// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Kernel Probes (KProbes)
- * kernel/kprobes.c
*
* Copyright (C) IBM Corporation, 2002, 2004
*
* <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>
static int kprobes_initialized;
/* kprobe_table can be accessed by
- * - Normal hlist traversal and RCU add/del under kprobe_mutex is held.
+ * - 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];
-/* 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 DEFINE_PER_CPU(struct kprobe *, kprobe_instance);
kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
unsigned int __unused)
return ((kprobe_opcode_t *)(kallsyms_lookup_name(name)));
}
-/* 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
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);
}
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;
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);
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--;
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)
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 */
list_for_each_entry_rcu(kip, &c->pages, list) {
if ((*symnum)--)
continue;
- strlcpy(sym, c->sym, KSYM_NAME_LEN);
+ strscpy(sym, c->sym, KSYM_NAME_LEN);
*type = 't';
*value = (unsigned long)kip->insns;
ret = 0;
/*
* 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)
{
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));
}
#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)
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;
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;
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);
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);
/*
* 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();
/*
* 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)
{
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;
/*
* 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
}
}
-/* 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;
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);
(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;
}
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;
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;
__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;
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);
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);
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;
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);
}
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;
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);
}
#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);
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 */
* 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;
}
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)++;
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;
}
ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
}
#else /* !CONFIG_KPROBES_ON_FTRACE */
-static inline int prepare_kprobe(struct kprobe *p)
-{
- return arch_prepare_kprobe(p);
-}
-
static inline int arm_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)))
return 0;
}
-/* Disarm a kprobe with text_mutex */
static int disarm_kprobe(struct kprobe *kp, bool reopt)
{
if (unlikely(kprobe_ftrace(kp)))
}
NOKPROBE_SYMBOL(aggr_post_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);
{
struct kretprobe *rp = get_kretprobe(ri);
- if (likely(rp)) {
+ if (likely(rp))
freelist_add(&ri->freelist, &rp->freelist);
- } else
+ 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 function-return probe instances
- * associated with this task. These left over instances represent probed
- * functions that have been called but will never return.
+ * 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)
{
}
}
-/* 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)
}
/*
- * 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;
}
/*
- * 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)
{
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;
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;
| 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);
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;
}
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)
}
/*
- * If we have a symbol_name argument, look it up and add the offset field
+ * 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.
return _kprobe_addr(p->addr, p->symbol_name, p->offset);
}
-/* 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;
return ret;
}
-int __weak arch_check_ftrace_location(struct kprobe *p)
+static int check_ftrace_location(struct kprobe *p)
{
unsigned long ftrace_addr;
{
int ret;
- ret = arch_check_ftrace_location(p);
+ ret = check_ftrace_location(p);
if (ret)
return ret;
jump_label_lock();
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) {
/*
}
/*
- * 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) &&
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;
}
}
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(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))
/* 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
+ * If 'kprobes_all_disarmed' is set, 'orig_p'
* should have already been disarmed, so
* skip unneed disarming process.
*/
.priority = 0x7fffffff /* we need to be notified first */
};
-unsigned long __weak arch_deref_entry_point(void *entry)
+#ifdef CONFIG_KRETPROBES
+
+/* 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)
{
- return (unsigned long)entry;
+ 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);
-#ifdef CONFIG_KRETPROBES
+/**
+ * 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 *trampoline_address,
void *frame_pointer)
{
kprobe_opcode_t *correct_ret_addr = NULL;
struct kretprobe_instance *ri = NULL;
- struct llist_node *first, *node;
+ struct llist_node *first, *node = NULL;
struct kretprobe *rp;
- /* Find all nodes for this frame. */
- first = node = current->kretprobe_instances.first;
- while (node) {
- ri = container_of(node, struct kretprobe_instance, llist);
-
- BUG_ON(ri->fp != frame_pointer);
-
- if (ri->ret_addr != trampoline_address) {
- correct_ret_addr = ri->ret_addr;
- /*
- * This is the real return address. Any other
- * instances associated with this task are for
- * other calls deeper on the call stack
- */
- goto found;
- }
-
- node = node->next;
+ /* 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);
}
- pr_err("Oops! Kretprobe fails to find correct return address.\n");
- BUG_ON(1);
-found:
- /* Unlink all nodes for this frame. */
- current->kretprobe_instances.first = node->next;
- node->next = NULL;
+ /*
+ * 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 them.. */
+ /* Run the user handler of the nodes. */
+ first = current->kretprobe_instances.first;
while (first) {
ri = container_of(first, struct kretprobe_instance, llist);
- first = first->next;
+
+ if (WARN_ON_ONCE(ri->fp != frame_pointer))
+ break;
rp = get_kretprobe(ri);
if (rp && rp->handler) {
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);
}
if (ret)
return ret;
- /* If only rp->kp.addr is specified, check reregistering kprobes */
+ /* If only 'rp->kp.addr' is specified, check reregistering kprobes */
if (rp->kp.addr && warn_kprobe_rereg(&rp->kp))
return -EINVAL;
#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);
/*
* 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.
+ * 'MODULE_STATE_GOING' notification.
*/
if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
disarm_kprobe_ftrace(p);
/* 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);
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;
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 */
+ /* Symbols in 'noinstr' section are blacklisted */
ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start,
(unsigned long)__noinstr_text_end);
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);
*
* 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);
}
.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);
mutex_lock(&kprobe_mutex);
- /* Kill all kprobes on initmem */
+ /* 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) {
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 */
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);
}
}
kprobes_all_disarmed = false;
#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT)
- /* Init kprobe_optinsn_slots for allocation */
+ /* Init 'kprobe_optinsn_slots' for allocation */
kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE;
#endif
err = register_module_notifier(&kprobe_module_nb);
kprobes_initialized = (err == 0);
-
- if (!err)
- init_test_probes();
return err;
}
early_initcall(init_kprobes);
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(m->file->f_cred))
}
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");
}
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");
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;
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, &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,
&kprobe_blacklist_fops);
projects / linux-2.6-microblaze.git / blobdiff