIGHT_OFFSET 0x02 #define MT_FLAGS_HEIGHT_MASK 0x7C #define MT_FLAGS_LOCK_MASK 0x300 #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 #define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 #define MAPLE_NODE_TYPE_MASK 0x0F #define MAPLE_NODE_TYPE_SHIFT 0x03 #define MAPLE_RESERVED_RANGE 4096 #ifdef CONFIG_LOCKDEP typedef struct lockdep_map *lockdep_map_p; #define mt_lock_is_held(mt) \ (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) #define mt_write_lock_is_held(mt) \ (!(mt)->ma_external_lock || \ lock_is_held_type((mt)->ma_external_lock, 0)) #define mt_set_external_lock(mt, lock) \ (mt)->ma_external_lock = &(lock)->dep_map #define mt_on_stack(mt) (mt).ma_external_lock = NULL #else typedef struct { /* nothing */ } lockdep_map_p; #define mt_lock_is_held(mt) 1 #define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) #define mt_on_stack(mt) do { } while (0) #endif /* * If the tree contains a single entry at index 0, it is usually stored in * tree->ma_root. To optimise for the page cache, an entry which ends in '00', * '01' or '11' is stored in the root, but an entry which ends in '10' will be * stored in a node. Bits 3-6 are used to store enum maple_type. * * The flags are used both to store some immutable information about this tree * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ struct maple_tree { union { spinlock_t ma_lock; lockdep_map_p ma_external_lock; }; unsigned int ma_flags; void __rcu *ma_root; }; /** * MTREE_INIT() - Initialize a maple tree * @name: The maple tree name * @__flags: The maple tree flags * */ #define MTREE_INIT(name, __flags) { \ .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ .ma_flags = __flags, \ .ma_root = NULL, \ } /** * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. * @name: The tree name * @__flags: The maple tree flags * @__lock: The external lock */ #ifdef CONFIG_LOCKDEP #define MTREE_INIT_EXT(name, __flags, __lock) { \ .ma_external_lock = &(__lock).dep_map, \ .ma_flags = (__flags), \ .ma_root = NULL, \ } #else #define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) #endif #define DEFINE_MTREE(name) \ struct maple_tree name = MTREE_INIT(name, 0) #define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) #define mtree_lock_nested(mas, subclass) \ spin_lock_nested((&(mt)->ma_lock), subclass) #define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) /* * The Maple Tree squeezes various bits in at various points which aren't * necessarily obvious. Usually, this is done by observing that pointers are * N-byte aligned and thus the bottom log_2(N) bits are available for use. We * don't use the high bits of pointers to store additional information because * we don't know what bits are unused on any given architecture. * * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 * low bits for our own purposes. Nodes are currently of 4 types: * 1. Single pointer (Range is 0-0) * 2. Non-leaf Allocation Range nodes * 3. Non-leaf Range nodes * 4. Leaf Range nodes All nodes consist of a number of node slots, * pivots, and a parent pointer. */ struct maple_node { union { struct { struct maple_pnode *parent; void __rcu *slot[MAPLE_NODE_SLOTS]; }; struct { void *pad; struct rcu_head rcu; struct maple_enode *piv_parent; unsigned char parent_slot; enum maple_type type; unsigned char slot_len; unsigned int ma_flags; }; struct maple_range_64 mr64; struct maple_arange_64 ma64; struct maple_alloc alloc; }; }; /* * More complicated stores can cause two nodes to become one or three and * potentially alter the height of the tree. Either half of the tree may need * to be rebalanced against the other. The ma_topiary struct is used to track * which nodes have been 'cut' from the tree so that the change can be done * safely at a later date. This is done to support RCU. */ struct ma_topiary { struct maple_enode *head; struct maple_enode *tail; struct maple_tree *mtree; }; void *mtree_load(struct maple_tree *mt, unsigned long index); int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_store_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); void *mtree_erase(struct maple_tree *mt, unsigned long index); int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); void mtree_destroy(struct maple_tree *mt); void __mt_destroy(struct maple_tree *mt); /** * mtree_empty() - Determine if a tree has any present entries. * @mt: Maple Tree. * * Context: Any context. * Return: %true if the tree contains only NULL pointers. */ static inline bool mtree_empty(const struct maple_tree *mt) { return mt->ma_root == NULL; } /* Advanced API */ /* * Maple State Status * ma_active means the maple state is pointing to a node and offset and can * continue operating on the tree. * ma_start means we have not searched the tree. * ma_root means we have searched the tree and the entry we found lives in * the root of the tree (ie it has index 0, length 1 and is the only entry in * the tree). * ma_none means we have searched the tree and there is no node in the * tree for this entry. For example, we searched for index 1 in an empty * tree. Or we have a tree which points to a full leaf node and we * searched for an entry which is larger than can be contained in that * leaf node. * ma_pause means the data within the maple state may be stale, restart the * operation * ma_overflow means the search has reached the upper limit of the search * ma_underflow means the search has reached the lower limit of the search * ma_error means there was an error, check the node for the error number. */ enum maple_status { ma_active, ma_start, ma_root, ma_none, ma_pause, ma_overflow, ma_underflow, ma_error, }; /* * The maple state is defined in the struct ma_state and is used to keep track * of information during operations, and even between operations when using the * advanced API. * * If state->node has bit 0 set then it references a tree location which is not * a node (eg the root). If bit 1 is set, the rest of the bits are a negative * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the * node type. * * state->alloc either has a request number of nodes or an allocated node. If * stat->alloc has a requested number of nodes, the first bit will be set (0x1) * and the remaining bits are the value. If state->alloc is a node, then the * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for * storing more allocated nodes, a total number of nodes allocated, and the * node_count in this node. node_count is the number of allocated nodes in this * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc * by removing a node from the state->alloc node until state->alloc->node_count * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted * to state->alloc. Nodes are pushed onto state->alloc by putting the current * state->alloc into the pushed node's slot[0]. * * The state also contains the implied min/max of the state->node, the depth of * this search, and the offset. The implied min/max are either from the parent * node or are 0-oo for the root node. The depth is incremented or decremented * every time a node is walked down or up. The offset is the slot/pivot of * interest in the node - either for reading or writing. * * When returning a value the maple state index and last respectively contain * the start and end of the range for the entry. Ranges are inclusive in the * Maple Tree. * * The status of the state is used to determine how the next action should treat * the state. For instance, if the status is ma_start then the next action * should start at the root of the tree and walk down. If the status is * ma_pause then the node may be stale data and should be discarded. If the * status is ma_overflow, then the last action hit the upper limit. * */ struct ma_state { struct maple_tree *tree; /* The tree we're operating in */ unsigned long index; /* The index we're operating on - range start */ unsigned long last; /* The last index we're operating on - range end */ struct maple_enode *node; /* The node containing this entry */ unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ struct maple_alloc *alloc; /* Allocated nodes for this operation */ enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { struct ma_state *mas; struct maple_node *node; /* Decoded mas->node */ unsigned long r_min; /* range min */ unsigned long r_max; /* range max */ enum maple_type type; /* mas->node type */ unsigned char offset_end; /* The offset where the write ends */ unsigned long *pivots; /* mas->node->pivots pointer */ unsigned long end_piv; /* The pivot at the offset end */ void __rcu **slots; /* mas->node->slots pointer */ void *entry; /* The entry to write */ void *content; /* The existing entry that is being overwritten */ }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) #define mas_lock_nested(mas, subclass) \ spin_lock_nested(&((mas)->tree->ma_lock), subclass) #define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) /* * Special values for ma_state.node. * MA_ERROR represents an errno. After dropping the lock and attempting * to resolve the error, the walk would have to be restarted from the * top of the tree as the tree may have been modified. */ #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) #define MA_STATE(name, mt, first, end) \ struct ma_state name = { \ .tree = mt, \ .index = first, \ .last = end, \ .node = NULL, \ .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ .alloc = NULL, \ .mas_flags = 0, \ .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ struct ma_wr_state name = { \ .mas = ma_state, \ .content = NULL, \ .entry = wr_entry, \ } #define MA_TOPIARY(name, tree) \ struct ma_topiary name = { \ .head = NULL, \ .tail = NULL, \ .mtree = tree, \ } void *mas_walk(struct ma_state *mas); void *mas_store(struct ma_state *mas, void *entry); void *mas_erase(struct ma_state *mas); int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); void maple_tree_init(void); void mas_destroy(struct ma_state *mas); int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); void *mas_prev(struct ma_state *mas, unsigned long min); void *mas_prev_range(struct ma_state *mas, unsigned long max); void *mas_next(struct ma_state *mas, unsigned long max); void *mas_next_range(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); /* * This finds an empty area from the highest address to the lowest. * AKA "Topdown" version, */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, unsigned long addr) { memset(mas, 0, sizeof(struct ma_state)); mas->tree = tree; mas->index = mas->last = addr; mas->max = ULONG_MAX; mas->status = ma_start; mas->node = NULL; } static inline bool mas_is_active(struct ma_state *mas) { return mas->status == ma_active; } static inline bool mas_is_err(struct ma_state *mas) { return mas->status == ma_error; } /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. * * Resets the error or walk state of the @mas so future walks of the * array will start from the root. Use this if you have dropped the * lock and want to reuse the ma_state. * * Context: Any context. */ static __always_inline void mas_reset(struct ma_state *mas) { mas->status = ma_start; mas->node = NULL; } /** * mas_for_each() - Iterate over a range of the maple tree. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__max: maximum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) /** * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__min: minimum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each_rev(__mas, __entry, __min) \ while (((__entry) = mas_find_rev((__mas), (__min))) != NULL) #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, mt_dump_hex, }; extern atomic_t maple_tree_tests_run; extern atomic_t maple_tree_tests_passed; void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); void mas_dump(const struct ma_state *mas); void mas_wr_dump(const struct ma_wr_state *wr_mas); void mt_validate(struct maple_tree *mt); void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_BUG_ON(__mas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_WR_BUG_ON(__wrmas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MT_WARN_ON(__tree, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WARN_ON(__mas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WR_WARN_ON(__wrmas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #else #define MT_BUG_ON(__tree, __x) BUG_ON(__x) #define MAS_BUG_ON(__mas, __x) BUG_ON(__x) #define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) #define MT_WARN_ON(__tree, __x) WARN_ON(__x) #define MAS_WARN_ON(__mas, __x) WARN_ON(__x) #define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) #endif /* CONFIG_DEBUG_MAPLE_TREE */ /** * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the * current location. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * set the internal maple state values to a sub-range. * Please use mas_set_range() if you do not know where you are in the tree. */ static inline void __mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { /* Ensure the range starts within the current slot */ MAS_WARN_ON(mas, mas_is_active(mas) && (mas->index > start || mas->last < start)); mas->index = start; mas->last = last; } /** * mas_set_range() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * Move the operation state to refer to a different range. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { mas_reset(mas); __mas_set_range(mas, start, last); } /** * mas_set() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @index: New index into the Maple Tree. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set(struct ma_state *mas, unsigned long index) { mas_set_range(mas, index, index); } static inline bool mt_external_lock(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; } /** * mt_init_flags() - Initialise an empty maple tree with flags. * @mt: Maple Tree * @flags: maple tree flags. * * If you need to initialise a Maple Tree with special flags (eg, an * allocation tree), use this function. * * Context: Any context. */ static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) { mt->ma_flags = flags; if (!mt_external_lock(mt)) spin_lock_init(&mt->ma_lock); rcu_assign_pointer(mt->ma_root, NULL); } /** * mt_init() - Initialise an empty maple tree. * @mt: Maple Tree * * An empty Maple Tree. * * Context: Any context. */ static inline void mt_init(struct maple_tree *mt) { mt_init_flags(mt, 0); } static inline bool mt_in_rcu(struct maple_tree *mt) { #ifdef CONFIG_MAPLE_RCU_DISABLED return false; #endif return mt->ma_flags & MT_FLAGS_USE_RCU; } /** * mt_clear_in_rcu() - Switch the tree to non-RCU mode. * @mt: The Maple Tree */ static inline void mt_clear_in_rcu(struct maple_tree *mt) { if (!mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags &= ~MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags &= ~MT_FLAGS_USE_RCU; mtree_unlock(mt); } } /** * mt_set_in_rcu() - Switch the tree to RCU safe mode. * @mt: The Maple Tree */ static inline void mt_set_in_rcu(struct maple_tree *mt) { if (mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags |= MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags |= MT_FLAGS_USE_RCU; mtree_unlock(mt); } } static inline unsigned int mt_height(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; } void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); /** * mt_for_each - Iterate over each entry starting at index until max. * @__tree: The Maple Tree * @__entry: The current entry * @__index: The index to start the search from. Subsequently used as iterator. * @__max: The maximum limit for @index * * This iterator skips all entries, which resolve to a NULL pointer, * e.g. entries which has been reserved with XA_ZERO_ENTRY. */ #define mt_for_each(__tree, __entry, __index, __max) \ for (__entry = mt_find(__tree, &(__index), __max); \ __entry; __entry = mt_find_after(__tree, &(__index), __max)) #endif /*_LINUX_MAPLE_TREE_H */ |
| 48 9 9 9 9 9 1 331 332 332 161 216 113 112 113 120 101 21 102 66 66 222 221 139 139 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <kunit/visibility.h> #include "internal.h" #include "swap.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated. * @s: The data to copy * @len: The size of the data, not including the NUL terminator * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; /* '+1' for the NUL terminator */ buf = kmalloc_track_caller(len + 1, gfp); if (!buf) return NULL; memcpy(buf, s, len); /* Ensure the buf is always NUL-terminated, regardless of @s. */ buf[len] = '\0'; return buf; } /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ noinline char *kstrdup(const char *s, gfp_t gfp) { return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup_noprof); /** * kmemdup_array - duplicate a given array. * * @src: array to duplicate. * @count: number of elements to duplicate from array. * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } EXPORT_SYMBOL(kmemdup_array); /** * kvmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result may be not physically contiguous. Use kvfree() to free. */ void *kvmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kvmalloc(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kvmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { return s ? __kmemdup_nul(s, len, gfp) : NULL; } EXPORT_SYMBOL(kmemdup_nul); static kmem_buckets *user_buckets __ro_after_init; static int __init init_user_buckets(void) { user_buckets = kmem_buckets_create("memdup_user", 0, 0, INT_MAX, NULL); return 0; } subsys_initcall(init_user_buckets); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_alloc_track_caller(user_buckets, len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_valloc(user_buckets, len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } /* * Change backing file, only valid to use during initial VMA setup. */ void vma_set_file(struct vm_area_struct *vma, struct file *file) { /* Changing an anonymous vma with this is illegal */ get_file(file); swap(vma->vm_file, file); fput(file); } EXPORT_SYMBOL(vma_set_file); #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long __weak arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; /* On parisc the stack always grows up - so a unlimited stack should * not be an indicator to use the legacy memory layout. */ if (rlim_stack->rlim_cur == RLIM_INFINITY && !IS_ENABLED(CONFIG_STACK_GROWSUP)) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { #ifdef CONFIG_STACK_GROWSUP /* * For an upwards growing stack the calculation is much simpler. * Memory for the maximum stack size is reserved at the top of the * task. mmap_base starts directly below the stack and grows * downwards. */ return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); #else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); #endif } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); set_bit(MMF_TOPDOWN, &mm->flags); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; clear_bit(MMF_TOPDOWN, &mm->flags); } #endif #ifdef CONFIG_MMU EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } /* * Perform a userland memory mapping into the current process address space. See * the comment for do_mmap() for more details on this operation in general. * * This differs from do_mmap() in that: * * a. An offset parameter is provided rather than pgoff, which is both checked * for overflow and page alignment. * b. mmap locking is performed on the caller's behalf. * c. Userfaultfd unmap events and memory population are handled. * * This means that this function performs essentially the same work as if * userland were invoking mmap (2). * * Returns either an error, or the address at which the requested mapping has * been performed. */ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size) { /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. * However make sure that larger requests are not too disruptive - no * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { flags |= __GFP_NOWARN; if (!(flags & __GFP_RETRY_MAYFAIL)) flags |= __GFP_NORETRY; /* nofail semantic is implemented by the vmalloc fallback */ flags &= ~__GFP_NOFAIL; } return flags; } /** * __kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. * @size: size of the request. * @b: which set of kmalloc buckets to allocate from. * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. * @node: numa node to allocate from * * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Return: pointer to the allocated memory of %NULL in case of failure */ void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) { void *ret; /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ ret = __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, b), kmalloc_gfp_adjust(flags, size), node); if (ret || size <= PAGE_SIZE) return ret; /* non-sleeping allocations are not supported by vmalloc */ if (!gfpflags_allow_blocking(flags)) return NULL; /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } /* * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, * since the callers already cannot assume anything * about the resulting pointer, and cannot play * protection games. */ return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, node, __builtin_return_address(0)); } EXPORT_SYMBOL(__kvmalloc_node_noprof); /** * kvfree() - Free memory. * @addr: Pointer to allocated memory. * * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); /** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. * * Use the special memzero_explicit() function to clear the content of a * kvmalloc'ed object containing sensitive data to make sure that the * compiler won't optimize out the data clearing. */ void kvfree_sensitive(const void *addr, size_t len) { if (likely(!ZERO_OR_NULL_PTR(addr))) { memzero_explicit((void *)addr, len); kvfree(addr); } } EXPORT_SYMBOL(kvfree_sensitive); /** * kvrealloc - reallocate memory; contents remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @flags: the flags for the page level allocator * * If @p is %NULL, kvrealloc() behaves exactly like kvmalloc(). If @size is 0 * and @p is not a %NULL pointer, the object pointed to is freed. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or kvfree() for the * same memory allocation. * * Return: pointer to the allocated memory or %NULL in case of error */ void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) { void *n; if (is_vmalloc_addr(p)) return vrealloc_noprof(p, size, flags); n = krealloc_noprof(p, size, kmalloc_gfp_adjust(flags, size)); if (!n) { /* We failed to krealloc(), fall back to kvmalloc(). */ n = kvmalloc_noprof(size, flags); if (!n) return NULL; if (p) { /* We already know that `p` is not a vmalloc address. */ kasan_disable_current(); memcpy(n, kasan_reset_tag(p), ksize(p)); kasan_enable_current(); kfree(p); } } return n; } EXPORT_SYMBOL(kvrealloc_noprof); /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc_noprof(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array_noprof); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array_noprof); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc_noprof); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc_noprof); struct anon_vma *folio_anon_vma(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; return (void *)(mapping - PAGE_MAPPING_ANON); } /** * folio_mapping - Find the mapping where this folio is stored. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the swap mapping * this page is stored in (which is different from the mapping for the * swap file or swap device where the data is stored). * * You can call this for folios which aren't in the swap cache or page * cache and it will return NULL. */ struct address_space *folio_mapping(struct folio *folio) { struct address_space *mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(folio_test_slab(folio))) return NULL; if (unlikely(folio_test_swapcache(folio))) return swap_address_space(folio->swap); mapping = folio->mapping; if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; return mapping; } EXPORT_SYMBOL(folio_mapping); /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. * @src: Folio to copy from. * * The bytes in the folio represented by @src are copied to @dst. * Assumes the caller has validated that @dst is at least as large as @src. * Can be called in atomic context for order-0 folios, but if the folio is * larger, it may sleep. */ void folio_copy(struct folio *dst, struct folio *src) { long i = 0; long nr = folio_nr_pages(src); for (;;) { copy_highpage(folio_page(dst, i), folio_page(src, i)); if (++i == nr) break; cond_resched(); } } EXPORT_SYMBOL(folio_copy); int folio_mc_copy(struct folio *dst, struct folio *src) { long nr = folio_nr_pages(src); long i = 0; for (;;) { if (copy_mc_highpage(folio_page(dst, i), folio_page(src, i))) return -EHWPOISON; if (++i == nr) break; cond_resched(); } return 0; } EXPORT_SYMBOL(folio_mc_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condition (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * 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. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; unsigned long bytes_failed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: bytes_failed = pages << PAGE_SHIFT; pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n", __func__, current->pid, current->comm, bytes_failed); vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_local_page(page1); addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_local(addr2); kunmap_local(addr1); return ret; } #ifdef CONFIG_PRINTK /** * mem_dump_obj - Print available provenance information * @object: object for which to find provenance information. * * This function uses pr_cont(), so that the caller is expected to have * printed out whatever preamble is appropriate. The provenance information * depends on the type of object and on how much debugging is enabled. * For example, for a slab-cache object, the slab name is printed, and, * if available, the return address and stack trace from the allocation * and last free path of that object. */ void mem_dump_obj(void *object) { const char *type; if (kmem_dump_obj(object)) return; if (vmalloc_dump_obj(object)) return; if (is_vmalloc_addr(object)) type = "vmalloc memory"; else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; else if (object == ZERO_SIZE_PTR) type = "zero-size pointer"; else type = "non-paged memory"; pr_cont(" %s\n", type); } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif /* * A driver might set a page logically offline -- PageOffline() -- and * turn the page inaccessible in the hypervisor; after that, access to page * content can be fatal. * * Some special PFN walkers -- i.e., /proc/kcore -- read content of random * pages after checking PageOffline(); however, these PFN walkers can race * with drivers that set PageOffline(). * * page_offline_freeze()/page_offline_thaw() allows for a subsystem to * synchronize with such drivers, achieving that a page cannot be set * PageOffline() while frozen. * * page_offline_begin()/page_offline_end() is used by drivers that care about * such races when setting a page PageOffline(). */ static DECLARE_RWSEM(page_offline_rwsem); void page_offline_freeze(void) { down_read(&page_offline_rwsem); } void page_offline_thaw(void) { up_read(&page_offline_rwsem); } void page_offline_begin(void) { down_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_begin); void page_offline_end(void) { up_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_end); #ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio) { long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) flush_dcache_page(folio_page(folio, i)); } EXPORT_SYMBOL(flush_dcache_folio); #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 | /* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * */ #ifndef _NET_BONDING_H #define _NET_BONDING_H #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> #include <linux/cpumask.h> #include <linux/in6.h> #include <linux/netpoll.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/reciprocal_div.h> #include <linux/if_link.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #include <net/bond_options.h> #include <net/ipv6.h> #include <net/addrconf.h> #define BOND_MAX_ARP_TARGETS 16 #define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif #define slave_info(bond_dev, slave_dev, fmt, ...) \ netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_warn(bond_dev, slave_dev, fmt, ...) \ netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_dbg(bond_dev, slave_dev, fmt, ...) \ netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_err(bond_dev, slave_dev, fmt, ...) \ netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) #define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ NULL) #define bond_last_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) /* Caller must have rcu_read_lock */ #define bond_first_slave_rcu(bond) \ netdev_lower_get_first_private_rcu(bond->dev) #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave * @iter: list_head * iterator * * Caller must hold RTNL */ #define bond_for_each_slave(bond, pos, iter) \ netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { if (unlikely(netpoll_tx_running(dev))) return atomic_read(&netpoll_block_tx); return 0; } #else #define block_netpoll_tx() #define unblock_netpoll_tx() #define is_netpoll_tx_blocked(dev) (0) #endif struct bond_params { int mode; int xmit_policy; int miimon; u8 num_peer_notif; u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; int use_carrier; int fail_over_mac; int updelay; int downdelay; int peer_notif_delay; int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; int tx_queues; int all_slaves_active; int resend_igmp; int lp_interval; int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif int coupled_control; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; }; struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; /* all 4 in jiffies */ unsigned long last_link_up; unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ rx_disabled:1, /* indicates whether slave's Rx is disabled */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; static inline struct slave *to_slave(struct kobject *kobj) { return container_of(kobj, struct slave, kobj); } struct bond_up_slave { unsigned int count; struct rcu_head rcu; struct slave *arr[]; }; /* * Link pseudo-state only used internally by monitors */ #define BOND_LINK_NOCHANGE -1 struct bond_ipsec { struct list_head list; struct xfrm_state *xs; }; /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); /* mode_lock is used for mode-specific locking needs, currently used by: * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and * bond_3ad_state_machine_handler() concurrently and also * the access to the state machine shared variables. * TLB mode (5) - to sync the use and modifications of its hash table * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; spinlock_t stats_lock; u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; }; /* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { return slave->bond; } static inline bool bond_should_override_tx_queue(struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; } static inline bool bond_is_lb(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB; } static inline bool bond_needs_speed_duplex(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); } static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0); } static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB); } static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || bond_is_nondyn_tlb(bond)); } static inline bool bond_mode_uses_arp(int mode) { return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && mode != BOND_MODE_ALB; } static inline bool bond_mode_uses_primary(int mode) { return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || mode == BOND_MODE_ALB; } static inline bool bond_uses_primary(struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } static inline bool bond_slave_is_up(struct slave *slave) { return netif_running(slave->dev) && netif_carrier_ok(slave->dev); } static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_slave_state(struct slave *slave, int slave_state, bool notify) { if (slave->backup == slave_state) return; slave->backup = slave_state; if (notify) { bond_lower_state_changed(slave); bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) slave->should_notify = 0; else slave->should_notify = 1; } } static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->link == BOND_LINK_UP) bond_set_active_slave(tmp); else if (tmp->link == BOND_LINK_DOWN) bond_set_backup_slave(tmp); } } static inline void bond_slave_state_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { bond_lower_state_changed(tmp); tmp->should_notify = 0; } } } static inline int bond_slave_state(struct slave *slave) { return slave->backup; } static inline bool bond_is_active_slave(struct slave *slave) { return !bond_slave_state(slave); } static inline bool bond_slave_can_tx(struct slave *slave) { return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && bond_is_active_slave(slave); } static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) { struct slave *slave; bool active; rcu_read_lock(); slave = bond_slave_get_rcu(slave_dev); active = bond_is_active_slave(slave); rcu_read_unlock(); return active; } static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { ether_addr_copy(dst, src); return; } memcpy(dst, src, len); } #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 #define BOND_FOM_NONE 0 #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 #define BOND_ARP_TARGETS_ANY 0 #define BOND_ARP_TARGETS_ALL 1 #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) #define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) #define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_FILTER) #define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ BOND_ARP_FILTER) #define BOND_SLAVE_NOTIFY_NOW true #define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline int slave_do_arp_validate_only(struct bonding *bond) { return bond->params.arp_validate & BOND_ARP_FILTER; } static inline int bond_is_ip_target_ok(__be32 addr) { return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } #endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { int i = 1; unsigned long ret = slave->target_last_arp_rx[0]; for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) if (time_before(slave->target_last_arp_rx[i], ret)) ret = slave->target_last_arp_rx[i]; return ret; } static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); return slave->last_rx; } static inline void slave_update_last_tx(struct slave *slave) { WRITE_ONCE(slave->last_tx, jiffies); } static inline unsigned long slave_last_tx(struct slave *slave) { return READ_ONCE(slave->last_tx); } #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { return netpoll_send_skb(slave->np, skb); } #else static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { BUG(); return NETDEV_TX_OK; } #endif static inline void bond_set_slave_inactive_flags(struct slave *slave, bool notify) { if (!bond_is_lb(slave->bond)) bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 1; } static inline void bond_set_slave_tx_disabled_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); } static inline void bond_set_slave_active_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 0; } static inline void bond_set_slave_rx_enabled_flags(struct slave *slave, bool notify) { slave->rx_disabled = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) { return slave->inactive; } static inline bool bond_is_slave_rx_disabled(struct slave *slave) { return slave->rx_disabled; } static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; } static inline void bond_commit_link_state(struct slave *slave, bool notify) { if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; if (notify) { bond_queue_slave_event(slave); bond_lower_state_changed(slave); slave->should_notify_link = 0; } else { if (slave->should_notify_link) slave->should_notify_link = 0; else slave->should_notify_link = 1; } } static inline void bond_set_slave_link_state(struct slave *slave, int state, bool notify) { bond_propose_link_state(slave, state); bond_commit_link_state(slave, notify); } static inline void bond_slave_link_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify_link) { bond_queue_slave_event(tmp); bond_lower_state_changed(tmp); tmp->should_notify_link = 0; } } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; __be32 addr = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, RT_SCOPE_HOST); rcu_read_unlock(); return addr; } struct bond_net { struct net *net; /* Associated network namespace */ struct list_head dev_list; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_dir; #endif struct class_attribute class_attr_bonding_masters; }; int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); void bond_destroy_debugfs(void); void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); void bond_remove_proc_entry(struct bonding *bond); void bond_create_proc_dir(struct bond_net *bn); void bond_destroy_proc_dir(struct bond_net *bn); #else static inline void bond_create_proc_entry(struct bonding *bond) { } static inline void bond_remove_proc_entry(struct bonding *bond) { } static inline void bond_create_proc_dir(struct bond_net *bn) { } static inline void bond_destroy_proc_dir(struct bond_net *bn) { } #endif static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; return NULL; } /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; return false; } /* Check if the ip is present in arp ip list, or first free slot if ip == 0 * Returns -1 if not found, index if found */ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) { int i; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) if (targets[i] == ip) return i; else if (targets[i] == 0) break; return -1; } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { struct in6_addr mcaddr; int i; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { addrconf_addr_solict_mult(&targets[i], &mcaddr); if ((ipv6_addr_equal(&targets[i], ip)) || (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; } return -1; } #endif /* exported from bond_main.c */ extern unsigned int bond_net_id; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; /* exported from bond_3ad.c */ extern const u8 lacpdu_mcast_addr[]; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ |
| 4 3 3 3 1 2 5 1 3 4 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 | /* * llc_input.c - Minimal input path for LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) #endif /* * Packet handler for the station, registerable because in the minimal * LLC core that is taking shape only the very minimal subset of LLC that * is needed for things like IPX, Appletalk, etc will stay, with all the * rest in the llc1 and llc2 modules. */ static void (*llc_station_handler)(struct sk_buff *skb); /* * Packet handlers for LLC_DEST_SAP and LLC_DEST_CONN. */ static void (*llc_type_handlers[2])(struct llc_sap *sap, struct sk_buff *skb); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)) { smp_wmb(); /* ensure initialisation is complete before it's called */ if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = handler; } void llc_remove_pack(int type) { if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = NULL; synchronize_net(); } void llc_set_station_handler(void (*handler)(struct sk_buff *skb)) { /* Ensure initialisation is complete before it's called */ if (handler) smp_wmb(); llc_station_handler = handler; if (!handler) synchronize_net(); } /** * llc_pdu_type - returns which LLC component must handle for PDU * @skb: input skb * * This function returns which LLC component must handle this PDU. */ static __inline__ int llc_pdu_type(struct sk_buff *skb) { int type = LLC_DEST_CONN; /* I-PDU or S-PDU type */ struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) != LLC_PDU_TYPE_U) goto out; switch (LLC_U_PDU_CMD(pdu)) { case LLC_1_PDU_CMD_XID: case LLC_1_PDU_CMD_UI: case LLC_1_PDU_CMD_TEST: type = LLC_DEST_SAP; break; case LLC_2_PDU_CMD_SABME: case LLC_2_PDU_CMD_DISC: case LLC_2_PDU_RSP_UA: case LLC_2_PDU_RSP_DM: case LLC_2_PDU_RSP_FRMR: break; default: type = LLC_DEST_INVALID; break; } out: return type; } /** * llc_fixup_skb - initializes skb pointers * @skb: This argument points to incoming skb * * Initializes internal skb pointer to start of network layer by deriving * length of LLC header; finds length of LLC control field in LLC header * by looking at the two lowest-order bits of the first control field * byte; field is either 3 or 4 bytes long. */ static inline int llc_fixup_skb(struct sk_buff *skb) { u8 llc_len = 2; struct llc_pdu_un *pdu; if (unlikely(!pskb_may_pull(skb, sizeof(*pdu)))) return 0; pdu = (struct llc_pdu_un *)skb->data; if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) == LLC_PDU_TYPE_U) llc_len = 1; llc_len += 2; if (unlikely(!pskb_may_pull(skb, llc_len))) return 0; skb_pull(skb, llc_len); skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) { __be16 pdulen; s32 data_size; if (skb->mac_len < ETH_HLEN) return 0; pdulen = eth_hdr(skb)->h_proto; data_size = ntohs(pdulen) - llc_len; if (data_size < 0 || !pskb_may_pull(skb, data_size)) return 0; if (unlikely(pskb_trim_rcsum(skb, data_size))) return 0; } return 1; } /** * llc_rcv - 802.2 entry point from net lower layers * @skb: received pdu * @dev: device that receive pdu * @pt: packet type * @orig_dev: the original receive net device * * When the system receives a 802.2 frame this function is called. It * checks SAP and connection of received pdu and passes frame to * llc_{station,sap,conn}_rcv for sending to proper state machine. If * the frame is related to a busy connection (a connection is sending * data now), it queues this frame in the connection's backlog. */ int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct llc_sap *sap; struct llc_pdu_sn *pdu; int dest; int (*rcv)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. */ if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { dprintk("%s: PACKET_OTHERHOST\n", __func__); goto drop; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto out; if (unlikely(!llc_fixup_skb(skb))) goto drop; pdu = llc_pdu_sn_hdr(skb); if (unlikely(!pdu->dsap)) /* NULL DSAP, refer to station */ goto handle_station; sap = llc_sap_find(pdu->dsap); if (unlikely(!sap)) {/* unknown SAP */ dprintk("%s: llc_sap_find(%02X) failed!\n", __func__, pdu->dsap); goto drop; } /* * First the upper layer protocols that don't need the full * LLC functionality */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL; if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); else kfree_skb(skb); } else { if (rcv) { struct sk_buff *cskb = skb_clone(skb, GFP_ATOMIC); if (cskb) rcv(cskb, dev, pt, orig_dev); } sap_handler(sap, skb); } llc_sap_put(sap); out: return 0; drop: kfree_skb(skb); goto out; handle_station: sta_handler = READ_ONCE(llc_station_handler); if (!sta_handler) goto drop; sta_handler(skb); goto out; } EXPORT_SYMBOL(llc_add_pack); EXPORT_SYMBOL(llc_remove_pack); EXPORT_SYMBOL(llc_set_station_handler); |
| 309 465 522 4 522 523 522 490 490 466 489 490 490 489 3 490 491 489 491 490 490 491 490 490 490 490 490 30 464 7 14 14 8 7 8 8 8 8 779 774 4 4 308 309 8 310 310 310 310 309 309 310 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" #include "internal.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistic load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @p: prepend buffer which contains buffer pointer and allocated length * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @p: prepend buffer which contains buffer pointer and allocated length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; } while (read_seqcount_retry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...) { va_list args; char temp[64]; int sz; va_start(args, fmt); sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; va_end(args); if (sz > sizeof(temp) || sz > buflen) return ERR_PTR(-ENAMETOOLONG); buffer += buflen - sz; return memcpy(buffer, temp, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqcount_retry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 147 89 | 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 */ #ifndef LINUX_RESUME_USER_MODE_H #define LINUX_RESUME_USER_MODE_H #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/rseq.h> #include <linux/blk-cgroup.h> /** * set_notify_resume - cause resume_user_mode_work() to be called * @task: task that will call resume_user_mode_work() * * Calling this arranges that @task will call resume_user_mode_work() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call resume_user_mode_work() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); } /** * resume_user_mode_work - Perform work before returning to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void resume_user_mode_work(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(task_work_pending(current))) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); } #endif /* LINUX_RESUME_USER_MODE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int __init macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void __exit macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_DESCRIPTION("MAC-VLAN based tap driver"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ union { wait_queue_head_t poll; struct rcu_head mnt_ns_rcu; }; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ struct list_head mnt_ns_list; /* entry in the sequential list of mounts namespace */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ /** * IS_ERR_VALUE - Detect an error pointer. * @x: The pointer to check. * * Like IS_ERR(), but does not generate a compiler warning if result is unused. */ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) /** * ERR_PTR - Create an error pointer. * @error: A negative error code. * * Encodes @error into a pointer value. Users should consider the result * opaque and not assume anything about how the error is encoded. * * Return: A pointer with @error encoded within its value. */ static inline void * __must_check ERR_PTR(long error) { return (void *) error; } /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. * Return: The error code within @ptr. */ static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } /* Read an error pointer from the percpu address space. */ #define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } /* Read an error pointer from the percpu address space. */ #define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. * * Like IS_ERR(), but also returns true for a null pointer. */ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } /** * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one. * @ptr: A potential error pointer. * * Convenience function that can be used inside a function that returns * an error code to propagate errors received as error pointers. * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces: * * .. code-block:: c * * if (IS_ERR(ptr)) * return PTR_ERR(ptr); * else * return 0; * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 353 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 88 87 40 109 72 65 1 54 24 59 10 79 326 128 128 79 74 78 67 71 68 65 64 68 64 68 5 75 5 59 75 89 72 89 66 82 89 89 83 89 3 45 37 16 212 16 7 322 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_HOST_H #define __KVM_HOST_H #include <linux/types.h> #include <linux/hardirq.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/preempt.h> #include <linux/msi.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rcupdate.h> #include <linux/ratelimit.h> #include <linux/err.h> #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> #include <linux/ftrace.h> #include <linux/hashtable.h> #include <linux/instrumentation.h> #include <linux/interval_tree.