summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-03-05 10:50:22 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-03-05 10:50:22 -0800
commit660f6a360be399f4ebdd6572a3d24afe54e9bb1c (patch)
tree9c16463c495a656e34577d59c97b58997b61d242 /kernel
parent586fac13f8685bf9dfb32e1ee98bfb14f0dd0061 (diff)
parente5a11016643d1ab7172193591506d33a844734cc (diff)
Merge branch 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: Issue at least one memory barrier in stop_machine_text_poke() perf probe: Correct probe syntax on command line help perf probe: Add lazy line matching support perf probe: Show more lines after last line perf probe: Check function address range strictly in line finder perf probe: Use libdw callback routines perf probe: Use elfutils-libdw for analyzing debuginfo perf probe: Rename probe finder functions perf probe: Fix bugs in line range finder perf probe: Update perf probe document perf probe: Do not show --line option without dwarf support kprobes: Add documents of jump optimization kprobes/x86: Support kprobes jump optimization on x86 x86: Add text_poke_smp for SMP cross modifying code kprobes/x86: Cleanup save/restore registers kprobes/x86: Boost probes when reentering kprobes: Jump optimization sysctl interface kprobes: Introduce kprobes jump optimization kprobes: Introduce generic insn_slot framework kprobes/x86: Cleanup RELATIVEJUMP_INSTRUCTION to RELATIVEJUMP_OPCODE
Diffstat (limited to 'kernel')
-rw-r--r--kernel/kprobes.c647
-rw-r--r--kernel/sysctl.c12
2 files changed, 569 insertions, 90 deletions
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ccec774c716d..fa034d29cf73 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -42,9 +42,11 @@
#include <linux/freezer.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
+#include <linux/sysctl.h>
#include <linux/kdebug.h>
#include <linux/memory.h>
#include <linux/ftrace.h>
+#include <linux/cpu.h>
#include <asm-generic/sections.h>
#include <asm/cacheflush.h>
@@ -105,57 +107,74 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
* stepping on the instruction on a vmalloced/kmalloced/data page
* is a recipe for disaster
*/
-#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
-
struct kprobe_insn_page {
struct list_head list;
kprobe_opcode_t *insns; /* Page of instruction slots */
- char slot_used[INSNS_PER_PAGE];
int nused;
int ngarbage;
+ char slot_used[];
+};
+
+#define KPROBE_INSN_PAGE_SIZE(slots) \
+ (offsetof(struct kprobe_insn_page, slot_used) + \
+ (sizeof(char) * (slots)))
+
+struct kprobe_insn_cache {
+ struct list_head pages; /* list of kprobe_insn_page */
+ size_t insn_size; /* size of instruction slot */
+ int nr_garbage;
};
+static int slots_per_page(struct kprobe_insn_cache *c)
+{
+ return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t));
+}
+
enum kprobe_slot_state {
SLOT_CLEAN = 0,
SLOT_DIRTY = 1,
SLOT_USED = 2,
};
-static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */
-static LIST_HEAD(kprobe_insn_pages);
-static int kprobe_garbage_slots;
-static int collect_garbage_slots(void);
+static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */
+static struct kprobe_insn_cache kprobe_insn_slots = {
+ .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
+ .insn_size = MAX_INSN_SIZE,
+ .nr_garbage = 0,
+};
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c);
/**
* __get_insn_slot() - Find a slot on an executable page for an instruction.
* We allocate an executable page if there's no room on existing ones.
