summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-05-03 18:41:21 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-03 18:41:21 -0700
commit4c174688ee92805aa5df6e06e5b625a3286e415c (patch)
tree78e18b242b31a3a50eda41bfdd4705e07f13647a /kernel
parent9c35baf6cee9a5745d55de6f9995916dde642517 (diff)
parent73a757e63114dfd765f1c5d1ff7e994f123d0234 (diff)
downloadlinux-4c174688ee92805aa5df6e06e5b625a3286e415c.tar.bz2
Merge tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt: "New features for this release: - Pretty much a full rewrite of the processing of function plugins. i.e. echo do_IRQ:stacktrace > set_ftrace_filter - The rewrite was needed to add plugins to be unique to tracing instances. i.e. mkdir instance/foo; cd instances/foo; echo do_IRQ:stacktrace > set_ftrace_filter The old way was written very hacky. This removes a lot of those hacks. - New "function-fork" tracing option. When set, pids in the set_ftrace_pid will have their children added when the processes with their pids listed in the set_ftrace_pid file forks. - Exposure of "maxactive" for kretprobe in kprobe_events - Allow for builtin init functions to be traced by the function tracer (via the kernel command line). Module init function tracing will come in the next release. - Added more selftests, and have selftests also test in an instance" * tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (60 commits) ring-buffer: Return reader page back into existing ring buffer selftests: ftrace: Allow some event trigger tests to run in an instance selftests: ftrace: Have some basic tests run in a tracing instance too selftests: ftrace: Have event tests also run in an tracing instance selftests: ftrace: Make func_event_triggers and func_traceonoff_triggers tests do instances selftests: ftrace: Allow some tests to be run in a tracing instance tracing/ftrace: Allow for instances to trigger their own stacktrace probes tracing/ftrace: Allow for the traceonoff probe be unique to instances tracing/ftrace: Enable snapshot function trigger to work with instances tracing/ftrace: Allow instances to have their own function probes tracing/ftrace: Add a better way to pass data via the probe functions ftrace: Dynamically create the probe ftrace_ops for the trace_array tracing: Pass the trace_array into ftrace_probe_ops functions tracing: Have the trace_array hold the list of registered func probes ftrace: If the hash for a probe fails to update then free what was initialized ftrace: Have the function probes call their own function ftrace: Have each function probe use its own ftrace_ops ftrace: Have unregister_ftrace_function_probe_func() return a value ftrace: Add helper function ftrace_hash_move_and_update_ops() ftrace: Remove data field from ftrace_func_probe structure ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/rcu/tree.c62
-rw-r--r--kernel/trace/Kconfig3
-rw-r--r--kernel/trace/ftrace.c996
-rw-r--r--kernel/trace/ring_buffer.c40
-rw-r--r--kernel/trace/ring_buffer_benchmark.c2
-rw-r--r--kernel/trace/trace.c242
-rw-r--r--kernel/trace/trace.h77
-rw-r--r--kernel/trace/trace_benchmark.c14
-rw-r--r--kernel/trace/trace_events.c151
-rw-r--r--kernel/trace/trace_functions.c227
-rw-r--r--kernel/trace/trace_kprobe.c39
-rw-r--r--kernel/trace/trace_stack.c35
12 files changed, 1303 insertions, 585 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 50fee7689e71..a6dcf3bd244f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -57,6 +57,7 @@
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
+#include <linux/ftrace.h>
#include "tree.h"
#include "rcu.h"
@@ -284,6 +285,20 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
};
/*
+ * There's a few places, currently just in the tracing infrastructure,
+ * that uses rcu_irq_enter() to make sure RCU is watching. But there's
+ * a small location where that will not even work. In those cases
+ * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter()
+ * can be called.
+ */
+static DEFINE_PER_CPU(bool, disable_rcu_irq_enter);
+
+bool rcu_irq_enter_disabled(void)
+{
+ return this_cpu_read(disable_rcu_irq_enter);
+}
+
+/*
* Record entry into an extended quiescent state. This is only to be
* called when not already in an extended quiescent state.
*/
@@ -771,25 +786,24 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
}
/*
- * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
+ * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
*
- * If the new value of the ->dynticks_nesting counter now is zero,
- * we really have entered idle, and must do the appropriate accounting.
- * The caller must have disabled interrupts.
+ * Enter idle, doing appropriate accounting. The caller must have
+ * disabled interrupts.
*/
-static void rcu_eqs_enter_common(long long oldval, bool user)
+static void rcu_eqs_enter_common(bool user)
{
struct rcu_state *rsp;
struct rcu_data *rdp;
- RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
+ trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
- trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
+ trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
rcu_ftrace_dump(DUMP_ORIG);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
@@ -800,7 +814,10 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
do_nocb_deferred_wakeup(rdp);
}
rcu_prepare_for_idle();
- rcu_dynticks_eqs_enter();
+ __this_cpu_inc(disable_rcu_irq_enter);
+ rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
+ rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
+ __this_cpu_dec(disable_rcu_irq_enter);
rcu_dynticks_task_enter();
/*
@@ -821,19 +838,15 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
*/
static void rcu_eqs_enter(bool user)
{
- long long oldval;
struct rcu_dynticks *rdtp;
rdtp = this_cpu_ptr(&rcu_dynticks);
- oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- (oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
- rdtp->dynticks_nesting = 0;
- rcu_eqs_enter_common(oldval, user);
- } else {
+ (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
+ if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ rcu_eqs_enter_common(user);
+ else
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- }
}
/**
@@ -892,19 +905,18 @@ void rcu_user_enter(void)
*/
void rcu_irq_exit(void)
{
- long long oldval;
struct rcu_dynticks *rdtp;
RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
rdtp = this_cpu_ptr(&rcu_dynticks);
- oldval = rdtp->dynticks_nesting;
- rdtp->dynticks_nesting--;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- rdtp->dynticks_nesting < 0);
- if (rdtp->dynticks_nesting)
- trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
- else
- rcu_eqs_enter_common(oldval, true);
+ rdtp->dynticks_nesting < 1);
+ if (rdtp->dynticks_nesting <= 1) {
+ rcu_eqs_enter_common(true);
+ } else {
+ trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1);
+ rdtp->dynticks_nesting--;
+ }
rcu_sysidle_enter(1);
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9619b5768e4b..7e06f04e98fe 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -134,7 +134,8 @@ config FUNCTION_TRACER
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
- select GLOB
+ select GLOB
+ select TASKS_RCU if PREEMPT
help
Enable the kernel to trace every kernel function. This is done
by using a compiler feature to insert a small, 5-byte No-Operation
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index dd3e91d68dc7..00077a57b746 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -36,6 +36,7 @@
#include <trace/events/sched.h>
+#include <asm/sections.h>
#include <asm/setup.h>
#include "trace_output.h"
@@ -1095,22 +1096,20 @@ static bool update_all_ops;
# error Dynamic ftrace depends on MCOUNT_RECORD
#endif
-static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly;
-
-struct ftrace_func_probe {
- struct hlist_node node;
- struct ftrace_probe_ops *ops;
- unsigned long flags;
- unsigned long ip;
- void *data;
- struct list_head free_list;
-};
-
struct ftrace_func_entry {
struct hlist_node hlist;
unsigned long ip;
};
+struct ftrace_func_probe {
+ struct ftrace_probe_ops *probe_ops;
+ struct ftrace_ops ops;
+ struct trace_array *tr;
+ struct list_head list;
+ void *data;
+ int ref;
+};
+
/*
* We make these constant because no one should touch them,
* but they are used as the default "empty hash", to avoid allocating
@@ -1271,7 +1270,7 @@ static void
remove_hash_entry(struct ftrace_hash *hash,
struct ftrace_func_entry *entry)
{
- hlist_del(&entry->hlist);
+ hlist_del_rcu(&entry->hlist);
hash->count--;
}
@@ -2807,18 +2806,28 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
* callers are done before leaving this function.
* The same goes for freeing the per_cpu data of the per_cpu
* ops.
- *
- * Again, normal synchronize_sched() is not good enough.
- * We need to do a hard force of sched synchronization.
- * This is because we use preempt_disable() to do RCU, but
- * the function tracers can be called where RCU is not watching
- * (like before user_exit()). We can not rely on the RCU
- * infrastructure to do the synchronization, thus we must do it
- * ourselves.