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <asm/kvm_host.h> #include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_IDS #define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally * used in kvm, other bits are visible for userspace which are defined in * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) /* * Bit 63 of the memslot generation number is an "update in-progress flag", * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. * * This is necessary because the actual memslots update is not atomic with * respect to the generation number update. Updating the generation number * first would allow a vCPU to cache a spte from the old memslots using the * new generation number, and updating the generation number after switching * to the new memslots would allow cache hits using the old generation number * to reference the defunct memslots. * * This mechanism is used to prevent getting hits in KVM's caches while a * memslot update is in-progress, and to prevent cache hits *after* updating * the actual generation number against accesses that were inserted into the * cache *before* the memslots were updated. */ #define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63) /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 #ifndef KVM_MAX_NR_ADDRESS_SPACES #define KVM_MAX_NR_ADDRESS_SPACES 1 #endif /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, * mask bit 63 to indicate the noslot pfn. */ #define KVM_PFN_ERR_MASK (0x7ffULL << 52) #define KVM_PFN_ERR_NOSLOT_MASK (0xfffULL << 52) #define KVM_PFN_NOSLOT (0x1ULL << 63) #define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK) #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) #define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) #define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } /* * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted * by a pending signal. Note, the signal may or may not be fatal. */ static inline bool is_sigpending_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_ERR_SIGPENDING; } /* * error_noslot pfns indicate that the gfn can not be * translated to pfn - it is not in slot or failed to * translate it to pfn. */ static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } /* * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) * provide own defines and kvm_is_error_hva */ #ifndef KVM_HVA_ERR_BAD #define KVM_HVA_ERR_BAD (PAGE_OFFSET) #define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE) static inline bool kvm_is_error_hva(unsigned long addr) { return addr >= PAGE_OFFSET; } #endif static inline bool kvm_is_error_gpa(gpa_t gpa) { return gpa == INVALID_GPA; } #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) #define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_DIRTY_RING_SOFT_FULL 3 #define KVM_REQUEST_ARCH_BASE 8 /* * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no * guarantee the vCPU received an IPI and has actually exited guest mode. */ #define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 extern struct mutex kvm_lock; extern struct list_head vm_list; struct kvm_io_range { gpa_t addr; int len; struct kvm_io_device *dev; }; #define NR_IOBUS_DEVS 1000 struct kvm_io_bus { int dev_count; int ioeventfd_count; struct kvm_io_range range[]; }; enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, KVM_IOCSR_BUS, KVM_NR_BUSES }; int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie); int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { struct work_struct work; struct list_head link; struct list_head queue; struct kvm_vcpu *vcpu; gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; bool notpresent_injected; }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { unsigned long attributes; }; enum kvm_gfn_range_filter { KVM_FILTER_SHARED = BIT(0), KVM_FILTER_PRIVATE = BIT(1), }; struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); #endif enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, EXITING_GUEST_MODE, READING_SHADOW_PAGE_TABLES, }; struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). */ struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; bool writable; }; /* * Used to check if the mapping is valid or not. Never use 'kvm_host_map' * directly to check for that. */ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) { return !!map->hva; } static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) { return single_task_running() && !need_resched() && ktime_before(cur, stop); } /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. */ struct kvm_mmio_fragment { gpa_t gpa; void *data; unsigned len; }; struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier preempt_notifier; #endif int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index into kvm->vcpu_array */ int ____srcu_idx; /* Don't use this directly. You've been warned. */ #ifdef CONFIG_PROVE_RCU int srcu_depth; #endif int mode; u64 requests; unsigned long guest_debug; struct mutex mutex; struct kvm_run *run; #ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; #endif struct pid *pid; rwlock_t pid_lock; int sigset_active; sigset_t sigset; unsigned int halt_poll_ns; bool valid_wakeup; #ifdef CONFIG_HAS_IOMEM int mmio_needed; int mmio_read_completed; int mmio_is_write; int mmio_cur_fragment; int mmio_nr_fragments; struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS]; #endif #ifdef CONFIG_KVM_ASYNC_PF struct { u32 queued; struct list_head queue; struct list_head done; spinlock_t lock; } async_pf; #endif #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT /* * Cpu relax intercept or pause loop exit optimization * in_spin_loop: set when a vcpu does a pause loop exit * or cpu relax intercepted. * dy_eligible: indicates whether vcpu is eligible for directed yield. */ struct { bool in_spin_loop; bool dy_eligible; } spin_loop; #endif bool wants_to_run; bool preempted; bool ready; bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; /* * The most recently used memslot by this vCPU and the slots generation * for which it is valid. * No wraparound protection is needed since generations won't overflow in * thousands of years, even assuming 1M memslot operations per second. */ struct kvm_memory_slot *last_used_slot; u64 last_used_slot_gen; }; /* * Start accounting time towards a guest. * Must be called before entering guest context. */ static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the * stime pending cputime to flush. */ instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); } /* * Enter guest context and enter an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_enter_irqoff(void) { /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In * addition CPU may stay in a guest mode for quite a long time (up to * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ if (!context_tracking_guest_enter()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Deprecated. Architectures should move to guest_timing_enter_irqoff() and * guest_state_enter_irqoff(). */ static __always_inline void guest_enter_irqoff(void) { guest_timing_enter_irqoff(); guest_context_enter_irqoff(); } /** * guest_state_enter_irqoff - Fixup state when entering a guest * * Entry to a guest will enable interrupts, but the kernel state is interrupts * disabled when this is invoked. Also tell RCU about it. * * 1) Trace interrupts on state * 2) Invoke context tracking if enabled to adjust RCU state * 3) Tell lockdep that interrupts are enabled * * Invoked from architecture specific code before entering a guest. * Must be called with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_enter_irqoff() before this. * * Note: this is analogous to exit_to_user_mode(). */ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); } /* * Exit guest context and exit an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_exit_irqoff(void) { /* * Guest mode is treated as a quiescent state, see * guest_context_enter_irqoff() for more details. */ if (!context_tracking_guest_exit()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Stop accounting time towards a guest. * Must be called after exiting guest context. */ static __always_inline void guest_timing_exit_irqoff(void) { instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } /* * Deprecated. Architectures should move to guest_state_exit_irqoff() and * guest_timing_exit_irqoff(). */ static __always_inline void guest_exit_irqoff(void) { guest_context_exit_irqoff(); guest_timing_exit_irqoff(); } static inline void guest_exit(void) { unsigned long flags; local_irq_save(flags); guest_exit_irqoff(); local_irq_restore(flags); } /** * guest_state_exit_irqoff - Establish state when returning from guest mode * * Entry from a guest disables interrupts, but guest mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. * * 1) Tell lockdep that interrupts are disabled * 2) Invoke context tracking if enabled to reactivate RCU * 3) Trace interrupts off state * * Invoked from architecture specific code after exiting a guest. * Must be invoked with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_exit_irqoff() after this. * * Note: this is analogous to enter_from_user_mode(). */ static __always_inline void guest_state_exit_irqoff(void) { lockdep_hardirqs_off(CALLER_ADDR0); guest_context_exit_irqoff(); instrumentation_begin(); trace_hardirqs_off_finish(); instrumentation_end(); } static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* * The memory barrier ensures a previous write to vcpu->requests cannot * be reordered with the read of vcpu->mode. It pairs with the general * memory barrier following the write of vcpu->mode in VCPU RUN. */ smp_mb__before_atomic(); return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE); } /* * Some of the bitops functions do not support too long bitmaps. * This number must be determined not to exceed such limits. */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) /* * Since at idle each memslot belongs to two memslot sets it has to contain * two embedded nodes for each data structure that it forms a part of. * * Two memslot sets (one active and one inactive) are necessary so the VM * continues to run on one memslot set while the other is being modified. * * These two memslot sets normally point to the same set of memslots. * They can, however, be desynchronized when performing a memslot management * operation by replacing the memslot to be modified by its copy. * After the operation is complete, both memslot sets once again point to * the same, common set of memslot data. * * The memslots themselves are independent of each other so they can be * individually added or deleted. */ struct kvm_memory_slot { struct hlist_node id_node[2]; struct interval_tree_node hva_node[2]; struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; u32 flags; short id; u16 as_id; #ifdef CONFIG_KVM_PRIVATE_MEM struct { /* * Writes protected by kvm->slots_lock. Acquiring a * reference via kvm_gmem_get_file() is protected by * either kvm->slots_lock or kvm->srcu. */ struct file *file; pgoff_t pgoff; } gmem; #endif }; static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) { return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); } static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; } static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long len = kvm_dirty_bitmap_bytes(memslot); return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); } #ifndef KVM_DIRTY_LOG_MANUAL_CAPS #define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE #endif struct kvm_s390_adapter_int { u64 ind_addr; u64 summary_addr; u64 ind_offset; u32 summary_offset; u32 adapter_id; }; struct kvm_hv_sint { u32 vcpu; u32 sint; }; struct kvm_xen_evtchn { u32 port; u32 vcpu_id; int vcpu_idx; u32 priority; }; struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); union { struct { unsigned irqchip; unsigned pin; } irqchip; struct { u32 address_lo; u32 address_hi; u32 data; u32 flags; u32 devid; } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; u32 nr_rt_entries; /* * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ struct hlist_head map[] __counted_by(nr_rt_entries); }; #endif bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); #ifndef KVM_INTERNAL_MEM_SLOTS #define KVM_INTERNAL_MEM_SLOTS 0 #endif #define KVM_MEM_SLOTS_NUM SHRT_MAX #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) #if KVM_MAX_NR_ADDRESS_SPACES == 1 static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) { return KVM_MAX_NR_ADDRESS_SPACES; } static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; } #endif /* * Arch code must define kvm_arch_has_private_mem if support for private memory * is enabled. */ #if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; } #endif #ifndef kvm_arch_has_readonly_mem static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) { return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); } #endif struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; struct rb_root_cached hva_tree; struct rb_root gfn_tree; /* * The mapping table from slot id to memslot. * * 7-bit bucket count matches the size of the old id to index array for * 512 slots, while giving good performance with this slot count. * Higher bucket counts bring only small performance improvements but * always result in higher memory usage (even for lower memslot counts). */ DECLARE_HASHTABLE(id_hash, 7); int node_idx; }; struct kvm { #ifdef KVM_HAVE_MMU_RWLOCK rwlock_t mmu_lock; #else spinlock_t mmu_lock; #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; /* * Protects the arch-specific fields of struct kvm_memory_slots in * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; /* The two memslot sets - active and inactive (per address space) */ struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2]; /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES]; struct xarray vcpu_array; /* * Protected by slots_lock, but can be read outside if an * incorrect answer is acceptable. */ atomic_t nr_memslots_dirty_logging; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; /* For management / invalidation of gfn_to_pfn_caches */ spinlock_t gpc_lock; struct list_head gpc_list; /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only * incremented after storing the kvm_vcpu pointer in vcpus, * and is accessed atomically. */ atomic_t online_vcpus; int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_IRQCHIP struct { spinlock_t lock; struct list_head items; /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; #endif struct list_head ioeventfds; struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; #ifdef CONFIG_KVM_MMIO struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; spinlock_t ring_lock; struct list_head coalesced_zones; #endif struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP /* * Update side is protected by irq_lock. */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head irq_ack_notifier_list; #endif #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; #endif struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool dirty_ring_with_bitmap; bool vm_bugged; bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES /* Protected by slots_locks (for writes) and RCU (for reads) */ struct xarray mem_attr_array; #endif char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_info(fmt, ...) \ pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug(fmt, ...) \ pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug_ratelimited(fmt, ...) \ pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \ ## __VA_ARGS__) #define kvm_pr_unimpl(fmt, ...) \ pr_err_ratelimited("kvm [%i]: " fmt, \ task_tgid_nr(current), ## __VA_ARGS__) /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...) \ kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \ (vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__) #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) #define vcpu_debug_ratelimited(vcpu, fmt, ...) \ kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \ ## __VA_ARGS__) #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) static inline void kvm_vm_dead(struct kvm *kvm) { kvm->vm_dead = true; kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); } static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; kvm_vm_dead(kvm); } #define KVM_BUG(cond, kvm, fmt...) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) #define KVM_BUG_ON(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) /* * Note, "data corruption" refers to corruption of host kernel data structures, * not guest data. Guest data corruption, suspected or confirmed, that is tied * and contained to a single VM should *never* BUG() and potentially panic the * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure * is corrupted and that corruption can have a cascading effect to other parts * of the hosts and/or to other VMs. */ #define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) \ BUG_ON(__ret); \ else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PROVE_RCU WARN_ONCE(vcpu->srcu_depth++, "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); #endif vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); } static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); #ifdef CONFIG_PROVE_RCU WARN_ONCE(--vcpu->srcu_depth, "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); #endif } static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); } static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) { return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); } static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); /* * Explicitly verify the target vCPU is online, as the anti-speculation * logic only limits the CPU's ability to speculate, e.g. given a "bad" * index, clamping the index to 0 would return vCPU0, not NULL. */ if (i >= num_vcpus) return NULL; i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return xa_load(&kvm->vcpu_array, i); } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ if (atomic_read(&kvm->online_vcpus)) \ xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; unsigned long i; if (id < 0) return NULL; if (id < KVM_MAX_VCPUS) vcpu = kvm_get_vcpu(kvm, id); if (vcpu && vcpu->vcpu_id == id) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) if (vcpu->vcpu_id == id) return vcpu; return NULL; } void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) { } #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else static inline int kvm_irqfd_init(void) { return 0; } static inline void kvm_irqfd_exit(void) { } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { return __kvm_memslots(kvm, 0); } static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) { int as_id = kvm_arch_vcpu_memslots_id(vcpu); return __kvm_memslots(vcpu->kvm, as_id); } static inline bool kvm_memslots_empty(struct kvm_memslots *slots) { return RB_EMPTY_ROOT(&slots->gfn_tree); } bool kvm_are_all_memslots_empty(struct kvm *kvm); #define kvm_for_each_memslot(memslot, bkt, slots) \ hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ if (WARN_ON_ONCE(!memslot->npages)) { \ } else static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { struct kvm_memory_slot *slot; int idx = slots->node_idx; hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { if (slot->id == id) return slot; } return NULL; } /* Iterator used for walking memslots that overlap a gfn range. */ struct kvm_memslot_iter { struct kvm_memslots *slots; struct rb_node *node; struct kvm_memory_slot *slot; }; static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) { iter->node = rb_next(iter->node); if (!iter->node) return; iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, struct kvm_memslots *slots, gfn_t start) { int idx = slots->node_idx; struct rb_node *tmp; struct kvm_memory_slot *slot; iter->slots = slots; /* * Find the so called "upper bound" of a key - the first node that has * its key strictly greater than the searched one (the start gfn in our case). */ iter->node = NULL; for (tmp = slots->gfn_tree.rb_node; tmp; ) { slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); if (start < slot->base_gfn) { iter->node = tmp; tmp = tmp->rb_left; } else { tmp = tmp->rb_right; } } /* * Find the slot with the lowest gfn that can possibly intersect with * the range, so we'll ideally have slot start <= range start */ if (iter->node) { /* * A NULL previous node means that the very first slot * already has a higher start gfn. * In this case slot start > range start. */ tmp = rb_prev(iter->node); if (tmp) iter->node = tmp; } else { /* a NULL node below means no slots */ iter->node = rb_last(&slots->gfn_tree); } if (iter->node) { iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); /* * It is possible in the slot start < range start case that the * found slot ends before or at range start (slot end <= range start) * and so it does not overlap the requested range. * * In such non-overlapping case the next slot (if it exists) will * already have slot start > range start, otherwise the logic above * would have found it instead of the current slot. */ if (iter->slot->base_gfn + iter->slot->npages <= start) kvm_memslot_iter_next(iter); } } static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) { if (!iter->node) return false; /* * If this slot starts beyond or at the end of the range so does * every next one */ return iter->slot->base_gfn < end; } /* Iterate over each memslot at least partially intersecting [start, end) range */ #define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ for (kvm_memslot_iter_start(iter, slots, start); \ kvm_memslot_iter_is_valid(iter, end); \ kvm_memslot_iter_next(iter)) struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot * - delete an existing memory slot * - modify an existing memory slot * -- move it in the guest physical memory space * -- just change its flags * * Since flags can be changed by some of these operations, the following * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, KVM_MR_DELETE, KVM_MR_MOVE, KVM_MR_FLAGS_ONLY, }; int kvm_set_internal_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages); struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { return __gfn_to_page(kvm, gfn, true); } unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); static inline void kvm_release_page_unused(struct page *page) { if (!page) return; put_page(page); } void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, bool unused, bool dirty) { lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); if (!page) return; /* * If the page that KVM got from the *primary MMU* is writable, and KVM * installed or reused a SPTE, mark the page/folio dirty. Note, this * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if * the GFN is write-protected. Folios can't be safely marked dirty * outside of mmu_lock as doing so could race with writeback on the * folio. As a result, KVM can't mark folios dirty in the fast page * fault handler, and so KVM must (somewhat) speculatively mark the * folio dirty if KVM could locklessly make the SPTE writable. */ if (unused) kvm_release_page_unused(page); else if (dirty) kvm_release_page_dirty(page); else kvm_release_page_clean(page); } kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, unsigned int foll, bool *writable, struct page **refcounted_page); static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool write, bool *writable, struct page **refcounted_page) { return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, write ? FOLL_WRITE : 0, writable, refcounted_page); } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); #define __kvm_get_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = get_user(v, __uaddr); \ __ret; \ }) #define kvm_get_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) #define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) #define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, bool writable); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, true); } static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, false); } unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len); int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** * kvm_gpc_init - initialize gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest * physical address. * * @gpc: struct gfn_to_pfn_cache object. * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for * invalidations to be processed. Callers are required to use kvm_gpc_check() * to ensure that the cache is valid before accessing the target page. */ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); /** * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. * * @gpc: struct gfn_to_pfn_cache object. * @hva: userspace virtual address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * The semantics of this function are the same as those of kvm_gpc_activate(). It * merely bypasses a layer of address translation. */ int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); /** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. * * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock * while calling this function, and then continue to hold the lock until the * access is complete. * * Callers in IN_GUEST_MODE may do so without locking, although they should * still hold a read lock on kvm->scru for the memslot checks. */ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_refresh - update a previously initialized cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful * return from this function does not mean the page can be immediately * accessed because it may have raced with an invalidation. Callers must * still lock and check the cache status, as this function does not return * with the lock still held to permit access. */ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * * This removes a cache from the VM's list to be processed on MMU notifier * invocation. */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && !kvm_is_error_gpa(gpc->gpa); } static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && kvm_is_error_gpa(gpc->gpa); } void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); void kvm_vcpu_halt(struct kvm_vcpu *vcpu); bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif void kvm_mmu_invalidate_begin(struct kvm *kvm); void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); void kvm_mmu_invalidate_end(struct kvm *kvm); bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot); #endif int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #endif #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #else static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING /* * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of * kvm_usage_count, i.e. at the beginning of the generic hardware enabling * sequence, and at the end of the generic hardware disabling sequence. */ void kvm_arch_enable_virtualization(void); void kvm_arch_disable_virtualization(void); /* * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to * do the actual twiddling of hardware bits. The hooks are called on all * online CPUs when KVM enables/disabled virtualization, and on a single CPU * when that CPU is onlined/offlined (including for Resume/Suspend). */ int