*/
-static kprobe_opcode_t __kprobes *__get_insn_slot(void)
+static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip;
retry:
- list_for_each_entry(kip, &kprobe_insn_pages, list) {
- if (kip->nused < INSNS_PER_PAGE) {
+ list_for_each_entry(kip, &c->pages, list) {
+ if (kip->nused < slots_per_page(c)) {
int i;
- for (i = 0; i < INSNS_PER_PAGE; i++) {
+ for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_CLEAN) {
kip->slot_used[i] = SLOT_USED;
kip->nused++;
- return kip->insns + (i * MAX_INSN_SIZE);
+ return kip->insns + (i * c->insn_size);
}
}
- /* Surprise! No unused slots. Fix kip->nused. */
- kip->nused = INSNS_PER_PAGE;
+ /* kip->nused is broken. Fix it. */
+ kip->nused = slots_per_page(c);
+ WARN_ON(1);
}
}
/* If there are any garbage slots, collect it and try again. */
- if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
+ if (c->nr_garbage && collect_garbage_slots(c) == 0)
goto retry;
- }
- /* All out of space. Need to allocate a new page. Use slot 0. */
- kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
+
+ /* All out of space. Need to allocate a new page. */
+ kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL);
if (!kip)
return NULL;
@@ -170,20 +189,23 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
return NULL;
}
INIT_LIST_HEAD(&kip->list);
- list_add(&kip->list, &kprobe_insn_pages);
- memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
+ memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c));
kip->slot_used[0] = SLOT_USED;
kip->nused = 1;
kip->ngarbage = 0;
+ list_add(&kip->list, &c->pages);
return kip->insns;
}
+
kprobe_opcode_t __kprobes *get_insn_slot(void)
{
- kprobe_opcode_t *ret;
+ kprobe_opcode_t *ret = NULL;
+
mutex_lock(&kprobe_insn_mutex);
- ret = __get_insn_slot();
+ ret = __get_insn_slot(&kprobe_insn_slots);
mutex_unlock(&kprobe_insn_mutex);
+
return ret;
}
@@ -199,7 +221,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
* so as not to have to set it up again the
* next time somebody inserts a probe.
*/
- if (!list_is_singular(&kprobe_insn_pages)) {
+ if (!list_is_singular(&kip->list)) {
list_del(&kip->list);
module_free(NULL, kip->insns);
kfree(kip);
@@ -209,51 +231,84 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
return 0;
}
-static int __kprobes collect_garbage_slots(void)
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
synchronize_sched();
- list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
+ 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 */
- for (i = 0; i < INSNS_PER_PAGE; i++) {
+ for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_DIRTY &&
collect_one_slot(kip, i))
break;
}
}
- kprobe_garbage_slots = 0;
+ c->nr_garbage = 0;
return 0;
}
-void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
+ kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
- mutex_lock(&kprobe_insn_mutex);
- list_for_each_entry(kip, &kprobe_insn_pages, list) {
- if (kip->insns <= slot &&
- slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
- int i = (slot - kip->insns) / MAX_INSN_SIZE;
+ list_for_each_entry(kip, &c->pages, list) {
+ long idx = ((long)slot - (long)kip->insns) / c->insn_size;
+ if (idx >= 0 && idx < slots_per_page(c)) {
+ WARN_ON(kip->slot_used[idx] != SLOT_USED);
if (dirty) {
- kip->slot_used[i] = SLOT_DIRTY;
+ kip->slot_used[idx] = SLOT_DIRTY;
kip->ngarbage++;
+ if (++c->nr_garbage > slots_per_page(c))
+ collect_garbage_slots(c);
} else
- collect_one_slot(kip, i);
- break;
+ collect_one_slot(kip, idx);
+ return;
}
}
+ /* Could not free this slot. */
+ WARN_ON(1);
+}
- if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
- collect_garbage_slots();
-
+void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+{
+ mutex_lock(&kprobe_insn_mutex);
+ __free_insn_slot(&kprobe_insn_slots, slot, dirty);
mutex_unlock(&kprobe_insn_mutex);
}
+#ifdef CONFIG_OPTPROBES
+/* For optimized_kprobe buffer */
+static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */
+static struct kprobe_insn_cache kprobe_optinsn_slots = {
+ .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
+ /* .insn_size is initialized later */
+ .nr_garbage = 0,
+};
+/* Get a slot for optimized_kprobe buffer */
+kprobe_opcode_t __kprobes *get_optinsn_slot(void)
+{
+ kprobe_opcode_t *ret = NULL;
+
+ mutex_lock(&kprobe_optinsn_mutex);
+ ret = __get_insn_slot(&kprobe_optinsn_slots);
+ mutex_unlock(&kprobe_optinsn_mutex);
+
+ return ret;
+}
+
+void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty)
+{
+ mutex_lock(&kprobe_optinsn_mutex);
+ __free_insn_slot(&kprobe_optinsn_slots, slot, dirty);
+ mutex_unlock(&kprobe_optinsn_mutex);
+}
+#endif
#endif
/* We have preemption disabled.. so it is safe to use __ versions */
@@ -284,23 +339,401 @@ struct kprobe __kprobes *get_kprobe(void *addr)
if (p->addr == addr)
return p;
}
+
+ return NULL;
+}
+
+static int __kprobes 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 p->pre_handler == aggr_pre_handler;
+}
+
+/*
+ * Keep all fields in the kprobe consistent
+ */
+static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+ memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
+ memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+}
+
+#ifdef CONFIG_OPTPROBES
+/* NOTE: change this value only with kprobe_mutex held */
+static bool kprobes_allow_optimization;
+
+/*
+ * Call all pre_handler on the list, but ignores its return value.