*/
if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
+ /*
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
schedule_on_each_cpu(ftrace_sync);
+ /*
+ * When the kernel is preeptive, tasks can be preempted
+ * while on a ftrace trampoline. Just scheduling a task on
+ * a CPU is not good enough to flush them. Calling
+ * synchornize_rcu_tasks() will wait for those tasks to
+ * execute and either schedule voluntarily or enter user space.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT))
+ synchronize_rcu_tasks();
+
arch_ftrace_trampoline_free(ops);
if (ops->flags & FTRACE_OPS_FL_PER_CPU)
@@ -3055,34 +3064,63 @@ struct ftrace_iterator {
struct ftrace_page *pg;
struct dyn_ftrace *func;
struct ftrace_func_probe *probe;
+ struct ftrace_func_entry *probe_entry;
struct trace_parser parser;
struct ftrace_hash *hash;
struct ftrace_ops *ops;
- int hidx;
+ int pidx;
int idx;
unsigned flags;
};
static void *
-t_hash_next(struct seq_file *m, loff_t *pos)
+t_probe_next(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
+ struct trace_array *tr = iter->ops->private;
+ struct list_head *func_probes;
+ struct ftrace_hash *hash;
+ struct list_head *next;
struct hlist_node *hnd = NULL;
struct hlist_head *hhd;
+ int size;
(*pos)++;
iter->pos = *pos;
- if (iter->probe)
- hnd = &iter->probe->node;
- retry:
- if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
+ if (!tr)
return NULL;
- hhd = &ftrace_func_hash[iter->hidx];
+ func_probes = &tr->func_probes;
+ if (list_empty(func_probes))
+ return NULL;
+
+ if (!iter->probe) {
+ next = func_probes->next;
+ iter->probe = list_entry(next, struct ftrace_func_probe, list);
+ }
+
+ if (iter->probe_entry)
+ hnd = &iter->probe_entry->hlist;
+
+ hash = iter->probe->ops.func_hash->filter_hash;
+ size = 1 << hash->size_bits;
+
+ retry:
+ if (iter->pidx >= size) {
+ if (iter->probe->list.next == func_probes)
+ return NULL;
+ next = iter->probe->list.next;
+ iter->probe = list_entry(next, struct ftrace_func_probe, list);
+ hash = iter->probe->ops.func_hash->filter_hash;
+ size = 1 << hash->size_bits;
+ iter->pidx = 0;
+ }
+
+ hhd = &hash->buckets[iter->pidx];
if (hlist_empty(hhd)) {
- iter->hidx++;
+ iter->pidx++;
hnd = NULL;
goto retry;
}
@@ -3092,7 +3130,7 @@ t_hash_next(struct seq_file *m, loff_t *pos)
else {
hnd = hnd->next;
if (!hnd) {
- iter->hidx++;
+ iter->pidx++;
goto retry;
}
}
@@ -3100,26 +3138,28 @@ t_hash_next(struct seq_file *m, loff_t *pos)
if (WARN_ON_ONCE(!hnd))
return NULL;
- iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node);
+ iter->probe_entry = hlist_entry(hnd, struct ftrace_func_entry, hlist);
return iter;
}
-static void *t_hash_start(struct seq_file *m, loff_t *pos)
+static void *t_probe_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
loff_t l;
- if (!(iter->flags & FTRACE_ITER_DO_HASH))
+ if (!(iter->flags & FTRACE_ITER_DO_PROBES))
return NULL;
if (iter->func_pos > *pos)
return NULL;
- iter->hidx = 0;
+ iter->probe = NULL;
+ iter->probe_entry = NULL;
+ iter->pidx = 0;
for (l = 0; l <= (*pos - iter->func_pos); ) {
- p = t_hash_next(m, &l);
+ p = t_probe_next(m, &l);
if (!p)
break;
}
@@ -3127,50 +3167,42 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
return NULL;
/* Only set this if we have an item */
- iter->flags |= FTRACE_ITER_HASH;
+ iter->flags |= FTRACE_ITER_PROBE;
return iter;
}
static int
-t_hash_show(struct seq_file *m, struct ftrace_iterator *iter)
+t_probe_show(struct seq_file *m, struct ftrace_iterator *iter)
{
- struct ftrace_func_probe *rec;
+ struct ftrace_func_entry *probe_entry;
+ struct ftrace_probe_ops *probe_ops;
+ struct ftrace_func_probe *probe;
+
+ probe = iter->probe;
+ probe_entry = iter->probe_entry;
- rec = iter->probe;
- if (WARN_ON_ONCE(!rec))
+ if (WARN_ON_ONCE(!probe || !probe_entry))
return -EIO;
- if (rec->ops->print)
- return rec->ops->print(m, rec->ip, rec->ops, rec->data);
+ probe_ops = probe->probe_ops;
- seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func);
+ if (probe_ops->print)
+ return probe_ops->print(m, probe_entry->ip, probe_ops, probe->data);
- if (rec->data)
- seq_printf(m, ":%p", rec->data);
- seq_putc(m, '\n');
+ seq_printf(m, "%ps:%ps\n", (void *)probe_entry->ip,
+ (void *)probe_ops->func);
return 0;
}
static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_func_next(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
- struct ftrace_ops *ops = iter->ops;
struct dyn_ftrace *rec = NULL;
- if (unlikely(ftrace_disabled))
- return NULL;
-
- if (iter->flags & FTRACE_ITER_HASH)
- return t_hash_next(m, pos);
-
(*pos)++;
- iter->pos = iter->func_pos = *pos;
-
- if (iter->flags & FTRACE_ITER_PRINTALL)
- return t_hash_start(m, pos);
retry:
if (iter->idx >= iter->pg->index) {
@@ -3181,11 +3213,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
}
} else {
rec = &iter->pg->records[iter->idx++];
- if (((iter->flags & FTRACE_ITER_FILTER) &&
- !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) ||
-
- ((iter->flags & FTRACE_ITER_NOTRACE) &&
- !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) ||
+ if (((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) &&
+ !ftrace_lookup_ip(iter->hash, rec->ip)) ||
((iter->flags & FTRACE_ITER_ENABLED) &&
!(rec->flags & FTRACE_FL_ENABLED))) {
@@ -3196,24 +3225,51 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
}
if (!rec)
- return t_hash_start(m, pos);
+ return NULL;
+ iter->pos = iter->func_pos = *pos;
iter->func = rec;
return iter;
}
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ loff_t l = *pos; /* t_hash_start() must use original pos */
+ void *ret;
+
+ if (unlikely(ftrace_disabled))
+ return NULL;
+
+ if (iter->flags & FTRACE_ITER_PROBE)
+ return t_probe_next(m, pos);
+
+ if (iter->flags & FTRACE_ITER_PRINTALL) {
+ /* next must increment pos, and t_probe_start does not */
+ (*pos)++;
+ return t_probe_start(m, &l);
+ }
+
+ ret = t_func_next(m, pos);
+
+ if (!ret)
+ return t_probe_start(m, &l);
+
+ return ret;
+}
+
static void reset_iter_read(struct ftrace_iterator *iter)
{
iter->pos = 0;
iter->func_pos = 0;
- iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_HASH);
+ iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE);
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
- struct ftrace_ops *ops = iter->ops;
void *p = NULL;
loff_t l;
@@ -3233,20 +3289,19 @@ static void *t_start(struct seq_file *m, loff_t *pos)
* off, we can short cut and just print out that all
* functions are enabled.
*/
- if ((iter->flags & FTRACE_ITER_FILTER &&
- ftrace_hash_empty(ops->func_hash->filter_hash)) ||
- (iter->flags & FTRACE_ITER_NOTRACE &&
- ftrace_hash_empty(ops->func_hash->notrace_hash))) {
+ if ((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) &&
+ ftrace_hash_empty(iter->hash)) {
+ iter->func_pos = 1; /* Account for the message */
if (*pos > 0)
- return t_hash_start(m, pos);
+ return t_probe_start(m, pos);
iter->flags |= FTRACE_ITER_PRINTALL;
/* reset in case of seek/pread */
- iter->flags &= ~FTRACE_ITER_HASH;
+ iter->flags &= ~FTRACE_ITER_PROBE;
return iter;
}
- if (iter->flags & FTRACE_ITER_HASH)
- return t_hash_start(m, pos);
+ if (iter->flags & FTRACE_ITER_PROBE)
+ return t_probe_start(m, pos);
/*
* Unfortunately, we need to restart at ftrace_pages_start
@@ -3256,13 +3311,13 @@ static void *t_start(struct seq_file *m, loff_t *pos)
iter->pg = ftrace_pages_start;
iter->idx = 0;
for (l = 0; l <= *pos; ) {
- p = t_next(m, p, &l);
+ p = t_func_next(m, &l);
if (!p)
break;
}
if (!p)
- return t_hash_start(m, pos);
+ return t_probe_start(m, pos);
return iter;
}
@@ -3293,8 +3348,8 @@ static int t_show(struct seq_file *m, void *v)
struct ftrace_iterator *iter = m->private;
struct dyn_ftrace *rec;
- if (iter->flags & FTRACE_ITER_HASH)
- return t_hash_show(m, iter);
+ if (iter->flags & FTRACE_ITER_PROBE)
+ return t_probe_show(m, iter);
if (iter->flags & FTRACE_ITER_PRINTALL) {
if (iter->flags & FTRACE_ITER_NOTRACE)
@@ -3355,12 +3410,13 @@ ftrace_avail_open(struct inode *inode, struct file *file)
return -ENODEV;
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
- if (iter) {
- iter->pg = ftrace_pages_start;
- iter->ops = &global_ops;
- }
+ if (!iter)
+ return -ENOMEM;
- return iter ? 0 : -ENOMEM;
+ iter->pg = ftrace_pages_start;
+ iter->ops = &global_ops;
+
+ return 0;
}
static int
@@ -3369,13 +3425,14 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
struct ftrace_iterator *iter;
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
- if (iter) {
- iter->pg = ftrace_pages_start;
- iter->flags = FTRACE_ITER_ENABLED;
- iter->ops = &global_ops;
- }
+ if (!iter)
+ return -ENOMEM;
- return iter ? 0 : -ENOMEM;
+ iter->pg = ftrace_pages_start;
+ iter->flags = FTRACE_ITER_ENABLED;
+ iter->ops = &global_ops;
+
+ return 0;
}
/**
@@ -3440,7 +3497,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
ret = -ENOMEM;
goto out_unlock;
}
- }
+ } else
+ iter->hash = hash;
if (file->f_mode & FMODE_READ) {
iter->pg = ftrace_pages_start;
@@ -3470,7 +3528,7 @@ ftrace_filter_open(struct inode *inode, struct file *file)
struct ftrace_ops *ops = inode->i_private;
return ftrace_regex_open(ops,
- FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH,
+ FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES,
inode, file);
}
@@ -3654,6 +3712,56 @@ ftrace_match_records(struct ftrace_hash *hash, char *buff, int len)
return match_records(hash, buff, len, NULL);
}
+static void ftrace_ops_update_code(struct ftrace_ops *ops,
+ struct ftrace_ops_hash *old_hash)
+{
+ struct ftrace_ops *op;
+
+ if (!ftrace_enabled)
+ return;
+
+ if (ops->flags & FTRACE_OPS_FL_ENABLED) {
+ ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
+ return;
+ }
+
+ /*
+ * If this is the shared global_ops filter, then we need to
+ * check if there is another ops that shares it, is enabled.
+ * If so, we still need to run the modify code.
+ */
+ if (ops->func_hash != &global_ops.local_hash)
+ return;
+
+ do_for_each_ftrace_op(op, ftrace_ops_list) {
+ if (op->func_hash == &global_ops.local_hash &&
+ op->flags & FTRACE_OPS_FL_ENABLED) {
+ ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash);
+ /* Only need to do this once */
+ return;
+ }
+ } while_for_each_ftrace_op(op);
+}
+
+static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
+ struct ftrace_hash **orig_hash,
+ struct ftrace_hash *hash,
+ int enable)
+{
+ struct ftrace_ops_hash old_hash_ops;
+ struct ftrace_hash *old_hash;
+ int ret;
+
+ old_hash = *orig_hash;
+ old_hash_ops.filter_hash = ops->func_hash->filter_hash;
+ old_hash_ops.notrace_hash = ops->func_hash->notrace_hash;
+ ret = ftrace_hash_move(ops, enable, orig_hash, hash);
+ if (!ret) {
+ ftrace_ops_update_code(ops, &old_hash_ops);
+ free_ftrace_hash_rcu(old_hash);
+ }
+ return ret;
+}
/*
* We register the module command as a template to show others how
@@ -3661,7 +3769,7 @@ ftrace_match_records(struct ftrace_hash *hash, char *buff, int len)
*/
static int
-ftrace_mod_callback(struct ftrace_hash *hash,
+ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *func, char *cmd, char *module, int enable)
{
int ret;
@@ -3695,16 +3803,11 @@ core_initcall(ftrace_mod_cmd_init);
static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
- struct ftrace_func_probe *entry;
- struct hlist_head *hhd;
- unsigned long key;
+ struct ftrace_probe_ops *probe_ops;
+ struct ftrace_func_probe *probe;
- key = hash_long(ip, FTRACE_HASH_BITS);
-
- hhd = &ftrace_func_hash[key];
-
- if (hlist_empty(hhd))
- return;
+ probe = container_of(op, struct ftrace_func_probe, ops);
+ probe_ops = probe->probe_ops;
/*
* Disable preemption for these calls to prevent a RCU grace
@@ -3712,209 +3815,336 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
* on the hash. rcu_read_lock is too dangerous here.
*/
preempt_disable_notrace();
- hlist_for_each_entry_rcu_notrace(entry, hhd, node) {
- if (entry->ip == ip)
- entry->ops->func(ip, parent_ip, &entry->data);
- }
+ probe_ops->func(ip, parent_ip, probe->tr, probe_ops, probe->data);
preempt_enable_notrace();
}
-static struct ftrace_ops trace_probe_ops __read_mostly =
-{
- .func = function_trace_probe_call,
- .flags = FTRACE_OPS_FL_INITIALIZED,
- INIT_OPS_HASH(trace_probe_ops)
+struct ftrace_func_map {
+ struct ftrace_func_entry entry;
+ void *data;
};
-static int ftrace_probe_registered;
+struct ftrace_func_mapper {
+ struct ftrace_hash hash;
+};
-static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
+/**
+ * allocate_ftrace_func_mapper - allocate a new ftrace_func_mapper
+ *
+ * Returns a ftrace_func_mapper descriptor that can be used to map ips to data.
