585 585 585 548 1105 1105 9 157 20 1105 1105 1105 1105 158 158 158 158 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 // SPDX-License-Identifier: GPL-2.0-only #include <linux/stat.h> #include <linux/sysctl.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/hash.h> #include <linux/kmemleak.h> #include <linux/user_namespace.h> #define UCOUNTS_HASHTABLE_BITS 10 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; static DEFINE_SPINLOCK(ucounts_lock); #define ucounts_hashfn(ns, uid) \ hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \ UCOUNTS_HASHTABLE_BITS) #define ucounts_hashentry(ns, uid) \ (ucounts_hashtable + ucounts_hashfn(ns, uid)) #ifdef CONFIG_SYSCTL static struct ctl_table_set * set_lookup(struct ctl_table_root *root) { return &current_user_ns()->set; } static int set_is_seen(struct ctl_table_set *set) { return &current_user_ns()->set == set; } static int set_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct user_namespace *user_ns = container_of(head->set, struct user_namespace, set); int mode; /* Allow users with CAP_SYS_RESOURCE unrestrained access */ if (ns_capable(user_ns, CAP_SYS_RESOURCE)) mode = (table->mode & S_IRWXU) >> 6; else /* Allow all others at most read-only access */ mode = table->mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = set_permissions, }; #define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(int), \ .mode = 0644, \ .proc_handler = proc_dointvec_minmax, \ .extra1 = SYSCTL_ZERO, \ .extra2 = SYSCTL_INT_MAX, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), UCOUNT_ENTRY("max_pid_namespaces"), UCOUNT_ENTRY("max_uts_namespaces"), UCOUNT_ENTRY("max_ipc_namespaces"), UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), #ifdef CONFIG_INOTIFY_USER UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), #endif { } }; #endif /* CONFIG_SYSCTL */ bool setup_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < UCOUNT_COUNTS; i++) { tbl[i].data = &ns->ucount_max[i]; } ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl); } if (!ns->sysctls) { kfree(tbl); retire_sysctl_set(&ns->set); return false; } #endif return true; } void retire_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; tbl = ns->sysctls->ctl_table_arg; unregister_sysctl_table(ns->sysctls); retire_sysctl_set(&ns->set); kfree(tbl); #endif } static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent) { struct ucounts *ucounts; hlist_for_each_entry(ucounts, hashent, node) { if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) return ucounts; } return NULL; } static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; new->ns = ns; new->uid = uid; new->count = 0; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); } else { hlist_add_head(&new->node, hashent); ucounts = new; } } if (ucounts->count == INT_MAX) ucounts = NULL; else ucounts->count += 1; spin_unlock_irq(&ucounts_lock); return ucounts; } static void put_ucounts(struct ucounts *ucounts) { unsigned long flags; spin_lock_irqsave(&ucounts_lock, flags); ucounts->count -= 1; if (!ucounts->count) hlist_del_init(&ucounts->node); else ucounts = NULL; spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); } static inline bool atomic_inc_below(atomic_t *v, int u) { int c, old; c = atomic_read(v); for (;;) { if (unlikely(c >= u)) return false; old = atomic_cmpxchg(v, c, c+1); if (likely(old == c)) return true; c = old; } } struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type) { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; ucounts = get_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { int max; tns = iter->ns; max = READ_ONCE(tns->ucount_max[type]); if (!atomic_inc_below(&iter->ucount[type], max)) goto fail; } return ucounts; fail: bad = iter; for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) atomic_dec(&iter->ucount[type]); put_ucounts(ucounts); return NULL; } void dec_ucount(struct ucounts *ucounts, enum ucount_type type) { struct ucounts *iter; for (iter = ucounts; iter; iter = iter->ns->ucounts) { int dec = atomic_dec_if_positive(&iter->ucount[type]); WARN_ON_ONCE(dec < 0); } put_ucounts(ucounts); } static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL static struct ctl_table_header *user_header; static struct ctl_table empty[1]; /* * It is necessary to register the user directory in the * default set so that registrations in the child sets work * properly. */ user_header = register_sysctl("user", empty); kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif return 0; } subsys_initcall(user_namespace_sysctl_init);
5 5 1 4 3 3 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_tunnel __rcu *tunnel6_handlers __read_mostly; static struct xfrm6_tunnel __rcu *tunnel46_handlers __read_mostly; static DEFINE_MUTEX(tunnel6_mutex); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -EEXIST; int priority = handler->priority; mutex_lock(&tunnel6_mutex); for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t->priority > priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&tunnel6_mutex); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_register); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -ENOENT; mutex_lock(&tunnel6_mutex); for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } mutex_unlock(&tunnel6_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_deregister); #define for_each_tunnel_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int tunnel6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol tunnel6_protocol = { .handler = tunnel6_rcv, .err_handler = tunnel6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static const struct inet6_protocol tunnel46_protocol = { .handler = tunnel46_rcv, .err_handler = tunnel46_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static int __init tunnel6_init(void) { if (inet6_add_protocol(&tunnel6_protocol, IPPROTO_IPV6)) { pr_err("%s: can't add protocol\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&tunnel46_protocol, IPPROTO_IPIP)) { pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); return -EAGAIN; } return 0; } static void __exit tunnel6_fini(void) { if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) pr_err("%s: can't remove protocol\n", __func__); } module_init(tunnel6_init); module_exit(tunnel6_fini); MODULE_LICENSE("GPL");
1614 283 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 */ #ifndef IOPRIO_H #define IOPRIO_H #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/iocontext.h> /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT (13) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT) #define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK) #define IOPRIO_PRIO_VALUE(class, data) (((class) << IOPRIO_CLASS_SHIFT) | data) #define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) /* * These are the io priority groups as implemented by CFQ. RT is the realtime * class, it always gets premium service. BE is the best-effort scheduling * class, the default for any process. IDLE is the idle scheduling class, it * is only served when no one else is using the disk. */ enum { IOPRIO_CLASS_NONE, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE, }; /* * 8 best effort priority levels are supported */ #define IOPRIO_BE_NR (8) enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, IOPRIO_WHO_USER, }; /* * Fallback BE priority */ #define IOPRIO_NORM (4) /* * if process has set io priority explicitly, use that. if not, convert * the cpu scheduler nice value to an io priority */ static inline int task_nice_ioprio(struct task_struct *task) { return (task_nice(task) + 20) / 5; } /* * This is for the case where the task hasn't asked for a specific IO class. * Check for idle and rt task process, and return appropriate IO class. */ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; else if (task_is_realtime(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; } /* * If the calling process has set an I/O priority, use that. Otherwise, return * the default I/O priority. */ static inline int get_current_ioprio(void) { struct io_context *ioc = current->io_context; if (ioc) return ioc->ioprio; return IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); } /* * For inheritance, return the highest of the two given priorities */ extern int ioprio_best(unsigned short aprio, unsigned short bprio); extern int set_task_ioprio(struct task_struct *task, int ioprio); #ifdef CONFIG_BLOCK extern int ioprio_check_cap(int ioprio); #else static inline int ioprio_check_cap(int ioprio) { return -ENOTBLK; } #endif /* CONFIG_BLOCK */ #endif
963 963 963 965 965 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 // SPDX-License-Identifier: GPL-2.0-only #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> #include <xen/xen.h> #include <asm/fpu/internal.h> #include <asm/traps.h> #include <asm/kdebug.h> typedef bool (*ex_handler_t)(const struct exception_table_entry *, struct pt_regs *, int, unsigned long, unsigned long); static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } static inline ex_handler_t ex_fixup_handler(const struct exception_table_entry *x) { return (ex_handler_t)((unsigned long)&x->handler + x->handler); } __visible bool ex_handler_default(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_default); __visible bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { regs->ip = ex_fixup_addr(fixup); regs->ax = trapnr; return true; } EXPORT_SYMBOL_GPL(ex_handler_fault); /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (task->thread.fpu.state) * should always be valid. However, past bugs have allowed userspace to set * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). * These caused XRSTOR to fail when switching to the task, leaking the FPU * registers of the task previously executing on the CPU. Mitigate this class * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { regs->ip = ex_fixup_addr(fixup); WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); __copy_kernel_to_fpregs(&init_fpstate, -1); return true; } EXPORT_SYMBOL_GPL(ex_handler_fprestore); __visible bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_uaccess); __visible bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { /* Special hack for uaccess_err */ current->thread.uaccess_err = 1; regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_ext); __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip)) show_stack_regs(regs); /* Pretend that the read succeeded and returned 0. */ regs->ip = ex_fixup_addr(fixup); regs->ax = 0; regs->dx = 0; return true; } EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, regs->ip, (void *)regs->ip)) show_stack_regs(regs); /* Pretend that the write succeeded. */ regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_wrmsr_unsafe); __visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr); } EXPORT_SYMBOL(ex_handler_clear_fs); __visible bool ex_has_fault_handler(unsigned long ip) { const struct exception_table_entry *e; ex_handler_t handler; e = search_exception_tables(ip); if (!e) return false; handler = ex_fixup_handler(e); return handler == ex_handler_fault; } __nocfi int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; ex_handler_t handler; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; pnp_bios_is_utter_crap = 1; printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n"); __asm__ volatile( "movl %0, %%esp\n\t" "jmp *%1\n\t" : : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip)); panic("do_trap: can't hit this"); } #endif e = search_exception_tables(regs->ip); if (!e) return 0; handler = ex_fixup_handler(e); return handler(e, regs, trapnr, error_code, fault_addr); } extern unsigned int early_recursion_flag; /* Restricted version used during very early boot */ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { /* Ignore early NMIs. */ if (trapnr == X86_TRAP_NMI) return; if (early_recursion_flag > 2) goto halt_loop; /* * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. * Xen pv domains are not using the default __KERNEL_CS. */ if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* * The full exception fixup machinery is available as soon as * the early IDT is loaded. This means that it is the * responsibility of extable users to either function correctly * when handlers are invoked early or to simply avoid causing * exceptions before they're ready to handle them. * * This is better than filtering which handlers can be used, * because refusing to call a handler here is guaranteed to * result in a hard-to-debug panic. * * Keep in mind that not all vectors actually get here. Early * page faults, for example, are special. */ if (fixup_exception(regs, trapnr, regs->orig_ax, 0)) return; if (fixup_bug(regs, trapnr)) return; fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, regs->orig_ax, read_cr2()); show_regs(regs); halt_loop: while (true) halt(); }
1 1253 1266 1266 1266 1265 1266 1265 1266 1266 1266 1266 221 1266 1266 221 1266 97 97 96 97 97 97 97 97 97 97 97 97 1254 1254 1131 1130 1131 1131 1131 1 1 1 1 1 1 220 149 220 220 220 1 1131 1131 1131 1131 1 1 1 1131 1131 1131 1131 1131 1131 1 1 1131 1130 1131 1 1 1 1 1 1 1131 1131 1131 1131 1131 1131 1130 380 1252 380 1131 380 1254 1254 1254 1253 286 1254 1181 1182 1182 688 1182 1182 1182 74 1182 1182 1266 1266 1266 1194 1194 696 1266 1266 1265 1266 1266 1266 1266 1266 1266 1266 220 1194 938 1194 938 715 1194 159 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0 /* * Block multiqueue core code * * Copyright (C) 2013-2014 Jens Axboe * Copyright (C) 2013-2014 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include <linux/llist.h> #include <linux/list_sort.h> #include <linux/cpu.h> #include <linux/cache.h> #include <linux/sched/sysctl.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> #include <linux/blk-crypto.h> #include <trace/events/block.h> #include <linux/blk-mq.h> #include <linux/t10-pi.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-tag.h" #include "blk-pm.h" #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); static int blk_mq_poll_stats_bkt(const struct request *rq) { int ddir, sectors, bucket; ddir = rq_data_dir(rq); sectors = blk_rq_stats_sectors(rq); bucket = ddir + 2 * ilog2(sectors); if (bucket < 0) return -1; else if (bucket >= BLK_MQ_POLL_STATS_BKTS) return ddir + BLK_MQ_POLL_STATS_BKTS - 2; return bucket; } /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return !list_empty_careful(&hctx->dispatch) || sbitmap_any_bit_set(&hctx->ctx_map) || blk_mq_sched_has_work(hctx); } /* * Mark this ctx as having pending work in this hardware queue */ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit); } static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; sbitmap_clear_bit(&hctx->ctx_map, bit); } struct mq_inflight { struct hd_struct *part; unsigned int *inflight; }; static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { struct mq_inflight *mi = priv; /* * index[0] counts the specific partition that was asked for. */ if (rq->part == mi->part) mi->inflight[0]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) { unsigned inflight[2]; struct mq_inflight mi = { .part = part, .inflight = inflight, }; inflight[0] = inflight[1] = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); return inflight[0]; } static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { struct mq_inflight *mi = priv; if (rq->part == mi->part) mi->inflight[rq_data_dir(rq)]++; return true; } void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part, .inflight = inflight, }; inflight[0] = inflight[1] = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi); } void blk_freeze_queue_start(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); if (++q->mq_freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); mutex_unlock(&q->mq_freeze_lock); if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } else { mutex_unlock(&q->mq_freeze_lock); } } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout) { return wait_event_timeout(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter), timeout); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */ void blk_freeze_queue(struct request_queue *q) { /* * In the !blk_mq case we are only calling this to kill the * q_usage_counter, otherwise this increases the freeze depth * and waits for it to return to zero. For this reason there is * no blk_unfreeze_queue(), and blk_freeze_queue() is not * exported to drivers as the only user for unfreeze is blk_mq. */ blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } void blk_mq_freeze_queue(struct request_queue *q) { /* * ...just an alias to keep freeze and unfreeze actions balanced * in the blk_mq_* namespace */ blk_freeze_queue(q); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); void blk_mq_unfreeze_queue(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { percpu_ref_resurrect(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } mutex_unlock(&q->mq_freeze_lock); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); /* * FIXME: replace the scsi_internal_device_*block_nowait() calls in the * mpt3sas driver such that this function can be removed. */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() * callback function is invoked. Once this function is returned, we make * sure no dispatch can happen until the queue is unquiesced via * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; bool rcu = false; blk_mq_quiesce_queue_nowait(q); queue_for_each_hw_ctx(q, hctx, i) { if (hctx->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(hctx->srcu); else rcu = true; } if (rcu) synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. * * This function recovers queue into the state before quiescing * which is done by blk_mq_quiesce_queue. */ void blk_mq_unquiesce_queue(struct request_queue *q) { blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); /* dispatch requests which are inserted during quiescing */ blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); } bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) { return blk_mq_has_free_tags(hctx->tags); } EXPORT_SYMBOL(blk_mq_can_queue); /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. */ static inline bool blk_mq_need_time_stamp(struct request *rq) { return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator; } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, unsigned int tag, unsigned int op, u64 alloc_time_ns) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct request *rq = tags->static_rqs[tag]; req_flags_t rq_flags = 0; if (data->flags & BLK_MQ_REQ_INTERNAL) { rq->tag = -1; rq->internal_tag = tag; } else { if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) { rq_flags = RQF_MQ_INFLIGHT; atomic_inc(&data->hctx->nr_active); } rq->tag = tag; rq->internal_tag = -1; data->hctx->tags->rqs[rq->tag] = rq; } /* csd/requeue_work/fifo_time is initialized before use */ rq->q = data->q; rq->mq_ctx = data->ctx; rq->mq_hctx = data->hctx; rq->rq_flags = rq_flags; rq->cmd_flags = op; if (data->flags & BLK_MQ_REQ_PREEMPT) rq->rq_flags |= RQF_PREEMPT; if (blk_queue_io_stat(data->q)) rq->rq_flags |= RQF_IO_STAT; INIT_LIST_HEAD(&rq->queuelist); INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->rq_disk = NULL; rq->part = NULL; #ifdef CONFIG_BLK_RQ_ALLOC_TIME rq->alloc_time_ns = alloc_time_ns; #endif if (blk_mq_need_time_stamp(rq)) rq->start_time_ns = ktime_get_ns(); else rq->start_time_ns = 0; rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif blk_crypto_rq_set_defaults(rq); /* tag was already set */ rq->extra_len = 0; WRITE_ONCE(rq->deadline, 0); rq->timeout = 0; rq->end_io = NULL; rq->end_io_data = NULL; data->ctx->rq_dispatched[op_is_sync(op)]++; refcount_set(&rq->ref, 1); return rq; } static struct request *blk_mq_get_request(struct request_queue *q, struct bio *bio, struct blk_mq_alloc_data *data) { struct elevator_queue *e = q->elevator; struct request *rq; unsigned int tag; bool clear_ctx_on_error = false; u64 alloc_time_ns = 0; blk_queue_enter_live(q); /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = ktime_get_ns(); data->q = q; if (likely(!data->ctx)) { data->ctx = blk_mq_get_ctx(q); clear_ctx_on_error = true; } if (likely(!data->hctx)) data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; if (e) { data->flags |= BLK_MQ_REQ_INTERNAL; /* * Flush requests are special and go directly to the * dispatch list. Don't include reserved tags in the * limiting, as it isn't useful. */ if (!op_is_flush(data->cmd_flags) && e->type->ops.limit_depth && !