kvm_arch_enable_virtualization_cpu(void); void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* * All architectures that want to use vzalloc currently also * need their own kvm_arch_alloc_vm implementation. */ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } #endif static inline void __kvm_arch_free_vm(struct kvm *kvm) { kvfree(kvm); } #ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { __kvm_arch_free_vm(kvm); } #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { return -ENOTSUPP; } #else int kvm_arch_flush_remote_tlbs(struct kvm *kvm); #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { return -EOPNOTSUPP; } #else int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); #endif #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA void kvm_arch_register_noncoherent_dma(struct kvm *kvm); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm); #else static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { } static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { } static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return false; } #endif #ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE void kvm_arch_start_assignment(struct kvm *kvm); void kvm_arch_end_assignment(struct kvm *kvm); bool kvm_arch_has_assigned_device(struct kvm *kvm); #else static inline void kvm_arch_start_assignment(struct kvm *kvm) { } static inline void kvm_arch_end_assignment(struct kvm *kvm) { } static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } #endif static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP return vcpu->arch.waitp; #else return &vcpu->wait; #endif } /* * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns * true if the vCPU was blocking and was awakened, false otherwise. */ static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); } static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) { return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); } #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and * ready to accept virtual IRQ. On some architectures the virtual interrupt * controller is dynamically instantiated and this is not always true. */ bool kvm_arch_intc_initialized(struct kvm *kvm); #else static inline bool kvm_arch_intc_initialized(struct kvm *kvm) { return true; } #endif #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); void kvm_unregister_perf_callbacks(void); #else static inline void kvm_register_perf_callbacks(void *ign) {} static inline void kvm_unregister_perf_callbacks(void) {} #endif /* CONFIG_GUEST_PERF_EVENTS */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; int kvm_irq_map_gsi(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *entries, int gsi); int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin); int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level, bool line_status); int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_gsi(struct kvm *kvm, int gsi); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { if (!slot) return NULL; if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else return NULL; } /* * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * * With "approx" set returns the memslot also when the address falls * in a hole. In that case one of the memslots bordering the hole is * returned. */ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; struct rb_node *node; int idx = slots->node_idx; slot = NULL; for (node = slots->gfn_tree.rb_node; node; ) { slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); if (gfn >= slot->base_gfn) { if (gfn < slot->base_gfn + slot->npages) return slot; node = node->rb_right; } else node = node->rb_left; } return approx ? slot : NULL; } static inline struct kvm_memory_slot * ____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); slot = try_get_memslot(slot, gfn); if (slot) return slot; slot = search_memslots(slots, gfn, approx); if (slot) { atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } /* * __gfn_to_memslot() and its descendants are here to allow arch code to inline * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline * because that would bloat other code too much. */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { return ____gfn_to_memslot(slots, gfn, false); } static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { /* * The index was checked originally in search_memslots. To avoid * that a malicious guest builds a Spectre gadget out of e.g. page * table walks, do not let the processor speculate loads outside * the guest's registered memslots. */ unsigned long offset = gfn - slot->base_gfn; offset = array_index_nospec(offset, slot->npages); return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) { return gfn_to_memslot(kvm, gfn)->id; } static inline gfn_t hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot) { gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT; return slot->base_gfn + gfn_offset; } static inline gpa_t gfn_to_gpa(gfn_t gfn) { return (gpa_t)gfn << PAGE_SHIFT; } static inline gfn_t gpa_to_gfn(gpa_t gpa) { return (gfn_t)(gpa >> PAGE_SHIFT); } static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); return !kvm_is_error_hva(hva); } static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) { lockdep_assert_held(&gpc->lock); if (!gpc->memslot) return; mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); } enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, }; struct kvm_stat_data { struct kvm *kvm; const struct _kvm_stats_desc *desc; enum kvm_stat_kind kind; }; struct _kvm_stats_desc { struct kvm_stats_desc desc; char name[KVM_STATS_NAME_SIZE]; }; #define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ .flags = type | unit | base | \ BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ .exponent = exp, \ .size = sz, \ .bucket_size = bsz #define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, generic.stat) \ }, \ .name = #stat, \ } #define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ }, \ .name = #stat, \ } #define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, stat) \ }, \ .name = #stat, \ } #define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, stat) \ }, \ .name = #stat, \ } /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) #define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ unit, base, exponent, 1, 0) #define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ unit, base, exponent, 1, 0) #define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ unit, base, exponent, 1, 0) #define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ unit, base, exponent, sz, bsz) #define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ unit, base, exponent, sz, 0) /* Cumulative counter, read/write */ #define STATS_DESC_COUNTER(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous counter, read only */ #define STATS_DESC_ICOUNTER(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Peak counter, read/write */ #define STATS_DESC_PCOUNTER(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous boolean value, read only */ #define STATS_DESC_IBOOLEAN(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Peak (sticky) boolean value, read/write */ #define STATS_DESC_PBOOLEAN(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9) /* Linear histogram for time in nanosecond */ #define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz, bsz) /* Logarithmic histogram for time in nanosecond */ #define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz) #define KVM_GENERIC_VM_STATS() \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) #define KVM_GENERIC_VCPU_STATS() \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); /** * kvm_stats_linear_hist_update() - Update bucket value for linear histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the linear histogram's bucket * @bucket_size: the size (width) of a bucket */ static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, u64 value, size_t bucket_size) { size_t index = div64_u64(value, bucket_size); index = min(index, size - 1); ++data[index]; } /** * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the logarithmic histogram's bucket */ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) { size_t index = fls64(value); index = min(index, size - 1); ++data[index]; } #define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) #define KVM_STATS_LOG_HIST_UPDATE(array, value) \ kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value) extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* * Ensure the read of mmu_invalidate_in_progress happens before * the read of mmu_invalidate_seq. This interacts with the * smp_wmb() in mmu_notifier_invalidate_range_end to make sure * that the caller either sees the old (non-zero) value of * mmu_invalidate_in_progress or the new (incremented) value of * mmu_invalidate_seq. * * PowerPC Book3s HV KVM calls this under a per-page lock rather * than under kvm->mmu_lock, for scalability, so can't rely on * kvm->mmu_lock to keep things ordered. */ smp_rmb(); if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { lockdep_assert_held(&kvm->mmu_lock); /* * If mmu_invalidate_in_progress is non-zero, then the range maintained * by kvm_mmu_notifier_invalidate_range_start contains all addresses * that might be being invalidated. Note that it may include some false * positives, due to shortcuts when handing concurrent invalidations. */ if (unlikely(kvm->mmu_invalidate_in_progress)) { /* * Dropping mmu_lock after bumping mmu_invalidate_in_progress * but before updating the range is a KVM bug. */ if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA || kvm->mmu_invalidate_range_end == INVALID_GPA)) return 1; if (gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return 1; } if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } /* * This lockless version of the range-based retry check *must* be paired with a * call to the locked version after acquiring mmu_lock, i.e. this is safe to * use only as a pre-check to avoid contending mmu_lock. This version *will* * get false negatives and false positives. */ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { /* * Use READ_ONCE() to ensure the in-progress flag and sequence counter * are always read from memory, e.g. so that checking for retry in a * loop won't result in an infinite retry loop. Don't force loads for * start+end, as the key to avoiding infinite retry loops is observing * the 1=>0 transition of in-progress, i.e. getting false negatives * due to stale start+end values is acceptable. */ if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return true; return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */ bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); #else static inline void kvm_free_irq_routing(struct kvm *kvm) {} static inline int kvm_init_irq_routing(struct kvm *kvm) { return 0; } #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin) { return false; } #endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's * caller. Paired with the smp_mb__after_atomic in kvm_check_request. */ smp_wmb(); set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Request that don't require vCPU action should never be logged in * vcpu->requests. The vCPU won't clear the request, so it will stay * logged indefinitely and prevent the vCPU from entering the guest. */ BUILD_BUG_ON(!__builtin_constant_p(req) || (req & KVM_REQUEST_NO_ACTION)); __kvm_make_request(req, vcpu); } static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); } static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) { clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { if (kvm_test_request(req, vcpu)) { kvm_clear_request(req, vcpu); /* * Ensure the rest of the request is visible to kvm_check_request's * caller. Paired with the smp_wmb in kvm_make_request. */ smp_mb__after_atomic(); return true; } else { return false; } } #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool kvm_rebooting; #endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; }; /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; /* * create is called holding kvm->lock and any operations not suitable * to do while holding the lock should be deferred to init (see * below). */ int (*create)(struct kvm_device *dev, u32 type); /* * init is called after create if create is successful and is called * outside of holding kvm->lock. */ void (*init)(struct kvm_device *dev); /* * Destroy is responsible for freeing dev. * * Destroy may be called before or after destructors are called * on emulated I/O regions, depending on whether a reference is * held by a vcpu or other kvm component that gets destroyed * after the emulated I/O. */ void (*destroy)(struct kvm_device *dev); /* * Release is an alternative method to free the device. It is * called when the device file descriptor is closed. Once * release is called, the destroy method will not be called * anymore as the device is removed from the device list of * the VM. kvm->lock is held. */ void (*release)(struct kvm_device *dev); int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, unsigned long arg); int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma); }; struct kvm_device *kvm_device_from_filp(struct file *filp); int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; extern struct kvm_device_ops kvm_arm_vgic_v3_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.in_spin_loop = val; } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.dy_eligible = val; } #else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) { return (memslot && memslot->id < KVM_USER_MEM_SLOTS && !(memslot->flags & KVM_MEMSLOT_INVALID)); } struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS /* If we wakeup during the poll time, was it a sucessful poll? */ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return vcpu->valid_wakeup; } #else static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return true; } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ #ifdef CONFIG_HAVE_KVM_NO_POLL /* Callback that tells if we must not poll */ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); #else static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return false; } #endif /* CONFIG_HAVE_KVM_NO_POLL */ #ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); #else static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -ENOIOCTLCMD; } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { return 0; } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { vcpu->run->exit_reason = KVM_EXIT_INTR; vcpu->stat.signal_exits++; } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ /* * If more than one page is being (un)accounted, @virt must be the address of * the first page of a block of pages what were allocated together (i.e * accounted together). * * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() * is thread-safe. */ static inline void kvm_account_pgtable_pages(void *virt, int nr) { mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); } /* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This * value can be tuned to higher if e.g. PML is enabled on the host. */ #define KVM_DIRTY_RING_RSVD_ENTRIES 64 /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES 65536 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t size, bool is_write, bool is_exec, bool is_private) { vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; vcpu->run->memory_fault.gpa = gpa; vcpu->run->memory_fault.size = size; /* RWX flags are not (yet) defined or communicated to userspace. */ vcpu->run->memory_fault.flags = 0; if (is_private) vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) { return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) && kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; } #else static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ #ifdef CONFIG_KVM_PRIVATE_MEM int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order); #else static inline int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order) { KVM_BUG_ON(1, kvm); return -EIO; } #endif /* CONFIG_KVM_PRIVATE_MEM */ #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); #endif #ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM /** * kvm_gmem_populate() - Populate/prepare a GPA range with guest data * * @kvm: KVM instance * @gfn: starting GFN to be populated * @src: userspace-provided buffer containing data to copy into GFN range * (passed to @post_populate, and incremented on each iteration * if not NULL) * @npages: number of pages to copy from userspace-buffer * @post_populate: callback to issue for each gmem page that backs the GPA * range * @opaque: opaque data to pass to @post_populate callback * * This is primarily intended for cases where a gmem-backed GPA range needs * to be initialized with userspace-provided data prior to being mapped into * the guest as a private page. This should be called with the slots->lock * held so that caller-enforced invariants regarding the expected memory * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. * * Returns the number of pages that were populated. */ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, void __user *src, int order, void *opaque); long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); #endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range); #endif #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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Events for filesystem locks * * Copyright 2013 Jeff Layton <jlayton@poochiereds.net> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filelock #if !defined(_TRACE_FILELOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILELOCK_H #include <linux/tracepoint.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/kdev_t.h> #define show_fl_flags(val) \ __print_flags(val, "|", \ { FL_POSIX, "FL_POSIX" }, \ { FL_FLOCK, "FL_FLOCK" }, \ { FL_DELEG, "FL_DELEG" }, \ { FL_ACCESS, "FL_ACCESS" }, \ { FL_EXISTS, "FL_EXISTS" }, \ { FL_LEASE, "FL_LEASE" }, \ { FL_CLOSE, "FL_CLOSE" }, \ { FL_SLEEP, "FL_SLEEP" }, \ { FL_DOWNGRADE_PENDING, "FL_DOWNGRADE_PENDING" }, \ { FL_UNLOCK_PENDING, "FL_UNLOCK_PENDING" }, \ { FL_OFDLCK, "FL_OFDLCK" }) #define show_fl_type(val) \ __print_symbolic(val, \ { F_RDLCK, "F_RDLCK" }, \ { F_WRLCK, "F_WRLCK" }, \ { F_UNLCK, "F_UNLCK" }) TRACE_EVENT(locks_get_lock_context, TP_PROTO(struct inode *inode, int type, struct file_lock_context *ctx), TP_ARGS(inode, type, ctx), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned char, type) __field(struct file_lock_context *, ctx) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->type = type; __entry->ctx = ctx; ), TP_printk("dev=0x%x:0x%x ino=0x%lx type=%s ctx=%p", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, show_fl_type(__entry->type), __entry->ctx) ); DECLARE_EVENT_CLASS(filelock_lock, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock_core *, blocker) __field(fl_owner_t, owner) __field(unsigned int, pid) __field(unsigned int, flags) __field(unsigned char, type) __field(loff_t, fl_start) __field(loff_t, fl_end) __field(int, ret) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->blocker = fl ? fl->c.flc_blocker : NULL; __entry->owner = fl ? fl->c.flc_owner : NULL; __entry->pid = fl ? fl->c.flc_pid : 0; __entry->flags = fl ? fl->c.flc_flags : 0; __entry->type = fl ? fl->c.flc_type : 0; __entry->fl_start = fl ? fl->fl_start : 0; __entry->fl_end = fl ? fl->fl_end : 0; __entry->ret = ret; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->blocker, __entry->owner, __entry->pid, show_fl_flags(__entry->flags), show_fl_type(__entry->type), __entry->fl_start, __entry->fl_end, __entry->ret) ); DEFINE_EVENT(filelock_lock, posix_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, fcntl_setlk, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, locks_remove_posix, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, flock_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DECLARE_EVENT_CLASS(filelock_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(struct file_lease *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock_core *, blocker) __field(fl_owner_t, owner) __field(unsigned int, flags) __field(unsigned char, type) __field(unsigned long, break_time) __field(unsigned long, downgrade_time) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->blocker = fl ? fl->c.flc_blocker : NULL; __entry->owner = fl ? fl->c.flc_owner : NULL; __entry->flags = fl ? fl->c.flc_flags : 0; __entry->type = fl ? fl->c.flc_type : 0; __entry->break_time = fl ? fl->fl_break_time : 0; __entry->downgrade_time = fl ? fl->fl_downgrade_time : 0; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->blocker, __entry->owner, show_fl_flags(__entry->flags), show_fl_type(__entry->type), __entry->break_time, __entry->downgrade_time) ); DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); TRACE_EVENT(generic_add_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(int, wcount) __field(int, rcount) __field(int, icount) __field(dev_t, s_dev) __field(fl_owner_t, owner) __field(unsigned int, flags) __field(unsigned char, type) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->wcount = atomic_read(&inode->i_writecount); __entry->rcount = atomic_read(&inode->i_readcount); __entry->icount = atomic_read(&inode->i_count); __entry->owner = fl->c.flc_owner; __entry->flags = fl->c.flc_flags; __entry->type = fl->c.flc_type; ), TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->wcount, __entry->rcount, __entry->icount, __entry->owner, show_fl_flags(__entry->flags), show_fl_type(__entry->type)) ); TRACE_EVENT(leases_conflict, TP_PROTO(bool conflict, struct file_lease *lease, struct file_lease *breaker), TP_ARGS(conflict, lease, breaker), TP_STRUCT__entry( __field(void *, lease) __field(void *, breaker) __field(unsigned int, l_fl_flags) __field(unsigned int, b_fl_flags) __field(unsigned char, l_fl_type) __field(unsigned char, b_fl_type) __field(bool, conflict) ), TP_fast_assign( __entry->lease = lease; __entry->l_fl_flags = lease->c.flc_flags; __entry->l_fl_type = lease->c.flc_type; __entry->breaker = breaker; __entry->b_fl_flags = breaker->c.flc_flags; __entry->b_fl_type = breaker->c.flc_type; __entry->conflict = conflict; ), TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s", __entry->conflict, __entry->lease, show_fl_flags(__entry->l_fl_flags), show_fl_type(__entry->l_fl_type), __entry->breaker, show_fl_flags(__entry->b_fl_flags), show_fl_type(__entry->b_fl_type)) ); #endif /* _TRACE_FILELOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 29 29 7 1 6 1 1 1 1 1 2 256 253 252 2 6 251 66 66 67 19 19 80 70 70 43 2 2 2 2 1 2 2 1 2 2 2 2 2 1 2 1 1 19 254 254 50 50 50 48 50 49 9 9 91 90 91 91 89 90 91 89 1 91 90 91 91 91 76 76 75 76 76 21 1 1 3 1 1 1 96 92 6 6 6 6 2 98 4 1 7 50 54 1 2 91 91 13 9 9 9 9 11 11 9 87 16 14 14 14 14 14 14 14 79 9 9 51 46 1 88 91 90 6 1 79 90 78 88 88 88 88 21 15 36 88 88 50 46 88 87 67 87 88 88 88 47 37 76 3 4 3 7 5 18 18 1 2 6 7 1 3 1 1 1 78 78 78 78 78 78 78 1 78 66 11 11 56 72 72 72 72 72 81 79 72 2 3 58 23 81 73 2 75 20 55 13 6 309 209 82 81 2 206 205 144 64 6 5 1 4 36 35 13 10 5 4 2 25 23 1 4 3 1 3 1 2 1 12 98 3 1 6 4 57 3 2 5 4 5 3 15 13 5 3 65 40 65 65 65 65 64 65 7 13 11 13 10 2 3 3 13 3 5 10 3 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/bug.h> #include <linux/cpu_pm.h> #include <linux/entry-kvm.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/kvm.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> #include <linux/psci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS #include "trace_arm.h" #include <linux/uaccess.h> #include <asm/ptrace.h> #include <asm/mman.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/virt.