diff options
Diffstat (limited to 'kernel/kprobes.c')
-rw-r--r-- | kernel/kprobes.c | 1332 |
1 files changed, 863 insertions, 469 deletions
diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 2625c241ac00..cd9f5a66a690 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * Kernel Probes (KProbes) - * kernel/kprobes.c * * Copyright (C) IBM Corporation, 2002, 2004 * @@ -18,6 +17,9 @@ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ + +#define pr_fmt(fmt) "kprobes: " fmt + #include <linux/kprobes.h> #include <linux/hash.h> #include <linux/init.h> @@ -35,6 +37,8 @@ #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/jump_label.h> +#include <linux/static_call.h> +#include <linux/perf_event.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -44,20 +48,24 @@ #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) +#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL) +#define kprobe_sysctls_init() do { } while (0) +#endif static int kprobes_initialized; +/* kprobe_table can be accessed by + * - Normal hlist traversal and RCU add/del under 'kprobe_mutex' is held. + * Or + * - RCU hlist traversal under disabling preempt (breakpoint handlers) + */ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; -static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; -/* NOTE: change this value only with kprobe_mutex held */ +/* NOTE: change this value only with 'kprobe_mutex' held */ static bool kprobes_all_disarmed; -/* This protects kprobe_table and optimizing_list */ +/* This protects 'kprobe_table' and 'optimizing_list' */ static DEFINE_MUTEX(kprobe_mutex); -static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; -static struct { - raw_spinlock_t lock ____cacheline_aligned_in_smp; -} kretprobe_table_locks[KPROBE_TABLE_SIZE]; +static DEFINE_PER_CPU(struct kprobe *, kprobe_instance); kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, unsigned int __unused) @@ -65,17 +73,15 @@ kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, return ((kprobe_opcode_t *)(kallsyms_lookup_name(name))); } -static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) -{ - return &(kretprobe_table_locks[hash].lock); -} - -/* Blacklist -- list of struct kprobe_blacklist_entry */ +/* + * Blacklist -- list of 'struct kprobe_blacklist_entry' to store info where + * kprobes can not probe. + */ static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* - * kprobe->ainsn.insn points to the copy of the instruction to be + * 'kprobe::ainsn.insn' points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster @@ -106,10 +112,16 @@ enum kprobe_slot_state { void __weak *alloc_insn_page(void) { + /* + * Use module_alloc() so this page is within +/- 2GB of where the + * kernel image and loaded module images reside. This is required + * for most of the architectures. + * (e.g. x86-64 needs this to handle the %rip-relative fixups.) + */ return module_alloc(PAGE_SIZE); } -void __weak free_insn_page(void *page) +static void free_insn_page(void *page) { module_memfree(page); } @@ -118,6 +130,7 @@ struct kprobe_insn_cache kprobe_insn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, + .sym = KPROBE_INSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), .insn_size = MAX_INSN_SIZE, .nr_garbage = 0, @@ -140,6 +153,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; @@ -165,11 +179,6 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) if (!kip) goto out; - /* - * Use module_alloc so this page is within +/- 2GB of where the - * kernel image and loaded module images reside. This is required - * so x86_64 can correctly handle the %rip-relative fixups. - */ kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); @@ -183,13 +192,17 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) kip->cache = c; list_add_rcu(&kip->list, &c->pages); slot = kip->insns; + + /* Record the perf ksymbol register event after adding the page */ + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, + PAGE_SIZE, false, c->sym); out: mutex_unlock(&c->mutex); return slot; } -/* Return 1 if all garbages are collected, otherwise 0. */ -static int collect_one_slot(struct kprobe_insn_page *kip, int idx) +/* Return true if all garbages are collected, otherwise false. */ +static bool collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; @@ -201,14 +214,21 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) * next time somebody inserts a probe. */ if (!list_is_singular(&kip->list)) { + /* + * Record perf ksymbol unregister event before removing + * the page. + */ + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, + (unsigned long)kip->insns, PAGE_SIZE, true, + kip->cache->sym); list_del_rcu(&kip->list); synchronize_rcu(); kip->cache->free(kip->insns); kfree(kip); } - return 1; + return true; } - return 0; + return false; } static int collect_garbage_slots(struct kprobe_insn_cache *c) @@ -220,6 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c) list_for_each_entry_safe(kip, next, &c->pages, list) { int i; + if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ @@ -290,12 +311,44 @@ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr) return ret; } +int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, + unsigned long *value, char *type, char *sym) +{ + struct kprobe_insn_page *kip; + int ret = -ERANGE; + + rcu_read_lock(); + list_for_each_entry_rcu(kip, &c->pages, list) { + if ((*symnum)--) + continue; + strscpy(sym, c->sym, KSYM_NAME_LEN); + *type = 't'; + *value = (unsigned long)kip->insns; + ret = 0; + break; + } + rcu_read_unlock(); + + return ret; +} + #ifdef CONFIG_OPTPROBES +void __weak *alloc_optinsn_page(void) +{ + return alloc_insn_page(); +} + +void __weak free_optinsn_page(void *page) +{ + free_insn_page(page); +} + /* For optimized_kprobe buffer */ struct kprobe_insn_cache kprobe_optinsn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex), - .alloc = alloc_insn_page, - .free = free_insn_page, + .alloc = alloc_optinsn_page, + .free = free_optinsn_page, + .sym = KPROBE_OPTINSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), /* .insn_size is initialized later */ .nr_garbage = 0, @@ -316,9 +369,9 @@ static inline void reset_kprobe_instance(void) /* * This routine is called either: - * - under the kprobe_mutex - during kprobe_[un]register() - * OR - * - with preemption disabled - from arch/xxx/kernel/kprobes.c + * - under the 'kprobe_mutex' - during kprobe_[un]register(). + * OR + * - with preemption disabled - from architecture specific code. */ struct kprobe *get_kprobe(void *addr) { @@ -326,7 +379,8 @@ struct kprobe *get_kprobe(void *addr) struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; - hlist_for_each_entry_rcu(p, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist, + lockdep_is_held(&kprobe_mutex)) { if (p->addr == addr) return p; } @@ -337,22 +391,20 @@ NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); -/* Return true if the kprobe is an aggregator */ -static inline int kprobe_aggrprobe(struct kprobe *p) +/* Return true if 'p' is an aggregator */ +static inline bool kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } -/* Return true(!0) if the kprobe is unused */ -static inline int kprobe_unused(struct kprobe *p) +/* Return true if 'p' is unused */ +static inline bool kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); } -/* - * Keep all fields in the kprobe consistent - */ +/* Keep all fields in the kprobe consistent. */ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) { memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); @@ -360,11 +412,11 @@ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) } #ifdef CONFIG_OPTPROBES -/* NOTE: change this value only with kprobe_mutex held */ +/* NOTE: This is protected by 'kprobe_mutex'. */ static bool kprobes_allow_optimization; /* - * Call all pre_handler on the list, but ignores its return value. + * Call all 'kprobe::pre_handler' on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) @@ -392,7 +444,7 @@ static void