+ * This must be called from arch-dep optimized caller.
+ */
+void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry_rcu(kp, &p->list, list) {
+ if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
+ set_kprobe_instance(kp);
+ kp->pre_handler(kp, regs);
+ }
+ reset_kprobe_instance();
+ }
+}
+
+/* Return true(!0) if the kprobe is ready for optimization. */
+static inline int kprobe_optready(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if (kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ return arch_prepared_optinsn(&op->optinsn);
+ }
+
+ return 0;
+}
+
+/*
+ * Return an optimized kprobe whose optimizing code replaces
+ * instructions including addr (exclude breakpoint).
+ */
+struct kprobe *__kprobes get_optimized_kprobe(unsigned long 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));
+
+ if (p && kprobe_optready(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (arch_within_optimized_kprobe(op, addr))
+ return p;
+ }
+
return NULL;
}
+/* Optimization staging list, protected by kprobe_mutex */
+static LIST_HEAD(optimizing_list);
+
+static void kprobe_optimizer(struct work_struct *work);
+static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+#define OPTIMIZE_DELAY 5
+
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ /* Lock modules while optimizing kprobes */
+ mutex_lock(&module_mutex);
+ mutex_lock(&kprobe_mutex);
+ if (kprobes_all_disarmed || !kprobes_allow_optimization)
+ goto end;
+
+ /*
+ * Wait for quiesence period to ensure all running interrupts
+ * are done. Because optprobe may modify multiple instructions
+ * there is a chance that Nth instruction is interrupted. In that
+ * case, running interrupt can return to 2nd-Nth byte of jump
+ * instruction. This wait is for avoiding it.
+ */
+ synchronize_sched();
+
+ /*
+ * 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, we need to call get_online_cpus()
+ * for preventing cpu-hotplug outside of text_mutex locking.
