aboutsummaryrefslogtreecommitdiff
path: root/kernel/kprobes.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/kprobes.c')
-rw-r--r--kernel/kprobes.c254
1 files changed, 171 insertions, 83 deletions
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 43460104f119..a1606a4224e1 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -58,15 +58,6 @@
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
-/*
- * Some oddball architectures like 64bit powerpc have function descriptors
- * so this must be overridable.
- */
-#ifndef kprobe_lookup_name
-#define kprobe_lookup_name(name, addr) \
- addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
-#endif
-
static int kprobes_initialized;
static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
@@ -81,6 +72,12 @@ static struct {
raw_spinlock_t lock ____cacheline_aligned_in_smp;
} kretprobe_table_locks[KPROBE_TABLE_SIZE];
+kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
+ unsigned int __unused)
+{
+ 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);
@@ -125,7 +122,7 @@ static void *alloc_insn_page(void)
return module_alloc(PAGE_SIZE);
}
-static void free_insn_page(void *page)
+void __weak free_insn_page(void *page)
{
module_memfree(page);
}
@@ -149,9 +146,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
struct kprobe_insn_page *kip;
kprobe_opcode_t *slot = NULL;
+ /* Since the slot array is not protected by rcu, we need a mutex */
mutex_lock(&c->mutex);
retry:
- list_for_each_entry(kip, &c->pages, list) {
+ rcu_read_lock();
+ 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++) {
@@ -159,6 +158,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->slot_used[i] = SLOT_USED;
kip->nused++;
slot = kip->insns + (i * c->insn_size);
+ rcu_read_unlock();
goto out;
}
}
@@ -167,6 +167,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
WARN_ON(1);
}
}
+ rcu_read_unlock();
/* If there are any garbage slots, collect it and try again. */
if (c->nr_garbage && collect_garbage_slots(c) == 0)
@@ -193,7 +194,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->nused = 1;
kip->ngarbage = 0;
kip->cache = c;
- list_add(&kip->list, &c->pages);
+ list_add_rcu(&kip->list, &c->pages);
slot = kip->insns;
out:
mutex_unlock(&c->mutex);
@@ -213,7 +214,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
* next time somebody inserts a probe.
*/
if (!list_is_singular(&kip->list)) {
- list_del(&kip->list);
+ list_del_rcu(&kip->list);
+ synchronize_rcu();
kip->cache->free(kip->insns);
kfree(kip);
}
@@ -235,8 +237,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
continue;
kip->ngarbage = 0; /* we will collect all garbages */
for (i = 0; i < slots_per_page(c); i++) {
- if (kip->slot_used[i] == SLOT_DIRTY &&
- collect_one_slot(kip, i))
+ if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
break;
}
}
@@ -248,29 +249,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
+ long idx;
mutex_lock(&c->mutex);
- list_for_each_entry(kip, &c->pages, list) {
- long idx = ((long)slot - (long)kip->insns) /
- (c->insn_size * sizeof(kprobe_opcode_t));
- if (idx >= 0 && idx < slots_per_page(c)) {
- WARN_ON(kip->slot_used[idx] != SLOT_USED);
- if (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, idx);
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ idx = ((long)slot - (long)kip->insns) /
+ (c->insn_size * sizeof(kprobe_opcode_t));
+ if (idx >= 0 && idx < slots_per_page(c))
goto out;
- }
}
- /* Could not free this slot. */
+ /* Could not find this slot. */
WARN_ON(1);
+ kip = NULL;
out:
+ rcu_read_unlock();
+ /* Mark and sweep: this may sleep */
+ if (kip) {
+ /* Check double free */
+ WARN_ON(kip->slot_used[idx] != SLOT_USED);
+ if (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, idx);
+ }
+ }
mutex_unlock(&c->mutex);
}
+/*
+ * Check given address is on the page of kprobe instruction slots.
+ * This will be used for checking whether the address on a stack
+ * is on a text area or not.