free_aggr_kprobe(struct kprobe *p) kfree(op); } -/* Return true(!0) if the kprobe is ready for optimization. */ +/* Return true if the kprobe is ready for optimization. */ static inline int kprobe_optready(struct kprobe *p) { struct optimized_kprobe *op; @@ -405,8 +457,8 @@ static inline int kprobe_optready(struct kprobe *p) return 0; } -/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */ -static inline int kprobe_disarmed(struct kprobe *p) +/* Return true if the kprobe is disarmed. Note: p must be on hash list */ +static inline bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; @@ -419,32 +471,32 @@ static inline int kprobe_disarmed(struct kprobe *p) return kprobe_disabled(p) && list_empty(&op->list); } -/* Return true(!0) if the probe is queued on (un)optimizing lists */ -static int kprobe_queued(struct kprobe *p) +/* Return true if the probe is queued on (un)optimizing lists */ +static bool kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) - return 1; + return true; } - return 0; + return false; } /* * Return an optimized kprobe whose optimizing code replaces - * instructions including addr (exclude breakpoint). + * instructions including 'addr' (exclude breakpoint). */ -static struct kprobe *get_optimized_kprobe(unsigned long addr) +static struct kprobe *get_optimized_kprobe(kprobe_opcode_t *addr) { int i; struct kprobe *p = NULL; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ - for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) - p = get_kprobe((void *)(addr - i)); + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH / sizeof(kprobe_opcode_t); i++) + p = get_kprobe(addr - i); if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); @@ -455,7 +507,7 @@ static struct kprobe *get_optimized_kprobe(unsigned long addr) return NULL; } -/* Optimization staging list, protected by kprobe_mutex */ +/* Optimization staging list, protected by 'kprobe_mutex' */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); static LIST_HEAD(freeing_list); @@ -466,20 +518,20 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); /* * Optimize (replace a breakpoint with a jump) kprobes listed on - * optimizing_list. + * 'optimizing_list'. */ static void do_optimize_kprobes(void) { lockdep_assert_held(&text_mutex); /* - * The optimization/unoptimization refers online_cpus via - * stop_machine() and cpu-hotplug modifies online_cpus. - * And same time, text_mutex will be held in cpu-hotplug and here. - * This combination can cause a deadlock (cpu-hotplug try to lock - * text_mutex but stop_machine can not be done because online_cpus - * has been changed) - * To avoid this deadlock, caller must have locked cpu hotplug - * for preventing cpu-hotplug outside of text_mutex locking. + * The optimization/unoptimization refers 'online_cpus' via + * stop_machine() and cpu-hotplug modifies the 'online_cpus'. + * And same time, 'text_mutex' will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug tries to lock + * 'text_mutex' but stop_machine() can not be done because + * the 'online_cpus' has been changed) + * To avoid this deadlock, caller must have locked cpu-hotplug + * for preventing cpu-hotplug outside of 'text_mutex' locking. */ lockdep_assert_cpus_held(); @@ -493,7 +545,7 @@ static void do_optimize_kprobes(void) /* * Unoptimize (replace a jump with a breakpoint and remove the breakpoint - * if need) kprobes listed on unoptimizing_list. + * if need) kprobes listed on 'unoptimizing_list'. */ static void do_unoptimize_kprobes(void) { @@ -508,7 +560,7 @@ static void do_unoptimize_kprobes(void) return; arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); - /* Loop free_list for disarming */ + /* Loop on 'freeing_list' for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Switching from detour code to origin */ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; @@ -519,7 +571,7 @@ static void do_unoptimize_kprobes(void) /* * Remove unused probes from hash list. After waiting * for synchronization, these probes are reclaimed. - * (reclaiming is done by do_free_cleaned_kprobes.) + * (reclaiming is done by do_free_cleaned_kprobes().) */ hlist_del_rcu(&op->kp.hlist); } else @@ -527,7 +579,7 @@ static void do_unoptimize_kprobes(void) } } -/* Reclaim all kprobes on the free_list */ +/* Reclaim all kprobes on the 'freeing_list' */ static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; @@ -557,8 +609,6 @@ static void kprobe_optimizer(struct work_struct *work) mutex_lock(&kprobe_mutex); cpus_read_lock(); mutex_lock(&text_mutex); - /* Lock modules while optimizing kprobes */ - mutex_lock(&module_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) @@ -583,14 +633,14 @@ static void kprobe_optimizer(struct work_struct *work) /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(); - mutex_unlock(&module_mutex); mutex_unlock(&text_mutex); cpus_read_unlock(); - mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); + + mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ @@ -601,9 +651,9 @@ void wait_for_kprobe_optimizer(void) while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); - /* this will also make optimizing_work execute immmediately */ + /* This will also make 'optimizing_work' execute immmediately */ flush_delayed_work(&optimizing_work); - /* @optimizing_work might not have been queued yet, relax */ + /* 'optimizing_work' might not have been queued yet, relax */ cpu_relax(); mutex_lock(&kprobe_mutex); @@ -634,7 +684,7 @@ static void optimize_kprobe(struct kprobe *p) (kprobe_disabled(p) || kprobes_all_disarmed)) return; - /* kprobes with post_handler can not be optimized */ + /* kprobes with 'post_handler' can not be optimized */ if (p->post_handler) return; @@ -654,7 +704,10 @@ static void optimize_kprobe(struct kprobe *p) } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; - /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ + /* + * On the 'unoptimizing_list' and 'optimizing_list', + * 'op' must have OPTIMIZED flag + */ if (WARN_ON_ONCE(!list_empty(&op->list))) return; @@ -668,8 +721,6 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; - if (kprobe_disabled(&op->kp)) - arch_disarm_kprobe(&op->kp); } /* Unoptimize a kprobe if p is optimized */ @@ -726,7 +777,7 @@ static int reuse_unused_kprobe(struct kprobe *ap) WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; - /* Optimize it again (remove from op->list) */ + /* Optimize it again. (remove from 'op->list') */ if (!kprobe_optready(ap)) return -EINVAL; @@ -776,7 +827,7 @@ static void prepare_optimized_kprobe(struct kprobe *p) __prepare_optimized_kprobe(op, p); } -/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +/* Allocate new optimized_kprobe and try to prepare optimized instructions. */ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -795,19 +846,19 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* - * Prepare an optimized_kprobe and optimize it - * NOTE: p must be a normal registered kprobe + * Prepare an optimized_kprobe and optimize it. + * NOTE: 'p' must be a normal registered kprobe. */ static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; - /* Impossible to optimize ftrace-based kprobe */ + /* Impossible to optimize ftrace-based kprobe. */ if (kprobe_ftrace(p)) return; - /* For preparing optimization, jump_label_text_reserved() is called */ + /* For preparing optimization, jump_label_text_reserved() is called. */ cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); @@ -818,14 +869,14 @@ static void try_to_optimize_kprobe(struct kprobe *p) op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { - /* If failed to setup optimizing, fallback to kprobe */ + /* If failed to setup optimizing, fallback to kprobe. */ arch_remove_optimized_kprobe(op); kfree(op); goto out; } init_aggr_kprobe(ap, p); - optimize_kprobe(ap); /* This just kicks optimizer thread */ + optimize_kprobe(ap); /* This just kicks optimizer thread. */ out: mutex_unlock(&text_mutex); @@ -833,7 +884,6 @@ out: cpus_read_unlock(); } -#ifdef CONFIG_SYSCTL static void optimize_all_kprobes(void) { struct hlist_head *head; @@ -841,7 +891,7 @@ static void optimize_all_kprobes(void) unsigned int i; mutex_lock(&kprobe_mutex); - /* If optimization is already allowed, just return */ + /* If optimization is already allowed, just return. */ if (kprobes_allow_optimization) goto out; @@ -849,16 +899,17 @@ static void optimize_all_kprobes(void) kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) + hlist_for_each_entry(p, head, hlist) if (!kprobe_disabled(p)) optimize_kprobe(p); } cpus_read_unlock(); - printk(KERN_INFO "Kprobes globally optimized\n"); + pr_info("kprobe jump-optimization is enabled. All kprobes are optimized if possible.