+ */
+struct ftrace_func_mapper *allocate_ftrace_func_mapper(void)
{
- int ret;
- int i;
+ struct ftrace_hash *hash;
- if (ftrace_probe_registered) {
- /* still need to update the function call sites */
- if (ftrace_enabled)
- ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
- old_hash);
- return;
- }
+ /*
+ * The mapper is simply a ftrace_hash, but since the entries
+ * in the hash are not ftrace_func_entry type, we define it
+ * as a separate structure.
+ */
+ hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+ return (struct ftrace_func_mapper *)hash;
+}
- for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
- struct hlist_head *hhd = &ftrace_func_hash[i];
- if (hhd->first)
- break;
- }
- /* Nothing registered? */
- if (i == FTRACE_FUNC_HASHSIZE)
- return;
+/**
+ * ftrace_func_mapper_find_ip - Find some data mapped to an ip
+ * @mapper: The mapper that has the ip maps
+ * @ip: the instruction pointer to find the data for
+ *
+ * Returns the data mapped to @ip if found otherwise NULL. The return
+ * is actually the address of the mapper data pointer. The address is
+ * returned for use cases where the data is no bigger than a long, and
+ * the user can use the data pointer as its data instead of having to
+ * allocate more memory for the reference.
+ */
+void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
- ret = ftrace_startup(&trace_probe_ops, 0);
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (!entry)
+ return NULL;
- ftrace_probe_registered = 1;
+ map = (struct ftrace_func_map *)entry;
+ return &map->data;
}
-static bool __disable_ftrace_function_probe(void)
+/**
+ * ftrace_func_mapper_add_ip - Map some data to an ip
+ * @mapper: The mapper that has the ip maps
+ * @ip: The instruction pointer address to map @data to
+ * @data: The data to map to @ip
+ *
+ * Returns 0 on succes otherwise an error.
+ */
+int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip, void *data)
{
- int i;
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
- if (!ftrace_probe_registered)
- return false;
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (entry)
+ return -EBUSY;
- for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
- struct hlist_head *hhd = &ftrace_func_hash[i];
- if (hhd->first)
- return false;
- }
+ map = kmalloc(sizeof(*map), GFP_KERNEL);
+ if (!map)
+ return -ENOMEM;
- /* no more funcs left */
- ftrace_shutdown(&trace_probe_ops, 0);
+ map->entry.ip = ip;
+ map->data = data;
- ftrace_probe_registered = 0;
- return true;
-}
+ __add_hash_entry(&mapper->hash, &map->entry);
+ return 0;
+}
-static void ftrace_free_entry(struct ftrace_func_probe *entry)
+/**
+ * ftrace_func_mapper_remove_ip - Remove an ip from the mapping
+ * @mapper: The mapper that has the ip maps
+ * @ip: The instruction pointer address to remove the data from
+ *
+ * Returns the data if it is found, otherwise NULL.
+ * Note, if the data pointer is used as the data itself, (see
+ * ftrace_func_mapper_find_ip(), then the return value may be meaningless,
+ * if the data pointer was set to zero.
+ */
+void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip)
{
- if (entry->ops->free)
- entry->ops->free(entry->ops, entry->ip, &entry->data);
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+ void *data;
+
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (!entry)
+ return NULL;
+
+ map = (struct ftrace_func_map *)entry;
+ data = map->data;
+
+ remove_hash_entry(&mapper->hash, entry);
kfree(entry);
+
+ return data;
+}
+
+/**
+ * free_ftrace_func_mapper - free a mapping of ips and data
+ * @mapper: The mapper that has the ip maps
+ * @free_func: A function to be called on each data item.
+ *
+ * This is used to free the function mapper. The @free_func is optional
+ * and can be used if the data needs to be freed as well.
+ */
+void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
+ ftrace_mapper_func free_func)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+ struct hlist_head *hhd;
+ int size = 1 << mapper->hash.size_bits;
+ int i;
+
+ if (free_func && mapper->hash.count) {
+ for (i = 0; i < size; i++) {
+ hhd = &mapper->hash.buckets[i];
+ hlist_for_each_entry(entry, hhd, hlist) {
+ map = (struct ftrace_func_map *)entry;
+ free_func(map);
+ }
+ }
+ }
+ free_ftrace_hash(&mapper->hash);
+}
+
+static void release_probe(struct ftrace_func_probe *probe)
+{
+ struct ftrace_probe_ops *probe_ops;
+
+ mutex_lock(&ftrace_lock);
+
+ WARN_ON(probe->ref <= 0);
+
+ /* Subtract the ref that was used to protect this instance */
+ probe->ref--;
+
+ if (!probe->ref) {
+ probe_ops = probe->probe_ops;
+ /*
+ * Sending zero as ip tells probe_ops to free
+ * the probe->data itself
+ */
+ if (probe_ops->free)
+ probe_ops->free(probe_ops, probe->tr, 0, probe->data);
+ list_del(&probe->list);
+ kfree(probe);
+ }
+ mutex_unlock(&ftrace_lock);
+}
+
+static void acquire_probe_locked(struct ftrace_func_probe *probe)
+{
+ /*
+ * Add one ref to keep it from being freed when releasing the
+ * ftrace_lock mutex.
+ */
+ probe->ref++;
}
int
-register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
- void *data)
+register_ftrace_function_probe(char *glob, struct trace_array *tr,
+ struct ftrace_probe_ops *probe_ops,
+ void *data)
{
- struct ftrace_ops_hash old_hash_ops;
- struct ftrace_func_probe *entry;
- struct ftrace_glob func_g;
- struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
- struct ftrace_hash *old_hash = *orig_hash;
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_probe *probe;
+ struct ftrace_hash **orig_hash;
+ struct ftrace_hash *old_hash;
struct ftrace_hash *hash;
- struct ftrace_page *pg;
- struct dyn_ftrace *rec;
- int not;
- unsigned long key;
int count = 0;
+ int size;
int ret;
+ int i;
- func_g.type = filter_parse_regex(glob, strlen(glob),
- &func_g.search, &not);
- func_g.len = strlen(func_g.search);
-
- /* we do not support '!' for function probes */
- if (WARN_ON(not))
+ if (WARN_ON(!tr))
return -EINVAL;
- mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ /* We do not support '!' for function probes */
+ if (WARN_ON(glob[0] == '!'))
+ return -EINVAL;
- old_hash_ops.filter_hash = old_hash;
- /* Probes only have filters */
- old_hash_ops.notrace_hash = NULL;
- hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
- if (!hash) {
- count = -ENOMEM;
- goto out;
+ mutex_lock(&ftrace_lock);
+ /* Check if the probe_ops is already registered */
+ list_for_each_entry(probe, &tr->func_probes, list) {
+ if (probe->probe_ops == probe_ops)
+ break;
}
-
- if (unlikely(ftrace_disabled)) {
- count = -ENODEV;
- goto out;
+ if (&probe->list == &tr->func_probes) {
+ probe = kzalloc(sizeof(*probe), GFP_KERNEL);
+ if (!probe) {
+ mutex_unlock(&ftrace_lock);
+ return -ENOMEM;
+ }
+ probe->probe_ops = probe_ops;
+ probe->ops.func = function_trace_probe_call;
+ probe->tr = tr;
+ ftrace_ops_init(&probe->ops);
+ list_add(&probe->list, &tr->func_probes);
}
- mutex_lock(&ftrace_lock);
+ acquire_probe_locked(probe);
- do_for_each_ftrace_rec(pg, rec) {
+ mutex_unlock(&ftrace_lock);
- if (rec->flags & FTRACE_FL_DISABLED)
- continue;
+ mutex_lock(&probe->ops.func_hash->regex_lock);
- if (!ftrace_match_record(rec, &func_g, NULL, 0))
- continue;
+ orig_hash = &probe->ops.func_hash->filter_hash;
+ old_hash = *orig_hash;
+ hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry) {
- /* If we did not process any, then return error */
- if (!count)
- count = -ENOMEM;
- goto out_unlock;
- }
+ ret = ftrace_match_records(hash, glob, strlen(glob));
- count++;
+ /* Nothing found? */
+ if (!ret)
+ ret = -EINVAL;
- entry->data = data;
+ if (ret < 0)
+ goto out;
- /*
- * The caller might want to do something special
- * for each function we find. We call the callback
- * to give the caller an opportunity to do so.
- */
- if (ops->init) {
- if (ops->init(ops, rec->ip, &entry->data) < 0) {
- /* caller does not like this func */
- kfree(entry);
+ size = 1 << hash->size_bits;
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+ if (ftrace_lookup_ip(old_hash, entry->ip))
continue;
+ /*
+ * The caller might want to do something special
+ * for each function we find. We call the callback
+ * to give the caller an opportunity to do so.