+ */
+ get_online_cpus();
+ mutex_lock(&text_mutex);
+ list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
+ WARN_ON(kprobe_disabled(&op->kp));
+ if (arch_optimize_kprobe(op) < 0)
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ list_del_init(&op->list);
+ }
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+end:
+ mutex_unlock(&kprobe_mutex);
+ mutex_unlock(&module_mutex);
+}
+
+/* Optimize kprobe if p is ready to be optimized */
+static __kprobes void optimize_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ /* Check if the kprobe is disabled or not ready for optimization. */
+ if (!kprobe_optready(p) || !kprobes_allow_optimization ||
+ (kprobe_disabled(p) || kprobes_all_disarmed))
+ return;
+
+ /* Both of break_handler and post_handler are not supported. */
+ if (p->break_handler || p->post_handler)
+ return;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+
+ /* Check there is no other kprobes at the optimized instructions */
+ if (arch_check_optimized_kprobe(op) < 0)
+ return;
+
+ /* Check if it is already optimized. */
+ if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
+ return;
+
+ op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
+ list_add(&op->list, &optimizing_list);
+ if (!delayed_work_pending(&optimizing_work))
+ schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+
+/* Unoptimize a kprobe if p is optimized */
+static __kprobes void unoptimize_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list))
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ else
+ /* Replace jump with break */
+ arch_unoptimize_kprobe(op);
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ }
+}
+
+/* Remove optimized instructions */
+static void __kprobes kill_optimized_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list)) {
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ }
+ /* Don't unoptimize, because the target code will be freed. */
+ arch_remove_optimized_kprobe(op);
+}
+
+/* Try to prepare optimized instructions */
+static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_prepare_optimized_kprobe(op);
+}
+
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_remove_optimized_kprobe(op);
+ kfree(op);
+}
+
+/* Allocate new optimized_kprobe and try to prepare optimized instructions */
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL);
+ if (!op)
+ return NULL;
+
+ INIT_LIST_HEAD(&op->list);
+ op->kp.addr = p->addr;
+ arch_prepare_optimized_kprobe(op);
+
+ return &op->kp;
+}
+
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
+
+/*
+ * Prepare an optimized_kprobe and optimize it
+ * NOTE: p must be a normal registered kprobe
+ */
+static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
+{
+ struct kprobe *ap;
+ struct optimized_kprobe *op;
+
+ ap = alloc_aggr_kprobe(p);
+ if (!ap)
+ return;
+
+ op = container_of(ap, struct optimized_kprobe, kp);
+ if (!arch_prepared_optinsn(&op->optinsn)) {
+ /* If failed to setup optimizing, fallback to kprobe */
+ free_aggr_kprobe(ap);
+ return;
+ }
+
+ init_aggr_kprobe(ap, p);
+ optimize_kprobe(ap);
+}
+
+#ifdef CONFIG_SYSCTL
+static void __kprobes optimize_all_kprobes(void)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct kprobe *p;
+ unsigned int i;
+
+ /* If optimization is already allowed, just return */
+ if (kprobes_allow_optimization)
+ return;
+
+ kprobes_allow_optimization = true;
+ mutex_lock(&text_mutex);
+ for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+ head = &kprobe_table[i];
+ hlist_for_each_entry_rcu(p, node, head, hlist)
+ if (!kprobe_disabled(p))
+ optimize_kprobe(p);
+ }
+ mutex_unlock(&text_mutex);
+ printk(KERN_INFO "Kprobes globally optimized\n");
+}
+
+static void __kprobes unoptimize_all_kprobes(void)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct kprobe *p;
+ unsigned int i;
+
+ /* If optimization is already prohibited, just return */
+ if (!kprobes_allow_optimization)
+ return;
+
+ kprobes_allow_optimization = false;
+ printk(KERN_INFO "Kprobes globally unoptimized\n");
+ get_online_cpus(); /* For avoiding text_mutex deadlock */
+ mutex_lock(&text_mutex);
+ for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+ head = &kprobe_table[i];
+ hlist_for_each_entry_rcu(p, node, head, hlist) {
+ if (!kprobe_disabled(p))
+ unoptimize_kprobe(p);
+ }
+ }
+
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+ /* Allow all currently running kprobes to complete */
+ synchronize_sched();
+}
+
+int sysctl_kprobes_optimization;
+int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length,
+ loff_t *ppos)
+{
+ int ret;
+
+ mutex_lock(&kprobe_mutex);
+ sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
+ ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+ if (sysctl_kprobes_optimization)
+ optimize_all_kprobes();
+ else
+ unoptimize_all_kprobes();
+ mutex_unlock(&kprobe_mutex);
+
+ return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+static void __kprobes __arm_kprobe(struct kprobe *p)
+{
+ struct kprobe *old_p;
+
+ /* Check collision with other optimized kprobes */
+ old_p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(old_p))
+ unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+
+ arch_arm_kprobe(p);
+ optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
+}
+
+static void __kprobes __disarm_kprobe(struct kprobe *p)
+{
+ struct kprobe *old_p;
+
+ unoptimize_kprobe(p); /* Try to unoptimize */
+ arch_disarm_kprobe(p);
+
+ /* If another kprobe was blocked, optimize it. */
+ old_p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(old_p))
+ optimize_kprobe(old_p);
+}
+
+#else /* !CONFIG_OPTPROBES */
+
+#define optimize_kprobe(p) do {} while (0)
+#define unoptimize_kprobe(p) do {} while (0)
+#define kill_optimized_kprobe(p) do {} while (0)
+#define prepare_optimized_kprobe(p) do {} while (0)
+#define try_to_optimize_kprobe(p) do {} while (0)
+#define __arm_kprobe(p) arch_arm_kprobe(p)
+#define __disarm_kprobe(p) arch_disarm_kprobe(p)
+
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ kfree(p);
+}
+
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+ return kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+}
+#endif /* CONFIG_OPTPROBES */
+
/* Arm a kprobe with text_mutex */
static void __kprobes arm_kprobe(struct kprobe *kp)
{
+ /*
+ * Here, since __arm_kprobe() doesn't use stop_machine(),
+ * this doesn't cause deadlock on text_mutex. So, we don't
+ * need get_online_cpus().