+ */
+bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
+{
+ struct kprobe_insn_page *kip;
+ bool ret = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ if (addr >= (unsigned long)kip->insns &&
+ addr < (unsigned long)kip->insns + PAGE_SIZE) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
struct kprobe_insn_cache kprobe_optinsn_slots = {
@@ -451,11 +483,6 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
*/
static void do_optimize_kprobes(void)
{
- /* Optimization never be done when disarmed */
- if (kprobes_all_disarmed || !kprobes_allow_optimization ||
- list_empty(&optimizing_list))
- return;
-
/*
* The optimization/unoptimization refers online_cpus via
* stop_machine() and cpu-hotplug modifies online_cpus.
@@ -463,14 +490,19 @@ static void do_optimize_kprobes(void)
* 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()
+ * To avoid this deadlock, caller must have locked cpu hotplug
* for preventing cpu-hotplug outside of text_mutex locking.
*/
- get_online_cpus();
+ lockdep_assert_cpus_held();
+
+ /* Optimization never be done when disarmed */
+ if (kprobes_all_disarmed || !kprobes_allow_optimization ||
+ list_empty(&optimizing_list))
+ return;
+
mutex_lock(&text_mutex);
arch_optimize_kprobes(&optimizing_list);
mutex_unlock(&text_mutex);
- put_online_cpus();
}
/*
@@ -481,12 +513,13 @@ static void do_unoptimize_kprobes(void)
{
struct optimized_kprobe *op, *tmp;
+ /* See comment in do_optimize_kprobes() */
+ lockdep_assert_cpus_held();
+
/* Unoptimization must be done anytime */
if (list_empty(&unoptimizing_list))
return;
- /* Ditto to do_optimize_kprobes */
- get_online_cpus();
mutex_lock(&text_mutex);
arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
/* Loop free_list for disarming */
@@ -505,7 +538,6 @@ static void do_unoptimize_kprobes(void)
list_del_init(&op->list);
}
mutex_unlock(&text_mutex);
- put_online_cpus();
}
/* Reclaim all kprobes on the free_list */
@@ -530,6 +562,7 @@ static void kick_kprobe_optimizer(void)
static void kprobe_optimizer(struct work_struct *work)
{
mutex_lock(&kprobe_mutex);
+ cpus_read_lock();
/* Lock modules while optimizing kprobes */
mutex_lock(&module_mutex);
@@ -555,6 +588,7 @@ static void kprobe_optimizer(struct work_struct *work)
do_free_cleaned_kprobes();
mutex_unlock(&module_mutex);
+ cpus_read_unlock();
mutex_unlock(&kprobe_mutex);
/* Step 5: Kick optimizer again if needed */
@@ -563,7 +597,7 @@ static void kprobe_optimizer(struct work_struct *work)
}
/* Wait for completing optimization and unoptimization */
-static void wait_for_kprobe_optimizer(void)
+void wait_for_kprobe_optimizer(void)
{
mutex_lock(&kprobe_mutex);
@@ -618,9 +652,8 @@ static void optimize_kprobe(struct kprobe *p)
/* Short cut to direct unoptimizing */
static void force_unoptimize_kprobe(struct optimized_kprobe *op)
{
- get_online_cpus();
+ lockdep_assert_cpus_held();
arch_unoptimize_kprobe(op);
- put_online_cpus();
if (kprobe_disabled(&op->kp))
arch_disarm_kprobe(&op->kp);
}
@@ -711,13 +744,20 @@ static void kill_optimized_kprobe(struct kprobe *p)
arch_remove_optimized_kprobe(op);
}
+static inline
+void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
+{
+ if (!kprobe_ftrace(p))
+ arch_prepare_optimized_kprobe(op, p);
+}
+
/* Try to prepare optimized instructions */
static void prepare_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
- arch_prepare_optimized_kprobe(op, p);
+ __prepare_optimized_kprobe(op, p);
}
/* Allocate new optimized_kprobe and try to prepare optimized instructions */
@@ -731,7 +771,7 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
INIT_LIST_HEAD(&op->list);
op->kp.addr = p->addr;
- arch_prepare_optimized_kprobe(op, p);
+ __prepare_optimized_kprobe(op, p);
return &op->kp;
}
@@ -752,6 +792,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
return;
/* For preparing optimization, jump_label_text_reserved() is called */
+ cpus_read_lock();
jump_label_lock();
mutex_lock(&text_mutex);
@@ -773,6 +814,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
out:
mutex_unlock(&text_mutex);
jump_label_unlock();
+ cpus_read_unlock();
}
#ifdef CONFIG_SYSCTL
@@ -787,6 +829,7 @@ static void optimize_all_kprobes(void)
if (kprobes_allow_optimization)
goto out;
+ cpus_read_lock();
kprobes_allow_optimization = true;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
@@ -794,6 +837,7 @@ static void optimize_all_kprobes(void)
if (!kprobe_disabled(p))
optimize_kprobe(p);
}
+ cpus_read_unlock();
printk(KERN_INFO "Kprobes globally optimized\n");
out:
mutex_unlock(&kprobe_mutex);
@@ -812,6 +856,7 @@ static void unoptimize_all_kprobes(void)
return;
}
+ cpus_read_lock();
kprobes_allow_optimization = false;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
@@ -820,6 +865,7 @@ static void unoptimize_all_kprobes(void)
unoptimize_kprobe(p, false);
}
}
+ cpus_read_unlock();
mutex_unlock(&kprobe_mutex);
/* Wait for unoptimizing completion */
@@ -971,14 +1017,11 @@ static void arm_kprobe(struct kprobe *kp)
arm_kprobe_ftrace(kp);
return;
}
- /*
- * 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().