+ */
+ if (probe_ops->init) {
+ ret = probe_ops->init(probe_ops, tr,
+ entry->ip, data,
+ &probe->data);
+ if (ret < 0) {
+ if (probe_ops->free && count)
+ probe_ops->free(probe_ops, tr,
+ 0, probe->data);
+ probe->data = NULL;
+ goto out;
+ }
}
+ count++;
}
+ }
- ret = enter_record(hash, rec, 0);
- if (ret < 0) {
- kfree(entry);
- count = ret;
- goto out_unlock;
- }
-
- entry->ops = ops;
- entry->ip = rec->ip;
-
- key = hash_long(entry->ip, FTRACE_HASH_BITS);
- hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
+ mutex_lock(&ftrace_lock);
- } while_for_each_ftrace_rec();
+ if (!count) {
+ /* Nothing was added? */
+ ret = -EINVAL;
+ goto out_unlock;
+ }
- ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+ ret = ftrace_hash_move_and_update_ops(&probe->ops, orig_hash,
+ hash, 1);
+ if (ret < 0)
+ goto err_unlock;
- __enable_ftrace_function_probe(&old_hash_ops);
+ /* One ref for each new function traced */
+ probe->ref += count;
- if (!ret)
- free_ftrace_hash_rcu(old_hash);
- else
- count = ret;
+ if (!(probe->ops.flags & FTRACE_OPS_FL_ENABLED))
+ ret = ftrace_startup(&probe->ops, 0);
out_unlock:
mutex_unlock(&ftrace_lock);
+
+ if (!ret)
+ ret = count;
out:
- mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
+ mutex_unlock(&probe->ops.func_hash->regex_lock);
free_ftrace_hash(hash);
- return count;
-}
+ release_probe(probe);
-enum {
- PROBE_TEST_FUNC = 1,
- PROBE_TEST_DATA = 2
-};
+ return ret;
-static void
-__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
- void *data, int flags)
+ err_unlock:
+ if (!probe_ops->free || !count)
+ goto out_unlock;
+
+ /* Failed to do the move, need to call the free functions */
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+ if (ftrace_lookup_ip(old_hash, entry->ip))
+ continue;
+ probe_ops->free(probe_ops, tr, entry->ip, probe->data);
+ }
+ }
+ goto out_unlock;
+}
+
+int
+unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
+ struct ftrace_probe_ops *probe_ops)
{
struct ftrace_ops_hash old_hash_ops;
- struct ftrace_func_entry *rec_entry;
- struct ftrace_func_probe *entry;
- struct ftrace_func_probe *p;
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_probe *probe;
struct ftrace_glob func_g;
- struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
- struct ftrace_hash *old_hash = *orig_hash;
- struct list_head free_list;
- struct ftrace_hash *hash;
+ struct ftrace_hash **orig_hash;
+ struct ftrace_hash *old_hash;
+ struct ftrace_hash *hash = NULL;
struct hlist_node *tmp;
+ struct hlist_head hhd;
char str[KSYM_SYMBOL_LEN];
- int i, ret;
- bool disabled;
+ int count = 0;
+ int i, ret = -ENODEV;
+ int size;
if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
func_g.search = NULL;
@@ -3928,95 +4158,104 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
/* we do not support '!' for function probes */
if (WARN_ON(not))
- return;
+ return -EINVAL;
+ }
+
+ mutex_lock(&ftrace_lock);
+ /* Check if the probe_ops is already registered */
+ list_for_each_entry(probe, &tr->func_probes, list) {
+ if (probe->probe_ops == probe_ops)
+ break;
}
+ if (&probe->list == &tr->func_probes)
+ goto err_unlock_ftrace;
+
+ ret = -EINVAL;
+ if (!(probe->ops.flags & FTRACE_OPS_FL_INITIALIZED))
+ goto err_unlock_ftrace;
+
+ acquire_probe_locked(probe);
+
+ mutex_unlock(&ftrace_lock);
- mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ mutex_lock(&probe->ops.func_hash->regex_lock);
+
+ orig_hash = &probe->ops.func_hash->filter_hash;
+ old_hash = *orig_hash;
+
+ if (ftrace_hash_empty(old_hash))
+ goto out_unlock;
old_hash_ops.filter_hash = old_hash;
/* Probes only have filters */
old_hash_ops.notrace_hash = NULL;
- hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+ ret = -ENOMEM;
+ hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
if (!hash)
- /* Hmm, should report this somehow */
goto out_unlock;
- INIT_LIST_HEAD(&free_list);
-
- for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
- struct hlist_head *hhd = &ftrace_func_hash[i];
+ INIT_HLIST_HEAD(&hhd);
- hlist_for_each_entry_safe(entry, tmp, hhd, node) {
-
- /* break up if statements for readability */
- if ((flags & PROBE_TEST_FUNC) && entry->ops != ops)
- continue;
-
- if ((flags & PROBE_TEST_DATA) && entry->data != data)
- continue;
+ size = 1 << hash->size_bits;
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &hash->buckets[i], hlist) {
- /* do this last, since it is the most expensive */
if (func_g.search) {
kallsyms_lookup(entry->ip, NULL, NULL,
NULL, str);
if (!ftrace_match(str, &func_g))
continue;
}
-
- rec_entry = ftrace_lookup_ip(hash, entry->ip);
- /* It is possible more than one entry had this ip */
- if (rec_entry)
- free_hash_entry(hash, rec_entry);
-
- hlist_del_rcu(&entry->node);
- list_add(&entry->free_list, &free_list);
+ count++;
+ remove_hash_entry(hash, entry);
+ hlist_add_head(&entry->hlist, &hhd);
}
}
+
+ /* Nothing found? */
+ if (!count) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
mutex_lock(&ftrace_lock);
- disabled = __disable_ftrace_function_probe();
- /*
- * Remove after the disable is called. Otherwise, if the last
- * probe is removed, a null hash means *all enabled*.
- */
- ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+ WARN_ON(probe->ref < count);
+
+ probe->ref -= count;
+
+ if (ftrace_hash_empty(hash))
+ ftrace_shutdown(&probe->ops, 0);
+
+ ret = ftrace_hash_move_and_update_ops(&probe->ops, orig_hash,
+ hash, 1);
/* still need to update the function call sites */
- if (ftrace_enabled && !disabled)
- ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+ if (ftrace_enabled && !ftrace_hash_empty(hash))
+ ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS,
&old_hash_ops);
synchronize_sched();
- if (!ret)
- free_ftrace_hash_rcu(old_hash);
- list_for_each_entry_safe(entry, p, &free_list, free_list) {
- list_del(&entry->free_list);
- ftrace_free_entry(entry);
+ hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) {
+ hlist_del(&entry->hlist);
+ if (probe_ops->free)
+ probe_ops->free(probe_ops, tr, entry->ip, probe->data);
+ kfree(entry);
}
mutex_unlock(&ftrace_lock);
out_unlock:
- mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
+ mutex_unlock(&probe->ops.func_hash->regex_lock);
free_ftrace_hash(hash);
-}
-void
-unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
- void *data)
-{
- __unregister_ftrace_function_probe(glob, ops, data,
- PROBE_TEST_FUNC | PROBE_TEST_DATA);
-}
+ release_probe(probe);
-void
-unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops)
-{
- __unregister_ftrace_function_probe(glob, ops, NULL, PROBE_TEST_FUNC);
-}
+ return ret;
-void unregister_ftrace_function_probe_all(char *glob)
-{
- __unregister_ftrace_function_probe(glob, NULL, NULL, 0);
+ err_unlock_ftrace:
+ mutex_unlock(&ftrace_lock);
+ return ret;
}
static LIST_HEAD(ftrace_commands);
@@ -4068,9 +4307,11 @@ __init int unregister_ftrace_command(struct ftrace_func_command *cmd)
return ret;
}
-static int ftrace_process_regex(struct ftrace_hash *hash,
+static int ftrace_process_regex(struct ftrace_iterator *iter,
char *buff, int len, int enable)
{
+ struct ftrace_hash *hash = iter->hash;
+ struct trace_array *tr = iter->ops->private;
char *func, *command, *next = buff;
struct ftrace_func_command *p;
int ret = -EINVAL;
@@ -4090,10 +4331,13 @@ static int ftrace_process_regex(struct ftrace_hash *hash,
command = strsep(&next, ":");
+ if (WARN_ON_ONCE(!tr))
+ return -EINVAL;
+
mutex_lock(&ftrace_cmd_mutex);
list_for_each_entry(p, &ftrace_commands, list) {
if (strcmp(p->name, command) == 0) {
- ret = p->func(hash, func, command, next, enable);
+ ret = p->func(tr, hash, func, command, next, enable);
goto out_unlock;
}
}
@@ -4130,7 +4374,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
if (read >= 0 && trace_parser_loaded(parser) &&
!trace_parser_cont(parser)) {
- ret = ftrace_process_regex(iter->hash, parser->buffer,
+ ret = ftrace_process_regex(iter, parser->buffer,
parser->idx, enable);
trace_parser_clear(parser);
if (ret < 0)
@@ -4175,44 +4419,11 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
return add_hash_entry(hash, ip);
}
-static void ftrace_ops_update_code(struct ftrace_ops *ops,
- struct ftrace_ops_hash *old_hash)
-{
- struct ftrace_ops *op;
-
- if (!ftrace_enabled)
- return;
-
- if (ops->flags & FTRACE_OPS_FL_ENABLED) {
- ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
- return;
- }
-
- /*
- * If this is the shared global_ops filter, then we need to
- * check if there is another ops that shares it, is enabled.
- * If so, we still need to run the modify code.
- */
- if (ops->func_hash != &global_ops.local_hash)
- return;
-
- do_for_each_ftrace_op(op, ftrace_ops_list) {
- if (op->func_hash == &global_ops.local_hash &&
- op->flags & FTRACE_OPS_FL_ENABLED) {
- ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash);
- /* Only need to do this once */
- return;
- }
- } while_for_each_ftrace_op(op);
-}
-
static int
ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
unsigned long ip, int remove, int reset, int enable)
{
struct ftrace_hash **orig_hash;
- struct ftrace_ops_hash old_hash_ops;
- struct ftrace_hash *old_hash;
struct ftrace_hash *hash;
int ret;
@@ -4247,14 +4458,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
}
mutex_lock(&ftrace_lock);
- old_hash = *orig_hash;
- old_hash_ops.filter_hash = ops->func_hash->filter_hash;
- old_hash_ops.notrace_hash = ops->func_hash->notrace_hash;
- ret = ftrace_hash_move(ops, enable, orig_hash, hash);
- if (!ret) {
- ftrace_ops_update_code(ops, &old_hash_ops);
- free_ftrace_hash_rcu(old_hash);
- }
+ ret = ftrace_hash_move_and_update_ops(ops, orig_hash, hash, enable);
mutex_unlock(&ftrace_lock);
out_regex_unlock:
@@ -4493,10 +4697,8 @@ static void __init set_ftrace_early_filters(void)
int ftrace_regex_release(struct inode *inode, struct file *file)
{
struct seq_file *m = (struct seq_file *)file->private_data;
- struct ftrace_ops_hash old_hash_ops;
struct ftrace_iterator *iter;
struct ftrace_hash **orig_hash;
- struct ftrace_hash *old_hash;
struct trace_parser *parser;
int filter_hash;
int ret;
@@ -4526,16 +4728,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
orig_hash = &iter->ops->func_hash->notrace_hash;
mutex_lock(&ftrace_lock);
- old_hash = *orig_hash;
- old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash;
- old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash;
- ret = ftrace_hash_move(iter->ops, filter_hash,
- orig_hash, iter->hash);
- if (!ret) {
- ftrace_ops_update_code(iter->ops, &old_hash_ops);
- free_ftrace_hash_rcu(old_hash);
- }
+ ret = ftrace_hash_move_and_update_ops(iter->ops, orig_hash,
+ iter->hash, filter_hash);
mutex_unlock(&ftrace_lock);
+ } else {
+ /* For read only, the hash is the ops hash */
+ iter->hash = NULL;
}
mutex_unlock(&iter->ops->func_hash->regex_lock);
@@ -5274,6 +5472,50 @@ void ftrace_module_init(struct module *mod)
}
#endif /* CONFIG_MODULES */
+void __init ftrace_free_init_mem(void)
+{
+ unsigned long start = (unsigned long)(&__init_begin);
+ unsigned long end = (unsigned long)(&__init_end);
+ struct ftrace_page **last_pg = &ftrace_pages_start;
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ struct dyn_ftrace key;
+ int order;
+
+ key.ip = start;
+ key.flags = end; /* overload flags, as it is unsigned long */
+
+ mutex_lock(&ftrace_lock);
+
+ for (pg = ftrace_pages_start; pg; last_pg = &pg->next, pg = *last_pg) {
+ if (end < pg->records[0].ip ||
+ start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
+ continue;
+ again:
+ rec = bsearch(&key, pg->records, pg->index,
+ sizeof(struct dyn_ftrace),
+ ftrace_cmp_recs);
+ if (!rec)
+ continue;
+ pg->index--;
+ if (!pg->index) {
+ *last_pg = pg->next;
+ order = get_count_order(pg->size / ENTRIES_PER_PAGE);
+ free_pages((unsigned long)pg->records, order);
+ kfree(pg);
+ pg = container_of(last_pg, struct ftrace_page, next);
+ if (!(*last_pg))
+ ftrace_pages = pg;
+ continue;
+ }
+ memmove(rec, rec + 1,
+ (pg->index - (rec - pg->records)) * sizeof(*rec));
+ /* More than one function may be in this block */
+ goto again;
+ }
+ mutex_unlock(&ftrace_lock);
+}
+
void __init ftrace_init(void)
{
extern unsigned long __start_mcount_loc[];
@@ -5316,25 +5558,13 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
static void ftrace_update_trampoline(struct ftrace_ops *ops)
{
-
-/*
- * Currently there's no safe way to free a trampoline when the kernel
- * is configured with PREEMPT. That is because a task could be preempted
- * when it jumped to the trampoline, it may be preempted for a long time
- * depending on the system load, and currently there's no way to know
- * when it will be off the trampoline. If the trampoline is freed
- * too early, when the task runs again, it will be executing on freed
- * memory and crash.