(data->flags & BLK_MQ_REQ_RESERVED)) e->type->ops.limit_depth(data->cmd_flags, data); } else { blk_mq_tag_busy(data->hctx); } tag = blk_mq_get_tag(data); if (tag == BLK_MQ_TAG_FAIL) { if (clear_ctx_on_error) data->ctx = NULL; blk_queue_exit(q); return NULL; } rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, alloc_time_ns); if (!op_is_flush(data->cmd_flags)) { rq->elv.icq = NULL; if (e && e->type->ops.prepare_request) { if (e->type->icq_cache) blk_mq_sched_assign_ioc(rq); e->type->ops.prepare_request(rq, bio); rq->rq_flags |= RQF_ELVPRIV; } } data->hctx->queued++; return rq; } struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op }; struct request *rq; int ret; ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); rq = blk_mq_get_request(q, NULL, &alloc_data); blk_queue_exit(q); if (!rq) return ERR_PTR(-EWOULDBLOCK); rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op }; struct request *rq; unsigned int cpu; int ret; /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ alloc_data.hctx = q->queue_hw_ctx[hctx_idx]; if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) { blk_queue_exit(q); return ERR_PTR(-EXDEV); } cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask); alloc_data.ctx = __blk_mq_get_ctx(q, cpu); rq = blk_mq_get_request(q, NULL, &alloc_data); blk_queue_exit(q); if (!rq) return ERR_PTR(-EWOULDBLOCK); return rq; } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != -1) blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); if (sched_tag != -1) blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (rq->rq_flags & RQF_ELVPRIV) { if (e && e->type->ops.finish_request) e->type->ops.finish_request(rq); if (rq->elv.icq) { put_io_context(rq->elv.icq->ioc); rq->elv.icq = NULL; } } ctx->rq_completed[rq_is_sync(rq)]++; if (rq->rq_flags & RQF_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (refcount_dec_and_test(&rq->ref)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { u64 now = 0; if (blk_mq_need_time_stamp(rq)) now = ktime_get_ns(); if (rq->rq_flags & RQF_STATS) { blk_mq_poll_stats_start(rq->q); blk_stat_add(rq, now); } if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); if (rq->end_io) { rq_qos_done(rq->q, rq); rq->end_io(rq, error); } else { blk_mq_free_request(rq); } } EXPORT_SYMBOL(__blk_mq_end_request); void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); } EXPORT_SYMBOL(blk_mq_end_request); static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; struct request_queue *q = rq->q; q->mq_ops->complete(rq); } static void __blk_mq_complete_request(struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; bool shared = false; int cpu; WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * Most of single queue controllers, there is only one irq vector * for handling IO completion, and the only irq's affinity is set * as all possible CPUs. On most of ARCHs, this affinity means the * irq is handled on one specific CPU. * * So complete IO reqeust in softirq context in case of single queue * for not degrading IO performance by irqsoff latency. */ if (q->nr_hw_queues == 1) { __blk_complete_request(rq); return; } /* * For a polled request, always complete locallly, it's pointless * to redirect the completion. */ if ((rq->cmd_flags & REQ_HIPRI) || !test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) { q->mq_ops->complete(rq); return; } cpu = get_cpu(); if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ctx->cpu); if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; smp_call_function_single_async(ctx->cpu, &rq->csd); } else { q->mq_ops->complete(rq); } put_cpu(); } static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) __releases(hctx->srcu) { if (!(hctx->flags & BLK_MQ_F_BLOCKING)) rcu_read_unlock(); else srcu_read_unlock(hctx->srcu, srcu_idx); } static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx) __acquires(hctx->srcu) { if (!(hctx->flags & BLK_MQ_F_BLOCKING)) { /* shut up gcc false positive */ *srcu_idx = 0; rcu_read_lock(); } else *srcu_idx = srcu_read_lock(hctx->srcu); } /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Ends all I/O on a request. It does not handle partial completions. * The actual completion happens out-of-order, through a IPI handler. **/ bool blk_mq_complete_request(struct request *rq) { if (unlikely(blk_should_fake_timeout(rq->q))) return false; __blk_mq_complete_request(rq); return true; } EXPORT_SYMBOL(blk_mq_complete_request); int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } EXPORT_SYMBOL_GPL(blk_mq_request_started); int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } EXPORT_SYMBOL_GPL(blk_mq_request_completed); void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(q, rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { rq->io_start_time_ns = ktime_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); if (q->dma_drain_size && blk_rq_bytes(rq)) { /* * Make sure space for the drain appears. We know we can do * this because max_hw_segments has been adjusted to be one * fewer than the device can handle. */ rq->nr_phys_segments++; } #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) q->integrity.profile->prepare_fn(rq); #endif } EXPORT_SYMBOL(blk_mq_start_request); static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_put_driver_tag(rq); trace_block_rq_requeue(q, rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; if (q->dma_drain_size && blk_rq_bytes(rq)) rq->nr_phys_segments--; } } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); blk_mq_add_to_requeue_list(rq, true, kick_requeue_list); } EXPORT_SYMBOL(blk_mq_requeue_request); static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); struct request *rq, *next; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); spin_unlock_irq(&q->requeue_lock); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP))) continue; rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); /* * If RQF_DONTPREP, rq has contained some driver specific * data, so insert it to hctx dispatch list to avoid any * merge. */ if (rq->rq_flags & RQF_DONTPREP) blk_mq_request_bypass_insert(rq, false, false); else blk_mq_sched_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_sched_insert_request(rq, false, false, false); } blk_mq_run_hw_queues(q, false); } void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list) { struct request_queue *q = rq->q; unsigned long flags; /* * We abuse this flag that is otherwise used by the I/O scheduler to * request head insertion from the workqueue. */ BUG_ON(rq->rq_flags & RQF_SOFTBARRIER); spin_lock_irqsave(&q->requeue_lock, flags); if (at_head) { rq->rq_flags |= RQF_SOFTBARRIER; list_add(&rq->queuelist, &q->requeue_list); } else { list_add_tail(&rq->queuelist, &q->requeue_list); } spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); } void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); } EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; } EXPORT_SYMBOL(blk_mq_tag_to_rq); static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { /* * If we find a request that isn't idle and the queue matches, * we know the queue is busy. Return false to stop the iteration. */ if (blk_mq_request_started(rq) && rq->q == hctx->queue) { bool *busy = priv; *busy = true; return false; } return true; } bool blk_mq_queue_inflight(struct request_queue *q) { bool busy = false; blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy); return busy; } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); static void blk_mq_rq_timed_out(struct request *req, bool reserved) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; ret = req->q->mq_ops->timeout(req, reserved); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } blk_add_timer(req); } static bool blk_mq_req_expired(struct request *rq, unsigned long *next) { unsigned long deadline; if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) return false; if (rq->rq_flags & RQF_TIMED_OUT) return false; deadline = READ_ONCE(rq->deadline); if (time_after_eq(jiffies, deadline)) return true; if (*next == 0) *next = deadline; else if (time_after(*next, deadline)) *next = deadline; return false; } void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) rq->end_io(rq, 0); else if (refcount_dec_and_test(&rq->ref)) __blk_mq_free_request(rq); } static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { unsigned long *next = priv; /* * Just do a quick check if it is expired before locking the request in * so we're not unnecessarilly synchronizing across CPUs. */ if (!blk_mq_req_expired(rq, next)) return true; /* * We have reason to believe the request may be expired. Take a * reference on the request to lock this request lifetime into its * currently allocated context to prevent it from being reallocated in * the event the completion by-passes this timeout handler. * * If the reference was already released, then the driver beat the * timeout handler to posting a natural completion. */ if (!refcount_inc_not_zero(&rq->ref)) return true; /* * The request is now locked and cannot be reallocated underneath the * timeout handler's processing. Re-verify this exact request is truly * expired; if it is not expired, then the request was completed and * reallocated as a new request. */ if (blk_mq_req_expired(rq, next)) blk_mq_rq_timed_out(rq, reserved); blk_mq_put_rq_ref(rq); return true; } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); unsigned long next = 0; struct blk_mq_hw_ctx *hctx; int i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next); if (next != 0) { mod_timer(&q->timeout, next); } else { /* * Request timeouts are handled as a forward rolling timer. If * we end up here it means that no requests are pending and * also that no request has been pending for a while. Mark * each hctx as idle. */ queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); } struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; }; static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_lists[type], flush_data->list); sbitmap_clear_bit(sb, bitnr); spin_unlock(&ctx->lock); return true; } /* * Process software queues that have been marked busy, splicing them * to the for-dispatch */ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); } EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs); struct dispatch_rq_data { struct blk_mq_hw_ctx *hctx; struct request *rq; }; static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct dispatch_rq_data *dispatch_data = data; struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_lists[type])) sbitmap_clear_bit(sb, bitnr); } spin_unlock(&ctx->lock); return !dispatch_data->rq; } struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start) { unsigned off = start ? start->index_hw[hctx->type] : 0; struct dispatch_rq_data data = { .hctx = hctx, .rq = NULL, }; __sbitmap_for_each_set(&hctx->ctx_map, off, dispatch_rq_from_ctx, &data); return data.rq; } static inline unsigned int queued_to_index(unsigned int queued) { if (!queued) return 0; return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1); } bool blk_mq_get_driver_tag(struct request *rq) { struct blk_mq_alloc_data data = { .q = rq->q, .hctx = rq->mq_hctx, .flags = BLK_MQ_REQ_NOWAIT, .cmd_flags = rq->cmd_flags, }; bool shared; if (rq->tag != -1) goto done; if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag)) data.flags |= BLK_MQ_REQ_RESERVED; shared = blk_mq_tag_busy(data.hctx); rq->tag = blk_mq_get_tag(&data); if (rq->tag >= 0) { if (shared) { rq->rq_flags |= RQF_MQ_INFLIGHT; atomic_inc(&data.hctx->nr_active); } data.hctx->tags->rqs[rq->tag] = rq; } done: return rq->tag != -1; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { struct sbitmap_queue *sbq; list_del_init(&wait->entry); sbq = &hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); return 1; } /* * Mark us waiting for a tag. For shared tags, this involves hooking us into * the tag wakeups. For non-shared tags, we can simply mark us needing a * restart. For both cases, take care to check the condition again after * marking us as waiting. */ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct sbitmap_queue *sbq; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) { blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. * * Don't clear RESTART here, someone else could have set it. * At most this will cost an extra queue run. */ return blk_mq_get_driver_tag(rq); } wait = &hctx->dispatch_wait; if (!list_empty_careful(&wait->entry)) return false; if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) sbq = &hctx->tags->breserved_tags; else sbq = &hctx->tags->bitmap_tags; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. */ ret = blk_mq_get_driver_tag(rq); if (!ret) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } /* * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ list_del_init(&wait->entry); atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return true; } #define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 #define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 /* * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): * - EWMA is one simple way to compute running average value * - weight(7/8 and 1/8) is applied so that it can decrease exponentially * - take 4 as factor for avoiding to get too small(0) result, and this * factor doesn't matter because EWMA decreases exponentially */ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; if (hctx->queue->elevator) return; ewma = hctx->dispatch_busy; if (!ewma && !busy) return; ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; if (busy) ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; hctx->dispatch_busy = ewma; } #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { struct request *next = list_first_entry_or_null(list, struct request, queuelist); /* * If an I/O scheduler has been configured and we got a driver tag for * the next request already, free it. */ if (next) blk_mq_put_driver_tag(next); list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } /* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bool got_budget) { struct blk_mq_hw_ctx *hctx; struct request *rq, *nxt; bool no_tag = false; int errors, queued; blk_status_t ret = BLK_STS_OK; bool no_budget_avail = false; if (list_empty(list)) return false; WARN_ON(!list_is_singular(list) && got_budget); /* * Now process all the entries, sending them to the driver. */ errors = queued = 0; do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); hctx = rq->mq_hctx; if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { blk_mq_put_driver_tag(rq); no_budget_avail = true; break; } if (!blk_mq_get_driver_tag(rq)) { /* * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. The * waitqueue takes care of that. If the queue is run * before we add this entry back on the dispatch list, * we'll re-run it below. */ if (!blk_mq_mark_tag_wait(hctx, rq)) { blk_mq_put_dispatch_budget(hctx); /* * For non-shared tags, the RESTART check * will suffice. */ if (hctx->flags & BLK_MQ_F_TAG_SHARED) no_tag = true; break; } } list_del_init(&rq->queuelist); bd.rq = rq; /* * Flag last if we have no more requests, or if we have more * but can't assign a driver tag to it. */ if (list_empty(list)) bd.last = true; else { nxt = list_first_entry(list, struct request, queuelist); bd.last = !blk_mq_get_driver_tag(nxt); } ret = q->mq_ops->queue_rq(hctx, &bd); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_handle_dev_resource(rq, list); break; } if (unlikely(ret != BLK_STS_OK)) { errors++; blk_mq_end_request(rq, BLK_STS_IOERR); continue; } queued++; } while (!list_empty(list)); hctx->dispatched[queued_to_index(queued)]++; /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(list)) { bool needs_restart; /* * If we didn't flush the entire list, we could have told * the driver there was more coming, but that turned out to * be a lie. */ if (q->mq_ops->commit_rqs) q->mq_ops->commit_rqs(hctx); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * Order adding requests to hctx->dispatch and checking * SCHED_RESTART flag. The pair of this smp_mb() is the one * in blk_mq_sched_restart(). Avoid restart code path to * miss the new added requests to hctx->dispatch, meantime * SCHED_RESTART is observed here. */ smp_mb(); /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. * * If 'no_tag' is set, that means that we failed getting * a driver tag with an I/O scheduler attached. If our dispatch * waitqueue is no longer active, ensure that we run the queue * AFTER adding our entries back to the list. * * If no I/O scheduler has been configured it is possible that * the hardware queue got stopped and restarted before requests * were pushed back onto the dispatch list. Rerun the queue to * avoid starvation. Notes: * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do * similar if we couldn't get budget and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); else if (needs_restart && (ret == BLK_STS_RESOURCE || no_budget_avail)) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); return false; } else blk_mq_update_dispatch_busy(hctx, false); /* * If the host/device is unable to accept more work, inform the * caller of that. */ if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) return false; return (queued + errors) != 0; } static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) { int srcu_idx; /* * We should be running this queue from one of the CPUs that * are mapped to it. * * There are at least two related races now between setting * hctx->next_cpu from blk_mq_hctx_next_cpu() and running * __blk_mq_run_hw_queue(): * * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(), * but later it becomes online, then this warning is harmless * at all * * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(), * but later it becomes offline, then the warning can't be * triggered, and we depend on blk-mq timeout handler to * handle dispatched requests to this hctx */ if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && cpu_online(hctx->next_cpu)) { printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n", raw_smp_processor_id(), cpumask_empty(hctx->cpumask) ? "inactive": "active"); dump_stack(); } /* * We can't run the queue inline with ints disabled. Ensure that * we catch bad users of this early. */ WARN_ON_ONCE(in_interrupt()); might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); hctx_lock(hctx, &srcu_idx); blk_mq_sched_dispatch_requests(hctx); hctx_unlock(hctx, srcu_idx); } static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) { int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(hctx->cpumask); return cpu; } /* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { bool tried = false; int next_cpu = hctx->next_cpu; if (hctx->queue->nr_hw_queues == 1) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { select_cpu: next_cpu = cpumask_next_and(next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } /* * Do unbound schedule if we can't find a online CPU for this hctx, * and it should only happen in the path of handling CPU DEAD. */ if (!cpu_online(next_cpu)) { if (!tried) { tried = true; goto select_cpu; } /* * Make sure to re-select CPU next time once after CPUs * in hctx->cpumask become online again. */ hctx->next_cpu = next_cpu; hctx->next_cpu_batch = 1; return WORK_CPU_UNBOUND; } hctx->next_cpu = next_cpu; return next_cpu; } static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx))) return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { int cpu = get_cpu(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); put_cpu(); return; } put_cpu(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, msecs_to_jiffies(msecs)); } void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { __blk_mq_delay_run_hw_queue(hctx, true, msecs); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; bool need_run; /* * When queue is quiesced, we may be switching io scheduler, or * updating nr_hw_queues, or other things, and we can't run queue * any more, even __blk_mq_hctx_has_pending() can't be called safely. * * And queue will be rerun in blk_mq_unquiesce_queue() if it is * quiesced. */ hctx_lock(hctx, &srcu_idx); need_run = !blk_queue_quiesced(hctx->queue) && blk_mq_hctx_has_pending(hctx); hctx_unlock(hctx, srcu_idx); if (need_run) { __blk_mq_delay_run_hw_queue(hctx, async, 0); return true; } return false; } EXPORT_SYMBOL(blk_mq_run_hw_queue); void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; blk_mq_run_hw_queue(hctx, async); } } EXPORT_SYMBOL(blk_mq_run_hw_queues); /** * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped * @q: request queue. * * The caller is responsible for serializing this function against * blk_mq_{start,stop}_hw_queue(). */ bool blk_mq_queue_stopped(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hctx_stopped(hctx)) return true; return false; } EXPORT_SYMBOL(blk_mq_queue_stopped); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queue() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } EXPORT_SYMBOL(blk_mq_stop_hw_queue); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queues() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, false); } EXPORT_SYMBOL(blk_mq_start_hw_queue); void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_start_hw_queues); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (!blk_mq_hctx_stopped(hctx)) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_stopped_hw_queue(hctx, async); } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx; hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work); /* * If we are stopped, don't run the queue. */ if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) return; __blk_mq_run_hw_queue(hctx); } static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; enum hctx_type type = hctx->type; lockdep_assert_held(&ctx->lock); trace_block_rq_insert(hctx->queue, rq); if (at_head) list_add(&rq->queuelist, &ctx->rq_lists[type]); else list_add_tail(&rq->queuelist, &ctx->rq_lists[type]); } void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; lockdep_assert_held(&ctx->lock); __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } /* * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ void blk_mq_request_bypass_insert(struct request *rq, bool at_head, bool run_queue) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); if (at_head) list_add(&rq->queuelist, &hctx->dispatch); else list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); if (run_queue) blk_mq_run_hw_queue(hctx, false); } void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list) { struct request *rq; enum hctx_type type = hctx->type; /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); trace_block_rq_insert(hctx->queue, rq); } spin_lock(&ctx->lock); list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); } static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); if (rqa->mq_ctx < rqb->mq_ctx) return -1; else if (rqa->mq_ctx > rqb->mq_ctx) return 1; else if (rqa->mq_hctx < rqb->mq_hctx) return -1; else if (rqa->mq_hctx > rqb->mq_hctx) return 1; return blk_rq_pos(rqa) > blk_rq_pos(rqb); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct blk_mq_hw_ctx *this_hctx; struct blk_mq_ctx *this_ctx; struct request_queue *this_q; struct request *rq; LIST_HEAD(list); LIST_HEAD(rq_list); unsigned int depth; list_splice_init(&plug->mq_list, &list); if (plug->rq_count > 2 && plug->multiple_queues) list_sort(NULL, &list, plug_rq_cmp); plug->rq_count = 0; this_q = NULL; this_hctx = NULL; this_ctx = NULL; depth = 0; while (!list_empty(&list)) { rq = list_entry_rq(list.next); list_del_init(&rq->queuelist); BUG_ON(!rq->q); if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) { if (this_hctx) { trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list, from_schedule); } this_q = rq->q; this_ctx = rq->mq_ctx; this_hctx = rq->mq_hctx; depth = 0; } depth++; list_add_tail(&rq->queuelist, &rq_list); } /* * If 'this_hctx' is set, we know we have entries to complete * on 'rq_list'. Do those. */ if (this_hctx) { trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list, from_schedule); } } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { int err; if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); WARN_ON_ONCE(err); blk_account_io_start(rq, true); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; blk_qc_t new_cookie; blk_status_t ret; new_cookie = request_to_qc_t(hctx, rq); /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we * previously would have done. */ ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); *cookie = new_cookie; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; default: blk_mq_update_dispatch_busy(hctx, false); *cookie = BLK_QC_T_NONE; break; } return ret; } static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, bool bypass_insert, bool last) { struct request_queue *q = rq->q; bool run_queue = true; /* * RCU or SRCU read lock is needed before checking quiesced flag. * * When queue is stopped or quiesced, ignore 'bypass_insert' from * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller, * and avoid driver to try to dispatch again. */ if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) { run_queue = false; bypass_insert = false; goto insert; } if (q->elevator && !bypass_insert) goto insert; if (!blk_mq_get_dispatch_budget(hctx)) goto insert; if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(hctx); goto insert; } return __blk_mq_issue_directly(hctx, rq, cookie, last); insert: if (bypass_insert) return BLK_STS_RESOURCE; blk_mq_sched_insert_request(rq, false, run_queue, false); return BLK_STS_OK; } static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie) { blk_status_t ret; int srcu_idx; might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); hctx_lock(hctx, &srcu_idx); ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) blk_mq_end_request(rq, ret); hctx_unlock(hctx, srcu_idx); } blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { blk_status_t ret; int srcu_idx; blk_qc_t unused_cookie; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; hctx_lock(hctx, &srcu_idx); ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last); hctx_unlock(hctx, srcu_idx); return ret; } void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { while (!list_empty(list)) { blk_status_t ret; struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); if (ret != BLK_STS_OK) { if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_request_bypass_insert(rq, false, list_empty(list)); break; } blk_mq_end_request(rq, ret); } } /* * If we didn't flush the entire list, we could have told * the driver there was more coming, but that turned out to * be a lie. */ if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs) hctx->queue->mq_ops->commit_rqs(hctx); } static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { list_add_tail(&rq->queuelist, &plug->mq_list); plug->rq_count++; if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) { struct request *tmp; tmp = list_first_entry(&plug->mq_list, struct request, queuelist); if (tmp->q != rq->q) plug->multiple_queues = true; } } static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; } /* called before freeing request pool in @tags */ static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct blk_mq_tags *drv_tags = set->tags[hctx_idx]; struct ext_blk_mq_tags *drv_etags; struct page *page; unsigned long flags; list_for_each_entry(page, &tags->page_list, lru) { unsigned long start = (unsigned long)page_address(page); unsigned long end = start + order_to_size(page->private); int i; for (i = 0; i < set->queue_depth; i++) { struct request *rq = drv_tags->rqs[i]; unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { WARN_ON_ONCE(refcount_read(&rq->ref) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } } /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ drv_etags = container_of(drv_tags, struct ext_blk_mq_tags, tags); spin_lock_irqsave(&drv_etags->lock, flags); spin_unlock_irqrestore(&drv_etags->lock, flags); } static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = op_is_flush(bio->bi_opf); struct blk_mq_alloc_data data = { .flags = 0}; struct request *rq; struct blk_plug *plug; struct request *same_queue_rq = NULL; unsigned int nr_segs; blk_qc_t cookie; blk_status_t ret; blk_queue_bounce(q, &bio); __blk_queue_split(q, &bio, &nr_segs); if (!bio_integrity_prep(bio)) return BLK_QC_T_NONE; if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq)) return BLK_QC_T_NONE; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) return BLK_QC_T_NONE; rq_qos_throttle(q, bio); data.cmd_flags = bio->bi_opf; rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); return BLK_QC_T_NONE; } trace_block_getrq(q, bio, bio->bi_opf); rq_qos_track(q, rq, bio); cookie = request_to_qc_t(data.hctx, rq); blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); return BLK_QC_T_NONE; } plug = blk_mq_plug(q, bio); if (unlikely(is_flush_fua)) { /* bypass scheduler for flush rq */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. * * Use normal plugging if this disk is slow HDD, as sequential * IO may benefit a lot from plug merging. */ unsigned int request_count = plug->rq_count; struct request *last = NULL; if (!request_count) trace_block_plug(q); else last = list_entry_rq(plug->mq_list.prev); if (request_count >= BLK_MAX_REQUEST_COUNT || (last && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_flush_plug_list(plug, false); trace_block_plug(q); } blk_add_rq_to_plug(plug, rq); } else if (q->elevator) { blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { /* * We do limited plugging. If the bio can be merged, do that. * Otherwise the existing request in the plug list will be * issued. So the plug list will have one request at most * The plug list might get flushed before this. If that happens, * the plug list is empty, and same_queue_rq is invalid. */ if (list_empty(&plug->mq_list)) same_queue_rq = NULL; if (same_queue_rq) { list_del_init(&same_queue_rq->queuelist); plug->rq_count--; } blk_add_rq_to_plug(plug, rq); trace_block_plug(q); if (same_queue_rq) { data.hctx = same_queue_rq->mq_hctx; trace_block_unplug(q, 1, true); blk_mq_try_issue_directly(data.hctx, same_queue_rq, &cookie); } } else if ((q->nr_hw_queues > 1 && is_sync) || !data.hctx->dispatch_busy) { blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { blk_mq_sched_insert_request(rq, false, true, true); } return cookie; } void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct page *page; if (tags->rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { struct request *rq = tags->static_rqs[i]; if (!rq) continue; set->ops->exit_request(set, rq, hctx_idx); tags->static_rqs[i] = NULL; } } blk_mq_clear_rq_mapping(set, tags, hctx_idx); while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); /* * Remove kmemleak object previously allocated in * blk_mq_alloc_rqs(). */ kmemleak_free(page_address(page)); __free_pages(page, page->private); } } void blk_mq_free_rq_map(struct blk_mq_tags *tags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; blk_mq_free_tags(tags); } struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags) { struct blk_mq_tags *tags; int node; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx); if (node == NUMA_NO_NODE) node = set->numa_node; tags = blk_mq_init_tags(nr_tags, reserved_tags, node, BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) { blk_mq_free_tags(tags); return NULL; } tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->static_rqs) { kfree(tags->rqs); blk_mq_free_tags(tags); return NULL; } return tags; } static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { int ret; if (set->ops->init_request) { ret = set->ops->init_request(set, rq, hctx_idx, node); if (ret) return ret; } WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth) { unsigned int i, j, entries_per_page, max_order = 4; size_t rq_size, left; int node; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx); if (node == NUMA_NO_NODE) node = set->numa_node; INIT_LIST_HEAD(&tags->page_list); /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * depth; for (i = 0; i < depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { struct request *rq = p; tags->static_rqs[i] = rq; if (blk_mq_init_request(set, rq, hctx_idx, node)) { tags->static_rqs[i] = NULL; goto fail; } p += rq_size; i++; } } return 0; fail: blk_mq_free_rqs(set, tags, hctx_idx); return -ENOMEM; } /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; } static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } /* * Before freeing hw queue, clearing the flush request reference in * tags->rqs[] for avoiding potential UAF. */ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, unsigned int queue_depth, struct request *flush_rq) { int i; unsigned long flags; struct ext_blk_mq_tags *etags; /* The hw queue may not be mapped yet */ if (!tags) return; WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ etags = container_of(tags, struct ext_blk_mq_tags, tags); spin_lock_irqsave(&etags->lock, flags); spin_unlock_irqrestore(&etags->lock, flags); } /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct request *flush_rq = hctx->fq->flush_rq; if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); blk_mq_remove_cpuhp(hctx); spin_lock(&q->unused_hctx_lock); list_add(&hctx->hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_debugfs_unregister_hctx(hctx); blk_mq_exit_hctx(q, set, hctx, i); } } static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set) { int hw_ctx_size = sizeof(struct blk_mq_hw_ctx); BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu), __alignof__(struct blk_mq_hw_ctx)) != sizeof(struct blk_mq_hw_ctx)); if (tag_set->flags & BLK_MQ_F_BLOCKING) hw_ctx_size += sizeof(struct srcu_struct); return hw_ctx_size; } static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { hctx->queue_num = hctx_idx; cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto unregister_cpu_notifier; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) goto exit_hctx; return 0; exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); unregister_cpu_notifier: blk_mq_remove_cpuhp(hctx); return -1; } static struct blk_mq_hw_ctx * blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, int node) { struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node); if (!hctx) goto fail_alloc_hctx; if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node)) goto free_hctx; atomic_set(&hctx->nr_active, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *), gfp, node); if (!hctx->ctxs) goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), gfp, node)) goto free_ctxs; hctx->nr_ctx = 0; spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size, gfp); if (!hctx->fq) goto free_bitmap; if (hctx->flags & BLK_MQ_F_BLOCKING) init_srcu_struct(hctx->srcu); blk_mq_hctx_kobj_init(hctx); return hctx; free_bitmap: sbitmap_free(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); fail_alloc_hctx: return NULL; } static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; unsigned int i, j; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; int k; __ctx->cpu = i; spin_lock_init(&__ctx->lock); for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++) INIT_LIST_HEAD(&__ctx->rq_lists[k]); __ctx->queue = q; /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ for (j = 0; j < set->nr_maps; j++) { hctx = blk_mq_map_queue_type(q, j, i); if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = local_memory_node(cpu_to_node(i)); } } } static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx) { int ret = 0; set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx, set->queue_depth, set->reserved_tags); if (!set->tags[hctx_idx]) return false; ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx, set->queue_depth); if (!ret) return true; blk_mq_free_rq_map(set->tags[hctx_idx]); set->tags[hctx_idx] = NULL; return false; } static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set, unsigned int hctx_idx) { if (set->tags && set->tags[hctx_idx]) { blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx); blk_mq_free_rq_map(set->tags[hctx_idx]); set->tags[hctx_idx] = NULL; } } static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int i, j, hctx_idx; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; hctx->dispatch_from = NULL; } /* * Map software to hardware queues. * * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { if (!set->map[j].nr_queues) { ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); continue; } hctx_idx = set->map[j].mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_rq_map(set, hctx_idx)) { /* * If tags initialization fail for some hctx, * that hctx won't be brought online. In this * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ set->map[j].mq_map[i] = 0; } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; /* * If the CPU is already set in the mask, then we've * mapped this one already. This can happen if * devices share queues across queue maps. */ if (cpumask_test_cpu(i, hctx->cpumask)) continue; cpumask_set_cpu(i, hctx->cpumask); hctx->type = j; ctx->index_hw[hctx->type] = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; /* * If the nr_ctx type overflows, we have exceeded the * amount of sw queues we can support. */ BUG_ON(!hctx->nr_ctx); } for (; j < HCTX_MAX_TYPES; j++) ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); } queue_for_each_hw_ctx(q, hctx, i) { /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { /* Never unmap queue 0. We need it as a * fallback in case of a new remap fails * allocation */ if (i && set->tags[i]) blk_mq_free_map_and_requests(set, i); hctx->tags = NULL; continue; } hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Initialize batch roundrobin counts */ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } } /* * Caller needs to ensure that we're either frozen/quiesced, or that * the queue isn't live yet. */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) hctx->flags |= BLK_MQ_F_TAG_SHARED; else hctx->flags &= ~BLK_MQ_F_TAG_SHARED; } } static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } } static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del_rcu(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, false); } mutex_unlock(&set->tag_list_lock); INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { mutex_lock(&set->tag_list_lock); /* * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_SHARED)) { set->flags |= BLK_MQ_F_TAG_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, true); } if (set->flags & BLK_MQ_F_TAG_SHARED) queue_set_hctx_shared(q, true); list_add_tail_rcu(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } /* All allocations will be freed in release handler of q->mq_kobj */ static int blk_mq_alloc_ctxs(struct