- */
+ cpus_read_lock();
mutex_lock(&text_mutex);
__arm_kprobe(kp);
mutex_unlock(&text_mutex);
+ cpus_read_unlock();
}
/* Disarm a kprobe with text_mutex */
@@ -988,10 +1031,12 @@ static void disarm_kprobe(struct kprobe *kp, bool reopt)
disarm_kprobe_ftrace(kp);
return;
}
- /* Ditto */
+
+ cpus_read_lock();
mutex_lock(&text_mutex);
__disarm_kprobe(kp, reopt);
mutex_unlock(&text_mutex);
+ cpus_read_unlock();
}
/*
@@ -1259,13 +1304,10 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
int ret = 0;
struct kprobe *ap = orig_p;
+ cpus_read_lock();
+
/* For preparing optimization, jump_label_text_reserved() is called */
jump_label_lock();
- /*
- * Get online CPUs to avoid text_mutex deadlock.with stop machine,
- * which is invoked by unoptimize_kprobe() in add_new_kprobe()
- */
- get_online_cpus();
mutex_lock(&text_mutex);
if (!kprobe_aggrprobe(orig_p)) {
@@ -1313,8 +1355,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
out:
mutex_unlock(&text_mutex);
- put_online_cpus();
jump_label_unlock();
+ cpus_read_unlock();
if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
ap->flags &= ~KPROBE_FLAG_DISABLED;
@@ -1356,21 +1398,19 @@ bool within_kprobe_blacklist(unsigned long addr)
* This returns encoded errors if it fails to look up symbol or invalid
* combination of parameters.
*/
-static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
+ const char *symbol_name, unsigned int offset)
{
- kprobe_opcode_t *addr = p->addr;
-
- if ((p->symbol_name && p->addr) ||
- (!p->symbol_name && !p->addr))
+ if ((symbol_name && addr) || (!symbol_name && !addr))
goto invalid;
- if (p->symbol_name) {
- kprobe_lookup_name(p->symbol_name, addr);
+ if (symbol_name) {
+ addr = kprobe_lookup_name(symbol_name, offset);
if (!addr)
return ERR_PTR(-ENOENT);
}
- addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+ addr = (kprobe_opcode_t *)(((char *)addr) + offset);
if (addr)
return addr;
@@ -1378,6 +1418,11 @@ invalid:
return ERR_PTR(-EINVAL);
}
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+{
+ return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+}
+
/* Check passed kprobe is valid and return kprobe in kprobe_table. */
static struct kprobe *__get_valid_kprobe(struct kprobe *p)
{
@@ -1513,9 +1558,12 @@ int register_kprobe(struct kprobe *p)
goto out;
}
- mutex_lock(&text_mutex); /* Avoiding text modification */
+ cpus_read_lock();
+ /* Prevent text modification */
+ mutex_lock(&text_mutex);
ret = prepare_kprobe(p);
mutex_unlock(&text_mutex);
+ cpus_read_unlock();
if (ret)
goto out;
@@ -1528,7 +1576,6 @@ int register_kprobe(struct kprobe *p)
/* Try to optimize kprobe */
try_to_optimize_kprobe(p);
-
out:
mutex_unlock(&kprobe_mutex);
@@ -1705,6 +1752,13 @@ void unregister_kprobes(struct kprobe **kps, int num)
}
EXPORT_SYMBOL_GPL(unregister_kprobes);
+int __weak kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return NOTIFY_DONE;
+}
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
+
static struct notifier_block kprobe_exceptions_nb = {
.notifier_call = kprobe_exceptions_notify,
.priority = 0x7fffffff /* we need to be notified first */