- */
-#ifdef CONFIG_PREEMPT
- /* Currently, only non dynamic ops can have a trampoline */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- return;
-#endif
-
arch_ftrace_update_trampoline(ops);
}
+void ftrace_init_trace_array(struct trace_array *tr)
+{
+ INIT_LIST_HEAD(&tr->func_probes);
+}
#else
static struct ftrace_ops global_ops = {
@@ -5389,6 +5619,7 @@ __init void ftrace_init_global_array_ops(struct trace_array *tr)
{
tr->ops = &global_ops;
tr->ops->private = tr;
+ ftrace_init_trace_array(tr);
}
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func)
@@ -5543,6 +5774,43 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
trace_ignore_this_task(pid_list, next));
}
+static void
+ftrace_pid_follow_sched_process_fork(void *data,
+ struct task_struct *self,
+ struct task_struct *task)
+{
+ struct trace_pid_list *pid_list;
+ struct trace_array *tr = data;
+
+ pid_list = rcu_dereference_sched(tr->function_pids);
+ trace_filter_add_remove_task(pid_list, self, task);
+}
+
+static void
+ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
+{
+ struct trace_pid_list *pid_list;
+ struct trace_array *tr = data;
+
+ pid_list = rcu_dereference_sched(tr->function_pids);
+ trace_filter_add_remove_task(pid_list, NULL, task);
+}
+
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
+{
+ if (enable) {
+ register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+ tr);
+ register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ tr);
+ } else {
+ unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+ tr);
+ unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ tr);
+ }
+}
+
static void clear_ftrace_pids(struct trace_array *tr)
{
struct trace_pid_list *pid_list;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ca47a4fa2986..4ae268e687fe 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -438,6 +438,7 @@ struct ring_buffer_per_cpu {
raw_spinlock_t reader_lock; /* serialize readers */
arch_spinlock_t lock;
struct lock_class_key lock_key;
+ struct buffer_data_page *free_page;
unsigned long nr_pages;
unsigned int current_context;
struct list_head *pages;
@@ -4389,9 +4390,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
*/
void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
{
- struct buffer_data_page *bpage;
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct buffer_data_page *bpage = NULL;
+ unsigned long flags;
struct page *page;
+ local_irq_save(flags);
+ arch_spin_lock(&cpu_buffer->lock);
+
+ if (cpu_buffer->free_page) {
+ bpage = cpu_buffer->free_page;
+ cpu_buffer->free_page = NULL;
+ }
+
+ arch_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ if (bpage)
+ goto out;
+
page = alloc_pages_node(cpu_to_node(cpu),
GFP_KERNEL | __GFP_NORETRY, 0);
if (!page)
@@ -4399,6 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
bpage = page_address(page);
+ out:
rb_init_page(bpage);
return bpage;
@@ -4408,13 +4426,29 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
/**
* ring_buffer_free_read_page - free an allocated read page
* @buffer: the buffer the page was allocate for
+ * @cpu: the cpu buffer the page came from
* @data: the page to free
*
* Free a page allocated from ring_buffer_alloc_read_page.
*/
-void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
+void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
{
- free_page((unsigned long)data);
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct buffer_data_page *bpage = data;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ arch_spin_lock(&cpu_buffer->lock);
+
+ if (!cpu_buffer->free_page) {
+ cpu_buffer->free_page = bpage;
+ bpage = NULL;
+ }
+
+ arch_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ free_page((unsigned long)bpage);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index c190a4d5013c..9fbcaf567886 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -171,7 +171,7 @@ static enum event_status read_page(int cpu)
}
}
}
- ring_buffer_free_read_page(buffer, bpage);
+ ring_buffer_free_read_page(buffer, cpu, bpage);
if (ret < 0)
return EVENT_DROPPED;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0029fe62b245..80eda7d254ed 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -257,7 +257,7 @@ unsigned long long ns2usecs(u64 nsec)
/* trace_flags that are default zero for instances */
#define ZEROED_TRACE_FLAGS \
- TRACE_ITER_EVENT_FORK
+ (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK)
/*
* The global_trace is the descriptor that holds the top-level tracing
@@ -757,7 +757,7 @@ __trace_buffer_lock_reserve(struct ring_buffer *buffer,
return event;
}
-static void tracer_tracing_on(struct trace_array *tr)
+void tracer_tracing_on(struct trace_array *tr)
{
if (tr->trace_buffer.buffer)
ring_buffer_record_on(tr->trace_buffer.buffer);
@@ -894,23 +894,8 @@ int __trace_bputs(unsigned long ip, const char *str)
EXPORT_SYMBOL_GPL(__trace_bputs);
#ifdef CONFIG_TRACER_SNAPSHOT
-/**
- * trace_snapshot - take a snapshot of the current buffer.
- *
- * This causes a swap between the snapshot buffer and the current live
- * tracing buffer. You can use this to take snapshots of the live
- * trace when some condition is triggered, but continue to trace.
- *
- * Note, make sure to allocate the snapshot with either
- * a tracing_snapshot_alloc(), or by doing it manually
- * with: echo 1 > /sys/kernel/debug/tracing/snapshot
- *
- * If the snapshot buffer is not allocated, it will stop tracing.
- * Basically making a permanent snapshot.
- */
-void tracing_snapshot(void)
+static void tracing_snapshot_instance(struct trace_array *tr)
{
- struct trace_array *tr = &global_trace;
struct tracer *tracer = tr->current_trace;
unsigned long flags;
@@ -938,6 +923,27 @@ void tracing_snapshot(void)
update_max_tr(tr, current, smp_processor_id());
local_irq_restore(flags);
}
+
+/**
+ * trace_snapshot - take a snapshot of the current buffer.
+ *
+ * This causes a swap between the snapshot buffer and the current live
+ * tracing buffer. You can use this to take snapshots of the live
+ * trace when some condition is triggered, but continue to trace.
+ *
+ * Note, make sure to allocate the snapshot with either
+ * a tracing_snapshot_alloc(), or by doing it manually
+ * with: echo 1 > /sys/kernel/debug/tracing/snapshot
+ *
+ * If the snapshot buffer is not allocated, it will stop tracing.
+ * Basically making a permanent snapshot.
+ */
+void tracing_snapshot(void)
+{
+ struct trace_array *tr = &global_trace;
+
+ tracing_snapshot_instance(tr);
+}
EXPORT_SYMBOL_GPL(tracing_snapshot);
static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
@@ -1039,7 +1045,7 @@ void tracing_snapshot_alloc(void)
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
#endif /* CONFIG_TRACER_SNAPSHOT */
-static void tracer_tracing_off(struct trace_array *tr)
+void tracer_tracing_off(struct trace_array *tr)
{
if (tr->trace_buffer.buffer)
ring_buffer_record_off(tr->trace_buffer.buffer);
@@ -1424,6 +1430,28 @@ static int wait_on_pipe(struct trace_iterator *iter, bool full)
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
+static bool selftests_can_run;
+
+struct trace_selftests {
+ struct list_head list;
+ struct tracer *type;
+};
+
+static LIST_HEAD(postponed_selftests);
+
+static int save_selftest(struct tracer *type)
+{
+ struct trace_selftests *selftest;
+
+ selftest = kmalloc(sizeof(*selftest), GFP_KERNEL);
+ if (!selftest)
+ return -ENOMEM;
+
+ selftest->type = type;
+ list_add(&selftest->list, &postponed_selftests);
+ return 0;
+}
+
static int run_tracer_selftest(struct tracer *type)
{
struct trace_array *tr = &global_trace;
@@ -1434,6 +1462,14 @@ static int run_tracer_selftest(struct tracer *type)
return 0;
/*
+ * If a tracer registers early in boot up (before scheduling is
+ * initialized and such), then do not run its selftests yet.
+ * Instead, run it a little later in the boot process.
+ */
+ if (!selftests_can_run)
+ return save_selftest(type);
+
+ /*
* Run a selftest on this tracer.
* Here we reset the trace buffer, and set the current
* tracer to be this tracer. The tracer can then run some
@@ -1482,6 +1518,47 @@ static int run_tracer_selftest(struct tracer *type)
printk(KERN_CONT "PASSED\n");
return 0;
}
+
+static __init int init_trace_selftests(void)
+{
+ struct trace_selftests *p, *n;
+ struct tracer *t, **last;
+ int ret;
+
+ selftests_can_run = true;
+
+ mutex_lock(&trace_types_lock);
+
+ if (list_empty(&postponed_selftests))
+ goto out;
+
+ pr_info("Running postponed tracer tests:\n");
+
+ list_for_each_entry_safe(p, n, &postponed_selftests, list) {
+ ret = run_tracer_selftest(p->type);
+ /* If the test fails, then warn and remove from available_tracers */
+ if (ret < 0) {
+ WARN(1, "tracer: %s failed selftest, disabling\n",
+ p->type->name);
+ last = &trace_types;
+ for (t = trace_types; t; t = t->next) {
+ if (t == p->type) {
+ *last = t->next;
+ break;
+ }
+ last = &t->next;
+ }
+ }
+ list_del(&p->list);
+ kfree(p);
+ }
+
+ out:
+ mutex_unlock(&trace_types_lock);
+
+ return 0;
+}
+early_initcall(init_trace_selftests);
#else
static inline int run_tracer_selftest(struct tracer *type)
{
@@ -1927,6 +2004,18 @@ void tracing_record_cmdline(struct task_struct *tsk)
__this_cpu_write(trace_cmdline_save, false);
}
+/*
+ * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
+ * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
+ * simplifies those functions and keeps them in sync.
+ */
+enum print_line_t trace_handle_return(struct trace_seq *s)
+{
+ return trace_seq_has_overflowed(s) ?
+ TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
+}
+EXPORT_SYMBOL_GPL(trace_handle_return);
+
void
tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
int pc)
@@ -4122,6 +4211,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
if (mask == TRACE_ITER_EVENT_FORK)
trace_event_follow_fork(tr, enabled);
+ if (mask == TRACE_ITER_FUNC_FORK)
+ ftrace_pid_follow_fork(tr, enabled);
+
if (mask == TRACE_ITER_OVERWRITE) {
ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5962,6 +6054,7 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
struct ftrace_buffer_info {
struct trace_iterator iter;
void *spare;
+ unsigned int spare_cpu;
unsigned int read;
};
@@ -6291,9 +6384,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
return -EBUSY;
#endif
- if (!info->spare)
+ if (!info->spare) {
info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
iter->cpu_file);
+ info->spare_cpu = iter->cpu_file;
+ }
if (!info->spare)
return -ENOMEM;
@@ -6353,7 +6448,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
__trace_array_put(iter->tr);
if (info->spare)
- ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
+ ring_buffer_free_read_page(iter->trace_buffer->buffer,
+ info->spare_cpu, info->spare);
kfree(info);
mutex_unlock(&trace_types_lock);
@@ -6364,6 +6460,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
struct buffer_ref {
struct ring_buffer *buffer;
void *page;
+ int cpu;
int ref;
};
@@ -6375,7 +6472,7 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
if (--ref->ref)
return;
- ring_buffer_free_read_page(ref->buffer, ref->page);
+ ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
kfree(ref);
buf->private = 0;
}
@@ -6409,7 +6506,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
if (--ref->ref)
return;
- ring_buffer_free_read_page(ref->buffer, ref->page);
+ ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
kfree(ref);
spd->partial[i].private = 0;
}
@@ -6473,11 +6570,13 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
kfree(ref);
break;
}
+ ref->cpu = iter->cpu_file;
r = ring_buffer_read_page(ref->buffer, &ref->page,
len, iter->cpu_file, 1);
if (r < 0) {
- ring_buffer_free_read_page(ref->buffer, ref->page);
+ ring_buffer_free_read_page(ref->buffer, ref->cpu,
+ ref->page);
kfree(ref);
break;
}
@@ -6648,43 +6747,89 @@ static const struct file_operations tracing_dyn_info_fops = {
#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE)
static void
-ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_snapshot(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- tracing_snapshot();
+ tracing_snapshot_instance(tr);
}
static void
-ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- unsigned long *count = (long *)data;
+ struct ftrace_func_mapper *mapper = data;
+ long *count = NULL;
- if (!*count)
- return;
+ if (mapper)
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+ if (count) {
+
+ if (*count <= 0)
+ return;
- if (*count != -1)
(*count)--;
+ }
- tracing_snapshot();
+ tracing_snapshot_instance(tr);
}
static int
ftrace_snapshot_print(struct seq_file *m, unsigned long ip,
struct ftrace_probe_ops *ops, void *data)
{
- long count = (long)data;
+ struct ftrace_func_mapper *mapper = data;
+ long *count = NULL;
seq_printf(m, "%ps:", (void *)ip);
seq_puts(m, "snapshot");
- if (count == -1)
- seq_puts(m, ":unlimited\n");
+ if (mapper)
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+ if (count)
+ seq_printf(m, ":count=%ld\n", *count);
else
- seq_printf(m, ":count=%ld\n", count);
+ seq_puts(m, ":unlimited\n");
return 0;
}
+static int
+ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *init_data, void **data)
+{
+ struct ftrace_func_mapper *mapper = *data;
+
+ if (!mapper) {
+ mapper = allocate_ftrace_func_mapper();
+ if (!mapper)
+ return -ENOMEM;
+ *data = mapper;
+ }
+
+ return ftrace_func_mapper_add_ip(mapper, ip, init_data);
+}
+
+static void
+ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *data)
+{
+ struct ftrace_func_mapper *mapper = data;
+
+ if (!ip) {
+ if (!mapper)
+ return;
+ free_ftrace_func_mapper(mapper, NULL);
+ return;
+ }
+
+ ftrace_func_mapper_remove_ip(mapper, ip);
+}
+
static struct ftrace_probe_ops snapshot_probe_ops = {
.func = ftrace_snapshot,
.print = ftrace_snapshot_print,
@@ -6693,10 +6838,12 @@ static struct ftrace_probe_ops snapshot_probe_ops = {
static struct ftrace_probe_ops snapshot_count_probe_ops = {
.func = ftrace_count_snapshot,
.print = ftrace_snapshot_print,
+ .init = ftrace_snapshot_init,
+ .free = ftrace_snapshot_free,
};
static int
-ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
+ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enable)
{
struct ftrace_probe_ops *ops;
@@ -6710,10 +6857,8 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops;
- if (glob[0] == '!') {
- unregister_ftrace_function_probe_func(glob+1, ops);
- return 0;
- }
+ if (glob[0] == '!')
+ return unregister_ftrace_function_probe_func(glob+1, tr, ops);
if (!param)
goto out_reg;
@@ -6732,11 +6877,11 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
return ret;
out_reg:
- ret = alloc_snapshot(&global_trace);
+ ret = alloc_snapshot(tr);
if (ret < 0)
goto out;
- ret = register_ftrace_function_probe(glob, ops, count);
+ ret = register_ftrace_function_probe(glob, tr, ops, count);
out:
return ret < 0 ? ret : 0;
@@ -7347,6 +7492,8 @@ static int instance_mkdir(const char *name)
goto out_free_tr;
}
+ ftrace_init_trace_array(tr);
+
init_tracer_tracefs(tr, tr->dir);
init_trace_flags_index(tr);
__update_tracer_options(tr);
@@ -7967,6 +8114,9 @@ __init static int tracer_alloc_buffers(void)
register_tracer(&nop_trace);
+ /* Function tracing may start here (via kernel command line) */
+ init_function_trace();
+
/* All seems OK, enable tracing */
tracing_disabled = 0;
@@ -8001,7 +8151,7 @@ out:
return ret;
}
-void __init trace_init(void)
+void __init early_trace_init(void)
{
if (tracepoint_printk) {
tracepoint_print_iter =
@@ -8012,6 +8162,10 @@ void __init trace_init(void)
static_key_enable(&tracepoint_printk_key.key);
}
tracer_alloc_buffers();
+}
+
+void __init trace_init(void)
+{
trace_event_init();
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d19d52d600d6..291a1bca5748 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -262,6 +262,9 @@ struct trace_array {
#ifdef CONFIG_FUNCTION_TRACER
struct ftrace_ops *ops;
struct trace_pid_list __rcu *function_pids;
+#ifdef CONFIG_DYNAMIC_FTRACE
+ struct list_head func_probes;
+#endif
/* function tracing enabled */
int function_enabled;
#endif
@@ -579,6 +582,8 @@ void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
int tracer_tracing_is_on(struct trace_array *tr);
+void tracer_tracing_on(struct trace_array *tr);
+void tracer_tracing_off(struct trace_array *tr);
struct dentry *trace_create_file(const char *name,
umode_t mode,
struct dentry *parent,
@@ -696,6 +701,9 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
+void ftrace_init_trace_array(struct trace_array *tr);
+#else
+static inline void ftrace_init_trace_array(struct trace_array *tr) { }
#endif
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
extern int DYN_FTRACE_TEST_NAME(void);
@@ -880,6 +888,14 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
extern struct list_head ftrace_pids;
#ifdef CONFIG_FUNCTION_TRACER
+struct ftrace_func_command {
+ struct list_head list;
+ char *name;
+ int (*func)(struct trace_array *tr,
+ struct ftrace_hash *hash,
+ char *func, char *cmd,
+ char *params, int enable);
+};
extern bool ftrace_filter_param __initdata;
static inline int ftrace_trace_task(struct trace_array *tr)
{
@@ -897,6 +913,8 @@ void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
struct dentry *d_tracer);
void ftrace_clear_pids(struct trace_array *tr);
+int init_function_trace(void);
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable);
#else
static inline int ftrace_trace_task(struct trace_array *tr)
{
@@ -916,15 +934,70 @@ static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
static inline void ftrace_clear_pids(struct trace_array *tr) { }
+static inline int init_function_trace(void) { return 0; }
+static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { }
/* ftace_func_t type is not defined, use macro instead of static inline */
#define ftrace_init_array_ops(tr, func) do { } while (0)
#endif /* CONFIG_FUNCTION_TRACER */
#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+
+struct ftrace_probe_ops {
+ void (*func)(unsigned long ip,
+ unsigned long parent_ip,
+ struct trace_array *tr,
+ struct ftrace_probe_ops *ops,
+ void *data);
+ int (*init)(struct ftrace_probe_ops *ops,
+ struct trace_array *tr,
+ unsigned long ip, void *init_data,
+ void **data);
+ void (*free)(struct ftrace_probe_ops *ops,
+ struct trace_array *tr,
+ unsigned long ip, void *data);
+ int (*print)(struct seq_file *m,
+ unsigned long ip,
+ struct ftrace_probe_ops *ops,
+ void *data);
+};
+
+struct ftrace_func_mapper;
+typedef int (*ftrace_mapper_func)(void *data);
+
+struct ftrace_func_mapper *allocate_ftrace_func_mapper(void);
+void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip);
+int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip, void *data);
+void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip);
+void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
+ ftrace_mapper_func free_func);
+
+extern int
+register_ftrace_function_probe(char *glob, struct trace_array *tr,
+ struct ftrace_probe_ops *ops, void *data);
+extern int
+unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
+ struct ftrace_probe_ops *ops);
+
+int register_ftrace_command(struct ftrace_func_command *cmd);
+int unregister_ftrace_command(struct ftrace_func_command *cmd);
+
void ftrace_create_filter_files(struct ftrace_ops *ops,
struct dentry *parent);
void ftrace_destroy_filter_files(struct ftrace_ops *ops);
#else
+struct ftrace_func_command;
+
+static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+ return -EINVAL;
+}
+static inline __init int unregister_ftrace_command(char *cmd_name)
+{
+ return -EINVAL;
+}
/*
* The ops parameter passed in is usually undefined.
* This must be a macro.
@@ -989,11 +1062,13 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
#ifdef CONFIG_FUNCTION_TRACER
# define FUNCTION_FLAGS \
- C(FUNCTION, "function-trace"),
+ C(FUNCTION, "function-trace"), \
+ C(FUNC_FORK, "function-fork"),
# define FUNCTION_DEFAULT_FLAGS TRACE_ITER_FUNCTION
#else
# define FUNCTION_FLAGS
# define FUNCTION_DEFAULT_FLAGS 0UL
+# define TRACE_ITER_FUNC_FORK 0UL
#endif
#ifdef CONFIG_STACKTRACE
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index e49fbe901cfc..16a8cf02eee9 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -153,10 +153,18 @@ static int benchmark_event_kthread(void *arg)
trace_do_benchmark();
/*
- * We don't go to sleep, but let others
- * run as well.
+ * We don't go to sleep, but let others run as well.
+ * This is bascially a "yield()" to let any task that
+ * wants to run, schedule in, but if the CPU is idle,
+ * we'll keep burning cycles.
+ *
+ * Note the _rcu_qs() version of cond_resched() will
+ * notify synchronize_rcu_tasks() that this thread has
+ * passed a quiescent state for rcu_tasks. Otherwise
+ * this thread will never voluntarily schedule which would
+ * block synchronize_rcu_tasks() indefinitely.