request_queue *q) { struct blk_mq_ctxs *ctxs; int cpu; ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL); if (!ctxs) return -ENOMEM; ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!ctxs->queue_ctx) goto fail; for_each_possible_cpu(cpu) { struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); ctx->ctxs = ctxs; } q->mq_kobj = &ctxs->kobj; q->queue_ctx = ctxs->queue_ctx; return 0; fail: kfree(ctxs); return -ENOMEM; } /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */ void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx, *next; int i; queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); /* all hctx are in .unused_hctx_list now */ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) { list_del_init(&hctx->hctx_list); kobject_put(&hctx->kobj); } kfree(q->queue_hw_ctx); /* * release .mq_kobj and sw queue's kobject now because * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); } struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) { struct request_queue *uninit_q, *q; uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node); if (!uninit_q) return ERR_PTR(-ENOMEM); /* * Initialize the queue without an elevator. device_add_disk() will do * the initialization. */ q = blk_mq_init_allocated_queue(set, uninit_q, false); if (IS_ERR(q)) blk_cleanup_queue(uninit_q); return q; } EXPORT_SYMBOL(blk_mq_init_queue); /* * Helper for setting up a queue with mq ops, given queue depth, and * the passed in mq ops flags. */ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags) { struct request_queue *q; int ret; memset(set, 0, sizeof(*set)); set->ops = ops; set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = queue_depth; set->numa_node = NUMA_NO_NODE; set->flags = set_flags; ret = blk_mq_alloc_tag_set(set); if (ret) return ERR_PTR(ret); q = blk_mq_init_queue(set); if (IS_ERR(q)) { blk_mq_free_tag_set(set); return q; } return q; } EXPORT_SYMBOL(blk_mq_init_sq_queue); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) { struct blk_mq_hw_ctx *hctx = NULL, *tmp; /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { if (tmp->numa_node == node) { hctx = tmp; break; } } if (hctx) list_del_init(&hctx->hctx_list); spin_unlock(&q->unused_hctx_lock); if (!hctx) hctx = blk_mq_alloc_hctx(q, set, node); if (!hctx) goto fail; if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) goto free_hctx; return hctx; free_hctx: kobject_put(&hctx->kobj); fail: return NULL; } static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { int i, j, end; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int node; struct blk_mq_hw_ctx *hctx; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], i); /* * If the hw queue has been mapped to another numa node, * we need to realloc the hctx. If allocation fails, fallback * to use the previous one. */ if (hctxs[i] && (hctxs[i]->numa_node == node)) continue; hctx = blk_mq_alloc_and_init_hctx(set, q, i, node); if (hctx) { if (hctxs[i]) blk_mq_exit_hctx(q, set, hctxs[i], i); hctxs[i] = hctx; } else { if (hctxs[i]) pr_warn("Allocate new hctx on node %d fails,\ fallback to previous one on node %d\n", node, hctxs[i]->numa_node); else break; } } /* * Increasing nr_hw_queues fails. Free the newly allocated * hctxs and keep the previous q->nr_hw_queues. */ if (i != set->nr_hw_queues) { j = q->nr_hw_queues; end = i; } else { j = i; end = q->nr_hw_queues; q->nr_hw_queues = set->nr_hw_queues; } for (; j < end; j++) { struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { if (hctx->tags) blk_mq_free_map_and_requests(set, j); blk_mq_exit_hctx(q, set, hctx, j); hctxs[j] = NULL; } } mutex_unlock(&q->sysfs_lock); } /* * Maximum number of hardware queues we support. For single sets, we'll never * have more than the CPUs (software queues). For multiple sets, the tag_set * user may have set ->nr_hw_queues larger. */ static unsigned int nr_hw_queues(struct blk_mq_tag_set *set) { if (set->nr_maps == 1) return nr_cpu_ids; return max(set->nr_hw_queues, nr_cpu_ids); } struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q, bool elevator_init) { /* mark the queue as mq asap */ q->mq_ops = set->ops; q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn, blk_mq_poll_stats_bkt, BLK_MQ_POLL_STATS_BKTS, q); if (!q->poll_cb) goto err_exit; if (blk_mq_alloc_ctxs(q)) goto err_poll; /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); q->nr_queues = nr_hw_queues(set); q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, set->numa_node); if (!q->queue_hw_ctx) goto err_sys_init; INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; if (set->nr_maps > HCTX_TYPE_POLL && set->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, q); q->sg_reserved_size = INT_MAX; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); blk_queue_make_request(q, blk_mq_make_request); /* * Do this after blk_queue_make_request() overrides it... */ q->nr_requests = set->queue_depth; /* * Default to classic polling */ q->poll_nsec = BLK_MQ_POLL_CLASSIC; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); if (elevator_init) elevator_init_mq(q); return q; err_hctxs: kfree(q->queue_hw_ctx); q->nr_hw_queues = 0; err_sys_init: blk_mq_sysfs_deinit(q); err_poll: blk_stat_free_callback(q->poll_cb); q->poll_cb = NULL; err_exit: q->mq_ops = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; for (i = 0; i < set->nr_hw_queues; i++) if (!__blk_mq_alloc_rq_map(set, i)) goto out_unwind; return 0; out_unwind: while (--i >= 0) blk_mq_free_rq_map(set->tags[i]); return -ENOMEM; } /* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; } static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the * number of hardware queues. */ if (set->nr_maps == 1) set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues; if (set->ops->map_queues && !is_kdump_kernel()) { int i; /* * transport .map_queues is usually done in the following * way: * * for (queue = 0; queue < set->nr_hw_queues; queue++) { * mask = get_cpu_mask(queue) * for_each_cpu(cpu, mask) * set->map[x].mq_map[cpu] = queue; * } * * When we need to remap, the table has to be cleared for * killing stale mapping since one CPU may not be mapped * to any hw queue. */ for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); return set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if it's too large. In that case, the set * value will be stored in set->queue_depth. */ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int i, ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (!set->ops->get_budget ^ !set->ops->put_budget) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } if (!set->nr_maps) set->nr_maps = 1; else if (set->nr_maps > HCTX_MAX_TYPES) return -EINVAL; /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 1 queue and * 64 tags to prevent using too much memory. */ if (is_kdump_kernel()) { set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = min(64U, set->queue_depth); } /* * There is no use for more h/w queues than cpus if we just have * a single map */ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!set->tags) return -ENOMEM; ret = -ENOMEM; for (i = 0; i < set->nr_maps; i++) { set->map[i].mq_map = kcalloc_node(nr_cpu_ids, sizeof(set->map[i].mq_map[0]), GFP_KERNEL, set->numa_node); if (!set->map[i].mq_map) goto out_free_mq_map; set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues; } ret = blk_mq_update_queue_map(set); if (ret) goto out_free_mq_map; ret = blk_mq_alloc_rq_maps(set); if (ret) goto out_free_mq_map; mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); set->map[i].mq_map = NULL; } kfree(set->tags); set->tags = NULL; return ret; } EXPORT_SYMBOL(blk_mq_alloc_tag_set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; for (i = 0; i < nr_hw_queues(set); i++) blk_mq_free_map_and_requests(set, i); for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; } kfree(set->tags); set->tags = NULL; } EXPORT_SYMBOL(blk_mq_free_tag_set); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; int i, ret; if (!set) return -EINVAL; if (q->nr_requests == nr) return 0; blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); ret = 0; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; /* * If we're using an MQ scheduler, just update the scheduler * queue depth. This is similar to what the old code would do. */ if (!hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } if (!ret) q->nr_requests = nr; blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); return ret; } /* * request_queue and elevator_type pair. * It is just used by __blk_mq_update_nr_hw_queues to cache * the elevator_type associated with a request_queue. */ struct blk_mq_qe_pair { struct list_head node; struct request_queue *q; struct elevator_type *type; }; /* * Cache the elevator_type in qe pair list and switch the * io scheduler to 'none' */ static bool blk_mq_elv_switch_none(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; if (!q->elevator) return true; qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; list_add(&qe->node, head); mutex_lock(&q->sysfs_lock); /* * After elevator_switch_mq, the previous elevator_queue will be * released by elevator_release. The reference of the io scheduler * module get by elevator_get will also be put. So we need to get * a reference of the io scheduler module here to prevent it to be * removed. */ __module_get(qe->type->elevator_owner); elevator_switch_mq(q, NULL); mutex_unlock(&q->sysfs_lock); return true; } static void blk_mq_elv_switch_back(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; struct elevator_type *t = NULL; list_for_each_entry(qe, head, node) if (qe->q == q) { t = qe->type; break; } if (!t) return; list_del(&qe->node); kfree(qe); mutex_lock(&q->sysfs_lock); elevator_switch_mq(q, t); mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues; lockdep_assert_held(&set->tag_list_lock); if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1) return; if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* * Sync with blk_mq_queue_tag_busy_iter. */ synchronize_rcu(); /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) if (!blk_mq_elv_switch_none(&head, q)) goto switch_back; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister(q); } prev_nr_hw_queues = set->nr_hw_queues; set->nr_hw_queues = nr_hw_queues; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); set->nr_hw_queues = prev_nr_hw_queues; blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); goto fallback; } blk_mq_map_swqueue(q); } list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register(q); blk_mq_debugfs_register_hctxs(q); } switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); /* Enable polling stats and return whether they were already enabled. */ static bool blk_poll_stats_enable(struct request_queue *q) { if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || blk_queue_flag_test_and_set(QUEUE_FLAG_POLL_STATS, q)) return true; blk_stat_add_callback(q, q->poll_cb); return false; } static void blk_mq_poll_stats_start(struct request_queue *q) { /* * We don't arm the callback if polling stats are not enabled or the * callback is already active. */ if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || blk_stat_is_active(q->poll_cb)) return; blk_stat_activate_msecs(q->poll_cb, 100); } static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb) { struct request_queue *q = cb->data; int bucket; for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) { if (cb->stat[bucket].nr_samples) q->poll_stat[bucket] = cb->stat[bucket]; } } static unsigned long blk_mq_poll_nsecs(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct request *rq) { unsigned long ret = 0; int bucket; /* * If stats collection isn't on, don't sleep but turn it on for * future users */ if (!blk_poll_stats_enable(q)) return 0; /* * As an optimistic guess, use half of the mean service time * for this type of request. We can (and should) make this smarter. * For instance, if the completion latencies are tight, we can * get closer than just half the mean. This is especially * important on devices where the completion latencies are longer * than ~10 usec. We do use the stats for the relevant IO size * if available which does lead to better estimates. */ bucket = blk_mq_poll_stats_bkt(rq); if (bucket < 0) return ret; if (q->poll_stat[bucket].nr_samples) ret = (q->poll_stat[bucket].mean + 1) / 2; return ret; } static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct request *rq) { struct hrtimer_sleeper hs; enum hrtimer_mode mode; unsigned int nsecs; ktime_t kt; if (rq->rq_flags & RQF_MQ_POLL_SLEPT) return false; /* * If we get here, hybrid polling is enabled. Hence poll_nsec can be: * * 0: use half of prev avg * >0: use this specific value */ if (q->poll_nsec > 0) nsecs = q->poll_nsec; else nsecs = blk_mq_poll_nsecs(q, hctx, rq); if (!nsecs) return false; rq->rq_flags |= RQF_MQ_POLL_SLEPT; /* * This will be replaced with the stats tracking code, using * 'avg_completion_time / 2' as the pre-sleep target. */ kt = nsecs; mode = HRTIMER_MODE_REL; hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode); hrtimer_set_expires(&hs.timer, kt); do { if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) break; set_current_state(TASK_UNINTERRUPTIBLE); hrtimer_sleeper_start_expires(&hs, mode); if (hs.task) io_schedule(); hrtimer_cancel(&hs.timer); mode = HRTIMER_MODE_ABS; } while (hs.task && !signal_pending(current)); __set_current_state(TASK_RUNNING); destroy_hrtimer_on_stack(&hs.timer); return true; } static bool blk_mq_poll_hybrid(struct request_queue *q, struct blk_mq_hw_ctx *hctx, blk_qc_t cookie) { struct request *rq; if (q->poll_nsec == BLK_MQ_POLL_CLASSIC) return false; if (!blk_qc_t_is_internal(cookie)) rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); else { rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); /* * With scheduling, if the request has completed, we'll * get a NULL return here, as we clear the sched tag when * that happens. The request still remains valid, like always, * so we should be safe with just the NULL check. */ if (!rq) return false; } return blk_mq_poll_hybrid_sleep(q, hctx, rq); } /** * blk_poll - poll for IO completions * @q: the queue * @cookie: cookie passed back at IO submission time * @spin: whether to spin for completions * * Description: * Poll for completions on the passed in queue. Returns number of * completed entries found. If @spin is true, then blk_poll will continue * looping until at least one completion is found, unless the task is * otherwise marked running (or we need to reschedule). */ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { struct blk_mq_hw_ctx *hctx; long state; if (!blk_qc_t_valid(cookie) || !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; if (current->plug) blk_flush_plug_list(current->plug, false); hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; /* * If we sleep, have the caller restart the poll loop to reset * the state. Like for the other success return cases, the * caller is responsible for checking if the IO completed. If * the IO isn't complete, we'll get called again and will go * straight to the busy poll loop. */ if (blk_mq_poll_hybrid(q, hctx, cookie)) return 1; hctx->poll_considered++; state = current->state; do { int ret; hctx->poll_invoked++; ret = q->mq_ops->poll(hctx); if (ret > 0) { hctx->poll_success++; __set_current_state(TASK_RUNNING); return ret; } if (signal_pending_state(state, current)) __set_current_state(TASK_RUNNING); if (current->state == TASK_RUNNING) return 1; if (ret < 0 || !spin) break; cpu_relax(); } while (!need_resched()); __set_current_state(TASK_RUNNING); return 0; } EXPORT_SYMBOL_GPL(blk_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; } EXPORT_SYMBOL(blk_mq_rq_cpu); static int __init blk_mq_init(void) { cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); return 0; } subsys_initcall(blk_mq_init);
15 842 474 12 2133 2081 2081 45 597 6 1350 606 20 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FREE_MORE_MEM, "free_more_memory") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EMe(WB_REASON_FORKER_THREAD, "forker_thread") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_page_template, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(unsigned long, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = page->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, __entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_page_template, writeback_dirty_page, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DEFINE_EVENT(writeback_page_template, wait_on_page_writeback, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(unsigned long, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, __entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return wb->memcg_css->cgroup->kn->id.ino; } static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return -1U; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return -1U; } static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return -1U; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, ino) __field(unsigned int, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%u history=0x%x", __entry->name, __entry->ino, __entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, ino) __field(unsigned int, old_cgroup_ino) __field(unsigned int, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%u new_cgroup_ino=%u", __entry->name, __entry->ino, __entry->old_cgroup_ino, __entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct page *page, struct bdi_writeback *wb), TP_ARGS(page, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(unsigned long, ino) __field(unsigned int, memcg_id) __field(unsigned int, cgroup_ino) __field(unsigned int, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino; ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%u page_cgroup_ino=%u", __entry->name, __entry->bdi_id, __entry->ino, __entry->memcg_id, __entry->cgroup_ino, __entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned int, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%u frn_bdi_id=%u frn_memcg_id=%u", __entry->name, __entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(unsigned long, ino) __field(int, sync_mode) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u", __entry->name, __entry->ino, __entry->sync_mode, __entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), __entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%u", __entry->name, __entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%u", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, __entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), __entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, nr_unstable) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu unstable=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->nr_unstable, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%u", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ __entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(unsigned int, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ __entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u", __entry->name, __entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_congest_waited_template, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed), TP_STRUCT__entry( __field( unsigned int, usec_timeout ) __field( unsigned int, usec_delayed ) ), TP_fast_assign( __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; ), TP_printk("usec_timeout=%u usec_delayed=%u", __entry->usec_timeout, __entry->usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(unsigned int, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u", __entry->name, __entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, __entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