\n"); out: mutex_unlock(&kprobe_mutex); } +#ifdef CONFIG_SYSCTL static void unoptimize_all_kprobes(void) { struct hlist_head *head; @@ -866,7 +917,7 @@ static void unoptimize_all_kprobes(void) unsigned int i; mutex_lock(&kprobe_mutex); - /* If optimization is already prohibited, just return */ + /* If optimization is already prohibited, just return. */ if (!kprobes_allow_optimization) { mutex_unlock(&kprobe_mutex); return; @@ -876,7 +927,7 @@ static void unoptimize_all_kprobes(void) kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) { + hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) unoptimize_kprobe(p, false); } @@ -884,16 +935,16 @@ static void unoptimize_all_kprobes(void) cpus_read_unlock(); mutex_unlock(&kprobe_mutex); - /* Wait for unoptimizing completion */ + /* Wait for unoptimizing completion. */ wait_for_kprobe_optimizer(); - printk(KERN_INFO "Kprobes globally unoptimized\n"); + pr_info("kprobe jump-optimization is disabled. All kprobes are based on software breakpoint.\n"); } static DEFINE_MUTEX(kprobe_sysctl_mutex); -int sysctl_kprobes_optimization; -int proc_kprobes_optimization_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos) +static int sysctl_kprobes_optimization; +static int proc_kprobes_optimization_handler(struct ctl_table *table, + int write, void *buffer, + size_t *length, loff_t *ppos) { int ret; @@ -909,15 +960,35 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table kprobe_sysctls[] = { + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static void __init kprobe_sysctls_init(void) +{ + register_sysctl_init("debug", kprobe_sysctls); +} #endif /* CONFIG_SYSCTL */ -/* Put a breakpoint for a probe. Must be called with text_mutex locked */ +/* Put a breakpoint for a probe. */ static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; - /* Check collision with other optimized kprobes */ - _p = get_optimized_kprobe((unsigned long)p->addr); + lockdep_assert_held(&text_mutex); + + /* Find the overlapping optimized kprobes. */ + _p = get_optimized_kprobe(p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ unoptimize_kprobe(_p, true); @@ -926,22 +997,29 @@ static void __arm_kprobe(struct kprobe *p) optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ } -/* Remove the breakpoint of a probe. Must be called with text_mutex locked */ +/* Remove the breakpoint of a probe. */ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; + lockdep_assert_held(&text_mutex); + /* Try to unoptimize */ unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); - /* If another kprobe was blocked, optimize it. */ - _p = get_optimized_kprobe((unsigned long)p->addr); + /* If another kprobe was blocked, re-optimize it. */ + _p = get_optimized_kprobe(p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } - /* TODO: reoptimize others after unoptimized this probe */ + /* + * TODO: Since unoptimization and real disarming will be done by + * the worker thread, we can not check whether another probe are + * unoptimized because of this probe here. It should be re-optimized + * by the worker thread. + */ } #else /* !CONFIG_OPTPROBES */ @@ -964,7 +1042,7 @@ static int reuse_unused_kprobe(struct kprobe *ap) * unregistered. * Thus there should be no chance to reuse unused kprobe. */ - printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); + WARN_ON_ONCE(1); return -EINVAL; } @@ -994,34 +1072,21 @@ static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; -/* Must ensure p->addr is really on ftrace */ -static int prepare_kprobe(struct kprobe *p) -{ - if (!kprobe_ftrace(p)) - return arch_prepare_kprobe(p); - - return arch_prepare_kprobe_ftrace(p); -} - -/* Caller must lock kprobe_mutex */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; + lockdep_assert_held(&kprobe_mutex); + ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); - if (ret) { - pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", - p->addr, ret); + if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret)) return ret; - } if (*cnt == 0) { ret = register_ftrace_function(ops); - if (ret) { - pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); + if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) goto err_ftrace; - } } (*cnt)++; @@ -1045,22 +1110,23 @@ static int arm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } -/* Caller must lock kprobe_mutex */ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; + lockdep_assert_held(&kprobe_mutex); + if (*cnt == 1) { ret = unregister_ftrace_function(ops); - if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) + if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (error %d)\n", ret)) return ret; } (*cnt)--; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); - WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", + WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (error %d)\n", p->addr, ret); return ret; } @@ -1074,12 +1140,26 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ -#define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) (-ENODEV) -#define disarm_kprobe_ftrace(p) (-ENODEV) +static inline int arm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} + +static inline int disarm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} #endif -/* Arm a kprobe with text_mutex */ +static int prepare_kprobe(struct kprobe *p) +{ + /* Must ensure p->addr is really on ftrace */ + if (kprobe_ftrace(p)) + return arch_prepare_kprobe_ftrace(p); + + return arch_prepare_kprobe(p); +} + static int arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) @@ -1094,7 +1174,6 @@ static int arm_kprobe(struct kprobe *kp) return 0; } -/* Disarm a kprobe with text_mutex */ static int disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) @@ -1144,164 +1223,41 @@ static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, } NOKPROBE_SYMBOL(aggr_post_handler); -static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, - int trapnr) -{ - struct kprobe *cur = __this_cpu_read(kprobe_instance); - - /* - * if we faulted "during" the execution of a user specified - * probe handler, invoke just that probe's fault handler - */ - if (cur && cur->fault_handler) { - if (cur->fault_handler(cur, regs, trapnr)) - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(aggr_fault_handler); - -/* Walks the list and increments nmissed count for multiprobe case */ +/* Walks the list and increments 'nmissed' if 'p' has child probes. */ void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; + if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) kp->nmissed++; } - return; } NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); -void recycle_rp_inst(struct kretprobe_instance *ri, - struct hlist_head *head) -{ - struct kretprobe *rp = ri->rp; - - /* remove rp inst off the rprobe_inst_table */ - hlist_del(&ri->hlist); - INIT_HLIST_NODE(&ri->hlist); - if (likely(rp)) { - raw_spin_lock(&rp->lock); - hlist_add_head(&ri->hlist, &rp->free_instances); - raw_spin_unlock(&rp->lock); - } else - /* Unregistering */ - hlist_add_head(&ri->hlist, head); -} -NOKPROBE_SYMBOL(recycle_rp_inst); - -void kretprobe_hash_lock(struct task_struct *tsk, - struct hlist_head **head, unsigned long *flags) -__acquires(hlist_lock) -{ - unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); - raw_spinlock_t *hlist_lock; - - *head = &kretprobe_inst_table[hash]; - hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); -} -NOKPROBE_SYMBOL(kretprobe_hash_lock); - -static void kretprobe_table_lock(unsigned long hash, - unsigned long *flags) -__acquires(hlist_lock) -{ - raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); -} -NOKPROBE_SYMBOL(kretprobe_table_lock); - -void kretprobe_hash_unlock(struct task_struct *tsk, - unsigned long *flags) -__releases(hlist_lock) -{ - unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); - raw_spinlock_t *hlist_lock; - - hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_unlock_irqrestore(hlist_lock, *flags); -} -NOKPROBE_SYMBOL(kretprobe_hash_unlock); - -static void kretprobe_table_unlock(unsigned long hash, - unsigned long *flags) -__releases(hlist_lock) -{ - raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_unlock_irqrestore(hlist_lock, *flags); -} -NOKPROBE_SYMBOL(kretprobe_table_unlock); - -/* - * This function is called from finish_task_switch when task tk becomes dead, - * so that we can recycle any function-return probe instances associated - * with this task. These left over instances represent probed functions - * that have been called but will never return. - */ -void kprobe_flush_task(struct task_struct *tk) -{ - struct kretprobe_instance *ri; - struct hlist_head *head, empty_rp; - struct hlist_node *tmp; - unsigned long hash, flags = 0; - - if (unlikely(!kprobes_initialized)) - /* Early boot. kretprobe_table_locks not yet initialized. */ - return; - - INIT_HLIST_HEAD(&empty_rp); - hash = hash_ptr(tk, KPROBE_HASH_BITS); - head = &kretprobe_inst_table[hash]; - kretprobe_table_lock(hash, &flags); - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task == tk) - recycle_rp_inst(ri, &empty_rp); - } - kretprobe_table_unlock(hash, &flags); - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } -} -NOKPROBE_SYMBOL(kprobe_flush_task); +static struct kprobe kprobe_busy = { + .addr = (void *) get_kprobe, +}; -static inline void free_rp_inst(struct kretprobe *rp) +void kprobe_busy_begin(void) { - struct kretprobe_instance *ri; - struct hlist_node *next; + struct kprobe_ctlblk *kcb; - hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } + preempt_disable(); + __this_cpu_write(current_kprobe, &kprobe_busy); + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; } -static void cleanup_rp_inst(struct kretprobe *rp) +void kprobe_busy_end(void) { - unsigned long flags, hash; - struct kretprobe_instance *ri; - struct hlist_node *next; - struct hlist_head *head; - - /* No race here */ - for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { - kretprobe_table_lock(hash, &flags); - head = &kretprobe_inst_table[hash]; - hlist_for_each_entry_safe(ri, next, head, hlist) { - if (ri->rp == rp) - ri->rp = NULL; - } - kretprobe_table_unlock(hash, &flags); - } - free_rp_inst(rp); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); } -NOKPROBE_SYMBOL(cleanup_rp_inst); -/* Add the new probe to ap->list */ +/* Add the new probe to 'ap->list'. */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { if (p->post_handler) @@ -1315,18 +1271,17 @@ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) } /* - * Fill in the required fields of the "manager kprobe". Replace the - * earlier kprobe in the hlist with the manager kprobe + * Fill in the required fields of the aggregator kprobe. Replace the + * earlier kprobe in the hlist with the aggregator kprobe. */ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { - /* Copy p's insn slot to ap */ + /* Copy the insn slot of 'p' to 'ap'. */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; - ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; @@ -1339,8 +1294,7 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) } /* - * This is the second or subsequent kprobe at the address - handle - * the intricacies + * This registers the second or subsequent kprobe at the same address. */ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { @@ -1354,7 +1308,7 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { - /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ + /* If 'orig_p' is not an 'aggr_kprobe', create new one. */ ap = alloc_aggr_kprobe(orig_p); if (!ap) { ret = -ENOMEM; @@ -1379,8 +1333,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) if (ret) /* * Even if fail to allocate new slot, don't need to - * free aggr_probe. It will be used next time, or - * freed by unregister_kprobe. + * free the 'ap'. It will be used next time, or + * freed by unregister_kprobe(). */ goto out; @@ -1395,7 +1349,7 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) | KPROBE_FLAG_DISABLED; } - /* Copy ap's insn slot to p */ + /* Copy the insn slot of 'p' to 'ap'. */ copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); @@ -1421,7 +1375,7 @@ out: bool __weak arch_within_kprobe_blacklist(unsigned long addr) { - /* The __kprobes marked functions and entry code must not be probed */ + /* The '__kprobes' functions and entry code must not be probed. */ return addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end; } @@ -1433,8 +1387,8 @@ static bool __within_kprobe_blacklist(unsigned long addr) if (arch_within_kprobe_blacklist(addr)) return true; /* - * If there exists a kprobe_blacklist, verify and - * fail any probe registration in the prohibited area + * If 'kprobe_blacklist' is defined, check the address and + * reject any probe registration in the prohibited area. */ list_for_each_entry(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) @@ -1464,24 +1418,68 @@ bool within_kprobe_blacklist(unsigned long addr) } /* - * If we have a symbol_name argument, look it up and add the offset field + * arch_adjust_kprobe_addr - adjust the address + * @addr: symbol base address + * @offset: offset within the symbol + * @on_func_entry: was this @addr+@offset on the function entry + * + * Typically returns @addr + @offset, except for special cases where the + * function might be prefixed by a CFI landing pad, in that case any offset + * inside the landing pad is mapped to the first 'real' instruction of the + * symbol. + * + * Specifically, for things like IBT/BTI, skip the resp. ENDBR/BTI.C + * instruction at +0. + */ +kprobe_opcode_t *__weak arch_adjust_kprobe_addr(unsigned long addr, + unsigned long offset, + bool *on_func_entry) +{ + *on_func_entry = !offset; + return (kprobe_opcode_t *)(addr + offset); +} + +/* + * If 'symbol_name' is specified, look it up and add the 'offset' * to it. This way, we can specify a relative address to a symbol. * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. */ -static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr, - const char *symbol_name, unsigned int offset) +static kprobe_opcode_t * +_kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, + unsigned long offset, bool *on_func_entry) { if ((symbol_name && addr) || (!symbol_name && !addr)) goto invalid; if (symbol_name) { + /* + * Input: @sym + @offset + * Output: @addr + @offset + * + * NOTE: kprobe_lookup_name() does *NOT* fold the offset + * argument into it's output! + */ addr = kprobe_lookup_name(symbol_name, offset); if (!addr) return ERR_PTR(-ENOENT); } - addr = (kprobe_opcode_t *)(((char *)addr) + offset); + /* + * So here we have @addr + @offset, displace it into a new + * @addr' + @offset' where @addr' is the symbol start address. + */ + addr = (void *)addr + offset; + if (!kallsyms_lookup_size_offset((unsigned long)addr, NULL, &offset)) + return ERR_PTR(-ENOENT); + addr = (void *)addr - offset; + + /* + * Then ask the architecture to re-combine them, taking care of + * magical function entry details while telling us if this was indeed + * at the start of the function. + */ + addr = arch_adjust_kprobe_addr((unsigned long)addr, offset, on_func_entry); if (addr) return addr; @@ -1491,20 +1489,26 @@ invalid: static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { - return _kprobe_addr(p->addr, p->symbol_name, p->offset); + bool on_func_entry; + return _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry); } -/* Check passed kprobe is valid and return kprobe in kprobe_table. */ +/* + * Check the 'p' is valid and return the aggregator kprobe + * at the same address. + */ static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; + lockdep_assert_held(&kprobe_mutex); + ap = get_kprobe(p->addr); if (unlikely(!ap)) return NULL; if (p != ap) { - list_for_each_entry_rcu(list_p, &ap->list, list) + list_for_each_entry(list_p, &ap->list, list) if (list_p == p) /* kprobe p is a valid probe */ goto valid; @@ -1514,29 +1518,28 @@ valid: return ap; } -/* Return error if the kprobe is being re-registered */ -static inline int check_kprobe_rereg(struct kprobe *p) +/* + * Warn and return error if the kprobe is being re-registered since + * there must be a software bug. + */ +static inline int warn_kprobe_rereg(struct kprobe *p) { int ret = 0; mutex_lock(&kprobe_mutex); - if (__get_valid_kprobe(p)) + if (WARN_ON_ONCE(__get_valid_kprobe(p))) ret = -EINVAL; mutex_unlock(&kprobe_mutex); return ret; } -int __weak arch_check_ftrace_location(struct kprobe *p) +static int check_ftrace_location(struct kprobe *p) { - unsigned long ftrace_addr; + unsigned long addr = (unsigned long)p->addr; - ftrace_addr = ftrace_location((unsigned long)p->addr); - if (ftrace_addr) { + if (ftrace_location(addr) == addr) { #ifdef CONFIG_KPROBES_ON_FTRACE - /* Given address is not on the instruction boundary */ - if ((unsigned long)p->addr != ftrace_addr) - return -EILSEQ; p->flags |= KPROBE_FLAG_FTRACE; #else /* !CONFIG_KPROBES_ON_FTRACE */ return -EINVAL; @@ -1550,22 +1553,25 @@ static int check_kprobe_address_safe(struct kprobe *p, { int ret; - ret = arch_check_ftrace_location(p); + ret = check_ftrace_location(p); if (ret) return ret; jump_label_lock(); preempt_disable(); /* Ensure it is not in reserved area nor out of text */ - if (!kernel_text_address((unsigned long) p->addr) || + if (!(core_kernel_text((unsigned long) p->addr) || + is_module_text_address((unsigned long) p->addr)) || + in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || + static_call_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr)) { ret = -EINVAL; goto out; } - /* Check if are we probing a module */ + /* Check if 'p' is probing a module. */ *probed_mod = __module_text_address((unsigned long) p->addr); if (*probed_mod) { /* @@ -1578,7 +1584,7 @@ static int check_kprobe_address_safe(struct kprobe *p, } /* - * If the module freed .init.text, we couldn't insert + * If the module freed '.init.text', we couldn't insert * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && @@ -1601,14 +1607,15 @@ int register_kprobe(struct kprobe *p) struct kprobe *old_p; struct module *probed_mod; kprobe_opcode_t *addr; + bool on_func_entry; /* Adjust probe address from symbol */ - addr = kprobe_addr(p); + addr = _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry); if (IS_ERR(addr)) return PTR_ERR(addr); p->addr = addr; - ret = check_kprobe_rereg(p); + ret = warn_kprobe_rereg(p); if (ret) return ret; @@ -1623,9 +1630,12 @@ int register_kprobe(struct kprobe *p) mutex_lock(&kprobe_mutex); + if (on_func_entry) + p->flags |= KPROBE_FLAG_ON_FUNC_ENTRY; + old_p = get_kprobe(p->addr); if (old_p) { - /* Since this may unoptimize old_p, locking text_mutex. */ + /* Since this may unoptimize 'old_p', locking 'text_mutex'. */ ret = register_aggr_kprobe(old_p, p); goto out; } @@ -1664,28 +1674,31 @@ out: } EXPORT_SYMBOL_GPL(register_kprobe); -/* Check if all probes on the aggrprobe are disabled */ -static int aggr_kprobe_disabled(struct kprobe *ap) +/* Check if all probes on the 'ap' are disabled. */ +static bool aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; - list_for_each_entry_rcu(kp, &ap->list, list) + lockdep_assert_held(&kprobe_mutex); + + list_for_each_entry(kp, &ap->list, list) if (!kprobe_disabled(kp)) /* - * There is an active probe on the list. - * We can't disable this ap. + * Since there is an active probe on the list, + * we can't disable this 'ap'. */ - return 0; + return false; - return 1; + return true; } -/* Disable one kprobe: Make sure called under kprobe_mutex is locked */ static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; int ret; + lockdep_assert_held(&kprobe_mutex); + /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) @@ -1699,11 +1712,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If kprobes_all_disarmed is set, orig_p - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; @@ -1748,7 +1762,7 @@ static int __unregister_kprobe_top(struct kprobe *p) else { /* If disabling probe has special handlers, update aggrprobe */ if (p->post_handler && !kprobe_gone(p)) { - list_for_each_entry_rcu(list_p, &ap->list, list) { + list_for_each_entry(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; } @@ -1845,12 +1859,212 @@ static struct notifier_block kprobe_exceptions_nb = { .priority = 0x7fffffff /* we need to be notified first */ }; -unsigned long __weak arch_deref_entry_point(void *entry) +#ifdef CONFIG_KRETPROBES + +#if !defined(CONFIG_KRETPROBE_ON_RETHOOK) +static void free_rp_inst_rcu(struct rcu_head *head) { - return (unsigned long)entry; + struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu); + + if (refcount_dec_and_test(&ri->rph->ref)) + kfree(ri->rph); + kfree(ri); } +NOKPROBE_SYMBOL(free_rp_inst_rcu); + +static void recycle_rp_inst(struct kretprobe_instance *ri) +{ + struct kretprobe *rp = get_kretprobe(ri); + + if (likely(rp)) + freelist_add(&ri->freelist, &rp->freelist); + else + call_rcu(&ri->rcu, free_rp_inst_rcu); +} +NOKPROBE_SYMBOL(recycle_rp_inst); + +/* + * This function is called from delayed_put_task_struct() when a task is + * dead and cleaned up to recycle any kretprobe instances associated with + * this task. These left over instances represent probed functions that + * have been called but will never return. + */ +void kprobe_flush_task(struct task_struct *tk) +{ + struct kretprobe_instance *ri; + struct llist_node *node; + + /* Early boot, not yet initialized. */ + if (unlikely(!kprobes_initialized)) + return; + + kprobe_busy_begin(); + + node = __llist_del_all(&tk->kretprobe_instances); + while (node) { + ri = container_of(node, struct kretprobe_instance, llist); + node = node->next; + + recycle_rp_inst(ri); + } + + kprobe_busy_end(); +} +NOKPROBE_SYMBOL(kprobe_flush_task); + +static inline void free_rp_inst(struct kretprobe *rp) +{ + struct kretprobe_instance *ri; + struct freelist_node *node; + int count = 0; + + node = rp->freelist.head; + while (node) { + ri = container_of(node, struct kretprobe_instance, freelist); + node = node->next; + + kfree(ri); + count++; + } + + if (refcount_sub_and_test(count, &rp->rph->ref)) { + kfree(rp->rph); + rp->rph = NULL; + } +} + +/* This assumes the 'tsk' is the current task or the is not running. */ +static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk, + struct llist_node **cur) +{ + struct kretprobe_instance *ri = NULL; + struct llist_node *node = *cur; + + if (!node) + node = tsk->kretprobe_instances.first; + else + node = node->next; + + while (node) { + ri = container_of(node, struct kretprobe_instance, llist); + if (ri->ret_addr != kretprobe_trampoline_addr()) { + *cur = node; + return ri->ret_addr; + } + node = node->next; + } + return NULL; +} +NOKPROBE_SYMBOL(__kretprobe_find_ret_addr); + +/** + * kretprobe_find_ret_addr -- Find correct return address modified by kretprobe + * @tsk: Target task + * @fp: A frame pointer + * @cur: a storage of the loop cursor llist_node pointer for next call + * + * Find the correct return address modified by a kretprobe on @tsk in unsigned + * long type. If it finds the return address, this returns that address value, + * or this returns 0. + * The @tsk must be 'current' or a task which is not running. @fp is a hint + * to get the currect return address - which is compared with the + * kretprobe_instance::fp