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/kvm_pkvm.h> #include <asm/kvm_ptrauth.h> #include <asm/sections.h> #include <kvm/arm_hypercalls.h> #include <kvm/arm_pmu.h> #include <kvm/arm_psci.h> #include "sys_regs.h" static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT; enum kvm_wfx_trap_policy { KVM_WFX_NOTRAP_SINGLE_TASK, /* Default option */ KVM_WFX_NOTRAP, KVM_WFX_TRAP, }; static enum kvm_wfx_trap_policy kvm_wfi_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK; static enum kvm_wfx_trap_policy kvm_wfe_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK; DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector); DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_base); DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool vgic_present, kvm_arm_initialised; static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized); bool is_kvm_arm_initialised(void) { return kvm_arm_initialised; } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { int r = -EINVAL; if (cap->flags) return -EINVAL; if (kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(cap->cap)) return -EINVAL; switch (cap->cap) { case KVM_CAP_ARM_NISV_TO_USER: r = 0; set_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER, &kvm->arch.flags); break; case KVM_CAP_ARM_MTE: mutex_lock(&kvm->lock); if (system_supports_mte() && !kvm->created_vcpus) { r = 0; set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); } mutex_unlock(&kvm->lock); break; case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 0; set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); break; case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE: mutex_lock(&kvm->slots_lock); /* * To keep things simple, allow changing the chunk * size only when no memory slots have been created. */ if (kvm_are_all_memslots_empty(kvm)) { u64 new_cap = cap->args[0]; if (!new_cap || kvm_is_block_size_supported(new_cap)) { r = 0; kvm->arch.mmu.split_page_chunk_size = new_cap; } } mutex_unlock(&kvm->slots_lock); break; default: break; } return r; } static int kvm_arm_default_max_vcpus(void) { return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct * @type: kvm device type */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; mutex_init(&kvm->arch.config_lock); #ifdef CONFIG_LOCKDEP /* Clue in lockdep that the config_lock must be taken inside kvm->lock */ mutex_lock(&kvm->lock); mutex_lock(&kvm->arch.config_lock); mutex_unlock(&kvm->arch.config_lock); mutex_unlock(&kvm->lock); #endif kvm_init_nested(kvm); ret = kvm_share_hyp(kvm, kvm + 1); if (ret) return ret; ret = pkvm_init_host_vm(kvm); if (ret) goto err_unshare_kvm; if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) { ret = -ENOMEM; goto err_unshare_kvm; } cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask); ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu, type); if (ret) goto err_free_cpumask; kvm_vgic_early_init(kvm); kvm_timer_init_vm(kvm); /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->max_vcpus = kvm_arm_default_max_vcpus(); kvm_arm_init_hypercalls(kvm); bitmap_zero(kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES); return 0; err_free_cpumask: free_cpumask_var(kvm->arch.supported_cpus); err_unshare_kvm: kvm_unshare_hyp(kvm, kvm + 1); return ret; } vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } void kvm_arch_create_vm_debugfs(struct kvm *kvm) { kvm_sys_regs_create_debugfs(kvm); kvm_s2_ptdump_create_debugfs(kvm); } static void kvm_destroy_mpidr_data(struct kvm *kvm) { struct kvm_mpidr_data *data; mutex_lock(&kvm->arch.config_lock); data = rcu_dereference_protected(kvm->arch.mpidr_data, lockdep_is_held(&kvm->arch.config_lock)); if (data) { rcu_assign_pointer(kvm->arch.mpidr_data, NULL); synchronize_rcu(); kfree(data); } mutex_unlock(&kvm->arch.config_lock); } /** * kvm_arch_destroy_vm - destroy the VM data structure * @kvm: pointer to the KVM struct */ void kvm_arch_destroy_vm(struct kvm *kvm) { bitmap_free(kvm->arch.pmu_filter); free_cpumask_var(kvm->arch.supported_cpus); kvm_vgic_destroy(kvm); if (is_protected_kvm_enabled()) pkvm_destroy_hyp_vm(kvm); kvm_destroy_mpidr_data(kvm); kfree(kvm->arch.sysreg_masks); kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); kvm_arm_teardown_hypercalls(kvm); } static bool kvm_has_full_ptr_auth(void) { bool apa, gpa, api, gpi, apa3, gpa3; u64 isar1, isar2, val; /* * Check that: * * - both Address and Generic auth are implemented for a given * algorithm (Q5, IMPDEF or Q3) * - only a single algorithm is implemented. */ if (!system_has_full_ptr_auth()) return false; isar1 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); apa = !!FIELD_GET(ID_AA64ISAR1_EL1_APA_MASK, isar1); val = FIELD_GET(ID_AA64ISAR1_EL1_GPA_MASK, isar1); gpa = (val == ID_AA64ISAR1_EL1_GPA_IMP); api = !!FIELD_GET(ID_AA64ISAR1_EL1_API_MASK, isar1); val = FIELD_GET(ID_AA64ISAR1_EL1_GPI_MASK, isar1); gpi = (val == ID_AA64ISAR1_EL1_GPI_IMP); apa3 = !!FIELD_GET(ID_AA64ISAR2_EL1_APA3_MASK, isar2); val = FIELD_GET(ID_AA64ISAR2_EL1_GPA3_MASK, isar2); gpa3 = (val == ID_AA64ISAR2_EL1_GPA3_IMP); return (apa == gpa && api == gpi && apa3 == gpa3 && (apa + api + apa3) == 1); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; if (kvm && kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(ext)) return 0; switch (ext) { case KVM_CAP_IRQCHIP: r = vgic_present; break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: case KVM_CAP_MP_STATE: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: case KVM_CAP_ARM_NISV_TO_USER: case KVM_CAP_ARM_INJECT_EXT_DABT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: case KVM_CAP_ARM_SYSTEM_SUSPEND: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_COUNTER_OFFSET: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; break; case KVM_CAP_NR_VCPUS: /* * ARM64 treats KVM_CAP_NR_CPUS differently from all other * architectures, as it does not always bound it to * KVM_CAP_MAX_VCPUS. It should not matter much because * this is just an advisory value. */ r = min_t(unsigned int, num_online_cpus(), kvm_arm_default_max_vcpus()); break; case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: if (kvm) r = kvm->max_vcpus; else r = kvm_arm_default_max_vcpus(); break; case KVM_CAP_MSI_DEVID: if (!kvm) r = -EINVAL; else r = kvm->arch.vgic.msis_require_devid; break; case KVM_CAP_ARM_USER_IRQ: /* * 1: EL1_VTIMER, EL1_PTIMER, and PMU. * (bump this number if adding more devices) */ r = 1; break; case KVM_CAP_ARM_MTE: r = system_supports_mte(); break; case KVM_CAP_STEAL_TIME: r = kvm_arm_pvtime_supported(); break; case KVM_CAP_ARM_EL1_32BIT: r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1); break; case KVM_CAP_GUEST_DEBUG_HW_BPS: r = get_num_brps(); break; case KVM_CAP_GUEST_DEBUG_HW_WPS: r = get_num_wrps(); break; case KVM_CAP_ARM_PMU_V3: r = kvm_arm_support_pmu_v3(); break; case KVM_CAP_ARM_INJECT_SERROR_ESR: r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); break; case KVM_CAP_ARM_VM_IPA_SIZE: r = get_kvm_ipa_limit(); break; case KVM_CAP_ARM_SVE: r = system_supports_sve(); break; case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: r = kvm_has_full_ptr_auth(); break; case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE: if (kvm) r = kvm->arch.mmu.split_page_chunk_size; else r = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; break; case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES: r = kvm_supported_block_sizes(); break; case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES: r = BIT(0); break; default: r = 0; } return r; } long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; } struct kvm *kvm_arch_alloc_vm(void) { size_t sz = sizeof(struct kvm); if (!has_vhe()) return kzalloc(sz, GFP_KERNEL_ACCOUNT); return __vmalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM | __GFP_ZERO); } int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) return -EBUSY; if (id >= kvm->max_vcpus) return -EINVAL; return 0; } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err; spin_lock_init(&vcpu->arch.mp_state_lock); #ifdef CONFIG_LOCKDEP /* Inform lockdep that the config_lock is acquired after vcpu->mutex */ mutex_lock(&vcpu->mutex); mutex_lock(&vcpu->kvm->arch.config_lock); mutex_unlock(&vcpu->kvm->arch.config_lock); mutex_unlock(&vcpu->mutex); #endif /* Force users to call KVM_ARM_VCPU_INIT */ vcpu_clear_flag(vcpu, VCPU_INITIALIZED); vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; /* Set up the timer */ kvm_timer_vcpu_init(vcpu); kvm_pmu_vcpu_init(vcpu); kvm_arm_pvtime_vcpu_init(&vcpu->arch); vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; /* * This vCPU may have been created after mpidr_data was initialized. * Throw out the pre-computed mappings if that is the case which forces * KVM to fall back to iteratively searching the vCPUs. */ kvm_destroy_mpidr_data(vcpu->kvm); err = kvm_vgic_vcpu_init(vcpu); if (err) return err; return kvm_share_hyp(vcpu, vcpu + 1); } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { if (!is_protected_kvm_enabled()) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); else free_hyp_memcache(&vcpu->arch.pkvm_memcache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { } static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) { if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) { /* * Either we're running an L2 guest, and the API/APK bits come * from L1's HCR_EL2, or API/APK are both set. */ if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) { u64 val; val = __vcpu_sys_reg(vcpu, HCR_EL2); val &= (HCR_API | HCR_APK); vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); vcpu->arch.hcr_el2 |= val; } else { vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); } /* * Save the host keys if there is any chance for the guest * to use pauth, as the entry code will reload the guest * keys in that case. */ if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) { struct kvm_cpu_context *ctxt; ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt); ptrauth_save_keys(ctxt); } } } static bool kvm_vcpu_should_clear_twi(struct kvm_vcpu *vcpu) { if (unlikely(kvm_wfi_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK)) return kvm_wfi_trap_policy == KVM_WFX_NOTRAP; return single_task_running() && (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || vcpu->kvm->arch.vgic.nassgireq); } static bool kvm_vcpu_should_clear_twe(struct kvm_vcpu *vcpu) { if (unlikely(kvm_wfe_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK)) return kvm_wfe_trap_policy == KVM_WFX_NOTRAP; return single_task_running(); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_s2_mmu *mmu; int *last_ran; if (is_protected_kvm_enabled()) goto nommu; if (vcpu_has_nv(vcpu)) kvm_vcpu_load_hw_mmu(vcpu); mmu = vcpu->arch.hw_mmu; last_ran = this_cpu_ptr(mmu->last_vcpu_ran); /* * We guarantee that both TLBs and I-cache are private to each * vcpu. If detecting that a vcpu from the same VM has * previously run on the same physical CPU, call into the * hypervisor code to nuke the relevant contexts. * * We might get preempted before the vCPU actually runs, but * over-invalidation doesn't affect correctness. */ if (*last_ran != vcpu->vcpu_idx) { kvm_call_hyp(__kvm_flush_cpu_context, mmu); *last_ran = vcpu->vcpu_idx; } nommu: vcpu->cpu = cpu; kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_debug(vcpu); if (has_vhe()) kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); if (kvm_vcpu_should_clear_twe(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_TWE; else vcpu->arch.hcr_el2 |= HCR_TWE; if (kvm_vcpu_should_clear_twi(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_TWI; else vcpu->arch.hcr_el2 |= HCR_TWI; vcpu_set_pauth_traps(vcpu); if (is_protected_kvm_enabled()) { kvm_call_hyp_nvhe(__pkvm_vcpu_load, vcpu->kvm->arch.pkvm.handle, vcpu->vcpu_idx, vcpu->arch.hcr_el2); kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, &vcpu->arch.vgic_cpu.vgic_v3); } if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus)) vcpu_set_on_unsupported_cpu(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { if (is_protected_kvm_enabled()) { kvm_call_hyp(__vgic_v3_save_vmcr_aprs, &vcpu->arch.vgic_cpu.vgic_v3); kvm_call_hyp_nvhe(__pkvm_vcpu_put); } kvm_vcpu_put_debug(vcpu); kvm_arch_vcpu_put_fp(vcpu); if (has_vhe()) kvm_vcpu_put_vhe(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); kvm_vcpu_pmu_restore_host(vcpu); if (vcpu_has_nv(vcpu)) kvm_vcpu_put_hw_mmu(vcpu); kvm_arm_vmid_clear_active(); vcpu_clear_on_unsupported_cpu(vcpu); vcpu->cpu = -1; } static void __kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { spin_lock(&vcpu->arch.mp_state_lock); __kvm_arm_vcpu_power_off(vcpu); spin_unlock(&vcpu->arch.mp_state_lock); } bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED; } static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_SUSPENDED); kvm_make_request(KVM_REQ_SUSPEND, vcpu); kvm_vcpu_kick(vcpu); } static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_SUSPENDED; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { *mp_state = READ_ONCE(vcpu->arch.mp_state); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int ret = 0; spin_lock(&vcpu->arch.mp_state_lock); switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: WRITE_ONCE(vcpu->arch.mp_state, *mp_state); break; case KVM_MP_STATE_STOPPED: __kvm_arm_vcpu_power_off(vcpu); break; case KVM_MP_STATE_SUSPENDED: kvm_arm_vcpu_suspend(vcpu); break; default: ret = -EINVAL; } spin_unlock(&vcpu->arch.mp_state_lock); return ret; } /** * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled * @v: The VCPU pointer * * If the guest CPU is not waiting for interrupts or an interrupt line is * asserted, the CPU is by definition runnable. */ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return vcpu_mode_priv(vcpu); } #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) { return *vcpu_pc(vcpu); } #endif static void kvm_init_mpidr_data(struct kvm *kvm) { struct kvm_mpidr_data *data = NULL; unsigned long c, mask, nr_entries; u64 aff_set = 0, aff_clr = ~0UL; struct kvm_vcpu *vcpu; mutex_lock(&kvm->arch.config_lock); if (rcu_access_pointer(kvm->arch.mpidr_data) || atomic_read(&kvm->online_vcpus) == 1) goto out; kvm_for_each_vcpu(c, vcpu, kvm) { u64 aff = kvm_vcpu_get_mpidr_aff(vcpu); aff_set |= aff; aff_clr &= aff; } /* * A significant bit can be either 0 or 1, and will only appear in * aff_set. Use aff_clr to weed out the useless stuff. */ mask = aff_set ^ aff_clr; nr_entries = BIT_ULL(hweight_long(mask)); /* * Don't let userspace fool us. If we need more than a single page * to describe the compressed MPIDR array, just fall back to the * iterative method. Single vcpu VMs do not need this either. */ if (struct_size(data, cmpidr_to_idx, nr_entries) <= PAGE_SIZE) data = kzalloc(struct_size(data, cmpidr_to_idx, nr_entries), GFP_KERNEL_ACCOUNT); if (!data) goto out; data->mpidr_mask = mask; kvm_for_each_vcpu(c, vcpu, kvm) { u64 aff = kvm_vcpu_get_mpidr_aff(vcpu); u16 index = kvm_mpidr_index(data, aff); data->cmpidr_to_idx[index] = c; } rcu_assign_pointer(kvm->arch.mpidr_data, data); out: mutex_unlock(&kvm->arch.config_lock); } /* * Handle both the initialisation that is being done when the vcpu is * run for the first time, as well as the updates that must be * performed each time we get a new thread dealing with this vcpu. */ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; int ret; if (!kvm_vcpu_initialized(vcpu)) return -ENOEXEC; if (!kvm_arm_vcpu_is_finalized(vcpu)) return -EPERM; ret = kvm_arch_vcpu_run_map_fp(vcpu); if (ret) return ret; if (likely(vcpu_has_run_once(vcpu))) return 0; kvm_init_mpidr_data(kvm); if (likely(irqchip_in_kernel(kvm))) { /* * Map the VGIC hardware resources before running a vcpu the * first time on this VM. */ ret = kvm_vgic_map_resources(kvm); if (ret) return ret; } ret = kvm_finalize_sys_regs(vcpu); if (ret) return ret; /* * This needs to happen after any restriction has been applied * to the feature set. */ kvm_calculate_traps(vcpu); ret = kvm_timer_enable(vcpu); if (ret) return ret; ret = kvm_arm_pmu_v3_enable(vcpu); if (ret) return ret; if (is_protected_kvm_enabled()) { ret = pkvm_create_hyp_vm(kvm); if (ret) return ret; } mutex_lock(&kvm->arch.config_lock); set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags); mutex_unlock(&kvm->arch.config_lock); return ret; } bool kvm_arch_intc_initialized(struct kvm *kvm) { return vgic_initialized(kvm); } void kvm_arm_halt_guest(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) vcpu->arch.pause = true; kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP); } void kvm_arm_resume_guest(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; __kvm_vcpu_wake_up(vcpu); } } static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); rcuwait_wait_event(wait, (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) { /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } /* * Make sure we will observe a potential reset request if we've * observed a change to the power state. Pairs with the smp_wmb() in * kvm_psci_vcpu_on(). */ smp_rmb(); } /** * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior * @vcpu: The VCPU pointer * * Suspend execution of a vCPU until a valid wake event is detected, i.e. until * the vCPU is runnable. The vCPU may or may not be scheduled out, depending * on when a wake event arrives, e.g. there may already be a pending wake event. */ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) { /* * Sync back the state of the GIC CPU interface so that we have * the latest PMR and group enables. This ensures that * kvm_arch_vcpu_runnable has up-to-date data to decide whether * we have pending interrupts, e.g. when determining if the * vCPU should block. * * For the same reason, we want to tell GICv4 that we need * doorbells to be signalled, should an interrupt become pending. */ preempt_disable(); vcpu_set_flag(vcpu, IN_WFI); kvm_vgic_put(vcpu); preempt_enable(); kvm_vcpu_halt(vcpu); vcpu_clear_flag(vcpu, IN_WFIT); preempt_disable(); vcpu_clear_flag(vcpu, IN_WFI); kvm_vgic_load(vcpu); preempt_enable(); } static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) { if (!kvm_arm_vcpu_suspended(vcpu)) return 1; kvm_vcpu_wfi(vcpu); /* * The suspend state is sticky; we do not leave it until userspace * explicitly marks the vCPU as runnable. Request that we suspend again * later. */ kvm_make_request(KVM_REQ_SUSPEND, vcpu); /* * Check to make sure the vCPU is actually runnable. If so, exit to * userspace informing it of the wakeup condition. */ if (kvm_arch_vcpu_runnable(vcpu)) { memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; return 0; } /* * Otherwise, we were unblocked to process a different event, such as a * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to * process the event. */ return 1; } /** * check_vcpu_requests - check and handle pending vCPU requests * @vcpu: the VCPU pointer * * Return: 1 if we should enter the guest * 0 if we should exit to userspace * < 0 if we should exit to userspace, where the return value indicates * an error */ static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) return -EIO; if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) kvm_vcpu_sleep(vcpu); if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); /* * Clear IRQ_PENDING requests that were made to guarantee * that a VCPU sees new virtual interrupts. */ kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) kvm_update_stolen_time(vcpu); if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { /* The distributor enable bits were changed */ preempt_disable(); vgic_v4_put(vcpu); vgic_v4_load(vcpu); preempt_enable(); } if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) kvm_vcpu_reload_pmu(vcpu); if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu)) kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_check_request(KVM_REQ_SUSPEND, vcpu)) return kvm_vcpu_suspend(vcpu); if (kvm_dirty_ring_check_request(vcpu)) return 0; check_nested_vcpu_requests(vcpu); } return 1; } static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu) { if (likely(!vcpu_mode_is_32bit(vcpu))) return false; if (vcpu_has_nv(vcpu)) return true; return !kvm_supports_32bit_el0(); } /** * kvm_vcpu_exit_request - returns true if the VCPU should *not* enter the guest * @vcpu: The VCPU pointer * @ret: Pointer to write optional return code * * Returns: true if the VCPU needs to return to a preemptible + interruptible * and skip guest entry. * * This function disambiguates between two different types of exits: exits to a * preemptible + interruptible kernel context and exits to userspace. For an * exit to userspace, this function will write the return code to ret and return * true. For an exit to preemptible + interruptible kernel context (i.e. check * for pending work and re-enter), return true without writing to ret. */ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) { struct kvm_run *run = vcpu->run; /* * If we're using a userspace irqchip, then check if we need * to tell a userspace irqchip about timer or PMU level * changes and if so, exit to userspace (the actual level * state gets updated in kvm_timer_update_run and * kvm_pmu_update_run below). */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { if (kvm_timer_should_notify_user(vcpu) || kvm_pmu_should_notify_user(vcpu)) { *ret = -EINTR; run->exit_reason = KVM_EXIT_INTR; return true; } } if (unlikely(vcpu_on_unsupported_cpu(vcpu))) { run->exit_reason = KVM_EXIT_FAIL_ENTRY; run->fail_entry.hardware_entry_failure_reason = KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED; run->fail_entry.cpu = smp_processor_id(); *ret = 0; return true; } return kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } /* * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while * the vCPU is running. * * This must be noinstr as instrumentation may make use of RCU, and this is not * safe during the EQS. */ static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu) { int ret; guest_state_enter_irqoff(); ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); guest_state_exit_irqoff(); return ret; } /** * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code * @vcpu: The VCPU pointer * * This function is called through the VCPU_RUN ioctl called from user space. It * will execute VM code in a loop until the time slice for the process is used * or some emulation is needed from user space in which case the function will * return with return value 0 and with the kvm_run structure filled in with the * required data for the requested emulation. */ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; int ret; if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_handle_mmio_return(vcpu); if (ret <= 0) return ret; } vcpu_load(vcpu); if (!vcpu->wants_to_run) { ret = -EINTR; goto out; } kvm_sigset_activate(vcpu); ret = 1; run->exit_reason = KVM_EXIT_UNKNOWN; run->flags = 0; while (ret > 0) { /* * Check conditions before entering the guest */ ret = xfer_to_guest_mode_handle_work(vcpu); if (!ret) ret = 1; if (ret > 0) ret = check_vcpu_requests(vcpu); /* * Preparing the interrupts to be injected also * involves poking the GIC, which must be done in a * non-preemptible context. */ preempt_disable(); /* * The VMID allocator only tracks active VMIDs per * physical CPU, and therefore the VMID allocated may not be * preserved on VMID roll-over if the task was preempted, * making a thread's VMID inactive. So we need to call * kvm_arm_vmid_update() in non-premptible context. */ if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) && has_vhe()) __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch); kvm_pmu_flush_hwstate(vcpu); local_irq_disable(); kvm_vgic_flush_hwstate(vcpu); kvm_pmu_update_vcpu_events(vcpu); /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and * Documentation/virt/kvm/vcpu-requests.rst */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate(vcpu); if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); preempt_enable(); continue; } kvm_arch_vcpu_ctxflush_fp(vcpu); /************************************************************** * Enter the guest */ trace_kvm_entry(*vcpu_pc(vcpu)); guest_timing_enter_irqoff(); ret = kvm_arm_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; /* * Back from guest *************************************************************/ /* * We must sync the PMU state before the vgic state so * that the vgic can properly sample the updated state of the * interrupt line. */ kvm_pmu_sync_hwstate(vcpu); /* * Sync the vgic state before syncing the timer state because * the timer code needs to know if the virtual timer * interrupts are active. */ kvm_vgic_sync_hwstate(vcpu); /* * Sync the timer hardware state before enabling interrupts as * we don't want vtimer interrupts to race with syncing the * timer virtual interrupt state. */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); if (is_hyp_ctxt(vcpu)) kvm_timer_sync_nested(vcpu); kvm_arch_vcpu_ctxsync_fp(vcpu); /* * We must ensure that any pending interrupts are taken before * we exit guest timing so that timer ticks are accounted as * guest time. Transiently unmask interrupts so that any * pending interrupts are taken. * * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other * context synchronization event) is necessary to ensure that * pending interrupts are taken. */ if (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_IRQ) { local_irq_enable(); isb(); local_irq_disable(); } guest_timing_exit_irqoff(); local_irq_enable(); trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* Exit types that need handling before we can be preempted */ handle_exit_early(vcpu, ret); preempt_enable(); /* * The ARMv8 architecture doesn't give the hypervisor * a mechanism to prevent a guest from dropping to AArch32 EL0 * if implemented by the CPU. If we spot the guest in such * state and that we decided it wasn't supposed to do so (like * with the asymmetric AArch32 case), return to userspace with * a fatal error. */ if (vcpu_mode_is_bad_32bit(vcpu)) { /* * As we have caught the guest red-handed, decide that * it isn't fit for purpose anymore by making the vcpu * invalid. The VMM can try and fix it by issuing a * KVM_ARM_VCPU_INIT if it really wants to. */ vcpu_clear_flag(vcpu, VCPU_INITIALIZED); ret = ARM_EXCEPTION_IL; } ret = handle_exit(vcpu, ret); } /* Tell userspace about in-kernel device output levels */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { kvm_timer_update_run(vcpu); kvm_pmu_update_run(vcpu); } kvm_sigset_deactivate(vcpu); out: /* * In the unlikely event that we are returning to userspace * with pending exceptions or PC adjustment, commit these * adjustments in order to give userspace a consistent view of * the vcpu state. Note that this relies on __kvm_adjust_pc() * being preempt-safe on VHE. */ if (unlikely(vcpu_get_flag(vcpu, PENDING_EXCEPTION) || vcpu_get_flag(vcpu, INCREMENT_PC))) kvm_call_hyp(__kvm_adjust_pc, vcpu); vcpu_put(vcpu); return ret; } static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) { int bit_index; bool set; unsigned long *hcr; if (number == KVM_ARM_IRQ_CPU_IRQ) bit_index = __ffs(HCR_VI); else /* KVM_ARM_IRQ_CPU_FIQ */ bit_index = __ffs(HCR_VF); hcr = vcpu_hcr(vcpu); if (level) set = test_and_set_bit(bit_index, hcr); else set = test_and_clear_bit(bit_index, hcr); /* * If we didn't change anything, no need to wake up or kick other CPUs */ if (set == level) return 0; /* * The vcpu irq_lines field was updated, wake up sleeping VCPUs and * trigger a world-switch round on the running physical CPU to set the * virtual IRQ/FIQ fields in the HCR appropriately. */ kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return 0; } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status) { u32 irq = irq_level->irq; unsigned int irq_type, vcpu_id, irq_num; struct kvm_vcpu *vcpu = NULL; bool level = irq_level->level; irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; vcpu_id += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1); irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; trace_kvm_irq_line(irq_type, vcpu_id, irq_num, irq_level->level); switch (irq_type) { case KVM_ARM_IRQ_TYPE_CPU: if (irqchip_in_kernel(kvm)) return -ENXIO; vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); if (!vcpu) return -EINVAL; if (irq_num > KVM_ARM_IRQ_CPU_FIQ) return -EINVAL; return vcpu_interrupt_line(vcpu, irq_num, level); case KVM_ARM_IRQ_TYPE_PPI: if (!irqchip_in_kernel(kvm)) return -ENXIO; vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); if (!vcpu) return -EINVAL; if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, vcpu, irq_num, level, NULL); case KVM_ARM_IRQ_TYPE_SPI: if (!irqchip_in_kernel(kvm)) return -ENXIO; if (irq_num < VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, NULL, irq_num, level, NULL); } return -EINVAL; } static unsigned long system_supported_vcpu_features(void) { unsigned long features = KVM_VCPU_VALID_FEATURES; if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1)) clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features); if (!kvm_arm_support_pmu_v3()) clear_bit(KVM_ARM_VCPU_PMU_V3, &features); if (!system_supports_sve()) clear_bit(KVM_ARM_VCPU_SVE, &features); if (!kvm_has_full_ptr_auth()) { clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features); clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features); } if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT)) clear_bit(KVM_ARM_VCPU_HAS_EL2, &features); return features; } static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; int i; if (features & ~KVM_VCPU_VALID_FEATURES) return -ENOENT; for (i = 1; i < ARRAY_SIZE(init->features); i++) { if (init->features[i]) return -ENOENT; } if (features & ~system_supported_vcpu_features()) return -EINVAL; /* * For now make sure that both address/generic pointer authentication * features are requested by the userspace together. */ if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features) != test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features)) return -EINVAL; if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features)) return 0; /* MTE is incompatible with AArch32 */ if (kvm_has_mte(vcpu->kvm)) return -EINVAL; /* NV is incompatible with AArch32 */ if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features)) return -EINVAL; return 0; } static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; return !bitmap_equal(vcpu->kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); } static int kvm_setup_vcpu(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; int ret = 0; /* * When the vCPU has a PMU, but no PMU is set for the guest * yet, set the default one. */ if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu) ret = kvm_arm_set_default_pmu(kvm); /* Prepare for nested if required */ if (!ret && vcpu_has_nv(vcpu)) ret = kvm_vcpu_init_nested(vcpu); return ret; } static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; struct kvm *kvm = vcpu->kvm; int ret = -EINVAL; mutex_lock(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags) && kvm_vcpu_init_changed(vcpu, init)) goto out_unlock; bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); ret = kvm_setup_vcpu(vcpu); if (ret) goto out_unlock; /* Now we know what it is, we can reset it. */ kvm_reset_vcpu(vcpu); set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags); vcpu_set_flag(vcpu, VCPU_INITIALIZED); ret = 0; out_unlock: mutex_unlock(&kvm->arch.config_lock); return ret; } static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { int ret; if (init->target != KVM_ARM_TARGET_GENERIC_V8 && init->target != kvm_target_cpu()) return -EINVAL; ret = kvm_vcpu_init_check_features(vcpu, init); if (ret) return ret; if (!kvm_vcpu_initialized(vcpu)) return __kvm_vcpu_set_target(vcpu, init); if (kvm_vcpu_init_changed(vcpu, init)) return -EINVAL; kvm_reset_vcpu(vcpu); return 0; } static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { bool power_off = false; int ret; /* * Treat the power-off vCPU feature as ephemeral. Clear the bit to avoid * reflecting it in the finalized feature set, thus limiting its scope * to a single KVM_ARM_VCPU_INIT call. */ if (init->features[0] & BIT(KVM_ARM_VCPU_POWER_OFF)) { init->features[0] &= ~BIT(KVM_ARM_VCPU_POWER_OFF); power_off = true; } ret = kvm_vcpu_set_target(vcpu, init); if (ret) return ret; /* * Ensure a rebooted VM will fault in RAM pages and detect if the * guest MMU is turned off and flush the caches as needed. * * S2FWB enforces all memory accesses to RAM being cacheable, * ensuring that the data side is always coherent. We still * need to invalidate the I-cache though, as FWB does *not* * imply CTR_EL0.DIC. */ if (vcpu_has_run_once(vcpu)) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) stage2_unmap_vm(vcpu->kvm); else icache_inval_all_pou(); } vcpu_reset_hcr(vcpu); /* * Handle the "start in power-off" case. */ spin_lock(&vcpu->arch.mp_state_lock); if (power_off) __kvm_arm_vcpu_power_off(vcpu); else WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); spin_unlock(&vcpu->arch.mp_state_lock); return 0; } static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { memset(events, 0, sizeof(*events)); return __kvm_arm_vcpu_get_events(vcpu, events); } static int kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { int i; /* check whether the reserved field is zero */ for (i = 0; i < ARRAY_SIZE(events->reserved); i++) if (events->reserved[i]) return -EINVAL; /* check whether the pad field is zero */ for (i = 0; i < ARRAY_SIZE(events->exception.pad); i++) if (events->exception.pad[i]) return -EINVAL; return __kvm_arm_vcpu_set_events(vcpu, events); } long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; long r; switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; r = -EFAULT; if (copy_from_user(&init, argp, sizeof(init))) break; r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); break; } case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) break; r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; /* * We could owe a reset due to PSCI. Handle the pending reset * here to ensure userspace register accesses are ordered after * the reset. */ if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); if (ioctl == KVM_SET_ONE_REG) r = kvm_arm_set_reg(vcpu, ®); else r = kvm_arm_get_reg(vcpu, ®); break; } case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n; r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) break; r = -EPERM; if (!kvm_arm_vcpu_is_finalized(vcpu)) break; r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) break; n = reg_list.n; reg_list.n = kvm_arm_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) break; r = -E2BIG; if (n < reg_list.n) break; r = kvm_arm_copy_reg_indices(vcpu, user_list->reg); break; } case KVM_SET_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_set_attr(vcpu, &attr); break; } case KVM_GET_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_get_attr(vcpu, &attr); break; } case KVM_HAS_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_has_attr(vcpu, &attr); break; } case KVM_GET_VCPU_EVENTS: { struct kvm_vcpu_events events; if (kvm_arm_vcpu_get_events(vcpu, &events)) return -EINVAL; if (copy_to_user(argp, &events, sizeof(events))) return -EFAULT; return 0; } case KVM_SET_VCPU_EVENTS: { struct kvm_vcpu_events events; if (copy_from_user(&events, argp, sizeof(events))) return -EFAULT; return kvm_arm_vcpu_set_events(vcpu, &events); } case KVM_ARM_VCPU_FINALIZE: { int what; if (!kvm_vcpu_initialized(vcpu)) return -ENOEXEC; if (get_user(what, (const int __user *)argp)) return -EFAULT; return kvm_arm_vcpu_finalize(vcpu, what); } default: r = -EINVAL; } return r; } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { } static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { switch (FIELD_GET(KVM_ARM_DEVICE_ID_MASK, dev_addr->id)) { case KVM_ARM_DEVICE_VGIC_V2: if (!vgic_present) return -ENXIO; return kvm_set_legacy_vgic_v2_addr(kvm, dev_addr); default: return -ENODEV; } } static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_ARM_VM_SMCCC_CTRL: return kvm_vm_smccc_has_attr(kvm, attr); default: return -ENXIO; } } static int kvm_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_ARM_VM_SMCCC_CTRL: return kvm_vm_smccc_set_attr(kvm, attr); default: return -ENXIO; } } int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; switch (ioctl) { case KVM_CREATE_IRQCHIP: { int ret; if (!vgic_present) return -ENXIO; mutex_lock(&kvm->lock); ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); mutex_unlock(&kvm->lock); return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; if (copy_from_user(&dev_addr, argp, sizeof(dev_addr))) return -EFAULT; return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } case KVM_ARM_PREFERRED_TARGET: { struct kvm_vcpu_init init = { .target = KVM_ARM_TARGET_GENERIC_V8, }; if (copy_to_user(argp, &init, sizeof(init))) return -EFAULT; return 0; } case KVM_ARM_MTE_COPY_TAGS: { struct kvm_arm_copy_mte_tags copy_tags; if (copy_from_user(©_tags, argp, sizeof(copy_tags))) return -EFAULT; return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); } case KVM_ARM_SET_COUNTER_OFFSET: { struct kvm_arm_counter_offset offset; if (copy_from_user(&offset, argp, sizeof(offset))) return -EFAULT; return kvm_vm_ioctl_set_counter_offset(kvm, &offset); } case KVM_HAS_DEVICE_ATTR: { if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; return kvm_vm_has_attr(kvm, &attr); } case KVM_SET_DEVICE_ATTR: { if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; return kvm_vm_set_attr(kvm, &attr); } case KVM_ARM_GET_REG_WRITABLE_MASKS: { struct reg_mask_range range; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range); } default: return -EINVAL; } } /* unlocks vcpus from @vcpu_lock_idx and smaller */ static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) { struct kvm_vcpu *tmp_vcpu; for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&tmp_vcpu->mutex); } } void unlock_all_vcpus(struct kvm *kvm) { lockdep_assert_held(&kvm->lock); unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); } /* Returns true if all vcpus were locked, false otherwise */ bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; unsigned long c; lockdep_assert_held(&kvm->lock); /* * Any time a vcpu is in an ioctl (including running), the * core KVM code tries to grab the vcpu->mutex. * * By grabbing the vcpu->mutex of all VCPUs we ensure that no * other VCPUs can fiddle with the state while we access it. */ kvm_for_each_vcpu(c, tmp_vcpu, kvm) { if (!mutex_trylock(&tmp_vcpu->mutex)) { unlock_vcpus(kvm, c - 1); return false; } } return true; } static unsigned long nvhe_percpu_size(void) { return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) - (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_start); } static unsigned long nvhe_percpu_order(void) { unsigned long size = nvhe_percpu_size(); return size ? get_order(size) : 0; } static size_t pkvm_host_sve_state_order(void) { return get_order(pkvm_host_sve_state_size()); } /* A lookup table holding the hypervisor VA for each vector slot */ static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS]; static void kvm_init_vector_slot(void *base, enum arm64_hyp_spectre_vector slot) { hyp_spectre_vector_selector[slot] = __kvm_vector_slot2addr(base, slot); } static int kvm_init_vector_slots(void) { int err; void *base; base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); kvm_init_vector_slot(base, HYP_VECTOR_DIRECT); base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); if (kvm_system_needs_idmapped_vectors() && !is_protected_kvm_enabled()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) return err; } kvm_init_vector_slot(base, HYP_VECTOR_INDIRECT); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_INDIRECT); return 0; } static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); unsigned long tcr, ips; /* * Calculate the raw per-cpu offset without a translation from the * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. * Also drop the KASAN tag which gets in the way... */ params->tpidr_el2 = (unsigned long)kasan_reset_tag(per_cpu_ptr_nvhe_sym(__per_cpu_start, cpu)) - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); params->mair_el2 = read_sysreg(mair_el1); tcr = read_sysreg(tcr_el1); ips = FIELD_GET(TCR_IPS_MASK, tcr); if (cpus_have_final_cap(ARM64_KVM_HVHE)) { tcr |= TCR_EPD1_MASK; } else { tcr &= TCR_EL2_MASK; tcr |= TCR_EL2_RES1; } tcr &= ~TCR_T0SZ_MASK; tcr |= TCR_T0SZ(hyp_va_bits); tcr &= ~TCR_EL2_PS_MASK; tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips); if (lpa2_is_enabled()) tcr |= TCR_EL2_DS; params->tcr_el2 = tcr; params->pgd_pa = kvm_mmu_get_httbr(); if (is_protected_kvm_enabled()) params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS; else params->hcr_el2 = HCR_HOST_NVHE_FLAGS; if (cpus_have_final_cap(ARM64_KVM_HVHE)) params->hcr_el2 |= HCR_E2H; params->vttbr = params->vtcr = 0; /* * Flush the init params from the data cache because the struct will * be read while the MMU is off. */ kvm_flush_dcache_to_poc(params, sizeof(*params)); } static void hyp_install_host_vector(void) { struct kvm_nvhe_init_params *params; struct arm_smccc_res res; /* Switch from the HYP stub to our own HYP init vector */ __hyp_set_vectors(kvm_get_idmap_vector()); /* * Call initialization code, and switch to the full blown HYP code. * If the cpucaps haven't been finalized yet, something has gone very * wrong, and hyp will crash and burn when it uses any * cpus_have_*_cap() wrapper. */ BUG_ON(!system_capabilities_finalized()); params = this_cpu_ptr_nvhe_sym(kvm_init_params); arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), virt_to_phys(params), &res); WARN_ON(res.a0 != SMCCC_RET_SUCCESS); } static void cpu_init_hyp_mode(void) { hyp_install_host_vector(); /* * Disabling SSBD on a non-VHE system requires us to enable SSBS * at EL2. */ if (this_cpu_has_cap(ARM64_SSBS) && arm64_get_spectre_v4_state() == SPECTRE_VULNERABLE) { kvm_call_hyp_nvhe(__kvm_enable_ssbs); } } static void cpu_hyp_reset(void) { if (!is_kernel_in_hyp_mode()) __hyp_reset_vectors(); } /* * EL2 vectors can be mapped and rerouted in a number of ways, * depending on the kernel configuration and CPU present: * * - If the CPU is affected by Spectre-v2, the hardening sequence is * placed in one of the vector slots, which is executed before jumping * to the real vectors. * * - If the CPU also has the ARM64_SPECTRE_V3A cap, the slot * containing the hardening sequence is mapped next to the idmap page, * and executed before jumping to the real vectors. * * - If the CPU only has the ARM64_SPECTRE_V3A cap, then an * empty slot is selected, mapped next to the idmap page, and * executed before jumping to the real vectors. * * Note that ARM64_SPECTRE_V3A is somewhat incompatible with * VHE, as we don't have hypervisor-specific mappings. If the system * is VHE and yet selects this capability, it will be ignored. */ static void cpu_set_hyp_vector(void) { struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); void *vector = hyp_spectre_vector_selector[data->slot]; if (!is_protected_kvm_enabled()) *this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)vector; else kvm_call_hyp_nvhe(__pkvm_cpu_set_vector, data->slot); } static void cpu_hyp_init_context(void) { kvm_init_host_cpu_context(host_data_ptr(host_ctxt)); kvm_init_host_debug_data(); if (!is_kernel_in_hyp_mode()) cpu_init_hyp_mode(); } static void cpu_hyp_init_features(void) { cpu_set_hyp_vector(); if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); if (vgic_present) kvm_vgic_init_cpu_hardware(); } static void cpu_hyp_reinit(void) { cpu_hyp_reset(); cpu_hyp_init_context(); cpu_hyp_init_features(); } static void cpu_hyp_init(void *discard) { if (!__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reinit(); __this_cpu_write(kvm_hyp_initialized, 1); } } static void cpu_hyp_uninit(void *discard) { if (__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reset(); __this_cpu_write(kvm_hyp_initialized, 0); } } int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration * disabled, but not with preemption disabled. The former is * enough to ensure correctness, but most of the helpers * expect the later and will throw a tantrum otherwise. */ preempt_disable(); cpu_hyp_init(NULL); kvm_vgic_cpu_up(); kvm_timer_cpu_up(); preempt_enable(); return 0; } void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); if (!is_protected_kvm_enabled()) cpu_hyp_uninit(NULL); } #ifdef CONFIG_CPU_PM static int hyp_init_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { /* * kvm_hyp_initialized is left with its old value over * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should * re-enable hyp. */ switch (cmd) { case CPU_PM_ENTER: if (__this_cpu_read(kvm_hyp_initialized)) /* * don't update kvm_hyp_initialized here * so that the hyp will be re-enabled * when we resume. See below. */ cpu_hyp_reset(); return NOTIFY_OK; case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: if (__this_cpu_read(kvm_hyp_initialized)) /* The hyp was enabled before suspend. */ cpu_hyp_reinit(); return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; static void __init hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } static void __init hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); } #else static inline void __init hyp_cpu_pm_init(void) { } static inline void __init hyp_cpu_pm_exit(void) { } #endif static void __init init_cpu_logical_map(void) { unsigned int cpu; /* * Copy the MPIDR <-> logical CPU ID mapping to hyp. * Only copy the set of online CPUs whose features have been checked * against the finalized system capabilities. The hypervisor will not * allow any other CPUs from the `possible` set to boot. */ for_each_online_cpu(cpu) hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu); } #define init_psci_0_1_impl_state(config, what) \ config.psci_0_1_ ## what ## _implemented = psci_ops.what static bool __init init_psci_relay(void) { /* * If PSCI has not been initialized, protected KVM cannot install * itself on newly booted CPUs. */ if (!psci_ops.get_version) { kvm_err("Cannot initialize protected mode without PSCI\n"); return false; } kvm_host_psci_config.version = psci_ops.get_version(); kvm_host_psci_config.smccc_version = arm_smccc_get_version(); if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) { kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids(); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off); init_psci_0_1_impl_state(kvm_host_psci_config, migrate); } return true; } static int __init init_subsystems(void) { int err = 0; /* * Enable hardware so that subsystem initialisation can access EL2. */ on_each_cpu(cpu_hyp_init, NULL, 1); /* * Register CPU lower-power notifier */ hyp_cpu_pm_init(); /* * Init HYP view of VGIC */ err = kvm_vgic_hyp_init(); switch (err) { case 0: vgic_present = true; break; case -ENODEV: case -ENXIO: /* * No VGIC? No pKVM for you. * * Protected mode assumes that VGICv3 is present, so no point * in trying to hobble along if vgic initialization fails. */ if (is_protected_kvm_enabled()) goto out; /* * Otherwise, userspace could choose to implement a GIC for its * guest on non-cooperative hardware. */ vgic_present = false; err = 0; break; default: goto out; } /* * Init HYP architected timer support */ err = kvm_timer_hyp_init(vgic_present); if (err) goto out; kvm_register_perf_callbacks(NULL); out: if (err) hyp_cpu_pm_exit(); if (err || !is_protected_kvm_enabled()) on_each_cpu(cpu_hyp_uninit, NULL, 1); return err; } static void __init teardown_subsystems(void) { kvm_unregister_perf_callbacks(); hyp_cpu_pm_exit(); } static void __init teardown_hyp_mode(void) { bool free_sve = system_supports_sve() && is_protected_kvm_enabled(); int cpu; free_hyp_pgds(); for_each_possible_cpu(cpu) { free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT); free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); if (free_sve) { struct cpu_sve_state *sve_state; sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state; free_pages((unsigned long) sve_state, pkvm_host_sve_state_order()); } } } static int __init do_pkvm_init(u32 hyp_va_bits) { void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)); int ret; preempt_disable(); cpu_hyp_init_context(); ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size, num_possible_cpus(), kern_hyp_va(per_cpu_base), hyp_va_bits); cpu_hyp_init_features(); /* * The stub hypercalls are now disabled, so set our local flag to * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); return ret; } static u64 get_hyp_id_aa64pfr0_el1(void) { /* * Track whether the system isn't affected by spectre/meltdown in the * hypervisor's view of id_aa64pfr0_el1, used for protected VMs. * Although this is per-CPU, we make it global for simplicity, e.g., not * to have to worry about vcpu migration. * * Unlike for non-protected VMs, userspace cannot override this for * protected VMs. */ u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3)); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), arm64_get_meltdown_state() == SPECTRE_UNAFFECTED); return val; } static void kvm_hyp_init_symbols(void) { kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); kvm_nvhe_sym(id_aa64isar2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; /* * Flush entire BSS since part of its data containing init symbols is read * while the MMU is off. */ kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start), kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start)); } static int __init kvm_hyp_init_protection(u32 hyp_va_bits) { void *addr = phys_to_virt(hyp_mem_base); int ret; ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP); if (ret) return ret; ret = do_pkvm_init(hyp_va_bits); if (ret) return ret; free_hyp_pgds(); return 0; } static int init_pkvm_host_sve_state(void) { int cpu; if (!system_supports_sve()) return 0; /* Allocate pages for host sve state in protected mode. */ for_each_possible_cpu(cpu) { struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order()); if (!page) return -ENOMEM; per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page); } /* * Don't map the pages in hyp since these are only used in protected * mode, which will (re)create its own mapping when initialized. */ return 0; } /* * Finalizes the initialization of hyp mode, once everything else is initialized * and the initialziation process cannot fail. */ static void finalize_init_hyp_mode(void) { int cpu; if (system_supports_sve() && is_protected_kvm_enabled()) { for_each_possible_cpu(cpu) { struct cpu_sve_state *sve_state; sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state; per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } } } static void pkvm_hyp_init_ptrauth(void) { struct kvm_cpu_context *hyp_ctxt; int cpu; for_each_possible_cpu(cpu) { hyp_ctxt = per_cpu_ptr_nvhe_sym(kvm_hyp_ctxt, cpu); hyp_ctxt->sys_regs[APIAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIAKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIBKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIBKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDAKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDBKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDBKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APGAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APGAKEYHI_EL1] = get_random_long(); } } /* Inits Hyp-mode on all online CPUs */ static int __init init_hyp_mode(void) { u32 hyp_va_bits; int cpu; int err = -ENOMEM; /* * The