@@ -1717,24 +1771,13 @@ unsigned long __weak arch_deref_entry_point(void *entry)
int register_jprobes(struct jprobe **jps, int num)
{
- struct jprobe *jp;
int ret = 0, i;
if (num <= 0)
return -EINVAL;
+
for (i = 0; i < num; i++) {
- unsigned long addr, offset;
- jp = jps[i];
- addr = arch_deref_entry_point(jp->entry);
-
- /* Verify probepoint is a function entry point */
- if (kallsyms_lookup_size_offset(addr, NULL, &offset) &&
- offset == 0) {
- jp->kp.pre_handler = setjmp_pre_handler;
- jp->kp.break_handler = longjmp_break_handler;
- ret = register_kprobe(&jp->kp);
- } else
- ret = -EINVAL;
+ ret = register_jprobe(jps[i]);
if (ret < 0) {
if (i > 0)
@@ -1742,13 +1785,30 @@ int register_jprobes(struct jprobe **jps, int num)
break;
}
}
+
return ret;
}
EXPORT_SYMBOL_GPL(register_jprobes);
int register_jprobe(struct jprobe *jp)
{
- return register_jprobes(&jp, 1);
+ unsigned long addr, offset;
+ struct kprobe *kp = &jp->kp;
+
+ /*
+ * Verify probepoint as well as the jprobe handler are
+ * valid function entry points.
+ */
+ addr = arch_deref_entry_point(jp->entry);
+
+ if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
+ kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
+ kp->pre_handler = setjmp_pre_handler;
+ kp->break_handler = longjmp_break_handler;
+ return register_kprobe(kp);
+ }
+
+ return -EINVAL;
}
EXPORT_SYMBOL_GPL(register_jprobe);
@@ -1834,6 +1894,25 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
}
NOKPROBE_SYMBOL(pre_handler_kretprobe);
+bool __weak arch_kprobe_on_func_entry(unsigned long offset)
+{
+ return !offset;
+}
+
+bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+{
+ kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+
+ if (IS_ERR(kp_addr))
+ return false;
+
+ if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
+ !arch_kprobe_on_func_entry(offset))
+ return false;
+
+ return true;
+}
+
int register_kretprobe(struct kretprobe *rp)
{
int ret = 0;
@@ -1841,6 +1920,9 @@ int register_kretprobe(struct kretprobe *rp)
int i;
void *addr;
+ if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+ return -EINVAL;
+
if (kretprobe_blacklist_size) {
addr = kprobe_addr(&rp->kp);
if (IS_ERR(addr))
@@ -2112,6 +2194,12 @@ static int kprobes_module_callback(struct notifier_block *nb,
* The vaddr this probe is installed will soon
* be vfreed buy not synced to disk. Hence,
* disarming the breakpoint isn't needed.
+ *
+ * Note, this will also move any optimized probes
+ * that are pending to be removed from their
+ * corresponding lists to the freeing_list and
+ * will not be touched by the delayed
+ * kprobe_optimizer work handler.
*/
kill_kprobe(p);
}
@@ -2151,8 +2239,8 @@ static int __init init_kprobes(void)
if (kretprobe_blacklist_size) {
/* lookup the function address from its name */
for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
- kprobe_lookup_name(kretprobe_blacklist[i].name,
- kretprobe_blacklist[i].addr);
+ kretprobe_blacklist[i].addr =
+ kprobe_lookup_name(kretprobe_blacklist[i].name, 0);
if (!kretprobe_blacklist[i].addr)
printk("kretprobe: lookup failed: %s\n",
kretprobe_blacklist[i].name);