field. The @cur is a loop cursor for searching the + * kretprobe return addresses on the @tsk. The '*@cur' should be NULL at the + * first call, but '@cur' itself must NOT NULL. + */ +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + struct kretprobe_instance *ri = NULL; + kprobe_opcode_t *ret; + + if (WARN_ON_ONCE(!cur)) + return 0; + + do { + ret = __kretprobe_find_ret_addr(tsk, cur); + if (!ret) + break; + ri = container_of(*cur, struct kretprobe_instance, llist); + } while (ri->fp != fp); + + return (unsigned long)ret; +} +NOKPROBE_SYMBOL(kretprobe_find_ret_addr); + +void __weak arch_kretprobe_fixup_return(struct pt_regs *regs, + kprobe_opcode_t *correct_ret_addr) +{ + /* + * Do nothing by default. Please fill this to update the fake return + * address on the stack with the correct one on each arch if possible. + */ +} + +unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, + void *frame_pointer) +{ + kprobe_opcode_t *correct_ret_addr = NULL; + struct kretprobe_instance *ri = NULL; + struct llist_node *first, *node = NULL; + struct kretprobe *rp; + + /* Find correct address and all nodes for this frame. */ + correct_ret_addr = __kretprobe_find_ret_addr(current, &node); + if (!correct_ret_addr) { + pr_err("kretprobe: Return address not found, not execute handler. Maybe there is a bug in the kernel.\n"); + BUG_ON(1); + } + + /* + * Set the return address as the instruction pointer, because if the + * user handler calls stack_trace_save_regs() with this 'regs', + * the stack trace will start from the instruction pointer. + */ + instruction_pointer_set(regs, (unsigned long)correct_ret_addr); + + /* Run the user handler of the nodes. */ + first = current->kretprobe_instances.first; + while (first) { + ri = container_of(first, struct kretprobe_instance, llist); + + if (WARN_ON_ONCE(ri->fp != frame_pointer)) + break; + + rp = get_kretprobe(ri); + if (rp && rp->handler) { + struct kprobe *prev = kprobe_running(); + + __this_cpu_write(current_kprobe, &rp->kp); + ri->ret_addr = correct_ret_addr; + rp->handler(ri, regs); + __this_cpu_write(current_kprobe, prev); + } + if (first == node) + break; + + first = first->next; + } + + arch_kretprobe_fixup_return(regs, correct_ret_addr); + + /* Unlink all nodes for this frame. */ + first = current->kretprobe_instances.first; + current->kretprobe_instances.first = node->next; + node->next = NULL; + + /* Recycle free instances. */ + while (first) { + ri = container_of(first, struct kretprobe_instance, llist); + first = first->next; + + recycle_rp_inst(ri); + } + + return (unsigned long)correct_ret_addr; +} +NOKPROBE_SYMBOL(__kretprobe_trampoline_handler) -#ifdef CONFIG_KRETPROBES /* * This kprobe pre_handler is registered with every kretprobe. When probe * hits it will set up the return probe. @@ -1858,81 +2072,121 @@ unsigned long __weak arch_deref_entry_point(void *entry) static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); - unsigned long hash, flags = 0; struct kretprobe_instance *ri; + struct freelist_node *fn; - /* - * To avoid deadlocks, prohibit return probing in NMI contexts, - * just skip the probe and increase the (inexact) 'nmissed' - * statistical counter, so that the user is informed that - * something happened: - */ - if (unlikely(in_nmi())) { + fn = freelist_try_get(&rp->freelist); + if (!fn) { rp->nmissed++; return 0; } - /* TODO: consider to only swap the RA after the last pre_handler fired */ - hash = hash_ptr(current, KPROBE_HASH_BITS); - raw_spin_lock_irqsave(&rp->lock, flags); - if (!hlist_empty(&rp->free_instances)) { - ri = hlist_entry(rp->free_instances.first, - struct kretprobe_instance, hlist); - hlist_del(&ri->hlist); - raw_spin_unlock_irqrestore(&rp->lock, flags); + ri = container_of(fn, struct kretprobe_instance, freelist); - ri->rp = rp; - ri->task = current; + if (rp->entry_handler && rp->entry_handler(ri, regs)) { + freelist_add(&ri->freelist, &rp->freelist); + return 0; + } - if (rp->entry_handler && rp->entry_handler(ri, regs)) { - raw_spin_lock_irqsave(&rp->lock, flags); - hlist_add_head(&ri->hlist, &rp->free_instances); - raw_spin_unlock_irqrestore(&rp->lock, flags); - return 0; - } + arch_prepare_kretprobe(ri, regs); - arch_prepare_kretprobe(ri, regs); + __llist_add(&ri->llist, ¤t->kretprobe_instances); - /* XXX(hch): why is there no hlist_move_head? */ - INIT_HLIST_NODE(&ri->hlist); - kretprobe_table_lock(hash, &flags); - hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]); - kretprobe_table_unlock(hash, &flags); - } else { + return 0; +} +NOKPROBE_SYMBOL(pre_handler_kretprobe); +#else /* CONFIG_KRETPROBE_ON_RETHOOK */ +/* + * This kprobe pre_handler is registered with every kretprobe. When probe + * hits it will set up the return probe. + */ +static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) +{ + struct kretprobe *rp = container_of(p, struct kretprobe, kp); + struct kretprobe_instance *ri; + struct rethook_node *rhn; + + rhn = rethook_try_get(rp->rh); + if (!rhn) { rp->nmissed++; - raw_spin_unlock_irqrestore(&rp->lock, flags); + return 0; } + + ri = container_of(rhn, struct kretprobe_instance, node); + + if (rp->entry_handler && rp->entry_handler(ri, regs)) + rethook_recycle(rhn); + else + rethook_hook(rhn, regs, kprobe_ftrace(p)); + return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); -bool __weak arch_kprobe_on_func_entry(unsigned long offset) +static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, + struct pt_regs *regs) { - return !offset; + struct kretprobe *rp = (struct kretprobe *)data; + struct kretprobe_instance *ri; + struct kprobe_ctlblk *kcb; + + /* The data must NOT be null. This means rethook data structure is broken. */ + if (WARN_ON_ONCE(!data) || !rp->handler) + return; + + __this_cpu_write(current_kprobe, &rp->kp); + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + ri = container_of(rh, struct kretprobe_instance, node); + rp->handler(ri, regs); + + __this_cpu_write(current_kprobe, NULL); } +NOKPROBE_SYMBOL(kretprobe_rethook_handler); + +#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */ -bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) +/** + * kprobe_on_func_entry() -- check whether given address is function entry + * @addr: Target address + * @sym: Target symbol name + * @offset: The offset from the symbol or the address + * + * This checks whether the given @addr+@offset or @sym+@offset is on the + * function entry address or not. + * This returns 0 if it is the function entry, or -EINVAL if it is not. + * And also it returns -ENOENT if it fails the symbol or address lookup. + * Caller must pass @addr or @sym (either one must be NULL), or this + * returns -EINVAL. + */ +int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { - kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); + bool on_func_entry; + kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset, &on_func_entry); if (IS_ERR(kp_addr)) - return false; + return PTR_ERR(kp_addr); - if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) || - !arch_kprobe_on_func_entry(offset)) - return false; + if (!on_func_entry) + return -EINVAL; - return true; + return 0; } int register_kretprobe(struct kretprobe *rp) { - int ret = 0; + int ret; struct kretprobe_instance *inst; int i; void *addr; - if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) + ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); + if (ret) + return ret; + + /* If only 'rp->kp.addr' is specified, check reregistering kprobes */ + if (rp->kp.addr && warn_kprobe_rereg(&rp->kp)) return -EINVAL; if (kretprobe_blacklist_size) { @@ -1946,9 +2200,11 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; - rp->kp.fault_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { @@ -1958,24 +2214,54 @@ int register_kretprobe(struct kretprobe *rp) rp->maxactive = num_possible_cpus(); #endif } - raw_spin_lock_init(&rp->lock); - INIT_HLIST_HEAD(&rp->free_instances); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler); + if (!rp->rh) + return -ENOMEM; + + for (i = 0; i < rp->maxactive; i++) { + inst = kzalloc(sizeof(struct kretprobe_instance) + + rp->data_size, GFP_KERNEL); + if (inst == NULL) { + rethook_free(rp->rh); + rp->rh = NULL; + return -ENOMEM; + } + rethook_add_node(rp->rh, &inst->node); + } + rp->nmissed = 0; + /* Establish function entry probe point */ + ret = register_kprobe(&rp->kp); + if (ret != 0) { + rethook_free(rp->rh); + rp->rh = NULL; + } +#else /* !CONFIG_KRETPROBE_ON_RETHOOK */ + rp->freelist.head = NULL; + rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL); + if (!rp->rph) + return -ENOMEM; + + rp->rph->rp = rp; for (i = 0; i < rp->maxactive; i++) { - inst = kmalloc(sizeof(struct kretprobe_instance) + + inst = kzalloc(sizeof(struct kretprobe_instance) + rp->data_size, GFP_KERNEL); if (inst == NULL) { + refcount_set(&rp->rph->ref, i); free_rp_inst(rp); return -ENOMEM; } - INIT_HLIST_NODE(&inst->hlist); - hlist_add_head(&inst->hlist, &rp->free_instances); + inst->rph = rp->rph; + freelist_add(&inst->freelist, &rp->freelist); } + refcount_set(&rp->rph->ref, i); rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); if (ret != 0) free_rp_inst(rp); +#endif return ret; } EXPORT_SYMBOL_GPL(register_kretprobe); @@ -2011,16 +2297,24 @@ void unregister_kretprobes(struct kretprobe **rps, int num) if (num <= 0) return; mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) + for (i = 0; i < num; i++) { if (__unregister_kprobe_top(&rps[i]->kp) < 0) rps[i]->kp.addr = NULL; +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + rethook_free(rps[i]->rh); +#else + rps[i]->rph->rp = NULL; +#endif + } mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) { if (rps[i]->kp.addr) { __unregister_kprobe_bottom(&rps[i]->kp); - cleanup_rp_inst(rps[i]); +#ifndef CONFIG_KRETPROBE_ON_RETHOOK + free_rp_inst(rps[i]); +#endif } } } @@ -2029,13 +2323,13 @@ EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ int register_kretprobe(struct kretprobe *rp) { - return -ENOSYS; + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { - return -ENOSYS; + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(register_kretprobes); @@ -2062,13 +2356,15 @@ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; + lockdep_assert_held(&kprobe_mutex); + p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. */ - list_for_each_entry_rcu(kp, &p->list, list) + list_for_each_entry(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; kill_optimized_kprobe(p); @@ -2078,6 +2374,14 @@ static void kill_kprobe(struct kprobe *p) * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); + + /* + * The module is going away. We should disarm the kprobe which + * is using ftrace, because ftrace framework is still available at + * 'MODULE_STATE_GOING' notification. + */ + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) + disarm_kprobe_ftrace(p); } /* Disable one kprobe */ @@ -2125,8 +2429,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); @@ -2137,8 +2444,7 @@ EXPORT_SYMBOL_GPL(enable_kprobe); /* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { - pr_err("Dumping kprobe:\n"); - pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", + pr_err("Dump kprobe:\n.symbol_name = %s, .offset = %x, .addr = %pS\n", kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); @@ -2179,6 +2485,46 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end) return 0; } +/* Remove all symbols in given area from kprobe blacklist */ +static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) +{ + struct kprobe_blacklist_entry *ent, *n; + + list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { + if (ent->start_addr < start || ent->start_addr >= end) + continue; + list_del(&ent->list); + kfree(ent); + } +} + +static void kprobe_remove_ksym_blacklist(unsigned long entry) +{ + kprobe_remove_area_blacklist(entry, entry + 1); +} + +int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, + char *type, char *sym) +{ + return -ERANGE; +} + +int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *sym) +{ +#ifdef __ARCH_WANT_KPROBES_INSN_SLOT + if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym)) + return 0; +#ifdef CONFIG_OPTPROBES + if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym)) + return 0; +#endif +#endif + if (!arch_kprobe_get_kallsym(&symnum, value, type, sym)) + return 0; + return -ERANGE; +} + int __init __weak arch_populate_kprobe_blacklist(void) { return 0; @@ -2200,7 +2546,7 @@ static int __init populate_kprobe_blacklist(unsigned long *start, int ret; for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)*iter); + entry = (unsigned long)dereference_symbol_descriptor((void *)*iter); ret = kprobe_add_ksym_blacklist(entry); if (ret == -EINVAL) continue; @@ -2208,13 +2554,65 @@ static int __init populate_kprobe_blacklist(unsigned long *start, return ret; } - /* Symbols in __kprobes_text are blacklisted */ + /* Symbols in '__kprobes_text' are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start, (unsigned long)__kprobes_text_end); + if (ret) + return ret; + + /* Symbols in 'noinstr' section are blacklisted */ + ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start, + (unsigned long)__noinstr_text_end); return ret ? : arch_populate_kprobe_blacklist(); } +static void add_module_kprobe_blacklist(struct module *mod) +{ + unsigned long start, end; + int i; + + if (mod->kprobe_blacklist) { + for (i = 0; i < mod->num_kprobe_blacklist; i++) + kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]); + } + + start = (unsigned long)mod->kprobes_text_start; + if (start) { + end = start + mod->kprobes_text_size; + kprobe_add_area_blacklist(start, end); + } + + start = (unsigned long)mod->noinstr_text_start; + if (start) { + end = start + mod->noinstr_text_size; + kprobe_add_area_blacklist(start, end); + } +} + +static void remove_module_kprobe_blacklist(struct module *mod) +{ + unsigned long start, end; + int i; + + if (mod->kprobe_blacklist) { + for (i = 0; i < mod->num_kprobe_blacklist; i++) + kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]); + } + + start = (unsigned long)mod->kprobes_text_start; + if (start) { + end = start + mod->kprobes_text_size; + kprobe_remove_area_blacklist(start, end); + } + + start = (unsigned long)mod->noinstr_text_start; + if (start) { + end = start + mod->noinstr_text_size; + kprobe_remove_area_blacklist(start, end); + } +} + /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -2225,19 +2623,24 @@ static int kprobes_module_callback(struct notifier_block *nb, unsigned int i; int checkcore = (val == MODULE_STATE_GOING); + if (val == MODULE_STATE_COMING) { + mutex_lock(&kprobe_mutex); + add_module_kprobe_blacklist(mod); + mutex_unlock(&kprobe_mutex); + } if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; /* - * When MODULE_STATE_GOING was notified, both of module .text and - * .init.text sections would be freed. When MODULE_STATE_LIVE was - * notified, only .init.text section would be freed. We need to + * When 'MODULE_STATE_GOING' was notified, both of module '.text' and + * '.init.text' sections would be freed. When 'MODULE_STATE_LIVE' was + * notified, only '.init.text' section would be freed. We need to * disable kprobes which have been inserted in the sections. */ mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) + hlist_for_each_entry(p, head, hlist) if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { @@ -2248,13 +2651,15 @@ static int kprobes_module_callback(struct notifier_block *nb, * * Note, this will also move any optimized probes * that are pending to be removed from their - * corresponding lists to the freeing_list and + * corresponding lists to the 'freeing_list' and * will not be touched by the delayed - * kprobe_optimizer work handler. + * kprobe_optimizer() work handler. */ kill_kprobe(p); } } + if (val == MODULE_STATE_GOING) + remove_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; } @@ -2264,9 +2669,27 @@ static struct notifier_block kprobe_module_nb = { .priority = 0 }; -/* Markers of _kprobe_blacklist section */ -extern unsigned long __start_kprobe_blacklist[]; -extern unsigned long __stop_kprobe_blacklist[]; +void kprobe_free_init_mem(void) +{ + void *start = (void *)(&__init_begin); + void *end = (void *)(&__init_end); + struct hlist_head *head; + struct kprobe *p; + int i; + + mutex_lock(&kprobe_mutex); + + /* Kill all kprobes on initmem because the target code has been freed. */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry(p, head, hlist) { + if (start <= (void *)p->addr && (void *)p->addr < end) + kill_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); +} static int __init init_kprobes(void) { @@ -2274,18 +2697,13 @@ static int __init init_kprobes(void) /* FIXME allocate the probe table, currently defined statically */ /* initialize all list heads */ - for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + for (i = 0; i < KPROBE_TABLE_SIZE; i++) INIT_HLIST_HEAD(&kprobe_table[i]); - INIT_HLIST_HEAD(&kretprobe_inst_table[i]); - raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); - } err = populate_kprobe_blacklist(__start_kprobe_blacklist, __stop_kprobe_blacklist); - if (err) { - pr_err("kprobes: failed to populate blacklist: %d\n", err); - pr_err("Please take care of using kprobes.\n"); - } + if (err) + pr_err("Failed to populate blacklist (error %d), kprobes not restricted, be careful using them!\n", err); if (kretprobe_blacklist_size) { /* lookup the function address from its name */ @@ -2293,23 +2711,19 @@ static int __init init_kprobes(void) kretprobe_blacklist[i].addr = kprobe_lookup_name(kretprobe_blacklist[i].name, 0); if (!kretprobe_blacklist[i].addr) - printk("kretprobe: lookup failed: %s\n", + pr_err("Failed to lookup symbol '%s' for kretprobe blacklist. Maybe the target function is removed or renamed.\n", kretprobe_blacklist[i].name); } } -#if defined(CONFIG_OPTPROBES) -#if defined(__ARCH_WANT_KPROBES_INSN_SLOT) - /* Init kprobe_optinsn_slots */ - kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; -#endif - /* By default, kprobes can be optimized */ - kprobes_allow_optimization = true; -#endif - /* By default, kprobes are armed */ kprobes_all_disarmed = false; +#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) + /* Init 'kprobe_optinsn_slots' for allocation */ + kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; +#endif + err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); @@ -2317,12 +2731,25 @@ static int __init init_kprobes(void) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); - - if (!err) - init_test_probes(); + kprobe_sysctls_init(); return err; } -subsys_initcall(init_kprobes); +early_initcall(init_kprobes); + +#if defined(CONFIG_OPTPROBES) +static int __init init_optprobes(void) +{ + /* + * Enable kprobe optimization - this kicks the optimizer which + * depends on synchronize_rcu_tasks() and ksoftirqd, that is + * not spawned in early initcall. So delay the optimization. + */ + optimize_all_kprobes(); + + return 0; +} +subsys_initcall(init_optprobes); +#endif #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, @@ -2336,7 +2763,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, else kprobe_type = "k"; - if (!kallsyms_show_value()) + if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) @@ -2398,28 +2825,19 @@ static int show_kprobe_addr(struct seq_file *pi, void *v) return 0; } -static const struct seq_operations kprobes_seq_ops = { +static const struct seq_operations kprobes_sops = { .start = kprobe_seq_start, .next = kprobe_seq_next, .stop = kprobe_seq_stop, .show = show_kprobe_addr }; -static int kprobes_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &kprobes_seq_ops); -} - -static const struct file_operations debugfs_kprobes_operations = { - .open = kprobes_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; +DEFINE_SEQ_ATTRIBUTE(kprobes); /* kprobes/blacklist -- shows which functions can not be probed */ static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) { + mutex_lock(&kprobe_mutex); return seq_list_start(&kprobe_blacklist, *pos); } @@ -2434,10 +2852,10 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) list_entry(v, struct kprobe_blacklist_entry, list); /* - * If /proc/kallsyms is not showing kernel address, we won't + * If '/proc/kallsyms' is not showing kernel address, we won't * show them here either. */ - if (!kallsyms_show_value()) + if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else @@ -2446,24 +2864,18 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) return 0; } -static const struct seq_operations kprobe_blacklist_seq_ops = { - .start = kprobe_blacklist_seq_start, - .next = kprobe_blacklist_seq_next, - .stop = kprobe_seq_stop, /* Reuse void function */ - .show = kprobe_blacklist_seq_show, -}; - -static int kprobe_blacklist_open(struct inode *inode, struct file *filp) +static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v) { - return seq_open(filp, &kprobe_blacklist_seq_ops); + mutex_unlock(&kprobe_mutex); } -static const struct file_operations debugfs_kprobe_blacklist_ops = { - .open = kprobe_blacklist_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct seq_operations kprobe_blacklist_sops = { + .start = kprobe_blacklist_seq_start, + .next = kprobe_blacklist_seq_next, + .stop = kprobe_blacklist_seq_stop, + .show = kprobe_blacklist_seq_show, }; +DEFINE_SEQ_ATTRIBUTE(kprobe_blacklist); static int arm_all_kprobes(void) { @@ -2488,7 +2900,7 @@ static int arm_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Arm all kprobes on a best-effort basis */ - hlist_for_each_entry_rcu(p, head, hlist) { + hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) { err = arm_kprobe(p); if (err) { @@ -2501,7 +2913,7 @@ static int arm_all_kprobes(void) } if (errors) - pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", + pr_warn("Kprobes globally enabled, but failed to enable %d out of %d probes. Please check which kprobes are kept disabled via debugfs.\n", errors, total); else pr_info("Kprobes globally enabled\n"); @@ -2531,7 +2943,7 @@ static int disarm_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Disarm all kprobes on a best-effort basis */ - hlist_for_each_entry_rcu(p, head, hlist) { + hlist_for_each_entry(p, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { err = disarm_kprobe(p, false); if (err) { @@ -2544,7 +2956,7 @@ static int disarm_all_kprobes(void) } if (errors) - pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", + pr_warn("Kprobes globally disabled, but failed to disable %d out of %d probes. Please check which kprobes are kept enabled via debugfs.\n", errors, total); else pr_info("Kprobes globally disabled\n"); @@ -2579,30 +2991,14 @@ static ssize_t read_enabled_file_bool(struct file *file, static ssize_t write_enabled_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { - char buf[32]; - size_t buf_size; - int ret = 0; - - buf_size = min(count, (sizeof(buf)-1)); - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; + bool enable; + int ret; - buf[buf_size] = '\0'; - switch (buf[0]) { - case 'y': - case 'Y': - case '1': - ret = arm_all_kprobes(); - break; - case 'n': - case 'N': - case '0': - ret = disarm_all_kprobes(); - break; - default: - return -EINVAL; - } + ret = kstrtobool_from_user(user_buf, count, &enable); + if (ret) + return ret; + ret = enable ? arm_all_kprobes() : disarm_all_kprobes(); if (ret) return ret; @@ -2618,17 +3014,15 @@ static const struct file_operations fops_kp = { static int __init debugfs_kprobe_init(void) { struct dentry *dir; - unsigned int value = 1; dir = debugfs_create_dir("kprobes", NULL); - debugfs_create_file("list", 0400, dir, NULL, - &debugfs_kprobes_operations); + debugfs_create_file("list", 0400, dir, NULL, &kprobes_fops); - debugfs_create_file("enabled", 0600, dir, &value, &fops_kp); + debugfs_create_file("enabled", 0600, dir, NULL, &fops_kp); debugfs_create_file("blacklist", 0400, dir, NULL, - &debugfs_kprobe_blacklist_ops); + &kprobe_blacklist_fops); return 0; } |