protected Hyp-mode cannot be initialized if the memory pool * allocation has failed. */ if (is_protected_kvm_enabled() && !hyp_mem_base) goto out_err; /* * Allocate Hyp PGD and setup Hyp identity mapping */ err = kvm_mmu_init(&hyp_va_bits); if (err) goto out_err; /* * Allocate stack pages for Hypervisor-mode */ for_each_possible_cpu(cpu) { unsigned long stack_base; stack_base = __get_free_pages(GFP_KERNEL, NVHE_STACK_SHIFT - PAGE_SHIFT); if (!stack_base) { err = -ENOMEM; goto out_err; } per_cpu(kvm_arm_hyp_stack_base, cpu) = stack_base; } /* * Allocate and initialize pages for Hypervisor-mode percpu regions. */ for_each_possible_cpu(cpu) { struct page *page; void *page_addr; page = alloc_pages(GFP_KERNEL, nvhe_percpu_order()); if (!page) { err = -ENOMEM; goto out_err; } page_addr = page_address(page); memcpy(page_addr, CHOOSE_NVHE_SYM(__per_cpu_start), nvhe_percpu_size()); kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu] = (unsigned long)page_addr; } /* * Map the Hyp-code called directly from the host */ err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start), kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC); if (err) { kvm_err("Cannot map world-switch code\n"); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start), kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO); if (err) { kvm_err("Cannot map .hyp.rodata section\n"); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__start_rodata), kvm_ksym_ref(__end_rodata), PAGE_HYP_RO); if (err) { kvm_err("Cannot map rodata section\n"); goto out_err; } /* * .hyp.bss is guaranteed to be placed at the beginning of the .bss * section thanks to an assertion in the linker script. Map it RW and * the rest of .bss RO. */ err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_start), kvm_ksym_ref(__hyp_bss_end), PAGE_HYP); if (err) { kvm_err("Cannot map hyp bss section: %d\n", err); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_end), kvm_ksym_ref(__bss_stop), PAGE_HYP_RO); if (err) { kvm_err("Cannot map bss section\n"); goto out_err; } /* * Map the Hyp stack pages */ for_each_possible_cpu(cpu) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); char *stack_base = (char *)per_cpu(kvm_arm_hyp_stack_base, cpu); err = create_hyp_stack(__pa(stack_base), ¶ms->stack_hyp_va); if (err) { kvm_err("Cannot map hyp stack\n"); goto out_err; } /* * Save the stack PA in nvhe_init_params. This will be needed * to recreate the stack mapping in protected nVHE mode. * __hyp_pa() won't do the right thing there, since the stack * has been mapped in the flexible private VA space. */ params->stack_pa = __pa(stack_base); } for_each_possible_cpu(cpu) { char *percpu_begin = (char *)kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu]; char *percpu_end = percpu_begin + nvhe_percpu_size(); /* Map Hyp percpu pages */ err = create_hyp_mappings(percpu_begin, percpu_end, PAGE_HYP); if (err) { kvm_err("Cannot map hyp percpu region\n"); goto out_err; } /* Prepare the CPU initialization parameters */ cpu_prepare_hyp_mode(cpu, hyp_va_bits); } kvm_hyp_init_symbols(); if (is_protected_kvm_enabled()) { if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH)) pkvm_hyp_init_ptrauth(); init_cpu_logical_map(); if (!init_psci_relay()) { err = -ENODEV; goto out_err; } err = init_pkvm_host_sve_state(); if (err) goto out_err; err = kvm_hyp_init_protection(hyp_va_bits); if (err) { kvm_err("Failed to init hyp memory protection\n"); goto out_err; } } return 0; out_err: teardown_hyp_mode(); kvm_err("error initializing Hyp mode: %d\n", err); return err; } struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu = NULL; struct kvm_mpidr_data *data; unsigned long i; mpidr &= MPIDR_HWID_BITMASK; rcu_read_lock(); data = rcu_dereference(kvm->arch.mpidr_data); if (data) { u16 idx = kvm_mpidr_index(data, mpidr); vcpu = kvm_get_vcpu(kvm, data->cmpidr_to_idx[idx]); if (mpidr != kvm_vcpu_get_mpidr_aff(vcpu)) vcpu = NULL; } rcu_read_unlock(); if (vcpu) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu)) return vcpu; } return NULL; } bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) { return irqchip_in_kernel(kvm); } bool kvm_arch_has_irq_bypass(void) { return true; } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); } void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_arm_halt_guest(irqfd->kvm); } void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_arm_resume_guest(irqfd->kvm); } /* Initialize Hyp-mode and memory mappings on all CPUs */ static __init int kvm_arm_init(void) { int err; bool in_hyp_mode; if (!is_hyp_mode_available()) { kvm_info("HYP mode not available\n"); return -ENODEV; } if (kvm_get_mode() == KVM_MODE_NONE) { kvm_info("KVM disabled from command line\n"); return -ENODEV; } err = kvm_sys_reg_table_init(); if (err) { kvm_info("Error initializing system register tables"); return err; } in_hyp_mode = is_kernel_in_hyp_mode(); if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) || cpus_have_final_cap(ARM64_WORKAROUND_1508412)) kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ "Only trusted guests should be used on this system.\n"); err = kvm_set_ipa_limit(); if (err) return err; err = kvm_arm_init_sve(); if (err) return err; err = kvm_arm_vmid_alloc_init(); if (err) { kvm_err("Failed to initialize VMID allocator.\n"); return err; } if (!in_hyp_mode) { err = init_hyp_mode(); if (err) goto out_err; } err = kvm_init_vector_slots(); if (err) { kvm_err("Cannot initialise vector slots\n"); goto out_hyp; } err = init_subsystems(); if (err) goto out_hyp; kvm_info("%s%sVHE mode initialized successfully\n", in_hyp_mode ? "" : (is_protected_kvm_enabled() ? "Protected " : "Hyp "), in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ? "h" : "n")); /* * FIXME: Do something reasonable if kvm_init() fails after pKVM * hypervisor protection is finalized. */ err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (err) goto out_subs; /* * This should be called after initialization is done and failure isn't * possible anymore. */ if (!in_hyp_mode) finalize_init_hyp_mode(); kvm_arm_initialised = true; return 0; out_subs: teardown_subsystems(); out_hyp: if (!in_hyp_mode) teardown_hyp_mode(); out_err: kvm_arm_vmid_alloc_free(); return err; } static int __init early_kvm_mode_cfg(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "none") == 0) { kvm_mode = KVM_MODE_NONE; return 0; } if (!is_hyp_mode_available()) { pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n"); return 0; } if (strcmp(arg, "protected") == 0) { if (!is_kernel_in_hyp_mode()) kvm_mode = KVM_MODE_PROTECTED; else pr_warn_once("Protected KVM not available with VHE\n"); return 0; } if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) { kvm_mode = KVM_MODE_DEFAULT; return 0; } if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) { kvm_mode = KVM_MODE_NV; return 0; } return -EINVAL; } early_param("kvm-arm.mode", early_kvm_mode_cfg); static int __init early_kvm_wfx_trap_policy_cfg(char *arg, enum kvm_wfx_trap_policy *p) { if (!arg) return -EINVAL; if (strcmp(arg, "trap") == 0) { *p = KVM_WFX_TRAP; return 0; } if (strcmp(arg, "notrap") == 0) { *p = KVM_WFX_NOTRAP; return 0; } return -EINVAL; } static int __init early_kvm_wfi_trap_policy_cfg(char *arg) { return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfi_trap_policy); } early_param("kvm-arm.wfi_trap_policy", early_kvm_wfi_trap_policy_cfg); static int __init early_kvm_wfe_trap_policy_cfg(char *arg) { return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfe_trap_policy); } early_param("kvm-arm.wfe_trap_policy", early_kvm_wfe_trap_policy_cfg); enum kvm_mode kvm_get_mode(void) { return kvm_mode; } module_init(kvm_arm_init); |
| 52 52 2 20 2 15 13 4 175 112 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /* * Return the ->prev pointer of a list_head in an rcu safe way. Don't * access it directly. * * Any list traversed with list_bidir_prev_rcu() must never use * list_del_rcu(). Doing so will poison the ->prev pointer that * list_bidir_prev_rcu() relies on, which will result in segfaults. * To prevent these segfaults, use list_bidir_del_rcu() instead * of list_del_rcu(). */ #define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() 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 list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * list_bidir_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * In contrast to list_del_rcu() doesn't poison the prev pointer thus * allowing backwards traversal via list_bidir_prev_rcu(). * * Note: list_empty() on entry does not return true after this because * the entry is in a special undefined state that permits RCU-based * lockfree reverse traversal. In particular this means that we can not * poison the forward and backwards pointers that may still be used for * walking the list. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another list-mutation * primitive, such as list_bidir_del_rcu() or list_add_rcu(), running on * this same list. However, it is perfectly legal to run concurrently * with the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that list_del_rcu() and list_bidir_del_rcu() must not be used on * the same list. * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_bidir_del_rcu(struct list_head *entry) { __list_del_entry(entry); } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. * * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the next element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_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, * 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_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_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_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, * 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_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_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 49 147 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Max time spent waiting on a runqueue: */ unsigned long long max_run_delay; /* Min time spent waiting on a runqueue: */ unsigned long long min_run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; s64 vlag; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for * * @server_has_tasks() returns true if @server_pick return a * runnable task. */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; struct list_head trc_holdout_list; struct list_head trc_blkd_node; int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; struct address_space *faults_disabled_mapping; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized begin_new_exec() * - set it with set_task_comm() * - strscpy_pad() to ensure it is always NUL-terminated and * zero-padded * - task_lock() to ensure the operation is atomic and the name is * fully updated. */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; # ifdef CONFIG_DEBUG_RSEQ /* * This is a place holder to save a copy of the rseq fields for * validation of read-only fields. The struct rseq has a * variable-length array at the end, so it cannot be used * directly. Reserve a size large enough for the known fields. */ char rseq_fields[sizeof(struct rseq)]; # endif #endif #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think * about adding more or developing a dynamic method. So far, * none of these are justified. */ union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. * Report frozen tasks as uninterruptible. */ if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); #define set_task_comm(tsk, from) ({ \ BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ __set_task_comm(tsk, from, false); \ }) /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } #else static inline void scheduler_ipi(void) { } #endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) void sched_dynamic_klp_enable(void); void sched_dynamic_klp_disable(void); DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { klp_sched_try_switch(); return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { klp_sched_try_switch(); return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); #include <linux/spinlock.h> /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif #endif |
| 20 20 20 20 20 20 20 20 20 20 121 | 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * * This driver produces cryptographically secure pseudorandom data. It is divided * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. * - Userspace reader/writer interfaces. * - Sysctl interface. * * The high level overview is that there is one input pool, into which * various pieces of data are hashed. Prior to initialization, some of that * data is then "credited" as having a certain number of bits of entropy. * When enough bits of entropy are available, the hash is finalized and * handed as a key to a stream cipher that expands it indefinitely for * various consumers. This key is periodically refreshed as the various * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/nodemask.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include <linux/siphash.h> #include <linux/sched/isolation.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #ifdef CONFIG_VDSO_GETRANDOM #include <vdso/getrandom.h> #include <vdso/datapage.h> #include <vdso/vsyscall.h> #endif #include <asm/archrandom.h> #include <asm/processor.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> /********************************************************************* * * Initialization and readiness waiting. * * Much of the RNG infrastructure is devoted to various dependencies * being able to wait until the RNG has collected enough entropy and * is ready for safe consumption. * *********************************************************************/ /* * crng_init is protected by base_crng->lock, and only increases * its value (from empty->early->ready). */ static enum { CRNG_EMPTY = 0, /* Little to no entropy collected */ CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ } crng_init __read_mostly = CRNG_EMPTY; static DEFINE_STATIC_KEY_FALSE(crng_is_ready); #define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) /* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; static ATOMIC_NOTIFIER_HEAD(random_ready_notifier); /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); /* * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. */ bool rng_is_initialized(void) { return crng_ready(); } EXPORT_SYMBOL(rng_is_initialized); static void __cold crng_set_ready(struct work_struct *work) { static_branch_enable(&crng_is_ready); } /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); /* * Wait for the input pool to be seeded and thus guaranteed to supply * cryptographically secure random numbers. This applies to: the /dev/urandom * device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64, * long} family of functions. Using any of these functions without first * calling this function forfeits the guarantee of security. * * Returns: 0 if the input pool has been seeded. * -ERESTARTSYS if the function was interrupted by a signal. */ int wait_for_random_bytes(void) { while (!crng_ready()) { int ret; try_to_generate_entropy(); ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ); if (ret) return ret > 0 ? 0 : ret; } return 0; } EXPORT_SYMBOL(wait_for_random_bytes); /* * Add a callback function that will be invoked when the crng is initialised, * or immediately if it already has been. Only use this is you are absolutely * sure it is required. Most users should instead be able to test * `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`. */ int __cold execute_with_initialized_rng(struct notifier_block *nb) { unsigned long flags; int ret = 0; spin_lock_irqsave(&random_ready_notifier.lock, flags); if (crng_ready()) nb->notifier_call(nb, 0, NULL); else ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb); spin_unlock_irqrestore(&random_ready_notifier.lock, flags); return ret; } #define warn_unseeded_randomness() \ if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \ printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \ __func__, (void *)_RET_IP_, crng_init) /********************************************************************* * * Fast key erasure RNG, the "crng". * * These functions expand entropy from the entropy extractor into * long streams for external consumption using the "fast key erasure" * RNG described at <https://blog.cr.yp.to/20170723-random.html>. * * There are a few exported interfaces for use by other drivers: * * void get_random_bytes(void *buf, size_t len) * u8 get_random_u8() * u16 get_random_u16() * u32 get_random_u32() * u32 get_random_u32_below(u32 ceil) * u32 get_random_u32_above(u32 floor) * u32 get_random_u32_inclusive(u32 floor, u32 ceil) * u64 get_random_u64() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to * a read from /dev/urandom. The u8, u16, u32, u64, long family of * functions may be higher performance for one-off random integers, * because they do a bit of buffering and do not invoke reseeding * until the buffer is emptied. * *********************************************************************/ enum { CRNG_RESEED_START_INTERVAL = HZ, CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); unsigned long generation; spinlock_t lock; } base_crng = { .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; struct crng { u8 key[CHACHA_KEY_SIZE]; unsigned long generation; local_lock_t lock; }; static DEFINE_PER_CPU(struct crng, crngs) = { .generation = ULONG_MAX, .lock = INIT_LOCAL_LOCK(crngs.lock), }; /* * Return the interval until the next reseeding, which is normally * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval * proportional to the uptime. */ static unsigned int crng_reseed_interval(void) { static bool early_boot = true; if (unlikely(READ_ONCE(early_boot))) { time64_t uptime = ktime_get_seconds(); if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } return CRNG_RESEED_INTERVAL; } /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ static void extract_entropy(void *buf, size_t len); /* This extracts a new crng key from the input pool. */ static void crng_reseed(struct work_struct *work) { static DECLARE_DELAYED_WORK(next_reseed, crng_reseed); unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; /* Immediately schedule the next reseeding, so that it fires sooner rather than later. */ if (likely(system_unbound_wq)) queue_delayed_work(system_unbound_wq, &next_reseed, crng_reseed_interval()); extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, * and update the generation counter. We avoid hitting ULONG_MAX, * because the per-cpu crngs are initialized to ULONG_MAX, so this * forces new CPUs that come online to always initialize. */ spin_lock_irqsave(&base_crng.lock, flags); memcpy(base_crng.key, key, sizeof(base_crng.key)); next_gen = base_crng.generation + 1; if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); #ifdef CONFIG_VDSO_GETRANDOM /* base_crng.generation's invalid value is ULONG_MAX, while * _vdso_rng_data.generation's invalid value is 0, so add one to the * former to arrive at the latter. Use smp_store_release so that this * is ordered with the write above to base_crng.generation. Pairs with * the smp_rmb() before the syscall in the vDSO code. * * Cast to unsigned long for 32-bit architectures, since atomic 64-bit * operations are not supported on those architectures. This is safe * because base_crng.generation is a 32-bit value. On big-endian * architectures it will be stored in the upper 32 bits, but that's okay * because the vDSO side only checks whether the value changed, without * actually using or interpreting the value. */ smp_store_release((unsigned long *)&__arch_get_k_vdso_rng_data()->generation, next_gen + 1); #endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); } /* * This generates a ChaCha block using the provided key, and then * immediately overwrites that key with half the block. It returns * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. * * The returned ChaCha state contains within it a copy of the old * key value, at index 4, so the state should always be zeroed out * immediately after using in order to maintain forward secrecy. * If the state cannot be erased in a timely manner, then it is * safer to set the random_data parameter to &chacha_state[4] so * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { u8 first_block[CHACHA_BLOCK_SIZE]; BUG_ON(random_data_len > 32); chacha_init_consts(chacha_state); memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE); memset(&chacha_state[12], 0, sizeof(u32) * 4); chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } /* * This function returns a ChaCha state that you may use for generating * random data. It also returns up to 32 bytes on its own of random data * that may be used; random_data_len may not be greater than 32. */ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { unsigned long flags; struct crng *crng; BUG_ON(random_data_len > 32); /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not * ready, we do fast key erasure with the base_crng directly, extracting * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); /* * If our per-cpu crng is older than the base_crng, then it means * somebody reseeded the base_crng. In that case, we do fast key * erasure on the base_crng, and use its output as the new key * for our per-cpu crng. This brings us up to date with base_crng. */ if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock); crng_fast_key_erasure(base_crng.key, chacha_state, crng->key, sizeof(crng->key)); crng->generation = base_crng.generation; spin_unlock(&base_crng.lock); } /* * Finally, when we've made it this far, our per-cpu crng has an up * to date key, and we can do fast key erasure with it to produce * some random data and a ChaCha state for the caller. All other * branches of this function are "unlikely", so most of the time we * should wind up here immediately. */ crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len); local_unlock_irqrestore(&crngs.lock, flags); } static void _get_random_bytes(void *buf, size_t len) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 tmp[CHACHA_BLOCK_SIZE]; size_t first_block_len; if (!len) return; first_block_len = min_t(size_t, 32, len); crng_make_state(chacha_state, buf, first_block_len); len -= first_block_len; buf += first_block_len; while (len) { if (len < CHACHA_BLOCK_SIZE) { chacha20_block(chacha_state, tmp); memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } chacha20_block(chacha_state, buf); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } memzero_explicit(chacha_state, sizeof(chacha_state)); } /* * This returns random bytes in arbitrary quantities. The quality of the * random bytes is good as /dev/urandom. In order to ensure that the * randomness provided by this function is okay, the function * wait_for_random_bytes() should be called and return 0 at least once * at any point prior. */ void get_random_bytes(void *buf, size_t len) { warn_unseeded_randomness(); _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(struct iov_iter *iter) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 block[CHACHA_BLOCK_SIZE]; size_t ret = 0, copied; if (unlikely(!iov_iter_count(iter))) return 0; /* * Immediately overwrite the ChaCha key at index 4 with random * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); /* * However, if we're doing a read of len <= 32, we don't need to * use chacha_state after, so we can simply return those bytes to * the user directly. */ if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter); goto out_zero_chacha; } for (;;) { chacha20_block(chacha_state, block); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; copied = copy_to_iter(block, sizeof(block), iter); ret += copied; if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); out_zero_chacha: memzero_explicit(chacha_state, sizeof(chacha_state)); return ret ? ret : -EFAULT; } /* * Batched entropy returns random integers. The quality of the random * number is good as /dev/urandom. In order to ensure that the randomness * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ #define DEFINE_BATCHED_ENTROPY(type) \ struct batch_ ##type { \ /* \ * We make this 1.5x a ChaCha block, so that we get the \ * remaining 32 bytes from fast key erasure, plus one full \ * block from the detached ChaCha state. We can increase \ * the size of this later if needed so long as we keep the \ * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ */ \ type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ local_lock_t lock; \ unsigned long generation; \ unsigned int position; \ }; \ \ static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ .position = UINT_MAX \ }; \ \ type get_random_ ##type(void) \ { \ type ret; \ unsigned long flags; \ struct batch_ ##type *batch; \ unsigned long next_gen; \ \ warn_unseeded_randomness(); \ \ if (!crng_ready()) { \ _get_random_bytes(&ret, sizeof(ret)); \ return ret; \ } \ \ local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ batch = raw_cpu_ptr(&batched_entropy_##type); \ \ next_gen = READ_ONCE(base_crng.generation); \ if (batch->position >= ARRAY_SIZE(batch->entropy) || \ next_gen != batch->generation) { \ _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ batch->position = 0; \ batch->generation = next_gen; \ } \ \ ret = batch->entropy[batch->position]; \ batch->entropy[batch->position] = 0; \ ++batch->position; \ local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ return ret; \ } \ EXPORT_SYMBOL(get_random_ ##type); DEFINE_BATCHED_ENTROPY(u8) DEFINE_BATCHED_ENTROPY(u16) DEFINE_BATCHED_ENTROPY(u32) DEFINE_BATCHED_ENTROPY(u64) u32 __get_random_u32_below(u32 ceil) { /* * This is the slow path for variable ceil. It is still fast, most of * the time, by doing traditional reciprocal multiplication and * opportunistically comparing the lower half to ceil itself, before * falling back to computing a larger bound, and then rejecting samples * whose lower half would indicate a range indivisible by ceil. The use * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable * in 32-bits. */ u32 rand = get_random_u32(); u64 mult; /* * This function is technically undefined for ceil == 0, and in fact * for the non-underscored constant version in the header, we build bug * on that. But for the non-constant case, it's convenient to have that * evaluate to being a straight call to get_random_u32(), so that * get_random_u32_inclusive() can work over its whole range without * undefined behavior. */ if (unlikely(!ceil)) return rand; mult = (u64)ceil * rand; if (unlikely((u32)mult < ceil)) { u32 bound = -ceil % ceil; while (unlikely((u32)mult < bound)) mult = (u64)ceil * get_random_u32(); } return mult >> 32; } EXPORT_SYMBOL(__get_random_u32_below); #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both * the per-cpu crng and all batches, so that we serve fresh * randomness. */ per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX; per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; return 0; } #endif /********************************************************************** * * Entropy accumulation and extraction routines. * * Callers may add entropy via: * * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * * static void credit_init_bits(size_t bits) * * Finally, extract entropy via: * * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; static struct { struct blake2s_state hash; spinlock_t lock; unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 }, .hash.outlen = BLAKE2S_HASH_SIZE, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; static void _mix_pool_bytes(const void *buf, size_t len) { blake2s_update(&input_pool.hash, buf, len); } /* * This function adds bytes into the input pool. It does not * update the initialization bit counter; the caller should call * credit_init_bits if this is appropriate. */ static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; struct { unsigned long rdseed[32 / sizeof(long)]; size_t counter; } block; size_t i, longs; for (i = 0; i < ARRAY_SIZE(block.rdseed);) { longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } block.rdseed[i++] = random_get_entropy(); } spin_lock_irqsave(&input_pool.lock, flags); /* seed = HASHPRF(last_key, entropy_input) */ blake2s_final(&input_pool.hash, seed); /* next_key = HASHPRF(seed, RDSEED || 0) */ block.counter = 0; blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed)); blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); while (len) { i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed)); len -= i; buf += i; } memzero_explicit(seed, sizeof(seed)); memzero_explicit(&block, sizeof(block)); } #define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) static void __cold _credit_init_bits(size_t bits) { static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; if (!bits) return; add = min_t(size_t, bits, POOL_BITS); orig = READ_ONCE(input_pool.init_bits); do { new = min_t(unsigned int, POOL_BITS, orig + add); } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); #ifdef CONFIG_VDSO_GETRANDOM WRITE_ONCE(__arch_get_k_vdso_rng_data()->is_ready, true); #endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); if (urandom_warning.missed) pr_notice("%d urandom warning(s) missed due to ratelimiting\n", urandom_warning.missed); } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { spin_lock_irqsave(&base_crng.lock, flags); /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ if (crng_init == CRNG_EMPTY) { extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_init = CRNG_EARLY; } spin_unlock_irqrestore(&base_crng.lock, flags); } } /********************************************************************** * * Entropy collection routines. * * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * * void add_device_randomness(const void *buf, size_t len); * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); * void add_bootloader_randomness(const void *buf, size_t len); * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). * This would be things like MAC addresses or serial numbers, or the * read-out of the RTC. This does *not* credit any actual entropy to * the pool, but it initializes the pool to different values for devices * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * * add_bootloader_randomness() is called by bootloader drivers, such as EFI * and device tree, and credits its input depending on whether or not the * command line option 'random.trust_bootloader'. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, * and then force-reseeds the crng so that it takes effect immediately. * * add_interrupt_randomness() uses the interrupt timing as random * inputs to the entropy pool. Using the cycle counters and the irq source * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * * add_input_randomness() uses the input layer interrupt timing, as well * as the event type information from the hardware. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the * entropy pool. Note that high-speed solid state drives with very low * seek times do not make for good sources of entropy, as their seek * times are usually fairly consistent. * * The last two routines try to estimate how many bits of entropy * to credit. They do this by keeping track of the first and second * order deltas of the event timings. * **********************************************************************/ static bool trust_cpu __initdata = true; static bool trust_bootloader __initdata = true; static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } static int __init parse_trust_bootloader(char *arg) { return kstrtobool(arg, &trust_bootloader); } early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { unsigned long flags, entropy = random_get_entropy(); /* * Encode a representation of how long the system has been suspended, * in a way that is distinct from prior system suspends. */ ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&action, sizeof(action)); _mix_pool_bytes(stamps, sizeof(stamps)); _mix_pool_bytes(&entropy, sizeof(entropy)); spin_unlock_irqrestore(&input_pool.lock, flags); if (crng_ready() && (action == PM_RESTORE_PREPARE || (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { crng_reseed(NULL); pr_notice("crng reseeded on system resumption\n"); } return 0; } static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; /* * This is called extremely early, before time keeping functionality is * available, but arch randomness is. Interrupts are not yet enabled. */ void __init random_init_early(const char *command_line) { unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; size_t i, longs, arch_bits; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } arch_bits -= sizeof(*entropy) * 8; ++i; } _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); _mix_pool_bytes(command_line, strlen(command_line)); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); else if (trust_cpu) _credit_init_bits(arch_bits); } /* * This is called a little bit after the prior function, and now there is * access to timestamps counters. Interrupts are not yet enabled. */ void __init random_init(void) { unsigned long entropy = random_get_entropy(); ktime_t now = ktime_get_real(); _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(&entropy, sizeof(entropy)); add_latent_entropy(); /* * If we were initialized by the cpu or bootloader before jump labels * or workqueues are initialized, then we should enable the static * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); WARN_ON(register_pm_notifier(&pm_notifier)); WARN(!entropy, "Missing cycle counter and fallback timer; RNG " "entropy collection will consequently suffer."); } /* * Add device- or boot-specific data to the input pool to help * initialize it. * * None of this adds any entropy; it is meant to avoid the problem of * the entropy pool having similar initial state across largely * identical devices. */ void add_device_randomness(const void *buf, size_t len) { unsigned long entropy = random_get_entropy(); unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); /* * Interface for in-kernel drivers of true hardware RNGs. Those devices * may produce endless random bits, so this function will sleep for * some amount of time after, if the sleep_after parameter is true. */ void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after) { mix_pool_bytes(buf, len); credit_init_bits(entropy); /* * Throttle writing to once every reseed interval, unless we're not yet * initialized or no entropy is credited. */ if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy)) schedule_timeout_interruptible(crng_reseed_interval()); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* * Handle random seed passed by bootloader, and credit it depending * on the command line option 'random.trust_bootloader'. */ void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); /* * Handle a new unique VM ID, which is unique, not secret, so we * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { add_device_randomness(unique_vm_id, len); if (crng_ready()) { crng_reseed(NULL); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } #if IS_MODULE(CONFIG_VMGENID) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); #endif struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; struct timer_list mix; }; static void mix_interrupt_randomness(struct timer_list *work); static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT #define FASTMIX_PERM SIPHASH_PERMUTATION .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }, #else #define FASTMIX_PERM HSIPHASH_PERMUTATION .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }, #endif .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) }; /* * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the * four-word SipHash state, while v represents a two-word input. */ static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { s[3] ^= v1; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v1; s[3] ^= v2; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v2; } #ifdef CONFIG_SMP /* * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ * randomness() may schedule mix_interrupt_randomness(), and * set the MIX_INFLIGHT flag. However, because the worker can * be scheduled on a different CPU during this period, that * flag will never be cleared. For that reason, we zero out * the flag here, which runs just after workqueues are onlined * for the CPU again. This also has the effect of setting the * irq randomness count to zero so that new accumulated irqs * are fresh. */ per_cpu_ptr(&irq_randomness, cpu)->count = 0; return 0; } #endif static void mix_interrupt_randomness(struct timer_list *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* * The size of the copied stack pool is explicitly 2 longs so that we * only ever ingest half of the siphash output each time, retaining * the other half as the next "key" that carries over. The entropy is * supposed to be sufficiently dispersed between bits so on average * we don't wind up "losing" some. */ unsigned long pool[2]; unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); if (fast_pool != this_cpu_ptr(&irq_randomness)) { local_irq_enable(); return; } /* * Copy the pool to the stack so that the mixer always has a * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); mix_pool_bytes(pool, sizeof(pool)); credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8)); memzero_explicit(pool, sizeof(pool)); } void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; fast_mix(fast_pool->pool, entropy, (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; fast_pool->count |= MIX_INFLIGHT; if (!timer_pending(&fast_pool->mix)) { fast_pool->mix.expires = jiffies; add_timer_on(&fast_pool->mix, raw_smp_processor_id()); } } EXPORT_SYMBOL_GPL(add_interrupt_randomness); /* There is one of these per entropy source */ struct timer_rand_state { unsigned long last_time; long last_delta, last_delta2; }; /* * This function adds entropy to the entropy "pool" by using timing * delays. It uses the timer_rand_state structure to make an estimate * of how many bits of entropy this call has added to the pool. The * value "num" is also added to the pool; it should somehow describe * the type of event that just happened. */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { unsigned long entropy = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; unsigned int bits; /* * If we're in a hard IRQ, add_interrupt_randomness() will be called * sometime after, so mix into the fast pool. */ if (in_hardirq()) { fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); } else { spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(&num, sizeof(num)); spin_unlock_irqrestore(&input_pool.lock, flags); } if (crng_ready()) return; /* * Calculate number of bits of randomness we probably added. * We take into account the first, second and third-order deltas * in order to make our estimate. */ delta = now - READ_ONCE(state->last_time); WRITE_ONCE(state->last_time, now); delta2 = delta - READ_ONCE(state->last_delta); WRITE_ONCE(state->last_delta, delta); delta3 = delta2 - READ_ONCE(state->last_delta2); WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; if (delta2 < 0) delta2 = -delta2; if (delta3 < 0) delta3 = -delta3; if (delta > delta2) delta = delta2; if (delta > delta3) delta = delta3; /* * delta is now minimum absolute delta. Round down by 1 bit * on general principles, and limit entropy estimate to 11 bits. */ bits = min(fls(delta >> 1), 11); /* * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() * will run after this, which uses a different crediting scheme of 1 bit * per every 64 interrupts. In order to let that function do accounting * close to the one in this function, we credit a full 64/64 bit per bit, * and then subtract one to account for the extra one added. */ if (in_hardirq()) this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; else _credit_init_bits(bits); } void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { static unsigned char last_value; static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; /* Ignore autorepeat and the like. */ if (value == last_value) return; last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); } EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) return; /* First major is 1, so we get >= 0x200 here. */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); } EXPORT_SYMBOL_GPL(add_disk_randomness); void __cold rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; /* * If kzalloc returns null, we just won't use that entropy * source. */ state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); if (state) { state->last_time = INITIAL_JIFFIES; disk->random = state; } } #endif struct entropy_timer_state { unsigned long entropy; struct timer_list timer; atomic_t samples; unsigned int samples_per_bit; }; /* * Each time the timer fires, we expect that we got an unpredictable jump in * the cycle counter. Even if the timer is running on another CPU, the timer * activity will be touching the stack of the CPU that is generating entropy. * * Note that we don't re-arm the timer in the timer itself - we are happy to be * scheduled away, since that just makes the load more complex, but we do not * want the timer to keep ticking unless the entropy loop is running. * * So the re-arming always happens in the entropy loop itself. */ static void __cold entropy_timer(struct timer_list *timer) { struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); unsigned long entropy = random_get_entropy(); mix_pool_bytes(&entropy, sizeof(entropy)); if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0) credit_init_bits(1); } /* * If we have an actual cycle counter, see if we can generate enough entropy * with timing noise. */ static void __cold try_to_generate_entropy(void) { enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1]; struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); int cpu = -1; for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { stack->entropy = random_get_entropy(); if (stack->entropy != last) ++num_different; last = stack->entropy; } stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT) return; atomic_set(&stack->samples, 0); timer_setup_on_stack(&stack->timer, entropy_timer, 0); while (!crng_ready() && !signal_pending(current)) { /* * Check !timer_pending() and then ensure that any previous callback has finished * executing by checking try_to_del_timer_sync(), before queueing the next one. */ if (!timer_pending(&stack->timer) && try_to_del_timer_sync(&stack->timer) >= 0) { struct cpumask timer_cpus; unsigned int num_cpus; /* * Preemption must be disabled here, both to read the current CPU number * and to avoid scheduling a timer on a dead CPU. */ preempt_disable(); /* Only schedule callbacks on timer CPUs that are online. */ cpumask_and(&timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); num_cpus = cpumask_weight(&timer_cpus); /* In very bizarre case of misconfiguration, fallback to all online. */ if (unlikely(num_cpus == 0)) { timer_cpus = *cpu_online_mask; num_cpus = cpumask_weight(&timer_cpus); } /* Basic CPU round-robin, which avoids the current CPU. */ do { cpu = cpumask_next(cpu, &timer_cpus); if (cpu >= nr_cpu_ids) cpu = cpumask_first(&timer_cpus); } while (cpu == smp_processor_id() && num_cpus > 1); /* Expiring the timer at `jiffies` means it's the next tick. */ stack->timer.expires = jiffies; add_timer_on(&stack->timer, cpu); preempt_enable(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); schedule(); stack->entropy = random_get_entropy(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); del_timer_sync(&stack->timer); destroy_timer_on_stack(&stack->timer); } /********************************************************************** * * Userspace reader/writer interfaces. * * getrandom(2) is the primary modern interface into the RNG and should * be used in preference to anything else. * * Reading from /dev/random has the same functionality as calling * getrandom(2) with flags=0. In earlier versions, however, it had * vastly different semantics and should therefore be avoided, to * prevent backwards compatibility issues. * * Reading from /dev/urandom has the same functionality as calling * getrandom(2) with flags=GRND_INSECURE. Because it does not block * waiting for the RNG to be ready, it should not be used. * * Writing to either /dev/random or /dev/urandom adds entropy to * the input pool but does not credit it. * * Polling on /dev/random indicates when the RNG is initialized, on * the read side, and when it wants new entropy, on the write side. * * Both /dev/random and /dev/urandom have the same set of ioctls for * adding entropy, getting the entropy count, zeroing the count, and * reseeding the crng. * **********************************************************************/ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } ret = import_ubuf(ITER_DEST, ubuf, len, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { poll_wait(file, &crng_init_wait, wait); return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } static ssize_t write_pool_user(struct iov_iter *iter) { u8 block[BLAKE2S_BLOCK_SIZE]; ssize_t ret = 0; size_t copied; if (unlikely(!iov_iter_count(iter))) return 0; for (;;) { copied = copy_from_iter(block, sizeof(block), iter); ret += copied; mix_pool_bytes(block, copied); if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); return ret ? ret : -EFAULT; } static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { return write_pool_user(iter); } static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; /* * Opportunistically attempt to initialize the RNG on platforms that * have fast cycle counters, but don't (for now) require it to succeed. */ if (!crng_ready()) try_to_generate_entropy(); if (!crng_ready()) { if (!ratelimit_disable && maxwarn <= 0) ++urandom_warning.missed; else if (ratelimit_disable || __ratelimit(&urandom_warning)) { --maxwarn; pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", current->comm, iov_iter_count(iter)); } } return get_random_bytes_user(iter); } static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; if (!crng_ready() && ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || (kiocb->ki_filp->f_flags & O_NONBLOCK))) return -EAGAIN; ret = wait_for_random_bytes(); if (ret != 0) return ret; return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { int __user *p = (int __user *)arg; int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; if (ent_count < 0) return -EINVAL; credit_init_bits(ent_count); return 0; case RNDADDENTROPY: { struct iov_iter iter; ssize_t ret; int len; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; if (get_user(len, p++)) return -EFAULT; ret = import_ubuf(ITER_SOURCE, p, len, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); if (unlikely(ret < 0)) return ret; /* Since we're crediting, enforce that it was all written into the pool. */ if (unlikely(ret != len)) return -EFAULT; credit_init_bits(ent_count); return 0; } case RNDZAPENTCNT: case RNDCLEARPOOL: /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; crng_reseed(NULL); return 0; default: return -EINVAL; } } static int random_fasync(int fd, struct file *filp, int on) { return fasync_helper(fd, filp, on, &fasync); } const struct file_operations random_fops = { .read_iter = random_read_iter, .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { .read_iter = urandom_read_iter, .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /******************************************************************** * * Sysctl interface. * * These are partly unused legacy knobs with dummy values to not break * userspace and partly still useful things. They are usually accessible * in /proc/sys/kernel/random/ and are as follows: * * - boot_id - a UUID representing the current boot. * * - uuid - a random UUID, different each time the file is read. * * - poolsize - the number of bits of entropy that the input pool can * hold, tied to the POOL_BITS constant. * * - entropy_avail - the number of bits of entropy currently in the * input pool. Always <= poolsize. * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL. * It is writable to avoid breaking old userspaces, but writing * to it does not change any behavior of the RNG. * ********************************************************************/ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; /* * This function is used to return both the bootid UUID, and random * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ static int proc_do_uuid(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; char uuid_string[UUID_STRING_LEN + 1]; struct ctl_table fake_table = { .data = uuid_string, .maxlen = UUID_STRING_LEN }; if (write) return -EPERM; uuid = table->data; if (!uuid) { uuid = tmp_uuid; generate_random_uuid(uuid); } else { static DEFINE_SPINLOCK(bootid_spinlock); spin_lock(&bootid_spinlock); if (!uuid[8]) generate_random_uuid(uuid); spin_unlock(&bootid_spinlock); } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "entropy_avail", .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "write_wakeup_threshold", .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "urandom_min_reseed_secs", .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", .mode = 0444, .proc_handler = proc_do_uuid, }, }; /* * random_init() is called before sysctl_init(), * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { register_sysctl_init("kernel/random", random_table); return 0; } device_initcall(random_sysctls_init); #endif |
| 77 2 1 75 3 1 1 1 41 41 39 1 32 2 2 1 1 35 2 46 1 38 38 2 1 34 1 34 2 5 2 40 4 6 13 6 5 6 13 13 7 5 1 3 6 1 1 1 7 5 50 6 46 15 7 7 12 8 2 2 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 | // 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); /* * Either userspace has already configured NR_IRQS or * the vgic has already been initialized and vgic_init() * supplied a default amount of SPIs. */ if (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, inti |