+ */
mutex_lock(&text_mutex);
- arch_arm_kprobe(kp);
+ __arm_kprobe(kp);
mutex_unlock(&text_mutex);
}
/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
+ get_online_cpus(); /* For avoiding text_mutex deadlock */
mutex_lock(&text_mutex);
- arch_disarm_kprobe(kp);
+ __disarm_kprobe(kp);
mutex_unlock(&text_mutex);
+ put_online_cpus();
}
/*
@@ -369,7 +802,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
{
struct kprobe *kp;
- if (p->pre_handler != aggr_pre_handler) {
+ if (!kprobe_aggrprobe(p)) {
p->nmissed++;
} else {
list_for_each_entry_rcu(kp, &p->list, list)
@@ -493,21 +926,16 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
}
/*
- * Keep all fields in the kprobe consistent
- */
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
-{
- memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
- memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
-}
-
-/*
* Add the new probe to ap->list. Fail if this is the
* second jprobe at the address - two jprobes can't coexist
*/
static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
+
+ if (p->break_handler || p->post_handler)
+ unoptimize_kprobe(ap); /* Fall back to normal kprobe */
+
if (p->break_handler) {
if (ap->break_handler)
return -EEXIST;
@@ -522,7 +950,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
ap->flags &= ~KPROBE_FLAG_DISABLED;
if (!kprobes_all_disarmed)
/* Arm the breakpoint again. */
- arm_kprobe(ap);
+ __arm_kprobe(ap);
}
return 0;
}
@@ -531,12 +959,13 @@ static int __kprobes 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
*/
-static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
{
+ /* Copy p's insn slot to ap */
copy_kprobe(p, ap);
flush_insn_slot(ap);
ap->addr = p->addr;
- ap->flags = p->flags;
+ 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. */
@@ -546,8 +975,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
ap->break_handler = aggr_break_handler;
INIT_LIST_HEAD(&ap->list);
- list_add_rcu(&p->list, &ap->list);
+ INIT_HLIST_NODE(&ap->hlist);
+ list_add_rcu(&p->list, &ap->list);
hlist_replace_rcu(&p->hlist, &ap->hlist);
}
@@ -561,12 +991,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
int ret = 0;
struct kprobe *ap = old_p;
- if (old_p->pre_handler != aggr_pre_handler) {
- /* If old_p is not an aggr_probe, create new aggr_kprobe. */
- ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+ if (!kprobe_aggrprobe(old_p)) {
+ /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
+ ap = alloc_aggr_kprobe(old_p);
if (!ap)
return -ENOMEM;
- add_aggr_kprobe(ap, old_p);
+ init_aggr_kprobe(ap, old_p);
}
if (kprobe_gone(ap)) {
@@ -585,6 +1015,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
*/
return ret;
+ /* Prepare optimized instructions if possible. */
+ prepare_optimized_kprobe(ap);
+
/*
* Clear gone flag to prevent allocating new slot again, and
* set disabled flag because it is not armed yet.
@@ -593,6 +1026,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
| KPROBE_FLAG_DISABLED;
}
+ /* Copy ap's insn slot to p */
copy_kprobe(ap, p);
return add_new_kprobe(ap, p);
}
@@ -743,27 +1177,34 @@ int __kprobes register_kprobe(struct kprobe *p)
p->nmissed = 0;
INIT_LIST_HEAD(&p->list);
mutex_lock(&kprobe_mutex);
+
+ get_online_cpus(); /* For avoiding text_mutex deadlock. */
+ mutex_lock(&text_mutex);
+
old_p = get_kprobe(p->addr);
if (old_p) {
+ /* Since this may unoptimize old_p, locking text_mutex. */
ret = register_aggr_kprobe(old_p, p);
goto out;
}
- mutex_lock(&text_mutex);
ret = arch_prepare_kprobe(p);
if (ret)
- goto out_unlock_text;
+ goto out;
INIT_HLIST_NODE(&p->hlist);
hlist_add_head_rcu(&p->hlist,
&kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
if (!kprobes_all_disarmed && !kprobe_disabled(p))
- arch_arm_kprobe(p);
+ __arm_kprobe(p);
+
+ /* Try to optimize kprobe */
+ try_to_optimize_kprobe(p);
-out_unlock_text:
- mutex_unlock(&text_mutex);
out:
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
mutex_unlock(&kprobe_mutex);
if (probed_mod)
@@ -785,7 +1226,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
return -EINVAL;
if (old_p == p ||
- (old_p->pre_handler == aggr_pre_handler &&
+ (kprobe_aggrprobe(old_p) &&
list_is_singular(&old_p->list))) {
/*
* Only probe on the hash list. Disarm only if kprobes are
@@ -793,7 +1234,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
* already have been removed. We save on flushing icache.
*/
if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
- disarm_kprobe(p);
+ disarm_kprobe(old_p);
hlist_del_rcu(&old_p->hlist);
} else {
if (p->break_handler && !kprobe_gone(p))
@@ -809,8 +1250,13 @@ noclean:
list_del_rcu(&p->list);
if (!kprobe_disabled(old_p)) {
try_to_disable_aggr_kprobe(old_p);
- if (!kprobes_all_disarmed && kprobe_disabled(old_p))
- disarm_kprobe(old_p);
+ if (!kprobes_all_disarmed) {
+ if (kprobe_disabled(old_p))
+ disarm_kprobe(old_p);
+ else
+ /* Try to optimize this probe again */
+ optimize_kprobe(old_p);
+ }
}
}
return 0;
@@ -827,7 +1273,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
old_p = list_entry(p->list.next, struct kprobe, list);
list_del(&p->list);
arch_remove_kprobe(old_p);
- kfree(old_p);
+ free_aggr_kprobe(old_p);
}
}
@@ -1123,7 +1569,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
struct kprobe *kp;
p->flags |= KPROBE_FLAG_GONE;
- if (p->pre_handler == aggr_pre_handler) {
+ if (kprobe_aggrprobe(p)) {
/*
* If this is an aggr_kprobe, we have to list all the
* chained probes and mark them GONE.
@@ -1132,6 +1578,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
kp->flags |= KPROBE_FLAG_GONE;
p->post_handler = NULL;
p->break_handler = NULL;
+ kill_optimized_kprobe(p);
}
/*
* Here, we can remove insn_slot safely, because no thread calls
@@ -1241,6 +1688,15 @@ static int __init init_kprobes(void)
}
}
+#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;
@@ -1259,7 +1715,7 @@ static int __init init_kprobes(void)
#ifdef CONFIG_DEBUG_FS
static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
- const char *sym, int offset,char *modname)
+ const char *sym, int offset, char *modname, struct kprobe *pp)
{
char *kprobe_type;
@@ -1269,19 +1725,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
kprobe_type = "j";
else
kprobe_type = "k";
+
if (sym)
- seq_printf(pi, "%p %s %s+0x%x %s %s%s\n",
+ seq_printf(pi, "%p %s %s+0x%x %s ",
p->addr, kprobe_type, sym, offset,
- (modname ? modname : " "),
- (kprobe_gone(p) ? "[GONE]" : ""),
- ((kprobe_disabled(p) && !kprobe_gone(p)) ?