17 17 16 1 17 7 11 18 18 18 18 11 11 6 6 6 6 280 280 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 /* * Performance events x86 architecture code * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * * For licencing details see kernel-base/COPYING */ #include <linux/perf_event.h> #include <linux/capability.h> #include <linux/notifier.h> #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kdebug.h> #include <linux/sched/mm.h> #include <linux/sched/clock.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> #include <linux/nospec.h> #include <asm/apic.h> #include <asm/stacktrace.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/alternative.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/timer.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/unwind.h> #include "perf_event.h" struct x86_pmu x86_pmu __read_mostly; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; /* * Propagate event elapsed time into the generic event. * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; int idx = hwc->idx; u64 delta; if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* * Careful: an NMI might modify the previous event value. * * Our tactic to handle this is to first atomically read and * exchange a new raw count - then add that new-prev delta * count to the generic event atomically: */ again: prev_raw_count = local64_read(&hwc->prev_count); rdpmcl(hwc->event_base_rdpmc, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); return new_raw_count; } /* * Find and validate any extra registers to set up. */ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) { struct hw_perf_event_extra *reg; struct extra_reg *er; reg = &event->hw.extra_reg; if (!x86_pmu.extra_regs) return 0; for (er = x86_pmu.extra_regs; er->msr; er++) { if (er->event != (config & er->config_mask)) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; /* Check if the extra msrs can be safely accessed*/ if (!er->extra_msr_access) return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; reg->reg = er->msr; break; } return 0; } static atomic_t active_events; static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC static bool reserve_pmc_hardware(void) { int i; for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu_event_addr(i))) goto perfctr_fail; } for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_evntsel_nmi(x86_pmu_config_addr(i))) goto eventsel_fail; } return true; eventsel_fail: for (i--; i >= 0; i--) release_evntsel_nmi(x86_pmu_config_addr(i)); i = x86_pmu.num_counters; perfctr_fail: for (i--; i >= 0; i--) release_perfctr_nmi(x86_pmu_event_addr(i)); return false; } static void release_pmc_hardware(void) { int i; for (i = 0; i < x86_pmu.num_counters; i++) { release_perfctr_nmi(x86_pmu_event_addr(i)); release_evntsel_nmi(x86_pmu_config_addr(i)); } } #else static bool reserve_pmc_hardware(void) { return true; } static void release_pmc_hardware(void) {} #endif static bool check_hw_exists(void) { u64 val, val_fail = -1, val_new= ~0; int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; /* * Check to see if the BIOS enabled any of the counters, if so * complain and bail. */ for (i = 0; i < x86_pmu.num_counters; i++) { reg = x86_pmu_config_addr(i); ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; if (val & ARCH_PERFMON_EVENTSEL_ENABLE) { bios_fail = 1; val_fail = val; reg_fail = reg; } else { reg_safe = i; } } if (x86_pmu.num_counters_fixed) { reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; for (i = 0; i < x86_pmu.num_counters_fixed; i++) { if (val & (0x03 << i*4)) { bios_fail = 1; val_fail = val; reg_fail = reg; } } } /* * If all the counters are enabled, the below test will always * fail. The tools will also become useless in this scenario. * Just fail and disable the hardware counters. */ if (reg_safe == -1) { reg = reg_safe; goto msr_fail; } /* * Read the current value, change it and read it back to see if it * matches, this is needed to detect certain hardware emulators * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ reg = x86_pmu_event_addr(reg_safe); if (rdmsrl_safe(reg, &val)) goto msr_fail; val ^= 0xffffUL; ret = wrmsrl_safe(reg, val); ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) goto msr_fail; /* * We still allow the PMU driver to operate: */ if (bios_fail) { pr_cont("Broken BIOS detected, complain to your hardware vendor.\n"); pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); } return true; msr_fail: if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { pr_cont("PMU not available due to virtualization, using software events only.\n"); } else { pr_cont("Broken PMU hardware detected, using software events only.\n"); pr_err("Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); } return false; } static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) { hw_perf_event_destroy(event); /* undo the lbr/bts event accounting */ x86_del_exclusive(x86_lbr_exclusive_lbr); } static inline int x86_pmu_initialized(void) { return x86_pmu.handle_irq != NULL; } static inline int set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) { struct perf_event_attr *attr = &event->attr; unsigned int cache_type, cache_op, cache_result; u64 config, val; config = attr->config; cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hw_cache_event_ids[cache_type][cache_op][cache_result]; if (val == 0) return -ENOENT; if (val == -1) return -EINVAL; hwc->config |= val; attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result]; return x86_pmu_extra_regs(val, event); } int x86_reserve_hardware(void) { int err = 0; if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; else reserve_ds_buffers(); } if (!err) atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } return err; } void x86_release_hardware(void) { if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); } } /* * Check if we can create event of a certain type (that no conflicting events * are present). */ int x86_add_exclusive(unsigned int what) { int i; /* * When lbr_pt_coexist we allow PT to coexist with either LBR or BTS. * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) goto fail_unlock; } atomic_inc(&x86_pmu.lbr_exclusive[what]); mutex_unlock(&pmc_reserve_mutex); } out: atomic_inc(&active_events); return 0; fail_unlock: mutex_unlock(&pmc_reserve_mutex); return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&active_events); /* * See the comment in x86_add_exclusive(). */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); } int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; u64 config; if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } if (attr->type == PERF_TYPE_RAW) return x86_pmu_extra_regs(event->attr.config, event); if (attr->type == PERF_TYPE_HW_CACHE) return set_ext_hw_attr(hwc, event); if (attr->config >= x86_pmu.max_events) return -EINVAL; attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); /* * The generic map: */ config = x86_pmu.event_map(attr->config); if (config == 0) return -ENOENT; if (config == -1LL) return -EINVAL; hwc->config |= config; return 0; } /* * check that branch_sample_type is compatible with * settings needed for precise_ip > 1 which implies * using the LBR to capture ALL taken branches at the * priv levels of the measurement */ static inline int precise_br_compat(struct perf_event *event) { u64 m = event->attr.branch_sample_type; u64 b = 0; /* must capture all branches */ if (!(m & PERF_SAMPLE_BRANCH_ANY)) return 0; m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_user) b |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) b |= PERF_SAMPLE_BRANCH_KERNEL; /* * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86 */ return m == b; } int x86_pmu_max_precise(void) { int precise = 0; /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; if (x86_pmu.pebs_prec_dist) precise++; } return precise; } int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = x86_pmu_max_precise(); if (event->attr.precise_ip > precise) return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; } /* * check that PEBS LBR correction does not conflict with * whatever the user is asking with attr->branch_sample_type */ if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) { u64 *br_type = &event->attr.branch_sample_type; if (has_branch_stack(event)) { if (!precise_br_compat(event)) return -EOPNOTSUPP; /* branch_sample_type is compatible */ } else { /* * user did not specify branch_sample_type * * For PEBS fixups, we capture all * the branches at the priv level of the * event. */ *br_type = PERF_SAMPLE_BRANCH_ANY; if (!event->attr.exclude_user) *br_type |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) *br_type |= PERF_SAMPLE_BRANCH_KERNEL; } } if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK) event->attach_state |= PERF_ATTACH_TASK_DATA; /* * Generate PMC IRQs: * (keep 'enabled' bit clear for now) */ event->hw.config = ARCH_PERFMON_EVENTSEL_INT; /* * Count user and OS events unless requested not to */ if (!event->attr.exclude_user) event->hw.config |= ARCH_PERFMON_EVENTSEL_USR; if (!event->attr.exclude_kernel) event->hw.config |= ARCH_PERFMON_EVENTSEL_OS; if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; if (event->attr.sample_period && x86_pmu.limit_period) { if (x86_pmu.limit_period(event, event->attr.sample_period) > event->attr.sample_period) return -EINVAL; } /* sample_regs_user never support XMM registers */ if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK)) return -EINVAL; /* * Besides the general purpose registers, XMM registers may * be collected in PEBS on some platforms, e.g. Icelake */ if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) { if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS)) return -EINVAL; if (!event->attr.precise_ip) return -EINVAL; } return x86_setup_perfctr(event); } /* * Setup the hardware configuration for a given attr_type */ static int __x86_pmu_event_init(struct perf_event *event) { int err; if (!x86_pmu_initialized()) return -ENODEV; err = x86_reserve_hardware(); if (err) return err; atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; event->hw.last_cpu = -1; event->hw.last_tag = ~0ULL; /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; event->hw.branch_reg.idx = EXTRA_REG_NONE; return x86_pmu.hw_config(event); } void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { u64 val; if (!test_bit(idx, cpuc->active_mask)) continue; rdmsrl(x86_pmu_config_addr(idx), val); if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu_config_addr(idx), val); } } /* * There may be PMI landing after enabled=0. The PMI hitting could be before or * after disable_all. * * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. * It will not be re-enabled in the NMI handler again, because enabled=0. After * handling the NMI, disable_all will be called, which will not change the * state either. If PMI hits after disable_all, the PMU is already disabled * before entering NMI handler. The NMI handler will not change the state * either. * * So either situation is harmless. */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu_initialized()) return; if (!cpuc->enabled) return; cpuc->n_added = 0; cpuc->enabled = 0; barrier(); x86_pmu.disable_all(); } void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { struct hw_perf_event *hwc = &cpuc->events[idx]->hw; if (!test_bit(idx, cpuc->active_mask)) continue; __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } } static struct pmu pmu; static inline int is_x86_event(struct perf_event *event) { return event->pmu == &pmu; } struct pmu *x86_get_pmu(void) { return &pmu; } /* * Event scheduler state: * * Assign events iterating over all events and counters, beginning * with events with least weights first. Keep the current iterator * state in struct sched_state. */ struct sched_state { int weight; int event; /* event index */ int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ #define SCHED_STATES_MAX 2 struct perf_sched { int max_weight; int max_events; int max_gp; int saved_states; struct event_constraint **constraints; struct sched_state state; struct sched_state saved[SCHED_STATES_MAX]; }; /* * Initialize interator that runs through all events and counters. */ static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, int num, int wmin, int wmax, int gpmax) { int idx; memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; sched->max_gp = gpmax; sched->constraints = constraints; for (idx = 0; idx < num; idx++) { if (constraints[idx]->weight == wmin) break; } sched->state.event = idx; /* start with min weight */ sched->state.weight = wmin; sched->state.unassigned = num; } static void perf_sched_save_state(struct perf_sched *sched) { if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX)) return; sched->saved[sched->saved_states] = sched->state; sched->saved_states++; } static bool perf_sched_restore_state(struct perf_sched *sched) { if (!sched->saved_states) return false; sched->saved_states--; sched->state = sched->saved[sched->saved_states]; /* continue with next counter: */ clear_bit(sched->state.counter++, sched->state.used); return true; } /* * Select a counter for the current event to schedule. Return true on * success. */ static bool __perf_sched_find_counter(struct perf_sched *sched) { struct event_constraint *c; int idx; if (!sched->state.unassigned) return false; if (sched->state.event >= sched->max_events) return false; c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) { if (sched->state.nr_gp++ >= sched->max_gp) return false; goto done; } } return false; done: sched->state.counter = idx; if (c->overlap) perf_sched_save_state(sched); return true; } static bool perf_sched_find_counter(struct perf_sched *sched) { while (!__perf_sched_find_counter(sched)) { if (!perf_sched_restore_state(sched)) return false; } return true; } /* * Go through all unassigned events and find the next one to schedule. * Take events with the least weight first. Return true on success. */ static bool perf_sched_next_event(struct perf_sched *sched) { struct event_constraint *c; if (!sched->state.unassigned || !--sched->state.unassigned) return false; do { /* next event */ sched->state.event++; if (sched->state.event >= sched->max_events) { /* next weight */ sched->state.event = 0; sched->state.weight++; if (sched->state.weight > sched->max_weight) return false; } c = sched->constraints[sched->state.event]; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ return true; } /* * Assign a counter for each event. */ int perf_assign_events(struct event_constraint **constraints, int n, int wmin, int wmax, int gpmax, int *assign) { struct perf_sched sched; perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax); do { if (!perf_sched_find_counter(&sched)) break; /* failed */ if (assign) assign[sched.state.event] = sched.state.counter; } while (perf_sched_next_event(&sched)); return sched.state.unassigned; } EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); /* * Compute the number of events already present; see x86_pmu_add(), * validate_group() and x86_pmu_commit_txn(). For the former two * cpuc->n_events hasn't been updated yet, while for the latter * cpuc->n_txn contains the number of events added in the current * transaction. */ n0 = cpuc->n_events; if (cpuc->txn_flags & PERF_PMU_TXN_ADD) n0 -= cpuc->n_txn; if (x86_pmu.start_scheduling) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { c = cpuc->event_constraint[i]; /* * Previously scheduled events should have a cached constraint, * while new events should not have one. */ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); /* * Request constraints for new events; or for those events that * have a dynamic constraint -- for those the constraint can * change due to external factors (sibling state, allow_tfa). */ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); cpuc->event_constraint[i] = c; } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } /* * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) break; /* constraint still honored */ if (!test_bit(hwc->idx, c->idxmsk)) break; /* not already used */ if (test_bit(hwc->idx, used_mask)) break; __set_bit(hwc->idx, used_mask); if (assign) assign[i] = hwc->idx; } /* slow path */ if (i != n) { int gpmax = x86_pmu.num_counters; /* * Do not allow scheduling of more than half the available * generic counters. * * This helps avoid counter starvation of sibling thread by * ensuring at most half the counters cannot be in exclusive * mode. There is no designated counters for the limits. Any * N/2 counters can be used. This helps with events with * specific counter constraints. */ if (is_ht_workaround_enabled() && !cpuc->is_fake && READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } /* * In case of success (unsched = 0), mark events as committed, * so we do not put_constraint() in case new events are added * and fail to be scheduled * * We invoke the lower level commit callback to lock the resource * * We do not need to do all of this in case we are called to * validate an event group (assign == NULL) */ if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } } else { for (i = n0; i < n; i++) { e = cpuc->event_list[i]; /* * release events that failed scheduling */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); cpuc->event_constraint[i] = NULL; } } if (x86_pmu.stop_scheduling) x86_pmu.stop_scheduling(cpuc); return unsched ? -EINVAL : 0; } /* * dogrp: true if must collect siblings events (group) * returns total number of events and error code */ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp) { struct perf_event *event; int n, max_count; max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed; /* current number of events already accepted */ n = cpuc->n_events; if (!cpuc->n_events) cpuc->pebs_output = 0; if (!cpuc->is_fake && leader->attr.precise_ip) { /* * For PEBS->PT, if !aux_event, the group leader (PT) went * away, the group was broken down and this singleton event * can't schedule any more. */ if (is_pebs_pt(leader) && !leader->aux_event) return -EINVAL; /* * pebs_output: 0: no PEBS so far, 1: PT, 2: DS */ if (cpuc->pebs_output && cpuc->pebs_output != is_pebs_pt(leader) + 1) return -EINVAL; cpuc->pebs_output = is_pebs_pt(leader) + 1; } if (is_x86_event(leader)) { if (n >= max_count) return -EINVAL; cpuc->event_list[n] = leader; n++; } if (!dogrp) return n; for_each_sibling_event(event, leader) { if (!is_x86_event(event) || event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) return -EINVAL; cpuc->event_list[n] = event; n++; } return n; } static inline void x86_assign_hw_event(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { struct hw_perf_event *hwc = &event->hw; hwc->idx = cpuc->assign[i]; hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) { hwc->config_base = 0; hwc->event_base = 0; } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) { hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED); hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30; } else { hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx); } } /** * x86_perf_rdpmc_index - Return PMC counter used for event * @event: the perf_event to which the PMC counter was assigned * * The counter assigned to this performance event may change if interrupts * are enabled. This counter should thus never be used while interrupts are * enabled. Before this function is used to obtain the assigned counter the * event should be checked for validity using, for example, * perf_event_read_local(), within the same interrupt disabled section in * which this counter is planned to be used. * * Return: The index of the performance monitoring counter assigned to * @perf_event. */ int x86_perf_rdpmc_index(struct perf_event *event) { lockdep_assert_irqs_disabled(); return event->hw.event_base_rdpmc; } static inline int match_prev_assignment(struct hw_perf_event *hwc, struct cpu_hw_events *cpuc, int i) { return hwc->idx == cpuc->assign[i] && hwc->last_cpu == smp_processor_id() && hwc->last_tag == cpuc->tags[i]; } static void x86_pmu_start(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; int i, added = cpuc->n_added; if (!x86_pmu_initialized()) return; if (cpuc->enabled) return; if (cpuc->n_added) { int n_running = cpuc->n_events - cpuc->n_added; /* * apply assignment obtained either from * hw_perf_group_sched_in() or x86_pmu_enable() * * step1: save events moving to new counters */ for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; hwc = &event->hw; /* * we can avoid reprogramming counter if: * - assigned same counter as last time * - running on same CPU as last time * - no other event has used the counter since */ if (hwc->idx == -1 || match_prev_assignment(hwc, cpuc, i)) continue; /* * Ensure we don't accidentally enable a stopped * counter simply because we rescheduled. */ if (hwc->state & PERF_HES_STOPPED) hwc->state |= PERF_HES_ARCH; x86_pmu_stop(event, PERF_EF_UPDATE); } /* * step2: reprogram moved events into new counters */ for (i = 0; i < cpuc->n_events; i++) { event = cpuc->event_list[i]; hwc = &event->hw; if (!match_prev_assignment(hwc, cpuc, i)) x86_assign_hw_event(event, cpuc, i); else if (i < n_running) continue; if (hwc->state & PERF_HES_ARCH) continue; x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; perf_events_lapic_init(); } cpuc->enabled = 1; barrier(); x86_pmu.enable_all(added); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* * If we are way outside a reasonable range then just skip forward: */ if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } /* * Quirk: certain CPUs dont like it if just 1 hw_event is left: */ if (unlikely(left < 2)) left = 2; if (left > x86_pmu.max_period) left = x86_pmu.max_period; if (x86_pmu.limit_period) left = x86_pmu.limit_period(event, left); per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ local64_set(&hwc->prev_count, (u64)-left); wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Due to erratum on certan cpu we need * a second write to be sure the register * is updated properly */ if (x86_pmu.perfctr_second_write) { wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); } perf_event_update_userpage(event); return ret; } void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, ARCH_PERFMON_EVENTSEL_ENABLE); } /* * Add a single event to the PMU. * * The event is added to the group of enabled events * but only if it can be scheduled with existing events. */ static int x86_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc; int assign[X86_PMC_IDX_MAX]; int n, n0, ret; hwc = &event->hw; n0 = cpuc->n_events; ret = n = collect_events(cpuc, event, false); if (ret < 0) goto out; hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (!(flags & PERF_EF_START)) hwc->state |= PERF_HES_ARCH; /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. * * If commit fails, we'll call ->del() on all events * for which ->add() was called. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) goto out; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); done_collect: /* * Commit the collect_events() state. See x86_pmu_del() and * x86_pmu_*_txn(). */ cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; if (x86_pmu.add) { /* * This is before x86_pmu_enable() will call x86_pmu_start(), * so we enable LBRs before an event needs them etc.. */ x86_pmu.add(event); } ret = 0; out: return ret; } static void x86_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = event->hw.idx; if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; if (WARN_ON_ONCE(idx == -1)) return; if (flags & PERF_EF_RELOAD) { WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); x86_perf_event_set_period(event); } event->hw.state = 0; cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); __set_bit(idx, cpuc->running); x86_pmu.enable(event); perf_event_update_userpage(event); } void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; u64 pebs, debugctl; struct cpu_hw_events *cpuc; unsigned long flags; int cpu, idx; if (!x86_pmu.num_counters) return; local_irq_save(flags); cpu = smp_processor_id(); cpuc = &per_cpu(cpu_hw_events, cpu); if (x86_pmu.version >= 2) { rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl); rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); if (x86_pmu.pebs_constraints) { rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); } if (x86_pmu.lbr_nr) { rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl); } } pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for (idx = 0; idx < x86_pmu.num_counters; idx++) { rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl); rdmsrl(x86_pmu_event_addr(idx), pmc_count); prev_left = per_cpu(pmc_prev_left[idx], cpu); pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n", cpu, idx, pmc_ctrl); pr_info("CPU#%d: gen-PMC%d count: %016llx\n", cpu, idx, pmc_count); pr_info("CPU#%d: gen-PMC%d left: %016llx\n", cpu, idx, prev_left); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) { rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", cpu, idx, pmc_count); } local_irq_restore(flags); } void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ x86_perf_event_update(event); hwc->state |= PERF_HES_UPTODATE; } } static void x86_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. * * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto do_del; /* * Not a TXN, therefore cleanup properly. */ x86_pmu_stop(event, PERF_EF_UPDATE); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) break; } if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */ return; /* If we have a newly added event; make sure to decrease n_added. */ if (i >= cpuc->n_events - cpuc->n_added) --cpuc->n_added; if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); /* Delete the array entry. */ while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; perf_event_update_userpage(event); do_del: if (x86_pmu.del) { /* * This is after x86_pmu_stop(); so we disable LBRs after any * event can need them etc.. */ x86_pmu.del(event); } } int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; struct perf_event *event; int idx, handled = 0; u64 val; cpuc = this_cpu_ptr(&cpu_hw_events); /* * Some chipsets need to unmask the LVTPC in a particular spot * inside the nmi handler. As a result, the unmasking was pushed * into all the nmi handlers. * * This generic handler doesn't seem to have any issues where the * unmasking occurs so it was left at the top. */ apic_write(APIC_LVTPC, APIC_DM_NMI); for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; event = cpuc->events[idx]; val = x86_perf_event_update(event); if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; /* * event overflow */ handled++; perf_sample_data_init(&data, 0, event->hw.last_period); if (!x86_perf_event_set_period(event)) continue; if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } if (handled) inc_irq_stat(apic_perf_irqs); return handled; } void perf_events_lapic_init(void) { if (!x86_pmu.apic || !x86_pmu_initialized()) return; /* * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); } static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { u64 start_clock; u64 finish_clock; int ret; /* * All PMUs/events that share this PMI handler should make sure to * increment active_events for their events. */ if (!atomic_read(&active_events)) return NMI_DONE; start_clock = sched_clock(); ret = x86_pmu.handle_irq(regs); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); return ret; } NOKPROBE_SYMBOL(perf_event_nmi_handler); struct event_constraint emptyconstraint; struct event_constraint unconstrained; static int x86_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) cpuc->kfree_on_online[i] = NULL; if (x86_pmu.cpu_prepare) return x86_pmu.cpu_prepare(cpu); return 0; } static int x86_pmu_dead_cpu(unsigned int cpu) { if (x86_pmu.cpu_dead) x86_pmu.cpu_dead(cpu); return 0; } static int x86_pmu_online_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) { kfree(cpuc->kfree_on_online[i]); cpuc->kfree_on_online[i] = NULL; } return 0; } static int x86_pmu_starting_cpu(unsigned int cpu) { if (x86_pmu.cpu_starting) x86_pmu.cpu_starting(cpu); return 0; } static int x86_pmu_dying_cpu(unsigned int cpu) { if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); return 0; } static void __init pmu_check_apic(void) { if (boot_cpu_has(X86_FEATURE_APIC)) return; x86_pmu.apic = 0; pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); pr_info("no hardware sampling interrupt available.\n"); /* * If we have a PMU initialized but no APIC * interrupts, we cannot sample hardware * events (user-space has to fall back and * sample via a hrtimer based software event): */ pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } static struct attribute_group x86_pmu_format_group __ro_after_init = { .name = "format", .attrs = NULL, }; ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); u64 config = 0; if (pmu_attr->id < x86_pmu.max_events) config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) return sprintf(page, "%s", pmu_attr->event_str); return x86_pmu.events_sysfs_show(page, config); } EXPORT_SYMBOL_GPL(events_sysfs_show); ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_ht_attr *pmu_attr = container_of(attr, struct perf_pmu_events_ht_attr, attr); /* * Report conditional events depending on Hyper-Threading. * * This is overly conservative as usually the HT special * handling is not needed if the other CPU thread is idle. * * Note this does not (and cannot) handle the case when thread * siblings are invisible, for example with virtualization * if they are owned by some other guest. The user tool * has to re-read when a thread sibling gets onlined later. */ return sprintf(page, "%s", topology_max_smt_threads() > 1 ? pmu_attr->event_str_ht : pmu_attr->event_str_noht); } EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); EVENT_ATTR(cache-references, CACHE_REFERENCES ); EVENT_ATTR(cache-misses, CACHE_MISSES ); EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); EVENT_ATTR(branch-misses, BRANCH_MISSES ); EVENT_ATTR(bus-cycles, BUS_CYCLES ); EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); static struct attribute *empty_attrs; static struct attribute *events_attr[] = { EVENT_PTR(CPU_CYCLES), EVENT_PTR(INSTRUCTIONS), EVENT_PTR(CACHE_REFERENCES), EVENT_PTR(CACHE_MISSES), EVENT_PTR(BRANCH_INSTRUCTIONS), EVENT_PTR(BRANCH_MISSES), EVENT_PTR(BUS_CYCLES), EVENT_PTR(STALLED_CYCLES_FRONTEND), EVENT_PTR(STALLED_CYCLES_BACKEND), EVENT_PTR(REF_CPU_CYCLES), NULL, }; /* * Remove all undefined events (x86_pmu.event_map(id) == 0) * out of events_attr attributes. */ static umode_t is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; if (idx >= x86_pmu.max_events) return 0; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; } static struct attribute_group x86_pmu_events_group __ro_after_init = { .name = "events", .attrs = events_attr, .is_visible = is_visible, }; ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) { u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); ssize_t ret; /* * We have whole page size to spend and just little data * to write, so we can safely use sprintf. */ ret = sprintf(page, "event=0x%02llx", event); if (umask) ret += sprintf(page + ret, ",umask=0x%02llx", umask); if (edge) ret += sprintf(page + ret, ",edge"); if (pc) ret += sprintf(page + ret, ",pc"); if (any) ret += sprintf(page + ret, ",any"); if (inv) ret += sprintf(page + ret, ",inv"); if (cmask) ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); ret += sprintf(page + ret, "\n"); return ret; } static struct attribute_group x86_pmu_attr_group; static struct attribute_group x86_pmu_caps_group; static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; int err; pr_info("Performance Events: "); switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: err = intel_pmu_init(); break; case X86_VENDOR_AMD: err = amd_pmu_init(); break; case X86_VENDOR_HYGON: err = amd_pmu_init(); x86_pmu.name = "HYGON"; break; default: err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); return 0; } pmu_check_apic(); /* sanity check that the hardware exists or is emulated */ if (!check_hw_exists()) return 0; pr_cont("%s PMU driver.\n", x86_pmu.name); x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); if (!x86_pmu.intel_ctrl) x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; perf_events_lapic_init(); register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0, 0); x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; pmu.attr_update = x86_pmu.attr_update; pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask); pr_info("... max period: %016Lx\n", x86_pmu.max_period); pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); /* * Install callbacks. Core will call them for each online * cpu. */ err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare", x86_pmu_prepare_cpu, x86_pmu_dead_cpu); if (err) return err; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING, "perf/x86:starting", x86_pmu_starting_cpu, x86_pmu_dying_cpu); if (err) goto out; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online", x86_pmu_online_cpu, NULL); if (err) goto out1; err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); if (err) goto out2; return 0; out2: cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE); out1: cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING); out: cpuhp_remove_state(CPUHP_PERF_X86_PREPARE); return err; } early_initcall(init_hw_perf_events); static inline void x86_pmu_read(struct perf_event *event) { if (x86_pmu.read) return x86_pmu.read(event); x86_perf_event_update(event); } /* * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time * * We only support PERF_PMU_TXN_ADD transactions. Save the * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD * transactions. */ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ cpuc->txn_flags = txn_flags; if (txn_flags & ~PERF_PMU_TXN_ADD) return; perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); } /* * Stop group events scheduling transaction * Clear the flag and pmu::enable() will perform the * schedulability test. */ static void x86_pmu_cancel_txn(struct pmu *pmu) { unsigned int txn_flags; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ txn_flags = cpuc->txn_flags; cpuc->txn_flags = 0; if (txn_flags & ~PERF_PMU_TXN_ADD) return; /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); perf_pmu_enable(pmu); } /* * Commit group events scheduling transaction * Perform the group schedulability test as a whole * Return 0 if success * * Does not cancel the transaction on failure; expects the caller to do this. */ static int x86_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int assign[X86_PMC_IDX_MAX]; int n, ret; WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { cpuc->txn_flags = 0; return 0; } n = cpuc->n_events; if (!x86_pmu_initialized()) return -EAGAIN; ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) return ret; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } /* * a fake_cpuc is used to validate event groups. Due to * the extra reg logic, we need to also allocate a fake * per_core and per_cpu structure. Otherwise, group events * using extra reg may conflict without the kernel being * able to catch this when the last event gets added to * the group. */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { intel_cpuc_finish(cpuc); kfree(cpuc); } static struct cpu_hw_events *allocate_fake_cpuc(void) { struct cpu_hw_events *cpuc; int cpu = raw_smp_processor_id(); cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); if (!cpuc) return ERR_PTR(-ENOMEM); cpuc->is_fake = 1; if (intel_cpuc_prepare(cpuc, cpu)) goto error; return cpuc; error: free_fake_cpuc(cpuc); return ERR_PTR(-ENOMEM); } /* * validate that we can schedule this event */ static int validate_event(struct perf_event *event) { struct cpu_hw_events *fake_cpuc; struct event_constraint *c; int ret = 0; fake_cpuc = allocate_fake_cpuc(); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(fake_cpuc, event); free_fake_cpuc(fake_cpuc); return ret; } /* * validate a single event group * * validation include: * - check events are compatible which each other * - events do not compete for the same counter * - number of events <= number of counters * * validation ensures the group can be loaded onto the * PMU if it was the only group available. */ static int validate_group(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct cpu_hw_events *fake_cpuc; int ret = -EINVAL, n; fake_cpuc = allocate_fake_cpuc(); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); /* * the event is not yet connected with its * siblings therefore we must first collect * existing siblings, then add the new event * before we can simulate the scheduling */ n = collect_events(fake_cpuc, leader, true); if (n < 0) goto out; fake_cpuc->n_events = n; n = collect_events(fake_cpuc, event, false); if (n < 0) goto out; fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: free_fake_cpuc(fake_cpuc); return ret; } static int x86_pmu_event_init(struct perf_event *event) { struct pmu *tmp; int err; switch (event->attr.type) { case PERF_TYPE_RAW: case PERF_TYPE_HARDWARE: case PERF_TYPE_HW_CACHE: break; default: return -ENOENT; } err = __x86_pmu_event_init(event); if (!err) { /* * we temporarily connect event to its pmu * such that validate_group() can classify * it as an x86 event using is_x86_event() */ tmp = event->pmu; event->pmu = &pmu; if (event->group_leader != event) err = validate_group(event); else err = validate_event(event); event->pmu = tmp; } if (err) { if (event->destroy) event->destroy(event); event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; } static void refresh_pce(void *ignored) { load_mm_cr4_irqsoff(this_cpu_read(cpu_tlbstate.loaded_mm)); } static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; /* * This function relies on not being called concurrently in two * tasks in the same mm. Otherwise one task could observe * perf_rdpmc_allowed > 1 and return all the way back to * userspace with CR4.PCE clear while another task is still * doing on_each_cpu_mask() to propagate CR4.PCE. * * For now, this can't happen because all callers hold mmap_sem * for write. If this changes, we'll need a different solution. */ lockdep_assert_held_write(&mm->mmap_sem); if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) { int idx = event->hw.idx; if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return 0; if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) { idx -= INTEL_PMC_IDX_FIXED; idx |= 1 << 30; } return idx + 1; } static ssize_t get_attr_rdpmc(struct device *cdev, struct device_attribute *attr, char *buf) { return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc); } static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long val; ssize_t ret; ret = kstrtoul(buf, 0, &val); if (ret) return ret; if (val > 2) return -EINVAL; if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) { /* * Changing into or out of always available, aka * perf-event-bypassing mode. This path is extremely slow, * but only root can trigger it, so it's okay. */ if (val == 2) static_branch_inc(&rdpmc_always_available_key); else static_branch_dec(&rdpmc_always_available_key); on_each_cpu(refresh_pce, NULL, 1); } x86_pmu.attr_rdpmc = val; return count; } static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc); static struct attribute *x86_pmu_attrs[] = { &dev_attr_rdpmc.attr, NULL, }; static struct attribute_group x86_pmu_attr_group __ro_after_init = { .attrs = x86_pmu_attrs, }; static ssize_t max_precise_show(struct device *cdev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise()); } static DEVICE_ATTR_RO(max_precise); static struct attribute *x86_pmu_caps_attrs[] = { &dev_attr_max_precise.attr, NULL }; static struct attribute_group x86_pmu_caps_group __ro_after_init = { .name = "caps", .attrs = x86_pmu_caps_attrs, }; static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, &x86_pmu_events_group, &x86_pmu_caps_group, NULL, }; static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { if (x86_pmu.sched_task) x86_pmu.sched_task(ctx, sched_in); } void perf_check_microcode(void) { if (x86_pmu.check_microcode) x86_pmu.check_microcode(); } static int x86_pmu_check_period(struct perf_event *event, u64 value) { if (x86_pmu.check_period && x86_pmu.check_period(event, value)) return -EINVAL; if (value && x86_pmu.limit_period) { if (x86_pmu.limit_period(event, value) > value) return -EINVAL; } return 0; } static int x86_pmu_aux_output_match(struct perf_event *event) { if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT)) return 0; if (x86_pmu.aux_output_match) return x86_pmu.aux_output_match(event); return 0; } static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, .attr_groups = x86_pmu_attr_groups, .event_init = x86_pmu_event_init, .event_mapped = x86_pmu_event_mapped, .event_unmapped = x86_pmu_event_unmapped, .add = x86_pmu_add, .del = x86_pmu_del, .start = x86_pmu_start, .stop = x86_pmu_stop, .read = x86_pmu_read, .start_txn = x86_pmu_start_txn, .cancel_txn = x86_pmu_cancel_txn, .commit_txn = x86_pmu_commit_txn, .