*/
- cond_resched();
+ cond_resched_rcu_qs();
}
return 0;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 93116549a284..e7973e10398c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2460,15 +2460,8 @@ struct event_probe_data {
bool enable;
};
-static void
-event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+static void update_event_probe(struct event_probe_data *data)
{
- struct event_probe_data **pdata = (struct event_probe_data **)_data;
- struct event_probe_data *data = *pdata;
-
- if (!data)
- return;
-
if (data->enable)
clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags);
else
@@ -2476,77 +2469,141 @@ event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
}
static void
-event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+event_enable_probe(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- struct event_probe_data **pdata = (struct event_probe_data **)_data;
- struct event_probe_data *data = *pdata;
+ struct ftrace_func_mapper *mapper = data;
+ struct event_probe_data *edata;
+ void **pdata;
- if (!data)
+ pdata = ftrace_func_mapper_find_ip(mapper, ip);
+ if (!pdata || !*pdata)
+ return;
+
+ edata = *pdata;
+ update_event_probe(edata);
+}
+
+static void
+event_enable_count_probe(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
+{
+ struct ftrace_func_mapper *mapper = data;
+ struct event_probe_data *edata;
+ void **pdata;
+
+ pdata = ftrace_func_mapper_find_ip(mapper, ip);
+ if (!pdata || !*pdata)
return;
- if (!data->count)
+ edata = *pdata;
+
+ if (!edata->count)
return;
/* Skip if the event is in a state we want to switch to */
- if (data->enable == !(data->file->flags & EVENT_FILE_FL_SOFT_DISABLED))
+ if (edata->enable == !(edata->file->flags & EVENT_FILE_FL_SOFT_DISABLED))
return;
- if (data->count != -1)
- (data->count)--;
+ if (edata->count != -1)
+ (edata->count)--;
- event_enable_probe(ip, parent_ip, _data);
+ update_event_probe(edata);
}
static int
event_enable_print(struct seq_file *m, unsigned long ip,
- struct ftrace_probe_ops *ops, void *_data)
+ struct ftrace_probe_ops *ops, void *data)
{
- struct event_probe_data *data = _data;
+ struct ftrace_func_mapper *mapper = data;
+ struct event_probe_data *edata;
+ void **pdata;
+
+ pdata = ftrace_func_mapper_find_ip(mapper, ip);
+
+ if (WARN_ON_ONCE(!pdata || !*pdata))
+ return 0;
+
+ edata = *pdata;
seq_printf(m, "%ps:", (void *)ip);
seq_printf(m, "%s:%s:%s",
- data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
- data->file->event_call->class->system,
- trace_event_name(data->file->event_call));
+ edata->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+ edata->file->event_call->class->system,
+ trace_event_name(edata->file->event_call));
- if (data->count == -1)
+ if (edata->count == -1)
seq_puts(m, ":unlimited\n");
else
- seq_printf(m, ":count=%ld\n", data->count);
+ seq_printf(m, ":count=%ld\n", edata->count);
return 0;
}
static int
-event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip,
- void **_data)
+event_enable_init(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *init_data, void **data)
{
- struct event_probe_data **pdata = (struct event_probe_data **)_data;
- struct event_probe_data *data = *pdata;
+ struct ftrace_func_mapper *mapper = *data;
+ struct event_probe_data *edata = init_data;
+ int ret;
+
+ if (!mapper) {
+ mapper = allocate_ftrace_func_mapper();
+ if (!mapper)
+ return -ENODEV;
+ *data = mapper;
+ }
+
+ ret = ftrace_func_mapper_add_ip(mapper, ip, edata);
+ if (ret < 0)
+ return ret;
+
+ edata->ref++;
- data->ref++;
+ return 0;
+}
+
+static int free_probe_data(void *data)
+{
+ struct event_probe_data *edata = data;
+
+ edata->ref--;
+ if (!edata->ref) {
+ /* Remove the SOFT_MODE flag */
+ __ftrace_event_enable_disable(edata->file, 0, 1);
+ module_put(edata->file->event_call->mod);
+ kfree(edata);
+ }
return 0;
}
static void
-event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip,
- void **_data)
+event_enable_free(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *data)
{
- struct event_probe_data **pdata = (struct event_probe_data **)_data;
- struct event_probe_data *data = *pdata;
+ struct ftrace_func_mapper *mapper = data;
+ struct event_probe_data *edata;
- if (WARN_ON_ONCE(data->ref <= 0))
+ if (!ip) {
+ if (!mapper)
+ return;
+ free_ftrace_func_mapper(mapper, free_probe_data);
return;
-
- data->ref--;
- if (!data->ref) {
- /* Remove the SOFT_MODE flag */
- __ftrace_event_enable_disable(data->file, 0, 1);
- module_put(data->file->event_call->mod);
- kfree(data);
}
- *pdata = NULL;
+
+ edata = ftrace_func_mapper_remove_ip(mapper, ip);
+
+ if (WARN_ON_ONCE(!edata))
+ return;
+
+ if (WARN_ON_ONCE(edata->ref <= 0))
+ return;
+
+ free_probe_data(edata);
}
static struct ftrace_probe_ops event_enable_probe_ops = {
@@ -2578,10 +2635,9 @@ static struct ftrace_probe_ops event_disable_count_probe_ops = {
};
static int
-event_enable_func(struct ftrace_hash *hash,
+event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enabled)
{
- struct trace_array *tr = top_trace_array();
struct trace_event_file *file;
struct ftrace_probe_ops *ops;
struct event_probe_data *data;
@@ -2619,12 +2675,12 @@ event_enable_func(struct ftrace_hash *hash,
ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops;
if (glob[0] == '!') {
- unregister_ftrace_function_probe_func(glob+1, ops);
- ret = 0;
+ ret = unregister_ftrace_function_probe_func(glob+1, tr, ops);
goto out;
}
ret = -ENOMEM;
+
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
goto out;
@@ -2661,7 +2717,8 @@ event_enable_func(struct ftrace_hash *hash,
ret = __ftrace_event_enable_disable(file, 1, 1);
if (ret < 0)
goto out_put;
- ret = register_ftrace_function_probe(glob, ops, data);
+
+ ret = register_ftrace_function_probe(glob, tr, ops, data);
/*
* The above returns on success the # of functions enabled,
* but if it didn't find any functions it returns zero.
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 0efa00d80623..a3bddbfd0874 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -267,10 +267,14 @@ static struct tracer function_trace __tracer_data =
};
#ifdef CONFIG_DYNAMIC_FTRACE
-static void update_traceon_count(void **data, bool on)
+static void update_traceon_count(struct ftrace_probe_ops *ops,
+ unsigned long ip,
+ struct trace_array *tr, bool on,
+ void *data)
{
- long *count = (long *)data;
- long old_count = *count;
+ struct ftrace_func_mapper *mapper = data;
+ long *count;
+ long old_count;
/*
* Tracing gets disabled (or enabled) once per count.
@@ -301,23 +305,22 @@ static void update_traceon_count(void **data, bool on)
* setting the tracing_on file. But we currently don't care
* about that.
*/
- if (!old_count)
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+ old_count = *count;
+
+ if (old_count <= 0)
return;
/* Make sure we see count before checking tracing state */
smp_rmb();
- if (on == !!tracing_is_on())
+ if (on == !!tracer_tracing_is_on(tr))
return;
if (on)
- tracing_on();
+ tracer_tracing_on(tr);
else
- tracing_off();
-
- /* unlimited? */
- if (old_count == -1)
- return;
+ tracer_tracing_off(tr);
/* Make sure tracing state is visible before updating count */
smp_wmb();
@@ -326,33 +329,41 @@ static void update_traceon_count(void **data, bool on)
}
static void
-ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceon_count(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- update_traceon_count(data, 1);
+ update_traceon_count(ops, ip, tr, 1, data);
}
static void
-ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- update_traceon_count(data, 0);
+ update_traceon_count(ops, ip, tr, 0, data);
}
static void
-ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceon(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- if (tracing_is_on())
+ if (tracer_tracing_is_on(tr))
return;
- tracing_on();
+ tracer_tracing_on(tr);
}
static void
-ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- if (!tracing_is_on())
+ if (!tracer_tracing_is_on(tr))
return;
- tracing_off();
+ tracer_tracing_off(tr);
}
/*
@@ -364,144 +375,218 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
*/
#define STACK_SKIP 4
+static __always_inline void trace_stack(struct trace_array *tr)
+{
+ unsigned long flags;
+ int pc;
+
+ local_save_flags(flags);
+ pc = preempt_count();
+
+ __trace_stack(tr, flags, STACK_SKIP, pc);
+}
+
static void
-ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_stacktrace(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- trace_dump_stack(STACK_SKIP);
+ trace_stack(tr);
}
static void
-ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- long *count = (long *)data;
+ struct ftrace_func_mapper *mapper = data;
+ long *count;
long old_count;
long new_count;
+ if (!tracing_is_on())
+ return;
+
+ /* unlimited? */
+ if (!mapper) {
+ trace_stack(tr);
+ return;
+ }
+
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
/*
* Stack traces should only execute the number of times the
* user specified in the counter.
*/
do {
-
- if (!tracing_is_on())
- return;
-
old_count = *count;
if (!old_count)
return;
- /* unlimited? */
- if (old_count == -1) {
- trace_dump_stack(STACK_SKIP);
- return;
- }
-
new_count = old_count - 1;
new_count = cmpxchg(count, old_count, new_count);
if (new_count == old_count)
- trace_dump_stack(STACK_SKIP);
+ trace_stack(tr);
+
+ if (!tracing_is_on())
+ return;
} while (new_count != old_count);
}
-static int update_count(void **data)
+static int update_count(struct ftrace_probe_ops *ops, unsigned long ip,
+ void *data)
{
- unsigned long *count = (long *)data;
+ struct ftrace_func_mapper *mapper = data;
+ long *count = NULL;
- if (!*count)
- return 0;
+ if (mapper)
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
- if (*count != -1)
+ if (count) {
+ if (*count <= 0)
+ return 0;
(*count)--;
+ }
return 1;
}
static void
-ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_dump_probe(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- if (update_count(data))
+ if (update_count(ops, ip, data))
ftrace_dump(DUMP_ALL);
}
/* Only dump the current CPU buffer. */
static void
-ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip,
+ struct trace_array *tr, struct ftrace_probe_ops *ops,
+ void *data)
{
- if (update_count(data))
+ if (update_count(ops, ip, data))
ftrace_dump(DUMP_ORIG);
}
static int
ftrace_probe_print(const char *name, struct seq_file *m,
- unsigned long ip, void *data)
+ unsigned long ip, struct ftrace_probe_ops *ops,
+ void *data)
{
- long count = (long)data;
+ struct ftrace_func_mapper *mapper = data;
+ long *count = NULL;
seq_printf(m, "%ps:%s", (void *)ip, name);
- if (count == -1)
- seq_puts(m, ":unlimited\n");
+ if (mapper)
+ count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+ if (count)
+ seq_printf(m, ":count=%ld\n", *count);
else
- seq_printf(m, ":count=%ld\n", count);
+ seq_puts(m, ":unlimited\n");
return 0;
}
static int
ftrace_traceon_print(struct seq_file *m, unsigned long ip,
- struct ftrace_probe_ops *ops, void *data)
+ struct ftrace_probe_ops *ops,
+ void *data)
{
- return ftrace_probe_print("traceon", m, ip, data);
+ return ftrace_probe_print("traceon", m, ip, ops, data);
}
static int
ftrace_traceoff_print(struct seq_file *m, unsigned long ip,
struct ftrace_probe_ops *ops, void *data)
{
- return ftrace_probe_print("traceoff", m, ip, data);
+ return ftrace_probe_print("traceoff", m, ip, ops, data);
}
static int
ftrace_stacktrace_print(struct seq_file *m, unsigned long ip,
struct ftrace_probe_ops *ops, void *data)
{
- return ftrace_probe_print("stacktrace", m, ip, data);
+ return ftrace_probe_print("stacktrace", m, ip, ops, data);
}
static int
ftrace_dump_print(struct seq_file *m, unsigned long ip,
struct ftrace_probe_ops *ops, void *data)
{
- return ftrace_probe_print("dump", m, ip, data);
+ return ftrace_probe_print("dump", m, ip, ops, data);
}
static int
ftrace_cpudump_print(struct seq_file *m, unsigned long ip,
struct ftrace_probe_ops *ops, void *data)
{
- return ftrace_probe_print("cpudump", m, ip, data);
+ return ftrace_probe_print("cpudump", m, ip, ops, data);
+}
+
+
+static int
+ftrace_count_init(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *init_data, void **data)
+{
+ struct ftrace_func_mapper *mapper = *data;
+
+ if (!mapper) {
+ mapper = allocate_ftrace_func_mapper();
+ if (!mapper)
+ return -ENOMEM;
+ *data = mapper;
+ }
+
+ return ftrace_func_mapper_add_ip(mapper, ip, init_data);
+}
+
+static void
+ftrace_count_free(struct ftrace_probe_ops *ops, struct trace_array *tr,
+ unsigned long ip, void *data)
+{
+ struct ftrace_func_mapper *mapper = data;
+
+ if (!ip) {
+ free_ftrace_func_mapper(mapper, NULL);
+ return;
+ }
+
+ ftrace_func_mapper_remove_ip(mapper, ip);
}
static struct ftrace_probe_ops traceon_count_probe_ops = {
.func = ftrace_traceon_count,
.print = ftrace_traceon_print,
+ .init = ftrace_count_init,
+ .free = ftrace_count_free,
};
static struct ftrace_probe_ops traceoff_count_probe_ops = {
.func = ftrace_traceoff_count,
.print = ftrace_traceoff_print,
+ .init = ftrace_count_init,
+ .free = ftrace_count_free,
};
static struct ftrace_probe_ops stacktrace_count_probe_ops = {
.func = ftrace_stacktrace_count,
.print = ftrace_stacktrace_print,
+ .init = ftrace_count_init,
+ .free = ftrace_count_free,
};
static struct ftrace_probe_ops dump_probe_ops = {
.func = ftrace_dump_probe,
.print = ftrace_dump_print,
+ .init = ftrace_count_init,
+ .free = ftrace_count_free,
};
static struct ftrace_probe_ops cpudump_probe_ops = {
@@ -525,7 +610,8 @@ static struct ftrace_probe_ops stacktrace_probe_ops = {
};
static int
-ftrace_trace_probe_callback(struct ftrace_probe_ops *ops,
+ftrace_trace_probe_callback(struct trace_array *tr,
+ struct ftrace_probe_ops *ops,
struct ftrace_hash *hash, char *glob,
char *cmd, char *param, int enable)
{
@@ -537,10 +623,8 @@ ftrace_trace_probe_callback(struct ftrace_probe_ops *ops,
if (!enable)
return -EINVAL;
- if (glob[0] == '!') {
- unregister_ftrace_function_probe_func(glob+1, ops);
- return 0;
- }
+ if (glob[0] == '!')
+ return unregister_ftrace_function_probe_func(glob+1, tr, ops);
if (!param)
goto out_reg;
@@ -559,13 +643,13 @@ ftrace_trace_probe_callback(struct ftrace_probe_ops *ops,
return ret;
out_reg:
- ret = register_ftrace_function_probe(glob, ops, count);
+ ret = register_ftrace_function_probe(glob, tr, ops, count);
return ret < 0 ? ret : 0;
}
static int
-ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+ftrace_trace_onoff_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enable)
{
struct ftrace_probe_ops *ops;
@@ -576,24 +660,24 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash,
else
ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops;
- return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+ return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
param, enable);
}
static int
-ftrace_stacktrace_callback(struct ftrace_hash *hash,
+ftrace_stacktrace_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enable)
{
struct ftrace_probe_ops *ops;
ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops;
- return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+ return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
param, enable);
}
static int
-ftrace_dump_callback(struct ftrace_hash *hash,
+ftrace_dump_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enable)
{
struct ftrace_probe_ops *ops;
@@ -601,12 +685,12 @@ ftrace_dump_callback(struct ftrace_hash *hash,
ops = &dump_probe_ops;
/* Only dump once. */
- return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+ return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
"1", enable);
}
static int
-ftrace_cpudump_callback(struct ftrace_hash *hash,
+ftrace_cpudump_callback(struct trace_array *tr, struct ftrace_hash *hash,
char *glob, char *cmd, char *param, int enable)
{
struct ftrace_probe_ops *ops;
@@ -614,7 +698,7 @@ ftrace_cpudump_callback(struct ftrace_hash *hash,
ops = &cpudump_probe_ops;
/* Only dump once. */
- return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+ return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
"1", enable);
}
@@ -687,9 +771,8 @@ static inline int init_func_cmd_traceon(void)
}
#endif /* CONFIG_DYNAMIC_FTRACE */
-static __init int init_function_trace(void)
+__init int init_function_trace(void)
{
init_func_cmd_traceon();
return register_tracer(&function_trace);
}
-core_initcall(init_function_trace);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 013f4e7146d4..8485f6738a87 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -25,6 +25,7 @@
#include "trace_probe.h"
#define KPROBE_EVENT_SYSTEM "kprobes"
+#define KRETPROBE_MAXACTIVE_MAX 4096
/**
* Kprobe event core functions
@@ -282,6 +283,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
void *addr,
const char *symbol,
unsigned long offs,
+ int maxactive,
int nargs, bool is_return)
{
struct trace_kprobe *tk;
@@ -309,6 +311,8 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
else
tk->rp.kp.pre_handler = kprobe_dispatcher;
+ tk->rp.maxactive = maxactive;
+
if (!event || !is_good_name(event)) {
ret = -EINVAL;
goto error;
@@ -598,8 +602,10 @@ static int create_trace_kprobe(int argc, char **argv)
{
/*
* Argument syntax:
- * - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
- * - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
+ * - Add kprobe:
+ * p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+ * - Add kretprobe:
+ * r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
* Fetch args:
* $retval : fetch return value
* $stack : fetch stack address
@@ -619,6 +625,7 @@ static int create_trace_kprobe(int argc, char **argv)
int i, ret = 0;
bool is_return = false, is_delete = false;
char *symbol = NULL, *event = NULL, *group = NULL;
+ int maxactive = 0;
char *arg;
unsigned long offset = 0;
void *addr = NULL;
@@ -637,8 +644,28 @@ static int create_trace_kprobe(int argc, char **argv)
return -EINVAL;
}
- if (argv[0][1] == ':') {
- event = &argv[0][2];
+ event = strchr(&argv[0][1], ':');
+ if (event) {
+ event[0] = '\0';
+ event++;
+ }
+ if (is_return && isdigit(argv[0][1])) {
+ ret = kstrtouint(&argv[0][1], 0, &maxactive);
+ if (ret) {
+ pr_info("Failed to parse maxactive.\n");
+ return ret;
+ }
+ /* kretprobes instances are iterated over via a list. The
+ * maximum should stay reasonable.
+ */
+ if (maxactive > KRETPROBE_MAXACTIVE_MAX) {
+ pr_info("Maxactive is too big (%d > %d).\n",
+ maxactive, KRETPROBE_MAXACTIVE_MAX);
+ return -E2BIG;
+ }
+ }
+
+ if (event) {
if (strchr(event, '/')) {
group = event;
event = strchr(group, '/') + 1;
@@ -715,8 +742,8 @@ static int create_trace_kprobe(int argc, char **argv)
is_return ? 'r' : 'p', addr);
event = buf;
}
- tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc,
- is_return);
+ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
+ argc, is_return);
if (IS_ERR(tk)) {
pr_info("Failed to allocate trace_probe.(%d)\n",
(int)PTR_ERR(tk));
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 5fb1f2c87e6b..76aa04d4c925 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -35,7 +35,7 @@ unsigned long stack_trace_max_size;
arch_spinlock_t stack_trace_max_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-static DEFINE_PER_CPU(int, trace_active);
+DEFINE_PER_CPU(int, disable_stack_tracer);
static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
@@ -96,6 +96,14 @@ check_stack(unsigned long ip, unsigned long *stack)
if (in_nmi())
return;
+ /*
+ * There's a slight chance that we are tracing inside the
+ * RCU infrastructure, and rcu_irq_enter() will not work
+ * as expected.
+ */
+ if (unlikely(rcu_irq_enter_disabled()))
+ return;
+
local_irq_save(flags);
arch_spin_lock(&stack_trace_max_lock);
@@ -207,13 +215,12 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
unsigned long stack;
- int cpu;
preempt_disable_notrace();
- cpu = raw_smp_processor_id();
/* no atomic needed, we only modify this variable by this cpu */
- if (per_cpu(trace_active, cpu)++ != 0)
+ __this_cpu_inc(disable_stack_tracer);
+ if (__this_cpu_read(disable_stack_tracer) != 1)
goto out;
ip += MCOUNT_INSN_SIZE;
@@ -221,7 +228,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
check_stack(ip, &stack);
out:
- per_cpu(trace_active, cpu)--;
+ __this_cpu_dec(disable_stack_tracer);
/* prevent recursion in schedule */
preempt_enable_notrace();
}
@@ -253,7 +260,6 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
long *ptr = filp->private_data;
unsigned long val, flags;
int ret;
- int cpu;
ret = kstrtoul_from_user(ubuf, count, 10, &val);
if (ret)
@@ -264,16 +270,15 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
/*
* In case we trace inside arch_spin_lock() or after (NMI),
* we will cause circular lock, so we also need to increase
- * the percpu trace_active here.
+ * the percpu disable_stack_tracer here.
*/
- cpu = smp_processor_id();
- per_cpu(trace_active, cpu)++;
+ __this_cpu_inc(disable_stack_tracer);
arch_spin_lock(&stack_trace_max_lock);
*ptr = val;
arch_spin_unlock(&stack_trace_max_lock);
- per_cpu(trace_active, cpu)--;
+ __this_cpu_dec(disable_stack_tracer);
local_irq_restore(flags);
return count;
@@ -307,12 +312,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
- int cpu;
-
local_irq_disable();
- cpu = smp_processor_id();
- per_cpu(trace_active, cpu)++;
+ __this_cpu_inc(disable_stack_tracer);
arch_spin_lock(&stack_trace_max_lock);
@@ -324,12 +326,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
static void t_stop(struct seq_file *m, void *p)
{
- int cpu;
-
arch_spin_unlock(&stack_trace_max_lock);
- cpu = smp_processor_id();
- per_cpu(trace_active, cpu)--;
+ __this_cpu_dec(disable_stack_tracer);
local_irq_enable();
}