- "[DISABLED]" : ""));
+ (modname ? modname : " "));
else
- seq_printf(pi, "%p %s %p %s%s\n",
- p->addr, kprobe_type, p->addr,
- (kprobe_gone(p) ? "[GONE]" : ""),
- ((kprobe_disabled(p) && !kprobe_gone(p)) ?
- "[DISABLED]" : ""));
+ seq_printf(pi, "%p %s %p ",
+ p->addr, kprobe_type, p->addr);
+
+ if (!pp)
+ pp = p;
+ seq_printf(pi, "%s%s%s\n",
+ (kprobe_gone(p) ? "[GONE]" : ""),
+ ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""),
+ (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""));
}
static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -1317,11 +1775,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
hlist_for_each_entry_rcu(p, node, head, hlist) {
sym = kallsyms_lookup((unsigned long)p->addr, NULL,
&offset, &modname, namebuf);
- if (p->pre_handler == aggr_pre_handler) {
+ if (kprobe_aggrprobe(p)) {
list_for_each_entry_rcu(kp, &p->list, list)
- report_probe(pi, kp, sym, offset, modname);
+ report_probe(pi, kp, sym, offset, modname, p);
} else
- report_probe(pi, p, sym, offset, modname);
+ report_probe(pi, p, sym, offset, modname, NULL);
}
preempt_enable();
return 0;
@@ -1399,12 +1857,13 @@ int __kprobes enable_kprobe(struct kprobe *kp)
goto out;
}
- if (!kprobes_all_disarmed && kprobe_disabled(p))
- arm_kprobe(p);
-
- p->flags &= ~KPROBE_FLAG_DISABLED;
if (p != kp)
kp->flags &= ~KPROBE_FLAG_DISABLED;
+
+ if (!kprobes_all_disarmed && kprobe_disabled(p)) {
+ p->flags &= ~KPROBE_FLAG_DISABLED;
+ arm_kprobe(p);
+ }
out:
mutex_unlock(&kprobe_mutex);
return ret;
@@ -1424,12 +1883,13 @@ static void __kprobes arm_all_kprobes(void)
if (!kprobes_all_disarmed)
goto already_enabled;
+ /* Arming kprobes doesn't optimize kprobe itself */
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist)
if (!kprobe_disabled(p))
- arch_arm_kprobe(p);
+ __arm_kprobe(p);
}
mutex_unlock(&text_mutex);
@@ -1456,16 +1916,23 @@ static void __kprobes disarm_all_kprobes(void)
kprobes_all_disarmed = true;
printk(KERN_INFO "Kprobes globally disabled\n");
+
+ /*
+ * Here we call get_online_cpus() for avoiding text_mutex deadlock,
+ * because disarming may also unoptimize kprobes.
+ */
+ get_online_cpus();
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
- arch_disarm_kprobe(p);
+ __disarm_kprobe(p);
}
}
mutex_unlock(&text_mutex);
+ put_online_cpus();
mutex_unlock(&kprobe_mutex);
/* Allow all currently running kprobes to complete */
synchronize_sched();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 33e7a38b6eb9..0ef19c614f6d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -50,6 +50,7 @@
#include <linux/ftrace.h>
#include <linux/slow-work.h>
#include <linux/perf_event.h>
+#include <linux/kprobes.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -1450,6 +1451,17 @@ static struct ctl_table debug_table[] = {
.proc_handler = proc_dointvec
},
#endif
+#if defined(CONFIG_OPTPROBES)
+ {
+ .procname = "kprobes-optimization",
+ .data = &sysctl_kprobes_optimization,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_kprobes_optimization_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
{ }
};