Skip to content

Commit

Permalink
Merge tag 'trace-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kern…
Browse files Browse the repository at this point in the history 
…el/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Have recordmcount work with > 64K sections (to support LTO)

 - kprobe RCU fixes

 - Correct a kprobe critical section with missing mutex

 - Remove redundant arch_disarm_kprobe() call

 - Fix lockup when kretprobe triggers within kprobe_flush_task()

 - Fix memory leak in fetch_op_data operations

 - Fix sleep in atomic in ftrace trace array sample code

 - Free up memory on failure in sample trace array code

 - Fix incorrect reporting of function_graph fields in format file

 - Fix quote within quote parsing in bootconfig

 - Fix return value of bootconfig tool

 - Add testcases for bootconfig tool

 - Fix maybe uninitialized warning in ftrace pid file code

 - Remove unused variable in tracing_iter_reset()

 - Fix some typos

* tag 'trace-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ftrace: Fix maybe-uninitialized compiler warning
  tools/bootconfig: Add testcase for show-command and quotes test
  tools/bootconfig: Fix to return 0 if succeeded to show the bootconfig
  tools/bootconfig: Fix to use correct quotes for value
  proc/bootconfig: Fix to use correct quotes for value
  tracing: Remove unused event variable in tracing_iter_reset
  tracing/probe: Fix memleak in fetch_op_data operations
  trace: Fix typo in allocate_ftrace_ops()'s comment
  tracing: Make ftrace packed events have align of 1
  sample-trace-array: Remove trace_array 'sample-instance'
  sample-trace-array: Fix sleeping function called from invalid context
  kretprobe: Prevent triggering kretprobe from within kprobe_flush_task
  kprobes: Remove redundant arch_disarm_kprobe() call
  kprobes: Fix to protect kick_kprobe_optimizer() by kprobe_mutex
  kprobes: Use non RCU traversal APIs on kprobe_tables if possible
  kprobes: Suppress the suspicious RCU warning on kprobes
  recordmcount: support >64k sections
  • Loading branch information
@torvalds
torvalds committed Jun 20, 2020
2 parents eede2b9 + 026bb84 commit 8b6ddd1
Show file tree
Hide file tree
Showing 15 changed files with 239 additions and 67 deletions.
16 changes: 3 additions & 13 deletions arch/x86/kernel/kprobes/core.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -754,16 +754,11 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);

static struct kprobe kretprobe_kprobe = {
.addr = (void *)kretprobe_trampoline,
};

/*
* Called from kretprobe_trampoline
*/
__used __visible void *trampoline_handler(struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
Expand All @@ -773,16 +768,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
void *frame_pointer;
bool skipped = false;

preempt_disable();

/*
* Set a dummy kprobe for avoiding kretprobe recursion.
* Since kretprobe never run in kprobe handler, kprobe must not
* be running at this point.
*/
kcb = get_kprobe_ctlblk();
__this_cpu_write(current_kprobe, &kretprobe_kprobe);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
kprobe_busy_begin();

INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
Expand Down Expand Up @@ -858,7 +849,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
__this_cpu_write(current_kprobe, &ri->rp->kp);
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
__this_cpu_write(current_kprobe, &kretprobe_kprobe);
__this_cpu_write(current_kprobe, &kprobe_busy);
}

recycle_rp_inst(ri, &empty_rp);
Expand All @@ -874,8 +865,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)

kretprobe_hash_unlock(current, &flags);

__this_cpu_write(current_kprobe, NULL);
preempt_enable();
kprobe_busy_end();

hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
Expand Down
15 changes: 10 additions & 5 deletions fs/proc/bootconfig.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -26,8 +26,9 @@ static int boot_config_proc_show(struct seq_file *m, void *v)
static int __init copy_xbc_key_value_list(char *dst, size_t size)
{
struct xbc_node *leaf, *vnode;
const char *val;
char *key, *end = dst + size;
const char *val;
char q;
int ret = 0;

key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL);
Expand All @@ -41,16 +42,20 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size)
break;
dst += ret;
vnode = xbc_node_get_child(leaf);
if (vnode && xbc_node_is_array(vnode)) {
if (vnode) {
xbc_array_for_each_value(vnode, val) {
ret = snprintf(dst, rest(dst, end), "\"%s\"%s",
val, vnode->next ? ", " : "\n");
if (strchr(val, '"'))
q = '\'';
else
q = '"';
ret = snprintf(dst, rest(dst, end), "%c%s%c%s",
q, val, q, vnode->next ? ", " : "\n");
if (ret < 0)
goto out;
dst += ret;
}
} else {
ret = snprintf(dst, rest(dst, end), "\"%s\"\n", val);
ret = snprintf(dst, rest(dst, end), "\"\"\n");
if (ret < 0)
break;
dst += ret;
Expand Down
4 changes: 4 additions & 0 deletions include/linux/kprobes.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -350,6 +350,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
return this_cpu_ptr(&kprobe_ctlblk);
}

extern struct kprobe kprobe_busy;
void kprobe_busy_begin(void);
void kprobe_busy_end(void);

kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
int register_kprobe(struct kprobe *p);
void unregister_kprobe(struct kprobe *p);
Expand Down
61 changes: 48 additions & 13 deletions kernel/kprobes.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,11 @@


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];