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .task_ctx_size = sizeof(struct x86_perf_task_context), .check_period = x86_pmu_check_period, .aux_output_match = x86_pmu_aux_output_match, }; void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); userpg->pmc_width = x86_pmu.cntval_bits; if (!using_native_sched_clock() || !sched_clock_stable()) return; cyc2ns_read_begin(&data); offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; userpg->time_mult = data.cyc2ns_mul; userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different * time base for the records. */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; userpg->time_zero = offset; } cyc2ns_read_end(); } /* * Determine whether the regs were taken from an irq/exception handler rather * than from perf_arch_fetch_caller_regs(). */ static bool perf_hw_regs(struct pt_regs *regs) { return regs->flags & X86_EFLAGS_FIXED; } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct unwind_state state; unsigned long addr; if (guest_cbs && guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } if (perf_callchain_store(entry, regs->ip)) return; if (perf_hw_regs(regs)) unwind_start(&state, current, regs, NULL); else unwind_start(&state, current, NULL, (void *)regs->sp); for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; } } static inline int valid_user_frame(const void __user *fp, unsigned long size) { return (__range_not_ok(fp, size, TASK_SIZE) == 0); } static unsigned long get_segment_base(unsigned int segment) { struct desc_struct *desc; unsigned int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; #else return 0; #endif } else { if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; } return get_desc_base(desc); } #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { /* 32-bit process in 64-bit kernel. */ unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const void __user *fp; if (!test_thread_flag(TIF_IA32)) return 0; cs_base = get_segment_base(regs->cs); ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; if (!valid_user_frame(fp, sizeof(frame))) break; bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); if (bytes != 0) break; bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } pagefault_enable(); return 1; } #else static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { return 0; } #endif void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stack_frame frame; const unsigned long __user *fp; if (guest_cbs && guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } /* * We don't know what to do with VM86 stacks.. ignore them for now. */ if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); if (!nmi_uaccess_okay()) return; if (perf_callchain_user32(regs, entry)) return; pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; if (!valid_user_frame(fp, sizeof(frame))) break; bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; perf_callchain_store(entry, frame.return_address); fp = (void __user *)frame.next_frame; } pagefault_enable(); } /* * Deal with code segment offsets for the various execution modes: * * VM86 - the good olde 16 bit days, where the linear address is * 20 bits and we use regs->ip + 0x10 * regs->cs. * * IA32 - Where we need to look at GDT/LDT segment descriptor tables * to figure out what the 32bit base address is. * * X32 - has TIF_X32 set, but is running in x86_64 * * X86_64 - CS,DS,SS,ES are all zero based. */ static unsigned long code_segment_base(struct pt_regs *regs) { /* * For IA32 we look at the GDT/LDT segment base to convert the * effective IP to a linear address. */ #ifdef CONFIG_X86_32 /* * If we are in VM86 mode, add the segment offset to convert to a * linear address. */ if (regs->flags & X86_VM_MASK) return 0x10 * regs->cs; if (user_mode(regs) && regs->cs != __USER_CS) return get_segment_base(regs->cs); #else if (user_mode(regs) && !user_64bit_mode(regs) && regs->cs != __USER32_CS) return get_segment_base(regs->cs); #endif return 0; } unsigned long perf_instruction_pointer(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); if (guest_cbs && guest_cbs->is_in_guest()) return guest_cbs->get_guest_ip(); return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); int misc = 0; if (guest_cbs && guest_cbs->is_in_guest()) { if (guest_cbs->is_user_mode()) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { if (user_mode(regs)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; } if (regs->flags & PERF_EFLAGS_EXACT) misc |= PERF_RECORD_MISC_EXACT_IP; return misc; } void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu.num_counters; cap->num_counters_fixed = x86_pmu.num_counters_fixed; cap->bit_width_gp = x86_pmu.cntval_bits; cap->bit_width_fixed = x86_pmu.cntval_bits; cap->events_mask = (unsigned int)x86_pmu.events_maskl; cap->events_mask_len = x86_pmu.events_mask_len; } EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability);
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the seven * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, page_to_pfn(page)); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline void make_device_private_entry_read(swp_entry_t *entry) { *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); } static inline bool is_write_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) { return swp_offset(entry); } static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { return swp_entry(0, 0); } static inline void make_device_private_entry_read(swp_entry_t *entry) { } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_write_device_private_entry(swp_entry_t entry) { return false; } static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) { return 0; } static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { BUG_ON(!PageLocked(compound_head(page))); return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, page_to_pfn(page)); } static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_write_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) { return swp_offset(entry); } static inline struct page *migration_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(!PageLocked(compound_head(p))); return p; } static inline void make_migration_entry_read(swp_entry_t *entry) { *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else #define make_migration_entry(page, write) swp_entry(0, 0) static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) { return 0; } static inline struct page *migration_entry_to_page(swp_entry_t entry) { return NULL; } static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } static inline int is_write_migration_entry(swp_entry_t entry) { return 0; } #endif struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif #ifdef CONFIG_MEMORY_FAILURE extern atomic_long_t num_poisoned_pages __read_mostly; /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } static inline void num_poisoned_pages_dec(void) { atomic_long_dec(&num_poisoned_pages); } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } static inline void num_poisoned_pages_inc(void) { } #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #else static inline int non_swap_entry(swp_entry_t entry) { return 0; } #endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */
141 292 982 1918 411 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 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/rculist.h> #include <linux/wait.h> #include <linux/refcount.h> enum pid_type { PIDTYPE_PID, PIDTYPE_TGID, PIDTYPE_PGID, PIDTYPE_SID, PIDTYPE_MAX, }; /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[1]; }; extern struct pid init_struct_pid; extern const struct file_operations pidfd_fops; struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); struct pid_namespace; extern struct pid_namespace init_pid_ns; /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) #endif /* _LINUX_PID_H */
1 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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * CIPSO - Commercial IP Security Option * * This is an implementation of the CIPSO 2.2 protocol as specified in * draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in * FIPS-188, copies of both documents can be found in the Documentation * directory. While CIPSO never became a full IETF RFC standard many vendors * have chosen to adopt the protocol and over the years it has become a * de-facto standard for labeled networking. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 */ #ifndef _CIPSO_IPV4_H #define _CIPSO_IPV4_H #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/net.h> #include <linux/skbuff.h> #include <net/netlabel.h> #include <net/request_sock.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <asm/unaligned.h> /* known doi values */ #define CIPSO_V4_DOI_UNKNOWN 0x00000000 /* standard tag types */ #define CIPSO_V4_TAG_INVALID 0 #define CIPSO_V4_TAG_RBITMAP 1 #define CIPSO_V4_TAG_ENUM 2 #define CIPSO_V4_TAG_RANGE 5 #define CIPSO_V4_TAG_PBITMAP 6 #define CIPSO_V4_TAG_FREEFORM 7 /* non-standard tag types (tags > 127) */ #define CIPSO_V4_TAG_LOCAL 128 /* doi mapping types */ #define CIPSO_V4_MAP_UNKNOWN 0 #define CIPSO_V4_MAP_TRANS 1 #define CIPSO_V4_MAP_PASS 2 #define CIPSO_V4_MAP_LOCAL 3 /* limits */ #define CIPSO_V4_MAX_REM_LVLS 255 #define CIPSO_V4_INV_LVL 0x80000000 #define CIPSO_V4_MAX_LOC_LVLS (CIPSO_V4_INV_LVL - 1) #define CIPSO_V4_MAX_REM_CATS 65534 #define CIPSO_V4_INV_CAT 0x80000000 #define CIPSO_V4_MAX_LOC_CATS (CIPSO_V4_INV_CAT - 1) /* * CIPSO DOI definitions */ /* DOI definition struct */ #define CIPSO_V4_TAG_MAXCNT 5 struct cipso_v4_doi { u32 doi; u32 type; union { struct cipso_v4_std_map_tbl *std; } map; u8 tags[CIPSO_V4_TAG_MAXCNT]; refcount_t refcount; struct list_head list; struct rcu_head rcu; }; /* Standard CIPSO mapping table */ /* NOTE: the highest order bit (i.e. 0x80000000) is an 'invalid' flag, if the * bit is set then consider that value as unspecified, meaning the * mapping for that particular level/category is invalid */ struct cipso_v4_std_map_tbl { struct { u32 *cipso; u32 *local; u32 cipso_size; u32 local_size; } lvl; struct { u32 *cipso; u32 *local; u32 cipso_size; u32 local_size; } cat; }; /* * Sysctl Variables */ #ifdef CONFIG_NETLABEL extern int cipso_v4_cache_enabled; extern int cipso_v4_cache_bucketsize; extern int cipso_v4_rbm_optfmt; extern int cipso_v4_rbm_strictvalid; #endif /* * DOI List Functions */ #ifdef CONFIG_NETLABEL int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, struct netlbl_audit *audit_info); void cipso_v4_doi_free(struct cipso_v4_doi *doi_def); int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info); struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi); void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def); int cipso_v4_doi_walk(u32 *skip_cnt, int (*callback) (struct cipso_v4_doi *doi_def, void *arg), void *cb_arg); #else static inline int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) { return; } static inline int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) { return 0; } static inline struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) { return NULL; } static inline int cipso_v4_doi_walk(u32 *skip_cnt, int (*callback) (struct cipso_v4_doi *doi_def, void *arg), void *cb_arg) { return 0; } static inline int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def, const char *domain) { return -ENOSYS; } static inline int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def, const char *domain) { return 0; } #endif /* CONFIG_NETLABEL */ /* * Label Mapping Cache Functions */ #ifdef CONFIG_NETLABEL void cipso_v4_cache_invalidate(void); int cipso_v4_cache_add(const unsigned char *cipso_ptr, const struct netlbl_lsm_secattr *secattr); #else static inline void cipso_v4_cache_invalidate(void) { return; } static inline int cipso_v4_cache_add(const unsigned char *cipso_ptr, const struct netlbl_lsm_secattr *secattr) { return 0; } #endif /* CONFIG_NETLABEL */ /* * Protocol Handling Functions */ #ifdef CONFIG_NETLABEL void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway); int cipso_v4_getattr(const unsigned char *cipso, struct netlbl_lsm_secattr *secattr); int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void cipso_v4_sock_delattr(struct sock *sk); int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); int cipso_v4_req_setattr(struct request_sock *req, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void cipso_v4_req_delattr(struct request_sock *req); int cipso_v4_skbuff_setattr(struct sk_buff *skb, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr); int cipso_v4_skbuff_delattr(struct sk_buff *skb); int cipso_v4_skbuff_getattr(const struct sk_buff *skb, struct netlbl_lsm_secattr *secattr); unsigned char *cipso_v4_optptr(const struct sk_buff *skb); int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option); #else static inline void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { return; } static inline int cipso_v4_getattr(const unsigned char *cipso, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline void cipso_v4_sock_delattr(struct sock *sk) { } static inline int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int cipso_v4_req_setattr(struct request_sock *req, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline void cipso_v4_req_delattr(struct request_sock *req) { return; } static inline int cipso_v4_skbuff_setattr(struct sk_buff *skb, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int cipso_v4_skbuff_delattr(struct sk_buff *skb) { return -ENOSYS; } static inline int cipso_v4_skbuff_getattr(const struct sk_buff *skb, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline unsigned char *cipso_v4_optptr(const struct sk_buff *skb) { return NULL; } static inline int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) { unsigned char *opt = *option; unsigned char err_offset = 0; u8 opt_len = opt[1]; u8 opt_iter; u8 tag_len; if (opt_len < 8) { err_offset = 1; goto out; } if (get_unaligned_be32(&opt[2]) == 0) { err_offset = 2; goto out; } for (opt_iter = 6; opt_iter < opt_len;) { if (opt_iter + 1 == opt_len) { err_offset = opt_iter; goto out; } tag_len = opt[opt_iter + 1]; if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) { err_offset = opt_iter + 1; goto out; } opt_iter += tag_len; } out: *option = opt + err_offset; return err_offset; } #endif /* CONFIG_NETLABEL */ #endif /* _CIPSO_IPV4_H */
1183 1183 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 // SPDX-License-Identifier: GPL-2.0 /* * Wakeup statistics in sysfs * * Copyright (c) 2019 Linux Foundation * Copyright (c) 2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2019 Google Inc. */ #include <linux/device.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/kobject.h> #include <linux/slab.h> #include <linux/timekeeping.h> #include "power.h" static struct class *wakeup_class; #define wakeup_attr(_name) \ static ssize_t _name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct wakeup_source *ws = dev_get_drvdata(dev); \ \ return sprintf(buf, "%lu\n", ws->_name); \ } \ static DEVICE_ATTR_RO(_name) wakeup_attr(active_count); wakeup_attr(event_count); wakeup_attr(wakeup_count); wakeup_attr(expire_count); static ssize_t active_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); ktime_t active_time = ws->active ? ktime_sub(ktime_get(), ws->last_time) : 0; return sysfs_emit(buf, "%lld\n", ktime_to_ms(active_time)); } static DEVICE_ATTR_RO(active_time_ms); static ssize_t total_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); ktime_t active_time; ktime_t total_time = ws->total_time; if (ws->active) { active_time = ktime_sub(ktime_get(), ws->last_time); total_time = ktime_add(total_time, active_time); } return sysfs_emit(buf, "%lld\n", ktime_to_ms(total_time)); } static DEVICE_ATTR_RO(total_time_ms); static ssize_t max_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); ktime_t active_time; ktime_t max_time = ws->max_time; if (ws->active) { active_time = ktime_sub(ktime_get(), ws->last_time); if (active_time > max_time) max_time = active_time; } return sysfs_emit(buf, "%lld\n", ktime_to_ms(max_time)); } static DEVICE_ATTR_RO(max_time_ms); static ssize_t last_change_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); return sysfs_emit(buf, "%lld\n", ktime_to_ms(ws->last_time)); } static DEVICE_ATTR_RO(last_change_ms); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); return sysfs_emit(buf, "%s\n", ws->name); } static DEVICE_ATTR_RO(name); static ssize_t prevent_suspend_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wakeup_source *ws = dev_get_drvdata(dev); ktime_t prevent_sleep_time = ws->prevent_sleep_time; if (ws->active && ws->autosleep_enabled) { prevent_sleep_time = ktime_add(prevent_sleep_time, ktime_sub(ktime_get(), ws->start_prevent_time)); } return sysfs_emit(buf, "%lld\n", ktime_to_ms(prevent_sleep_time)); } static DEVICE_ATTR_RO(prevent_suspend_time_ms); static struct attribute *wakeup_source_attrs[] = { &dev_attr_name.attr, &dev_attr_active_count.attr, &dev_attr_event_count.attr, &dev_attr_wakeup_count.attr, &dev_attr_expire_count.attr, &dev_attr_active_time_ms.attr, &dev_attr_total_time_ms.attr, &dev_attr_max_time_ms.attr, &dev_attr_last_change_ms.attr, &dev_attr_prevent_suspend_time_ms.attr, NULL, }; ATTRIBUTE_GROUPS(wakeup_source); static void device_create_release(struct device *dev) { kfree(dev); } static struct device *wakeup_source_device_create(struct device *parent, struct wakeup_source *ws) { struct device *dev = NULL; int retval = -ENODEV; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { retval = -ENOMEM; goto error; } device_initialize(dev); dev->devt = MKDEV(0, 0); dev->class = wakeup_class; dev->parent = parent; dev->groups = wakeup_source_groups; dev->release = device_create_release; dev_set_drvdata(dev, ws); device_set_pm_not_required(dev); retval = kobject_set_name(&dev->kobj, "wakeup%d", ws->id); if (retval) goto error; retval = device_add(dev); if (retval) goto error; return dev; error: put_device(dev); return ERR_PTR(retval); } /** * wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs. * @parent: Device given wakeup source is associated with (or NULL if virtual). * @ws: Wakeup source to be added in sysfs. */ int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws) { struct device *dev; dev = wakeup_source_device_create(parent, ws); if (IS_ERR(dev)) return PTR_ERR(dev); ws->dev = dev; return 0; } /** * pm_wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs * for a device if they're missing. * @parent: Device given wakeup source is associated with */ int pm_wakeup_source_sysfs_add(struct device *parent) { if (!parent->power.wakeup || parent->power.wakeup->dev) return 0; return wakeup_source_sysfs_add(parent, parent->power.wakeup); } /** * wakeup_source_sysfs_remove - Remove wakeup_source attributes from sysfs. * @ws: Wakeup source to be removed from sysfs. */ void wakeup_source_sysfs_remove(struct wakeup_source *ws) { device_unregister(ws->dev); } static int __init wakeup_sources_sysfs_init(void) { wakeup_class = class_create(THIS_MODULE, "wakeup"); return PTR_ERR_OR_ZERO(wakeup_class); } postcore_initcall(wakeup_sources_sysfs_init);