Expand Down Expand Up @@ -326,7 +331,8 @@ 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;
}
Expand Down Expand Up @@ -586,11 +592,12 @@ static void kprobe_optimizer(struct work_struct *work)
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 */
Expand Down Expand Up @@ -668,8 +675,6 @@ 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 */
Expand Down Expand Up @@ -849,7 +854,7 @@ 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);
}
Expand All @@ -876,7 +881,7 @@ 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);
}
Expand Down Expand Up @@ -1236,6 +1241,26 @@ __releases(hlist_lock)
}
NOKPROBE_SYMBOL(kretprobe_table_unlock);

struct kprobe kprobe_busy = {
.addr = (void *) get_kprobe,
};

void kprobe_busy_begin(void)
{
struct kprobe_ctlblk *kcb;

preempt_disable();
__this_cpu_write(current_kprobe, &kprobe_busy);
kcb = get_kprobe_ctlblk();
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
}

void kprobe_busy_end(void)
{
__this_cpu_write(current_kprobe, NULL);
preempt_enable();
}

/*
* This function is called from finish_task_switch when task tk becomes dead,
* so that we can recycle any function-return probe instances associated
Expand All @@ -1253,6 +1278,8 @@ void kprobe_flush_task(struct task_struct *tk)
/* Early boot. kretprobe_table_locks not yet initialized. */
return;

kprobe_busy_begin();

INIT_HLIST_HEAD(&empty_rp);
hash = hash_ptr(tk, KPROBE_HASH_BITS);
head = &kretprobe_inst_table[hash];
Expand All @@ -1266,6 +1293,8 @@ void kprobe_flush_task(struct task_struct *tk)
hlist_del(&ri->hlist);
kfree(ri);
}

kprobe_busy_end();
}
NOKPROBE_SYMBOL(kprobe_flush_task);

Expand Down Expand Up @@ -1499,12 +1528,14 @@ 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;
Expand Down Expand Up @@ -1669,7 +1700,9 @@ static int 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.
Expand Down Expand Up @@ -1748,7 +1781,7 @@ 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;
}
Expand Down Expand Up @@ -2062,13 +2095,15 @@ 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);
Expand Down Expand Up @@ -2312,7 +2347,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
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))) {
Expand Down Expand Up @@ -2550,7 +2585,7 @@ 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) {
Expand Down Expand Up @@ -2593,7 +2628,7 @@ 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) {
Expand Down
12 changes: 10 additions & 2 deletions kernel/trace/ftrace.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2260,7 +2260,7 @@ ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,

if (hash_contains_ip(ip, op->func_hash))
return op;
}
}

return NULL;
}
Expand Down Expand Up @@ -3599,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v)
if (direct)
seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
}
}
}

seq_putc(m, '\n');

Expand Down Expand Up @@ -7151,6 +7151,10 @@ static int pid_open(struct inode *inode, struct file *file, int type)
case TRACE_NO_PIDS:
seq_ops = &ftrace_no_pid_sops;
break;
default:
trace_array_put(tr);
WARN_ON_ONCE(1);
return -EINVAL;
}

ret = seq_open(file, seq_ops);
Expand Down Expand Up @@ -7229,6 +7233,10 @@ pid_write(struct file *filp, const char __user *ubuf,
other_pids = rcu_dereference_protected(tr->function_pids,
lockdep_is_held(&ftrace_lock));
break;
default:
ret = -EINVAL;
WARN_ON_ONCE(1);
goto out;
}

ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
Expand Down
3 changes: 1 addition & 2 deletions kernel/trace/trace.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3570,7 +3570,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)

void tracing_iter_reset(struct trace_iterator *iter, int cpu)
{
struct ring_buffer_event *event;
struct ring_buffer_iter *buf_iter;
unsigned long entries = 0;
u64 ts;
Expand All @@ -3588,7 +3587,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
* that a reset never took place on a cpu. This is evident
* by the timestamp being before the start of the buffer.
*/
while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
while (ring_buffer_iter_peek(buf_iter, &ts)) {
if (ts >= iter->array_buffer->time_start)
break;
entries++;
Expand Down
3 changes: 3 additions & 0 deletions kernel/trace/trace.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,9 @@ enum trace_type {
#undef __field_desc
#define __field_desc(type, container, item)

#undef __field_packed
#define __field_packed(type, container, item)

#undef __array
#define __array(type, item, size) type item[size];

Expand Down
14 changes: 7 additions & 7 deletions kernel/trace/trace_entries.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -78,8 +78,8 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,

F_STRUCT(
__field_struct( struct ftrace_graph_ent, graph_ent )
__field_desc( unsigned long, graph_ent, func )
__field_desc( int, graph_ent, depth )
__field_packed( unsigned long, graph_ent, func )
__field_packed( int, graph_ent, depth )
),

F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
Expand All @@ -92,11 +92,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,

F_STRUCT(
__field_struct( struct ftrace_graph_ret, ret )
__field_desc( unsigned long, ret, func )
__field_desc( unsigned long, ret, overrun )
__field_desc( unsigned long long, ret, calltime)
__field_desc( unsigned long long, ret, rettime )
__field_desc( int, ret, depth )
__field_packed( unsigned long, ret, func )
__field_packed( unsigned long, ret, overrun )
__field_packed( unsigned long long, ret, calltime)
__field_packed( unsigned long long, ret, rettime )
__field_packed( int, ret, depth )
),

F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d",
Expand Down
Loading

0 comments on commit 8b6ddd1

Please sign in to comment.