6 8766 8762 8762 2 2 2 5 4 5 5 8763 8760 8766 8763 8760 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 // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *parent; unsigned long flags; /* nothing to do for root */ if (!cgroup_parent(cgrp)) return; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) return; raw_spin_lock_irqsave(cpu_lock, flags); /* put @cgrp and all ancestors on the corresponding updated lists */ for (parent = cgroup_parent(cgrp); parent; cgrp = parent, parent = cgroup_parent(cgrp)) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; } raw_spin_unlock_irqrestore(cpu_lock, flags); } EXPORT_SYMBOL_GPL(cgroup_rstat_updated); /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree * @pos: current position * @root: root of the tree to traversal * @cpu: target cpu * * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, if a child is visited, its parent is * guaranteed to be visited afterwards. */ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; if (pos == root) return NULL; /* * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ if (!pos) pos = root; else pos = cgroup_parent(pos); /* walk down to the first leaf */ while (true) { rstatc = cgroup_rstat_cpu(pos, cpu); if (rstatc->updated_children == pos) break; pos = rstatc->updated_children; } /* * Unlink @pos from the tree. As the updated_children list is * singly linked, we have to walk it to find the removal point. * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ if (rstatc->updated_next) { struct cgroup *parent = cgroup_parent(pos); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); struct cgroup_rstat_cpu *nrstatc; struct cgroup **nextp; nextp = &prstatc->updated_children; while (true) { nrstatc = cgroup_rstat_cpu(*nextp, cpu); if (*nextp == pos) break; WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; rstatc->updated_next = NULL; return pos; } /* only happens for @root */ return NULL; } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } raw_spin_unlock(cpu_lock); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || spin_needbreak(&cgroup_rstat_lock))) { spin_unlock_irq(&cgroup_rstat_lock); if (!cond_resched()) cpu_relax(); spin_lock_irq(&cgroup_rstat_lock); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) { unsigned long flags; spin_lock_irqsave(&cgroup_rstat_lock, flags); cgroup_rstat_flush_locked(cgrp, false); spin_unlock_irqrestore(&cgroup_rstat_lock, flags); } /** * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() */ void cgroup_rstat_flush_release(void) __releases(&cgroup_rstat_lock) { spin_unlock_irq(&cgroup_rstat_lock); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct task_cputime *last_cputime = &rstatc->last_bstat.cputime; struct task_cputime cputime; struct cgroup_base_stat delta; unsigned seq; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* calculate the delta to propgate */ delta.cputime.utime = cputime.utime - last_cputime->utime; delta.cputime.stime = cputime.stime - last_cputime->stime; delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime - last_cputime->sum_exec_runtime; *last_cputime = cputime; /* transfer the pending stat into delta */ cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat); memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat)); /* propagate delta into the global stat and the parent's pending */ cgroup_base_stat_accumulate(&cgrp->bstat, &delta); if (parent) cgroup_base_stat_accumulate(&parent->pending_bstat, &delta); } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); u64_stats_update_begin(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc) { u64_stats_update_end(&rstatc->bsync); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc); } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; if (!cgroup_parent(cgrp)) return; cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); cgroup_rstat_flush_release(); do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); }
410 13 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM task #if !defined(_TRACE_TASK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TASK_H #include <linux/tracepoint.h> TRACE_EVENT(task_newtask, TP_PROTO(struct task_struct *task, unsigned long clone_flags), TP_ARGS(task, clone_flags), TP_STRUCT__entry( __field( pid_t, pid) __array( char, comm, TASK_COMM_LEN) __field( unsigned long, clone_flags) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->clone_flags = clone_flags; __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%hd", __entry->pid, __entry->comm, __entry->clone_flags, __entry->oom_score_adj) ); TRACE_EVENT(task_rename, TP_PROTO(struct task_struct *task, const char *comm), TP_ARGS(task, comm), TP_STRUCT__entry( __field( pid_t, pid) __array( char, oldcomm, TASK_COMM_LEN) __array( char, newcomm, TASK_COMM_LEN) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN); strlcpy(entry->newcomm, comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd", __entry->pid, __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h>
1131 1 1131 1125 86 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 /* * Functions related to generic timeout handling of requests. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/fault-inject.h> #include "blk.h" #include "blk-mq.h" #ifdef CONFIG_FAIL_IO_TIMEOUT static DECLARE_FAULT_ATTR(fail_io_timeout); static int __init setup_fail_io_timeout(char *str) { return setup_fault_attr(&fail_io_timeout, str); } __setup("fail_io_timeout=", setup_fail_io_timeout); int blk_should_fake_timeout(struct request_queue *q) { if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return 0; return should_fail(&fail_io_timeout, 1); } static int __init fail_io_timeout_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout", NULL, &fail_io_timeout); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_io_timeout_debugfs); ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags); return sprintf(buf, "%d\n", set != 0); } ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); int val; if (count) { struct request_queue *q = disk->queue; char *p = (char *) buf; val = simple_strtoul(p, &p, 10); if (val) blk_queue_flag_set(QUEUE_FLAG_FAIL_IO, q); else blk_queue_flag_clear(QUEUE_FLAG_FAIL_IO, q); } return count; } #endif /* CONFIG_FAIL_IO_TIMEOUT */ /** * blk_abort_request -- Request request recovery for the specified command * @req: pointer to the request of interest * * This function requests that the block layer start recovery for the * request by deleting the timer and calling the q's timeout function. * LLDDs who implement their own error recovery MAY ignore the timeout * event if they generated blk_abort_request. */ void blk_abort_request(struct request *req) { /* * All we need to ensure is that timeout scan takes place * immediately and that scan sees the new timeout value. * No need for fancy synchronizations. */ WRITE_ONCE(req->deadline, jiffies); kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); unsigned long blk_rq_timeout(unsigned long timeout) { unsigned long maxt; maxt = round_jiffies_up(jiffies + BLK_MAX_TIMEOUT); if (time_after(timeout, maxt)) timeout = maxt; return timeout; } /** * blk_add_timer - Start timeout timer for a single request * @req: request that is about to start running. * * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; /* * Some LLDs, like scsi, peek at the timeout to prevent a * command from being retried forever. */ if (!req->timeout) req->timeout = q->rq_timeout; req->rq_flags &= ~RQF_TIMED_OUT; expiry = jiffies + req->timeout; WRITE_ONCE(req->deadline, expiry); /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest * second. */ expiry = blk_rq_timeout(round_jiffies_up(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { unsigned long diff = q->timeout.expires - expiry; /* * Due to added timer slack to group timers, the timer * will often be a little in front of what we asked for. * So apply some tolerance here too, otherwise we keep * modifying the timer because expires for value X * will be X + something. */ if (!timer_pending(&q->timeout) || (diff >= HZ / 2)) mod_timer(&q->timeout, expiry); } }
3 3 3 3 3 5709 5716 1749 5689 5829 5829 2245 5802 3 7 3 8 11 6 3 7 11 6 6 6 3 13 39 7 3 2 39 3 3 10 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 // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/export.h> #include <linux/thread_info.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> #include <asm/page.h> #include "kstrtox.h" /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return 0; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 0; return 1; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return 1; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 1; return 0; } EXPORT_SYMBOL(__bitmap_intersects); int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return 0; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 0; return 1; } EXPORT_SYMBOL(__bitmap_subset); int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; int w = 0; for (k = 0; k < lim; k++) w += hweight_long(bitmap[k]); if (bits % BITS_PER_LONG) w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); return w; } EXPORT_SYMBOL(__bitmap_weight); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /* * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers, * second version by Paul Jackson, third by Joe Korty. */ #define CHUNKSZ 32 #define nbits_to_hold_value(val) fls(val) #define BASEDEC 10 /* fancier cpuset lists input in decimal */ /** * __bitmap_parse - convert an ASCII hex string into a bitmap. * @buf: pointer to buffer containing string. * @buflen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @is_user: location of buffer, 0 indicates kernel space * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * * Commas group hex digits into chunks. Each chunk defines exactly 32 * bits of the resultant bitmask. No chunk may specify a value larger * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value * then leading 0-bits are prepended. %-EINVAL is returned for illegal * characters and for grouping errors such as "1,,5", ",44", "," and "". * Leading and trailing whitespace accepted, but not embedded whitespace. */ int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, unsigned long *maskp, int nmaskbits) { int c, old_c, totaldigits, ndigits, nchunks, nbits; u32 chunk; const char __user __force *ubuf = (const char __user __force *)buf; bitmap_zero(maskp, nmaskbits); nchunks = nbits = totaldigits = c = 0; do { chunk = 0; ndigits = totaldigits; /* Get the next chunk of the bitmap */ while (buflen) { old_c = c; if (is_user) { if (__get_user(c, ubuf++)) return -EFAULT; } else c = *buf++; buflen--; if (isspace(c)) continue; /* * If the last character was a space and the current * character isn't '\0', we've got embedded whitespace. * This is a no-no, so throw an error. */ if (totaldigits && c && isspace(old_c)) return -EINVAL; /* A '\0' or a ',' signal the end of the chunk */ if (c == '\0' || c == ',') break; if (!isxdigit(c)) return -EINVAL; /* * Make sure there are at least 4 free bits in 'chunk'. * If not, this hexdigit will overflow 'chunk', so * throw an error. */ if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1)) return -EOVERFLOW; chunk = (chunk << 4) | hex_to_bin(c); totaldigits++; } if (ndigits == totaldigits) return -EINVAL; if (nchunks == 0 && chunk == 0) continue; __bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits); *maskp |= chunk; nchunks++; nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ; if (nbits > nmaskbits) return -EOVERFLOW; } while (buflen && c == ','); return 0; } EXPORT_SYMBOL(__bitmap_parse); /** * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap * * @ubuf: pointer to user buffer containing string. * @ulen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * * Wrapper for __bitmap_parse(), providing it with user buffer. * * We cannot have this as an inline function in bitmap.h because it needs * linux/uaccess.h to get the access_ok() declaration and this causes * cyclic dependencies. */ int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *maskp, int nmaskbits) { if (!access_ok(ubuf, ulen)) return -EFAULT; return __bitmap_parse((const char __force *)ubuf, ulen, 1, maskp, nmaskbits); } EXPORT_SYMBOL(bitmap_parse_user); /** * bitmap_print_to_pagebuf - convert bitmap to list or hex format ASCII string * @list: indicates whether the bitmap must be list * @buf: page aligned buffer into which string is placed * @maskp: pointer to bitmap to convert * @nmaskbits: size of bitmap, in bits * * Output format is a comma-separated list of decimal numbers and * ranges if list is specified or hex digits grouped into comma-separated * sets of 8 digits/set. Returns the number of characters written to buf. * * It is assumed that @buf is a pointer into a PAGE_SIZE, page-aligned * area and that sufficient storage remains at @buf to accommodate the * bitmap_print_to_pagebuf() output. Returns the number of characters * actually printed to @buf, excluding terminating '\0'. */ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits) { ptrdiff_t len = PAGE_SIZE - offset_in_page(buf); return list ? scnprintf(buf, len, "%*pbl\n", nmaskbits, maskp) : scnprintf(buf, len, "%*pb\n", nmaskbits, maskp); } EXPORT_SYMBOL(bitmap_print_to_pagebuf); /* * Region 9-38:4/10 describes the following bitmap structure: * 0 9 12 18 38 * .........****......****......****...... * ^ ^ ^ ^ * start off group_len end */ struct region { unsigned int start; unsigned int off; unsigned int group_len; unsigned int end; }; static int bitmap_set_region(const struct region *r, unsigned long *bitmap, int nbits) { unsigned int start; if (r->end >= nbits) return -ERANGE; for (start = r->start; start <= r->end; start += r->group_len) bitmap_set(bitmap, start, min(r->end - start + 1, r->off)); return 0; } static int bitmap_check_region(const struct region *r) { if (r->start > r->end || r->group_len == 0 || r->off > r->group_len) return -EINVAL; return 0; } static const char *bitmap_getnum(const char *str, unsigned int *num) { unsigned long long n; unsigned int len; len = _parse_integer(str, 10, &n); if (!len) return ERR_PTR(-EINVAL); if (len & KSTRTOX_OVERFLOW || n != (unsigned int)n) return ERR_PTR(-EOVERFLOW); *num = n; return str + len; } static inline bool end_of_str(char c) { return c == '\0' || c == '\n'; } static inline bool __end_of_region(char c) { return isspace(c) || c == ','; } static inline bool end_of_region(char c) { return __end_of_region(c) || end_of_str(c); } /* * The format allows commas and whitespases at the beginning * of the region. */ static const char *bitmap_find_region(const char *str) { while (__end_of_region(*str)) str++; return end_of_str(*str) ? NULL : str; } static const char *bitmap_parse_region(const char *str, struct region *r) { str = bitmap_getnum(str, &r->start); if (IS_ERR(str)) return str; if (end_of_region(*str)) goto no_end; if (*str != '-') return ERR_PTR(-EINVAL); str = bitmap_getnum(str + 1, &r->end); if (IS_ERR(str)) return str; if (end_of_region(*str)) goto no_pattern; if (*str != ':') return ERR_PTR(-EINVAL); str = bitmap_getnum(str + 1, &r->off); if (IS_ERR(str)) return str; if (*str != '/') return ERR_PTR(-EINVAL); return bitmap_getnum(str + 1, &r->group_len); no_end: r->end = r->start; no_pattern: r->off = r->end + 1; r->group_len = r->end + 1; return end_of_str(*str) ? NULL : str; } /** * bitmap_parselist - convert list format ASCII string to bitmap * @buf: read user string from this buffer; must be terminated * with a \0 or \n. * @maskp: write resulting mask here * @nmaskbits: number of bits in mask to be written * * Input format is a comma-separated list of decimal numbers and * ranges. Consecutively set bits are shown as two hyphen-separated * decimal numbers, the smallest and largest bit numbers set in * the range. * Optionally each range can be postfixed to denote that only parts of it * should be set. The range will divided to groups of specific size. * From each group will be used only defined amount of bits. * Syntax: range:used_size/group_size * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769 * * Returns: 0 on success, -errno on invalid input strings. Error values: * * - ``-EINVAL``: wrong region format * - ``-EINVAL``: invalid character in string * - ``-ERANGE``: bit number specified too large for mask * - ``-EOVERFLOW``: integer overflow in the input parameters */ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits) { struct region r; long ret; bitmap_zero(maskp, nmaskbits); while (buf) { buf = bitmap_find_region(buf); if (buf == NULL) return 0; buf = bitmap_parse_region(buf, &r); if (IS_ERR(buf)) return PTR_ERR(buf); ret = bitmap_check_region(&r); if (ret) return ret; ret = bitmap_set_region(&r, maskp, nmaskbits); if (ret) return ret; } return 0; } EXPORT_SYMBOL(bitmap_parselist); /** * bitmap_parselist_user() * * @ubuf: pointer to user buffer containing string. * @ulen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * * Wrapper for bitmap_parselist(), providing it with user buffer. */ int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *maskp, int nmaskbits) { char *buf; int ret; buf = memdup_user_nul(ubuf, ulen); if (IS_ERR(buf)) return PTR_ERR(buf); ret = bitmap_parselist(buf, maskp, nmaskbits); kfree(buf); return ret; } EXPORT_SYMBOL(bitmap_parselist_user); #ifdef CONFIG_NUMA /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return __bitmap_weight(buf, pos); } /** * bitmap_ord_to_pos - find position of n-th set bit in bitmap * @buf: pointer to bitmap * @ord: ordinal bit position (n-th set bit, n >= 0) * @nbits: number of valid bit positions in @buf * * Map the ordinal offset of bit @ord in @buf to its position in @buf. * Value of @ord should be in range 0 <= @ord < weight(buf). If @ord * >= weight(buf), returns @nbits. * * If for example, just bits 4 through 7 are set in @buf, then @ord * values 0 through 3 will get mapped to 4 through 7, respectively, * and all other @ord values returns @nbits. When @ord value 3 * gets mapped to (returns) @pos value 7 in this example, that means * that the 3rd set bit (starting with 0th) is at position 7 in @buf. * * The bit positions 0 through @nbits-1 are valid positions in @buf. */ unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits) { unsigned int pos; for (pos = find_first_bit(buf, nbits); pos < nbits && ord; pos = find_next_bit(buf, nbits, pos + 1)) ord--; return pos; } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identify map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst); } } /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identify map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return bitmap_ord_to_pos(new, n % w, bits); } /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated *