summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig49
-rw-r--r--kernel/trace/blktrace.c30
-rw-r--r--kernel/trace/ftrace.c154
-rw-r--r--kernel/trace/ring_buffer.c500
-rw-r--r--kernel/trace/trace.c2248
-rw-r--r--kernel/trace/trace.h151
-rw-r--r--kernel/trace/trace_branch.c8
-rw-r--r--kernel/trace/trace_clock.c10
-rw-r--r--kernel/trace/trace_entries.h23
-rw-r--r--kernel/trace/trace_events.c1397
-rw-r--r--kernel/trace/trace_events_filter.c34
-rw-r--r--kernel/trace/trace_export.c4
-rw-r--r--kernel/trace/trace_functions.c207
-rw-r--r--kernel/trace/trace_functions_graph.c12
-rw-r--r--kernel/trace/trace_irqsoff.c90
-rw-r--r--kernel/trace/trace_kdb.c12
-rw-r--r--kernel/trace/trace_mmiotrace.c12
-rw-r--r--kernel/trace/trace_output.c119
-rw-r--r--kernel/trace/trace_output.h4
-rw-r--r--kernel/trace/trace_sched_switch.c8
-rw-r--r--kernel/trace/trace_sched_wakeup.c93
-rw-r--r--kernel/trace/trace_selftest.c51
-rw-r--r--kernel/trace/trace_stack.c78
-rw-r--r--kernel/trace/trace_stat.c2
-rw-r--r--kernel/trace/trace_syscalls.c90
-rw-r--r--kernel/trace/trace_uprobe.c203
26 files changed, 4235 insertions, 1354 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index fc382d6e2765..5e9efd4b83a4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -176,6 +176,8 @@ config IRQSOFF_TRACER
select GENERIC_TRACER
select TRACER_MAX_TRACE
select RING_BUFFER_ALLOW_SWAP
+ select TRACER_SNAPSHOT
+ select TRACER_SNAPSHOT_PER_CPU_SWAP
help
This option measures the time spent in irqs-off critical
sections, with microsecond accuracy.
@@ -198,6 +200,8 @@ config PREEMPT_TRACER
select GENERIC_TRACER
select TRACER_MAX_TRACE
select RING_BUFFER_ALLOW_SWAP
+ select TRACER_SNAPSHOT
+ select TRACER_SNAPSHOT_PER_CPU_SWAP
help
This option measures the time spent in preemption-off critical
sections, with microsecond accuracy.
@@ -217,6 +221,7 @@ config SCHED_TRACER
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
select TRACER_MAX_TRACE
+ select TRACER_SNAPSHOT
help
This tracer tracks the latency of the highest priority task
to be scheduled in, starting from the point it has woken up.
@@ -248,6 +253,27 @@ config TRACER_SNAPSHOT
echo 1 > /sys/kernel/debug/tracing/snapshot
cat snapshot
+config TRACER_SNAPSHOT_PER_CPU_SWAP
+ bool "Allow snapshot to swap per CPU"
+ depends on TRACER_SNAPSHOT
+ select RING_BUFFER_ALLOW_SWAP
+ help
+ Allow doing a snapshot of a single CPU buffer instead of a
+ full swap (all buffers). If this is set, then the following is
+ allowed:
+
+ echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
+
+ After which, only the tracing buffer for CPU 2 was swapped with
+ the main tracing buffer, and the other CPU buffers remain the same.
+
+ When this is enabled, this adds a little more overhead to the
+ trace recording, as it needs to add some checks to synchronize
+ recording with swaps. But this does not affect the performance
+ of the overall system. This is enabled by default when the preempt
+ or irq latency tracers are enabled, as those need to swap as well
+ and already adds the overhead (plus a lot more).
+
config TRACE_BRANCH_PROFILING
bool
select GENERIC_TRACER
@@ -524,6 +550,29 @@ config RING_BUFFER_BENCHMARK
If unsure, say N.
+config RING_BUFFER_STARTUP_TEST
+ bool "Ring buffer startup self test"
+ depends on RING_BUFFER
+ help
+ Run a simple self test on the ring buffer on boot up. Late in the
+ kernel boot sequence, the test will start that kicks off
+ a thread per cpu. Each thread will write various size events
+ into the ring buffer. Another thread is created to send IPIs
+ to each of the threads, where the IPI handler will also write
+ to the ring buffer, to test/stress the nesting ability.
+ If any anomalies are discovered, a warning will be displayed
+ and all ring buffers will be disabled.
+
+ The test runs for 10 seconds. This will slow your boot time
+ by at least 10 more seconds.
+
+ At the end of the test, statics and more checks are done.
+ It will output the stats of each per cpu buffer. What
+ was written, the sizes, what was read, what was lost, and
+ other similar details.
+
+ If unsure, say N
+
endif # FTRACE
endif # TRACING_SUPPORT
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 20d8a9825f96..b8b8560bfb95 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -72,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
bool blk_tracer = blk_tracer_enabled;
if (blk_tracer) {
- buffer = blk_tr->buffer;
+ buffer = blk_tr->trace_buffer.buffer;
pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
sizeof(*t) + len,
@@ -218,7 +218,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
if (blk_tracer) {
tracing_record_cmdline(current);
- buffer = blk_tr->buffer;
+ buffer = blk_tr->trace_buffer.buffer;
pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
sizeof(*t) + pdu_len,
@@ -739,12 +739,6 @@ static void blk_add_trace_rq_complete(void *ignore,
struct request_queue *q,
struct request *rq)
{
- struct blk_trace *bt = q->blk_trace;
-
- /* if control ever passes through here, it's a request based driver */
- if (unlikely(bt && !bt->rq_based))
- bt->rq_based = true;
-
blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
}
@@ -780,24 +774,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
}
-static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
+static void blk_add_trace_bio_complete(void *ignore,
+ struct request_queue *q, struct bio *bio,
+ int error)
{
- struct request_queue *q;
- struct blk_trace *bt;
-
- if (!bio->bi_bdev)
- return;
-
- q = bdev_get_queue(bio->bi_bdev);
- bt = q->blk_trace;
-
- /*
- * Request based drivers will generate both rq and bio completions.
- * Ignore bio ones.
- */
- if (likely(!bt) || bt->rq_based)
- return;
-
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ab25b88aae56..8a5c017bb50c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -66,7 +66,7 @@
static struct ftrace_ops ftrace_list_end __read_mostly = {
.func = ftrace_stub,
- .flags = FTRACE_OPS_FL_RECURSION_SAFE,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
};
/* ftrace_enabled is a method to turn ftrace on or off */
@@ -486,7 +486,6 @@ struct ftrace_profile_stat {
#define PROFILES_PER_PAGE \
(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
-static int ftrace_profile_bits __read_mostly;
static int ftrace_profile_enabled __read_mostly;
/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
@@ -494,7 +493,8 @@ static DEFINE_MUTEX(ftrace_profile_lock);
static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
-#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+#define FTRACE_PROFILE_HASH_BITS 10
+#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS)
static void *
function_stat_next(void *v, int idx)
@@ -676,7 +676,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
- for (i = 0; i < pages; i++) {
+ for (i = 1; i < pages; i++) {
pg->next = (void *)get_zeroed_page(GFP_KERNEL);
if (!pg->next)
goto out_free;
@@ -694,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
free_page(tmp);
}
- free_page((unsigned long)stat->pages);
stat->pages = NULL;
stat->start = NULL;
@@ -725,13 +724,6 @@ static int ftrace_profile_init_cpu(int cpu)
if (!stat->hash)
return -ENOMEM;
- if (!ftrace_profile_bits) {
- size--;
-
- for (; size; size >>= 1)
- ftrace_profile_bits++;
- }
-
/* Preallocate the function profiling pages */
if (ftrace_profile_pages_init(stat) < 0) {
kfree(stat->hash);
@@ -764,7 +756,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
struct hlist_head *hhd;
unsigned long key;
- key = hash_long(ip, ftrace_profile_bits);
+ key = hash_long(ip, FTRACE_PROFILE_HASH_BITS);
hhd = &stat->hash[key];
if (hlist_empty(hhd))
@@ -783,7 +775,7 @@ static void ftrace_add_profile(struct ftrace_profile_stat *stat,
{
unsigned long key;
- key = hash_long(rec->ip, ftrace_profile_bits);
+ key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS);
hlist_add_head_rcu(&rec->node, &stat->hash[key]);
}
@@ -1053,6 +1045,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+ loff_t ret;
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_lseek(file, offset, whence);
+ else
+ file->f_pos = ret = 1;
+
+ return ret;
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -1067,7 +1072,7 @@ struct ftrace_func_probe {
unsigned long flags;
unsigned long ip;
void *data;
- struct rcu_head rcu;
+ struct list_head free_list;
};
struct ftrace_func_entry {
@@ -1317,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
struct hlist_head *hhd;
struct ftrace_hash *old_hash;
struct ftrace_hash *new_hash;
- unsigned long key;
int size = src->count;
int bits = 0;
int ret;
@@ -1360,10 +1364,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
for (i = 0; i < size; i++) {
hhd = &src->buckets[i];
hlist_for_each_entry_safe(entry, tn, hhd, hlist) {
- if (bits > 0)
- key = hash_long(entry->ip, bits);
- else
- key = 0;
remove_hash_entry(src, entry);
__add_hash_entry(new_hash, entry);
}
@@ -2613,7 +2613,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
* routine, you can use ftrace_filter_write() for the write
* routine if @flag has FTRACE_ITER_FILTER set, or
* ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
* release must call ftrace_regex_release().
*/
int
@@ -2697,19 +2697,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
inode, file);
}
-loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
-{
- loff_t ret;
-
- if (file->f_mode & FMODE_READ)
- ret = seq_lseek(file, offset, whence);
- else
- file->f_pos = ret = 1;
-
- return ret;
-}
-
static int ftrace_match(char *str, char *regex, int len, int type)
{
int matched = 0;
@@ -2974,28 +2961,27 @@ static void __disable_ftrace_function_probe(void)
}
-static void ftrace_free_entry_rcu(struct rcu_head *rhp)
+static void ftrace_free_entry(struct ftrace_func_probe *entry)
{
- struct ftrace_func_probe *entry =
- container_of(rhp, struct ftrace_func_probe, rcu);
-
if (entry->ops->free)
- entry->ops->free(&entry->data);
+ entry->ops->free(entry->ops, entry->ip, &entry->data);
kfree(entry);
}
-
int
register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data)
{
struct ftrace_func_probe *entry;
+ struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+ struct ftrace_hash *hash;
struct ftrace_page *pg;
struct dyn_ftrace *rec;
int type, len, not;
unsigned long key;
int count = 0;
char *search;
+ int ret;
type = filter_parse_regex(glob, strlen(glob), &search, &not);
len = strlen(search);
@@ -3006,8 +2992,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
mutex_lock(&ftrace_lock);
- if (unlikely(ftrace_disabled))
+ hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+ if (!hash) {
+ count = -ENOMEM;
+ goto out_unlock;
+ }
+
+ if (unlikely(ftrace_disabled)) {
+ count = -ENODEV;
goto out_unlock;
+ }
do_for_each_ftrace_rec(pg, rec) {
@@ -3031,14 +3025,21 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
* for each function we find. We call the callback
* to give the caller an opportunity to do so.
*/
- if (ops->callback) {
- if (ops->callback(rec->ip, &entry->data) < 0) {
+ if (ops->init) {
+ if (ops->init(ops, rec->ip, &entry->data) < 0) {
/* caller does not like this func */
kfree(entry);
continue;
}
}
+ ret = enter_record(hash, rec, 0);
+ if (ret < 0) {
+ kfree(entry);
+ count = ret;
+ goto out_unlock;
+ }
+
entry->ops = ops;
entry->ip = rec->ip;
@@ -3046,10 +3047,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
} while_for_each_ftrace_rec();
+
+ ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+ if (ret < 0)
+ count = ret;
+
__enable_ftrace_function_probe();
out_unlock:
mutex_unlock(&ftrace_lock);
+ free_ftrace_hash(hash);
return count;
}
@@ -3063,7 +3070,12 @@ static void
__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data, int flags)
{
+ struct ftrace_func_entry *rec_entry;
struct ftrace_func_probe *entry;
+ struct ftrace_func_probe *p;
+ struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+ struct list_head free_list;
+ struct ftrace_hash *hash;
struct hlist_node *tmp;
char str[KSYM_SYMBOL_LEN];
int type = MATCH_FULL;
@@ -3084,6 +3096,14 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
}
mutex_lock(&ftrace_lock);
+
+ hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_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];
@@ -3104,12 +3124,30 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
continue;
}
- hlist_del(&entry->node);
- call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+ 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);
}
}
__disable_ftrace_function_probe();
+ /*
+ * Remove after the disable is called. Otherwise, if the last
+ * probe is removed, a null hash means *all enabled*.
+ */
+ ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+ synchronize_sched();
+ list_for_each_entry_safe(entry, p, &free_list, free_list) {
+ list_del(&entry->free_list);
+ ftrace_free_entry(entry);
+ }
+
+ out_unlock:
mutex_unlock(&ftrace_lock);
+ free_ftrace_hash(hash);
}
void
@@ -3441,14 +3479,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
static int __init set_ftrace_notrace(char *str)
{
- strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+ strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_notrace=", set_ftrace_notrace);
static int __init set_ftrace_filter(char *str)
{
- strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+ strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_filter=", set_ftrace_filter);
@@ -3571,7 +3609,7 @@ static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_regex_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_regex_release,
};
@@ -3579,7 +3617,7 @@ static const struct file_operations ftrace_notrace_fops = {
.open = ftrace_notrace_open,
.read = seq_read,
.write = ftrace_notrace_write,
- .llseek = ftrace_regex_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_regex_release,
};
@@ -3737,7 +3775,8 @@ out:
if (fail)
return -EINVAL;
- ftrace_graph_filter_enabled = 1;
+ ftrace_graph_filter_enabled = !!(*idx);
+
return 0;
}
@@ -3784,8 +3823,8 @@ static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_graph_release,
- .llseek = seq_lseek,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -4131,7 +4170,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
preempt_disable_notrace();
trace_recursion_set(TRACE_CONTROL_BIT);
do_for_each_ftrace_op(op, ftrace_control_list) {
- if (!ftrace_function_local_disabled(op) &&
+ if (!(op->flags & FTRACE_OPS_FL_STUB) &&
+ !ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip))
op->func(ip, parent_ip, op, regs);
} while_for_each_ftrace_op(op);
@@ -4439,7 +4479,7 @@ static const struct file_operations ftrace_pid_fops = {
.open = ftrace_pid_open,
.write = ftrace_pid_write,
.read = seq_read,
- .llseek = seq_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_pid_release,
};
@@ -4555,12 +4595,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
ftrace_startup_sysctl();
/* we are starting ftrace again */
- if (ftrace_ops_list != &ftrace_list_end) {
- if (ftrace_ops_list->next == &ftrace_list_end)
- ftrace_trace_function = ftrace_ops_list->func;
- else
- ftrace_trace_function = ftrace_ops_list_func;
- }
+ if (ftrace_ops_list != &ftrace_list_end)
+ update_ftrace_function();
} else {
/* stopping ftrace calls (just send to ftrace_stub) */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6989df2ba194..b59aea2c48c2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -8,13 +8,16 @@
#include <linux/trace_clock.h>
#include <linux/trace_seq.h>
#include <linux/spinlock.h>
+#include <linux/irq_work.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
+#include <linux/kthread.h> /* for self test */
#include <linux/kmemcheck.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
+#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
@@ -444,6 +447,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
return ret;
}
+struct rb_irq_work {
+ struct irq_work work;
+ wait_queue_head_t waiters;
+ bool waiters_pending;
+};
+
/*
* head_page == tail_page && head == tail then buffer is empty.
*/
@@ -478,6 +487,8 @@ struct ring_buffer_per_cpu {
struct list_head new_pages; /* new pages to add */
struct work_struct update_pages_work;
struct completion update_done;
+
+ struct rb_irq_work irq_work;
};
struct ring_buffer {
@@ -497,6 +508,8 @@ struct ring_buffer {
struct notifier_block cpu_notify;
#endif
u64 (*clock)(void);
+
+ struct rb_irq_work irq_work;
};
struct ring_buffer_iter {
@@ -508,6 +521,118 @@ struct ring_buffer_iter {
u64 read_stamp;
};
+/*
+ * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
+ *
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * ring buffer waiters queue.
+ */
+static void rb_wake_up_waiters(struct irq_work *work)
+{
+ struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
+
+ wake_up_all(&rbwork->waiters);
+}
+
+/**
+ * ring_buffer_wait - wait for input to the ring buffer
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ */
+void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ DEFINE_WAIT(wait);
+ struct rb_irq_work *work;
+
+ /*
+ * Depending on what the caller is waiting for, either any
+ * data in any cpu buffer, or a specific buffer, put the
+ * caller on the appropriate wait queue.
+ */
+ if (cpu == RING_BUFFER_ALL_CPUS)
+ work = &buffer->irq_work;
+ else {
+ cpu_buffer = buffer->buffers[cpu];
+ work = &cpu_buffer->irq_work;
+ }
+
+
+ prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+
+ /*
+ * The events can happen in critical sections where
+ * checking a work queue can cause deadlocks.
+ * After adding a task to the queue, this flag is set
+ * only to notify events to try to wake up the queue
+ * using irq_work.
+ *
+ * We don't clear it even if the buffer is no longer
+ * empty. The flag only causes the next event to run
+ * irq_work to do the work queue wake up. The worse
+ * that can happen if we race with !trace_empty() is that
+ * an event will cause an irq_work to try to wake up
+ * an empty queue.
+ *
+ * There's no reason to protect this flag either, as
+ * the work queue and irq_work logic will do the necessary
+ * synchronization for the wake ups. The only thing
+ * that is necessary is that the wake up happens after
+ * a task has been queued. It's OK for spurious wake ups.
+ */
+ work->waiters_pending = true;
+
+ if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) ||
+ (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu)))
+ schedule();
+
+ finish_wait(&work->waiters, &wait);
+}
+
+/**
+ * ring_buffer_poll_wait - poll on buffer input
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ * @filp: the file descriptor
+ * @poll_table: The poll descriptor
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ *
+ * Returns POLLIN | POLLRDNORM if data exists in the buffers,
+ * zero otherwise.
+ */
+int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
+ struct file *filp, poll_table *poll_table)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct rb_irq_work *work;
+
+ if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+ (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+ return POLLIN | POLLRDNORM;
+
+ if (cpu == RING_BUFFER_ALL_CPUS)
+ work = &buffer->irq_work;
+ else {
+ cpu_buffer = buffer->buffers[cpu];
+ work = &cpu_buffer->irq_work;
+ }
+
+ work->waiters_pending = true;
+ poll_wait(filp, &work->waiters, poll_table);
+
+ if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+ (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+ return POLLIN | POLLRDNORM;
+ return 0;
+}
+
/* buffer may be either ring_buffer or ring_buffer_per_cpu */
#define RB_WARN_ON(b, cond) \
({ \
@@ -1063,6 +1188,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler);
init_completion(&cpu_buffer->update_done);
+ init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters);
+ init_waitqueue_head(&cpu_buffer->irq_work.waiters);
bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
@@ -1158,6 +1285,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
buffer->clock = trace_clock_local;
buffer->reader_lock_key = key;
+ init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters);
+ init_waitqueue_head(&buffer->irq_work.waiters);
+
/* need at least two pages */
if (nr_pages < 2)
nr_pages = 2;
@@ -1553,11 +1683,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
if (!cpu_buffer->nr_pages_to_update)
continue;
- if (cpu_online(cpu))
+ /* The update must run on the CPU that is being updated. */
+ preempt_disable();
+ if (cpu == smp_processor_id() || !cpu_online(cpu)) {
+ rb_update_pages(cpu_buffer);
+ cpu_buffer->nr_pages_to_update = 0;
+ } else {
+ /*
+ * Can not disable preemption for schedule_work_on()
+ * on PREEMPT_RT.
+ */
+ preempt_enable();
schedule_work_on(cpu,
&cpu_buffer->update_pages_work);
- else
- rb_update_pages(cpu_buffer);
+ preempt_disable();
+ }
+ preempt_enable();
}
/* wait for all the updates to complete */
@@ -1595,12 +1736,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
get_online_cpus();
- if (cpu_online(cpu_id)) {
+ preempt_disable();
+ /* The update must run on the CPU that is being updated. */
+ if (cpu_id == smp_processor_id() || !cpu_online(cpu_id))
+ rb_update_pages(cpu_buffer);
+ else {
+ /*
+ * Can not disable preemption for schedule_work_on()
+ * on PREEMPT_RT.
+ */
+ preempt_enable();
schedule_work_on(cpu_id,
&cpu_buffer->update_pages_work);
wait_for_completion(&cpu_buffer->update_done);
- } else
- rb_update_pages(cpu_buffer);
+ preempt_disable();
+ }
+ preempt_enable();
cpu_buffer->nr_pages_to_update = 0;
put_online_cpus();
@@ -2612,6 +2763,22 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
rb_end_commit(cpu_buffer);
}
+static __always_inline void
+rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
+{
+ if (buffer->irq_work.waiters_pending) {
+ buffer->irq_work.waiters_pending = false;
+ /* irq_work_queue() supplies it's own memory barriers */
+ irq_work_queue(&buffer->irq_work.work);
+ }
+
+ if (cpu_buffer->irq_work.waiters_pending) {
+ cpu_buffer->irq_work.waiters_pending = false;
+ /* irq_work_queue() supplies it's own memory barriers */
+ irq_work_queue(&cpu_buffer->irq_work.work);
+ }
+}
+
/**
* ring_buffer_unlock_commit - commit a reserved
* @buffer: The buffer to commit to
@@ -2631,6 +2798,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
rb_commit(cpu_buffer, event);
+ rb_wakeups(buffer, cpu_buffer);
+
trace_recursive_unlock();
preempt_enable_notrace();
@@ -2803,6 +2972,8 @@ int ring_buffer_write(struct ring_buffer *buffer,
rb_commit(cpu_buffer, event);
+ rb_wakeups(buffer, cpu_buffer);
+
ret = 0;
out:
preempt_enable_notrace();
@@ -4467,3 +4638,320 @@ static int rb_cpu_notify(struct notifier_block *self,
return NOTIFY_OK;
}
#endif
+
+#ifdef CONFIG_RING_BUFFER_STARTUP_TEST
+/*
+ * This is a basic integrity check of the ring buffer.
+ * Late in the boot cycle this test will run when configured in.
+ * It will kick off a thread per CPU that will go into a loop
+ * writing to the per cpu ring buffer various sizes of data.
+ * Some of the data will be large items, some small.
+ *
+ * Another thread is created that goes into a spin, sending out
+ * IPIs to the other CPUs to also write into the ring buffer.
+ * this is to test the nesting ability of the buffer.
+ *
+ * Basic stats are recorded and reported. If something in the
+ * ring buffer should happen that's not expected, a big warning
+ * is displayed and all ring buffers are disabled.
+ */
+static struct task_struct *rb_threads[NR_CPUS] __initdata;
+
+struct rb_test_data {
+ struct ring_buffer *buffer;
+ unsigned long events;
+ unsigned long bytes_written;
+ unsigned long bytes_alloc;
+ unsigned long bytes_dropped;
+ unsigned long events_nested;
+ unsigned long bytes_written_nested;
+ unsigned long bytes_alloc_nested;
+ unsigned long bytes_dropped_nested;
+ int min_size_nested;
+ int max_size_nested;
+ int max_size;
+ int min_size;
+ int cpu;
+ int cnt;
+};
+
+static struct rb_test_data rb_data[NR_CPUS] __initdata;
+
+/* 1 meg per cpu */
+#define RB_TEST_BUFFER_SIZE 1048576
+
+static char rb_string[] __initdata =
+ "abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\"
+ "?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890"
+ "!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv";
+
+static bool rb_test_started __initdata;
+
+struct rb_item {
+ int size;
+ char str[];
+};
+
+static __init int rb_write_something(struct rb_test_data *data, bool nested)
+{
+ struct ring_buffer_event *event;
+ struct rb_item *item;
+ bool started;
+ int event_len;
+ int size;
+ int len;
+ int cnt;
+
+ /* Have nested writes different that what is written */
+ cnt = data->cnt + (nested ? 27 : 0);
+
+ /* Multiply cnt by ~e, to make some unique increment */
+ size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1);
+
+ len = size + sizeof(struct rb_item);
+
+ started = rb_test_started;
+ /* read rb_test_started before checking buffer enabled */
+ smp_rmb();
+
+ event = ring_buffer_lock_reserve(data->buffer, len);
+ if (!event) {
+ /* Ignore dropped events before test starts. */
+ if (started) {
+ if (nested)
+ data->bytes_dropped += len;
+ else
+ data->bytes_dropped_nested += len;
+ }
+ return len;
+ }
+
+ event_len = ring_buffer_event_length(event);
+
+ if (RB_WARN_ON(data->buffer, event_len < len))
+ goto out;
+
+ item = ring_buffer_event_data(event);
+ item->size = size;
+ memcpy(item->str, rb_string, size);
+
+ if (nested) {
+ data->bytes_alloc_nested += event_len;
+ data->bytes_written_nested += len;
+ data->events_nested++;
+ if (!data->min_size_nested || len < data->min_size_nested)
+ data->min_size_nested = len;
+ if (len > data->max_size_nested)
+ data->max_size_nested = len;
+ } else {
+ data->bytes_alloc += event_len;
+ data->bytes_written += len;
+ data->events++;
+ if (!data->min_size || len < data->min_size)
+ data->max_size = len;
+ if (len > data->max_size)
+ data->max_size = len;
+ }
+
+ out:
+ ring_buffer_unlock_commit(data->buffer, event);
+
+ return 0;
+}
+
+static __init int rb_test(void *arg)
+{
+ struct rb_test_data *data = arg;
+
+ while (!kthread_should_stop()) {
+ rb_write_something(data, false);
+ data->cnt++;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* Now sleep between a min of 100-300us and a max of 1ms */
+ usleep_range(((data->cnt % 3) + 1) * 100, 1000);
+ }
+
+ return 0;
+}
+
+static __init void rb_ipi(void *ignore)
+{
+ struct rb_test_data *data;
+ int cpu = smp_processor_id();
+
+ data = &rb_data[cpu];
+ rb_write_something(data, true);
+}
+
+static __init int rb_hammer_test(void *arg)
+{
+ while (!kthread_should_stop()) {
+
+ /* Send an IPI to all cpus to write data! */
+ smp_call_function(rb_ipi, NULL, 1);
+ /* No sleep, but for non preempt, let others run */
+ schedule();
+ }
+
+ return 0;
+}
+
+static __init int test_ringbuffer(void)
+{
+ struct task_struct *rb_hammer;
+ struct ring_buffer *buffer;
+ int cpu;
+ int ret = 0;
+
+ pr_info("Running ring buffer tests...\n");
+
+ buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE);
+ if (WARN_ON(!buffer))
+ return 0;
+
+ /* Disable buffer so that threads can't write to it yet */
+ ring_buffer_record_off(buffer);
+
+ for_each_online_cpu(cpu) {
+ rb_data[cpu].buffer = buffer;
+ rb_data[cpu].cpu = cpu;
+ rb_data[cpu].cnt = cpu;
+ rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
+ "rbtester/%d", cpu);
+ if (WARN_ON(!rb_threads[cpu])) {
+ pr_cont("FAILED\n");
+ ret = -1;
+ goto out_free;
+ }
+
+ kthread_bind(rb_threads[cpu], cpu);
+ wake_up_process(rb_threads[cpu]);
+ }
+
+ /* Now create the rb hammer! */
+ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
+ if (WARN_ON(!rb_hammer)) {
+ pr_cont("FAILED\n");
+ ret = -1;
+ goto out_free;
+ }
+
+ ring_buffer_record_on(buffer);
+ /*
+ * Show buffer is enabled before setting rb_test_started.
+ * Yes there's a small race window where events could be
+ * dropped and the thread wont catch it. But when a ring
+ * buffer gets enabled, there will always be some kind of
+ * delay before other CPUs see it. Thus, we don't care about
+ * those dropped events. We care about events dropped after
+ * the threads see that the buffer is active.
+ */
+ smp_wmb();
+ rb_test_started = true;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* Just run for 10 seconds */;
+ schedule_timeout(10 * HZ);
+
+ kthread_stop(rb_hammer);
+
+ out_free:
+ for_each_online_cpu(cpu) {
+ if (!rb_threads[cpu])
+ break;
+ kthread_stop(rb_threads[cpu]);
+ }
+ if (ret) {
+ ring_buffer_free(buffer);
+ return ret;
+ }
+
+ /* Report! */
+ pr_info("finished\n");
+ for_each_online_cpu(cpu) {
+ struct ring_buffer_event *event;
+ struct rb_test_data *data = &rb_data[cpu];
+ struct rb_item *item;
+ unsigned long total_events;
+ unsigned long total_dropped;
+ unsigned long total_written;
+ unsigned long total_alloc;
+ unsigned long total_read = 0;
+ unsigned long total_size = 0;
+ unsigned long total_len = 0;
+ unsigned long total_lost = 0;
+ unsigned long lost;
+ int big_event_size;
+ int small_event_size;
+
+ ret = -1;
+
+ total_events = data->events + data->events_nested;
+ total_written = data->bytes_written + data->bytes_written_nested;
+ total_alloc = data->bytes_alloc + data->bytes_alloc_nested;
+ total_dropped = data->bytes_dropped + data->bytes_dropped_nested;
+
+ big_event_size = data->max_size + data->max_size_nested;
+ small_event_size = data->min_size + data->min_size_nested;
+
+ pr_info("CPU %d:\n", cpu);
+ pr_info(" events: %ld\n", total_events);
+ pr_info(" dropped bytes: %ld\n", total_dropped);
+ pr_info(" alloced bytes: %ld\n", total_alloc);
+ pr_info(" written bytes: %ld\n", total_written);
+ pr_info(" biggest event: %d\n", big_event_size);
+ pr_info(" smallest event: %d\n", small_event_size);
+
+ if (RB_WARN_ON(buffer, total_dropped))
+ break;
+
+ ret = 0;
+
+ while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) {
+ total_lost += lost;
+ item = ring_buffer_event_data(event);
+ total_len += ring_buffer_event_length(event);
+ total_size += item->size + sizeof(struct rb_item);
+ if (memcmp(&item->str[0], rb_string, item->size) != 0) {
+ pr_info("FAILED!\n");
+ pr_info("buffer had: %.*s\n", item->size, item->str);
+ pr_info("expected: %.*s\n", item->size, rb_string);
+ RB_WARN_ON(buffer, 1);
+ ret = -1;
+ break;
+ }
+ total_read++;
+ }
+ if (ret)
+ break;
+
+ ret = -1;
+
+ pr_info(" read events: %ld\n", total_read);
+ pr_info(" lost events: %ld\n", total_lost);
+ pr_info(" total events: %ld\n", total_lost + total_read);
+ pr_info(" recorded len bytes: %ld\n", total_len);
+ pr_info(" recorded size bytes: %ld\n", total_size);
+ if (total_lost)
+ pr_info(" With dropped events, record len and size may not match\n"
+ " alloced and written from above\n");
+ if (!total_lost) {
+ if (RB_WARN_ON(buffer, total_len != total_alloc ||
+ total_size != total_written))
+ break;
+ }
+ if (RB_WARN_ON(buffer, total_lost + total_read != total_events))
+ break;
+
+ ret = 0;
+ }
+ if (!ret)
+ pr_info("Ring buffer PASSED!\n");
+
+ ring_buffer_free(buffer);
+ return 0;
+}
+
+late_initcall(test_ringbuffer);
+#endif /* CONFIG_RING_BUFFER_STARTUP_TEST */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1f835a83cb2c..ae6fa2d1cdf7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1,7 +1,7 @@
/*
* ring buffer based function tracer
*
- * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2007-2012 Steven Rostedt <srostedt@redhat.com>
* Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
*
* Originally taken from the RT patch by:
@@ -19,7 +19,6 @@
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
-#include <linux/irq_work.h>
#include <linux/debugfs.h>
#include <linux/pagemap.h>
#include <linux/hardirq.h>
@@ -48,7 +47,7 @@
* On boot up, the ring buffer is set to the minimum size, so that
* we do not waste memory on systems that are not using tracing.
*/
-int ring_buffer_expanded;
+bool ring_buffer_expanded;
/*
* We need to change this state when a selftest is running.
@@ -87,14 +86,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
static DEFINE_PER_CPU(bool, trace_cmdline_save);
/*
- * When a reader is waiting for data, then this variable is
- * set to true.
- */
-static bool trace_wakeup_needed;
-
-static struct irq_work trace_work_wakeup;
-
-/*
* Kill all tracing for good (never come back).
* It is initialized to 1 but will turn to zero if the initialization
* of the tracer is successful. But that is the only place that sets
@@ -130,12 +121,14 @@ static int tracing_set_tracer(const char *buf);
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;
+static bool allocate_snapshot;
+
static int __init set_cmdline_ftrace(char *str)
{
- strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+ strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
/* We are using ftrace early, expand it */
- ring_buffer_expanded = 1;
+ ring_buffer_expanded = true;
return 1;
}
__setup("ftrace=", set_cmdline_ftrace);
@@ -156,13 +149,22 @@ static int __init set_ftrace_dump_on_oops(char *str)
}
__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
+static int __init boot_alloc_snapshot(char *str)
+{
+ allocate_snapshot = true;
+ /* We also need the main ring buffer expanded */
+ ring_buffer_expanded = true;
+ return 1;
+}
+__setup("alloc_snapshot", boot_alloc_snapshot);
+
static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static char *trace_boot_options __initdata;
static int __init set_trace_boot_options(char *str)
{
- strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+ strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
trace_boot_options = trace_boot_options_buf;
return 0;
}
@@ -189,7 +191,7 @@ unsigned long long ns2usecs(cycle_t nsec)
*/
static struct trace_array global_trace;
-static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+LIST_HEAD(ftrace_trace_arrays);
int filter_current_check_discard(struct ring_buffer *buffer,
struct ftrace_event_call *call, void *rec,
@@ -204,29 +206,15 @@ cycle_t ftrace_now(int cpu)
u64 ts;
/* Early boot up does not have a buffer yet */
- if (!global_trace.buffer)
+ if (!global_trace.trace_buffer.buffer)
return trace_clock_local();
- ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
- ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);
+ ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu);
+ ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts);
return ts;
}
-/*
- * The max_tr is used to snapshot the global_trace when a maximum
- * latency is reached. Some tracers will use this to store a maximum
- * trace while it continues examining live traces.
- *
- * The buffers for the max_tr are set up the same as the global_trace.
- * When a snapshot is taken, the link list of the max_tr is swapped
- * with the link list of the global_trace and the buffers are reset for
- * the global_trace so the tracing can continue.
- */
-static struct trace_array max_tr;
-
-static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
-
int tracing_is_enabled(void)
{
return tracing_is_on();
@@ -249,9 +237,6 @@ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
/* trace_types holds a link list of available tracers. */
static struct tracer *trace_types __read_mostly;
-/* current_trace points to the tracer that is currently active */
-static struct tracer *current_trace __read_mostly = &nop_trace;
-
/*
* trace_types_lock is used to protect the trace_types list.
*/
@@ -285,13 +270,13 @@ static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
static inline void trace_access_lock(int cpu)
{
- if (cpu == TRACE_PIPE_ALL_CPU) {
+ if (cpu == RING_BUFFER_ALL_CPUS) {
/* gain it for accessing the whole ring buffer. */
down_write(&all_cpu_access_lock);
} else {
/* gain it for accessing a cpu ring buffer. */
- /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+ /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */
down_read(&all_cpu_access_lock);
/* Secondly block other access to this @cpu ring buffer. */
@@ -301,7 +286,7 @@ static inline void trace_access_lock(int cpu)
static inline void trace_access_unlock(int cpu)
{
- if (cpu == TRACE_PIPE_ALL_CPU) {
+ if (cpu == RING_BUFFER_ALL_CPUS) {
up_write(&all_cpu_access_lock);
} else {
mutex_unlock(&per_cpu(cpu_access_lock, cpu));
@@ -339,30 +324,11 @@ static inline void trace_access_lock_init(void)
#endif
-/* trace_wait is a waitqueue for tasks blocked on trace_poll */
-static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
-
/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
- TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;
-
-static int trace_stop_count;
-static DEFINE_RAW_SPINLOCK(tracing_start_lock);
-
-/**
- * trace_wake_up - wake up tasks waiting for trace input
- *
- * Schedules a delayed work to wake up any task that is blocked on the
- * trace_wait queue. These is used with trace_poll for tasks polling the
- * trace.
- */
-static void trace_wake_up(struct irq_work *work)
-{
- wake_up_all(&trace_wait);
-
-}
+ TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
/**
* tracing_on - enable tracing buffers
@@ -372,8 +338,8 @@ static void trace_wake_up(struct irq_work *work)
*/
void tracing_on(void)
{
- if (global_trace.buffer)
- ring_buffer_record_on(global_trace.buffer);
+ if (global_trace.trace_buffer.buffer)
+ ring_buffer_record_on(global_trace.trace_buffer.buffer);
/*
* This flag is only looked at when buffers haven't been
* allocated yet. We don't really care about the race
@@ -385,6 +351,196 @@ void tracing_on(void)
EXPORT_SYMBOL_GPL(tracing_on);
/**
+ * __trace_puts - write a constant string into the trace buffer.
+ * @ip: The address of the caller
+ * @str: The constant string to write
+ * @size: The size of the string.
+ */
+int __trace_puts(unsigned long ip, const char *str, int size)
+{
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct print_entry *entry;
+ unsigned long irq_flags;
+ int alloc;
+
+ alloc = sizeof(*entry) + size + 2; /* possible \n added */
+
+ local_save_flags(irq_flags);
+ buffer = global_trace.trace_buffer.buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
+ irq_flags, preempt_count());
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+
+ memcpy(&entry->buf, str, size);
+
+ /* Add a newline if necessary */
+ if (entry->buf[size - 1] != '\n') {
+ entry->buf[size] = '\n';
+ entry->buf[size + 1] = '\0';
+ } else
+ entry->buf[size] = '\0';
+
+ __buffer_unlock_commit(buffer, event);
+
+ return size;
+}
+EXPORT_SYMBOL_GPL(__trace_puts);
+
+/**
+ * __trace_bputs - write the pointer to a constant string into trace buffer
+ * @ip: The address of the caller
+ * @str: The constant string to write to the buffer to
+ */
+int __trace_bputs(unsigned long ip, const char *str)
+{
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct bputs_entry *entry;
+ unsigned long irq_flags;
+ int size = sizeof(struct bputs_entry);
+
+ local_save_flags(irq_flags);
+ buffer = global_trace.trace_buffer.buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
+ irq_flags, preempt_count());
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->str = str;
+
+ __buffer_unlock_commit(buffer, event);
+
+ return 1;
+}
+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)
+{
+ struct trace_array *tr = &global_trace;
+ struct tracer *tracer = tr->current_trace;
+ unsigned long flags;
+
+ if (in_nmi()) {
+ internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n");
+ internal_trace_puts("*** snapshot is being ignored ***\n");
+ return;
+ }
+
+ if (!tr->allocated_snapshot) {
+ internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n");
+ internal_trace_puts("*** stopping trace here! ***\n");
+ tracing_off();
+ return;
+ }
+
+ /* Note, snapshot can not be used when the tracer uses it */
+ if (tracer->use_max_tr) {
+ internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n");
+ internal_trace_puts("*** Can not use snapshot (sorry) ***\n");
+ return;
+ }
+
+ local_irq_save(flags);
+ update_max_tr(tr, current, smp_processor_id());
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+
+static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
+ struct trace_buffer *size_buf, int cpu_id);
+static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
+
+static int alloc_snapshot(struct trace_array *tr)
+{
+ int ret;
+
+ if (!tr->allocated_snapshot) {
+
+ /* allocate spare buffer */
+ ret = resize_buffer_duplicate_size(&tr->max_buffer,
+ &tr->trace_buffer, RING_BUFFER_ALL_CPUS);
+ if (ret < 0)
+ return ret;
+
+ tr->allocated_snapshot = true;
+ }
+
+ return 0;
+}
+
+void free_snapshot(struct trace_array *tr)
+{
+ /*
+ * We don't free the ring buffer. instead, resize it because
+ * The max_tr ring buffer has some state (e.g. ring->clock) and
+ * we want preserve it.
+ */
+ ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
+ set_buffer_entries(&tr->max_buffer, 1);
+ tracing_reset_online_cpus(&tr->max_buffer);
+ tr->allocated_snapshot = false;
+}
+
+/**
+ * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
+ *
+ * This is similar to trace_snapshot(), but it will allocate the
+ * snapshot buffer if it isn't already allocated. Use this only
+ * where it is safe to sleep, as the allocation may sleep.
+ *
+ * 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.
+ */
+void tracing_snapshot_alloc(void)
+{
+ struct trace_array *tr = &global_trace;
+ int ret;
+
+ ret = alloc_snapshot(tr);
+ if (WARN_ON(ret < 0))
+ return;
+
+ tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#else
+void tracing_snapshot(void)
+{
+ WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+void tracing_snapshot_alloc(void)
+{
+ /* Give warning */
+ tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+/**
* tracing_off - turn off tracing buffers
*
* This function stops the tracing buffers from recording data.
@@ -394,8 +550,8 @@ EXPORT_SYMBOL_GPL(tracing_on);
*/
void tracing_off(void)
{
- if (global_trace.buffer)
- ring_buffer_record_off(global_trace.buffer);
+ if (global_trace.trace_buffer.buffer)
+ ring_buffer_record_off(global_trace.trace_buffer.buffer);
/*
* This flag is only looked at when buffers haven't been
* allocated yet. We don't really care about the race
@@ -411,8 +567,8 @@ EXPORT_SYMBOL_GPL(tracing_off);
*/
int tracing_is_on(void)
{
- if (global_trace.buffer)
- return ring_buffer_record_is_on(global_trace.buffer);
+ if (global_trace.trace_buffer.buffer)
+ return ring_buffer_record_is_on(global_trace.trace_buffer.buffer);
return !global_trace.buffer_disabled;
}
EXPORT_SYMBOL_GPL(tracing_is_on);
@@ -479,6 +635,7 @@ static const char *trace_options[] = {
"disable_on_free",
"irq-info",
"markers",
+ "function-trace",
NULL
};
@@ -490,6 +647,8 @@ static struct {
{ trace_clock_local, "local", 1 },
{ trace_clock_global, "global", 1 },
{ trace_clock_counter, "counter", 0 },
+ { trace_clock_jiffies, "uptime", 1 },
+ { trace_clock, "perf", 1 },
ARCH_TRACE_CLOCKS
};
@@ -670,13 +829,14 @@ unsigned long __read_mostly tracing_max_latency;
static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct trace_array_cpu *data = tr->data[cpu];
- struct trace_array_cpu *max_data;
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
+ struct trace_buffer *max_buf = &tr->max_buffer;
+ struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu);
+ struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu);
- max_tr.cpu = cpu;
- max_tr.time_start = data->preempt_timestamp;
+ max_buf->cpu = cpu;
+ max_buf->time_start = data->preempt_timestamp;
- max_data = max_tr.data[cpu];
max_data->saved_latency = tracing_max_latency;
max_data->critical_start = data->critical_start;
max_data->critical_end = data->critical_end;
@@ -704,23 +864,24 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf = tr->buffer;
+ struct ring_buffer *buf;
- if (trace_stop_count)
+ if (tr->stop_count)
return;
WARN_ON_ONCE(!irqs_disabled());
- if (!current_trace->allocated_snapshot) {
+ if (!tr->allocated_snapshot) {
/* Only the nop tracer should hit this when disabling */
- WARN_ON_ONCE(current_trace != &nop_trace);
+ WARN_ON_ONCE(tr->current_trace != &nop_trace);
return;
}
arch_spin_lock(&ftrace_max_lock);
- tr->buffer = max_tr.buffer;
- max_tr.buffer = buf;
+ buf = tr->trace_buffer.buffer;
+ tr->trace_buffer.buffer = tr->max_buffer.buffer;
+ tr->max_buffer.buffer = buf;
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&ftrace_max_lock);
@@ -739,16 +900,19 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
int ret;
- if (trace_stop_count)
+ if (tr->stop_count)
return;
WARN_ON_ONCE(!irqs_disabled());
- if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
+ if (!tr->allocated_snapshot) {
+ /* Only the nop tracer should hit this when disabling */
+ WARN_ON_ONCE(tr->current_trace != &nop_trace);
return;
+ }
arch_spin_lock(&ftrace_max_lock);
- ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
+ ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
if (ret == -EBUSY) {
/*
@@ -757,7 +921,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
* the max trace buffer (no one writes directly to it)
* and flag that it failed.
*/
- trace_array_printk(&max_tr, _THIS_IP_,
+ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
"Failed to swap buffers due to commit in progress\n");
}
@@ -770,37 +934,78 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
static void default_wait_pipe(struct trace_iterator *iter)
{
- DEFINE_WAIT(wait);
+ /* Iterators are static, they should be filled or empty */
+ if (trace_buffer_iter(iter, iter->cpu_file))
+ return;
+
+ ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+}
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+static int run_tracer_selftest(struct tracer *type)
+{
+ struct trace_array *tr = &global_trace;
+ struct tracer *saved_tracer = tr->current_trace;
+ int ret;
- prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
+ if (!type->selftest || tracing_selftest_disabled)
+ return 0;
/*
- * The events can happen in critical sections where
- * checking a work queue can cause deadlocks.
- * After adding a task to the queue, this flag is set
- * only to notify events to try to wake up the queue
- * using irq_work.
- *
- * We don't clear it even if the buffer is no longer
- * empty. The flag only causes the next event to run
- * irq_work to do the work queue wake up. The worse
- * that can happen if we race with !trace_empty() is that
- * an event will cause an irq_work to try to wake up
- * an empty queue.
- *
- * There's no reason to protect this flag either, as
- * the work queue and irq_work logic will do the necessary
- * synchronization for the wake ups. The only thing
- * that is necessary is that the wake up happens after
- * a task has been queued. It's OK for spurious wake ups.
+ * 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
+ * internal tracing to verify that everything is in order.
+ * If we fail, we do not register this tracer.
*/
- trace_wakeup_needed = true;
+ tracing_reset_online_cpus(&tr->trace_buffer);
- if (trace_empty(iter))
- schedule();
+ tr->current_trace = type;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (type->use_max_tr) {
+ /* If we expanded the buffers, make sure the max is expanded too */
+ if (ring_buffer_expanded)
+ ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size,
+ RING_BUFFER_ALL_CPUS);
+ tr->allocated_snapshot = true;
+ }
+#endif
+
+ /* the test is responsible for initializing and enabling */
+ pr_info("Testing tracer %s: ", type->name);
+ ret = type->selftest(type, tr);
+ /* the test is responsible for resetting too */
+ tr->current_trace = saved_tracer;
+ if (ret) {
+ printk(KERN_CONT "FAILED!\n");
+ /* Add the warning after printing 'FAILED' */
+ WARN_ON(1);
+ return -1;
+ }
+ /* Only reset on passing, to avoid touching corrupted buffers */
+ tracing_reset_online_cpus(&tr->trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (type->use_max_tr) {
+ tr->allocated_snapshot = false;
- finish_wait(&trace_wait, &wait);
+ /* Shrink the max buffer again */
+ if (ring_buffer_expanded)
+ ring_buffer_resize(tr->max_buffer.buffer, 1,
+ RING_BUFFER_ALL_CPUS);
+ }
+#endif
+
+ printk(KERN_CONT "PASSED\n");
+ return 0;
+}
+#else
+static inline int run_tracer_selftest(struct tracer *type)
+{
+ return 0;
}
+#endif /* CONFIG_FTRACE_STARTUP_TEST */
/**
* register_tracer - register a tracer with the ftrace system.
@@ -847,57 +1052,9 @@ int register_tracer(struct tracer *type)
if (!type->wait_pipe)
type->wait_pipe = default_wait_pipe;
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
- if (type->selftest && !tracing_selftest_disabled) {
- struct tracer *saved_tracer = current_trace;
- struct trace_array *tr = &global_trace;
-
- /*
- * 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
- * internal tracing to verify that everything is in order.
- * If we fail, we do not register this tracer.
- */
- tracing_reset_online_cpus(tr);
-
- current_trace = type;
-
- if (type->use_max_tr) {
- /* If we expanded the buffers, make sure the max is expanded too */
- if (ring_buffer_expanded)
- ring_buffer_resize(max_tr.buffer, trace_buf_size,
- RING_BUFFER_ALL_CPUS);
- type->allocated_snapshot = true;
- }
-
- /* the test is responsible for initializing and enabling */
- pr_info("Testing tracer %s: ", type->name);
- ret = type->selftest(type, tr);
- /* the test is responsible for resetting too */
- current_trace = saved_tracer;
- if (ret) {
- printk(KERN_CONT "FAILED!\n");
- /* Add the warning after printing 'FAILED' */
- WARN_ON(1);
- goto out;
- }
- /* Only reset on passing, to avoid touching corrupted buffers */
- tracing_reset_online_cpus(tr);
-
- if (type->use_max_tr) {
- type->allocated_snapshot = false;
-
- /* Shrink the max buffer again */
- if (ring_buffer_expanded)
- ring_buffer_resize(max_tr.buffer, 1,
- RING_BUFFER_ALL_CPUS);
- }
-
- printk(KERN_CONT "PASSED\n");
- }
-#endif
+ ret = run_tracer_selftest(type);
+ if (ret < 0)
+ goto out;
type->next = trace_types;
trace_types = type;
@@ -917,7 +1074,7 @@ int register_tracer(struct tracer *type)
tracing_set_tracer(type->name);
default_bootup_tracer = NULL;
/* disable other selftests, since this will break it. */
- tracing_selftest_disabled = 1;
+ tracing_selftest_disabled = true;
#ifdef CONFIG_FTRACE_STARTUP_TEST
printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
type->name);
@@ -927,9 +1084,9 @@ int register_tracer(struct tracer *type)
return ret;
}
-void tracing_reset(struct trace_array *tr, int cpu)
+void tracing_reset(struct trace_buffer *buf, int cpu)
{
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = buf->buffer;
if (!buffer)
return;
@@ -943,9 +1100,9 @@ void tracing_reset(struct trace_array *tr, int cpu)
ring_buffer_record_enable(buffer);
}
-void tracing_reset_online_cpus(struct trace_array *tr)
+void tracing_reset_online_cpus(struct trace_buffer *buf)
{
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = buf->buffer;
int cpu;
if (!buffer)
@@ -956,7 +1113,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
/* Make sure all commits have finished */
synchronize_sched();
- tr->time_start = ftrace_now(tr->cpu);
+ buf->time_start = ftrace_now(buf->cpu);
for_each_online_cpu(cpu)
ring_buffer_reset_cpu(buffer, cpu);
@@ -966,12 +1123,21 @@ void tracing_reset_online_cpus(struct trace_array *tr)
void tracing_reset_current(int cpu)
{
- tracing_reset(&global_trace, cpu);
+ tracing_reset(&global_trace.trace_buffer, cpu);
}
-void tracing_reset_current_online_cpus(void)
+void tracing_reset_all_online_cpus(void)
{
- tracing_reset_online_cpus(&global_trace);
+ struct trace_array *tr;
+
+ mutex_lock(&trace_types_lock);
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ tracing_reset_online_cpus(&tr->trace_buffer);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ tracing_reset_online_cpus(&tr->max_buffer);
+#endif
+ }
+ mutex_unlock(&trace_types_lock);
}
#define SAVED_CMDLINES 128
@@ -994,7 +1160,7 @@ static void trace_init_cmdlines(void)
int is_tracing_stopped(void)
{
- return trace_stop_count;
+ return global_trace.stop_count;
}
/**
@@ -1026,12 +1192,12 @@ void tracing_start(void)
if (tracing_disabled)
return;
- raw_spin_lock_irqsave(&tracing_start_lock, flags);
- if (--trace_stop_count) {
- if (trace_stop_count < 0) {
+ raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+ if (--global_trace.stop_count) {
+ if (global_trace.stop_count < 0) {
/* Someone screwed up their debugging */
WARN_ON_ONCE(1);
- trace_stop_count = 0;
+ global_trace.stop_count = 0;
}
goto out;
}
@@ -1039,19 +1205,52 @@ void tracing_start(void)
/* Prevent the buffers from switching */
arch_spin_lock(&ftrace_max_lock);
- buffer = global_trace.buffer;
+ buffer = global_trace.trace_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
- buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+ buffer = global_trace.max_buffer.buffer;
if (buffer)
ring_buffer_record_enable(buffer);
+#endif
arch_spin_unlock(&ftrace_max_lock);
ftrace_start();
out:
- raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+ raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_start_tr(struct trace_array *tr)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ if (tracing_disabled)
+ return;
+
+ /* If global, we need to also start the max tracer */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ return tracing_start();
+
+ raw_spin_lock_irqsave(&tr->start_lock, flags);
+
+ if (--tr->stop_count) {
+ if (tr->stop_count < 0) {
+ /* Someone screwed up their debugging */
+ WARN_ON_ONCE(1);
+ tr->stop_count = 0;
+ }
+ goto out;
+ }
+
+ buffer = tr->trace_buffer.buffer;
+ if (buffer)
+ ring_buffer_record_enable(buffer);
+
+ out:
+ raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}
/**
@@ -1066,25 +1265,48 @@ void tracing_stop(void)
unsigned long flags;
ftrace_stop();
- raw_spin_lock_irqsave(&tracing_start_lock, flags);
- if (trace_stop_count++)
+ raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+ if (global_trace.stop_count++)
goto out;
/* Prevent the buffers from switching */
arch_spin_lock(&ftrace_max_lock);
- buffer = global_trace.buffer;
+ buffer = global_trace.trace_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
- buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+ buffer = global_trace.max_buffer.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
+#endif
arch_spin_unlock(&ftrace_max_lock);
out:
- raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+ raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ /* If global, we need to also stop the max tracer */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ return tracing_stop();
+
+ raw_spin_lock_irqsave(&tr->start_lock, flags);
+ if (tr->stop_count++)
+ goto out;
+
+ buffer = tr->trace_buffer.buffer;
+ if (buffer)
+ ring_buffer_record_disable(buffer);
+
+ out:
+ raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}
void trace_stop_cmdline_recording(void);
@@ -1217,11 +1439,6 @@ void
__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
{
__this_cpu_write(trace_cmdline_save, true);
- if (trace_wakeup_needed) {
- trace_wakeup_needed = false;
- /* irq_work_queue() supplies it's own memory barriers */
- irq_work_queue(&trace_work_wakeup);
- }
ring_buffer_unlock_commit(buffer, event);
}
@@ -1245,11 +1462,23 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
struct ring_buffer_event *
+trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
+ struct ftrace_event_file *ftrace_file,
+ int type, unsigned long len,
+ unsigned long flags, int pc)
+{
+ *current_rb = ftrace_file->tr->trace_buffer.buffer;
+ return trace_buffer_lock_reserve(*current_rb,
+ type, len, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
+
+struct ring_buffer_event *
trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
int type, unsigned long len,
unsigned long flags, int pc)
{
- *current_rb = global_trace.buffer;
+ *current_rb = global_trace.trace_buffer.buffer;
return trace_buffer_lock_reserve(*current_rb,
type, len, flags, pc);
}
@@ -1288,7 +1517,7 @@ trace_function(struct trace_array *tr,
int pc)
{
struct ftrace_event_call *call = &event_function;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ring_buffer_event *event;
struct ftrace_entry *entry;
@@ -1429,13 +1658,14 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc)
{
- __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
+ __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL);
}
/**
* trace_dump_stack - record a stack back trace in the trace buffer
+ * @skip: Number of functions to skip (helper handlers)
*/
-void trace_dump_stack(void)
+void trace_dump_stack(int skip)
{
unsigned long flags;
@@ -1444,8 +1674,13 @@ void trace_dump_stack(void)
local_save_flags(flags);
- /* skipping 3 traces, seems to get us at the caller of this function */
- __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
+ /*
+ * Skip 3 more, seems to get us at the caller of
+ * this function.
+ */
+ skip += 3;
+ __ftrace_trace_stack(global_trace.trace_buffer.buffer,
+ flags, skip, preempt_count(), NULL);
}
static DEFINE_PER_CPU(int, user_stack_count);
@@ -1615,7 +1850,7 @@ void trace_printk_init_buffers(void)
* directly here. If the global_trace.buffer is already
* allocated here, then this was called by module code.
*/
- if (global_trace.buffer)
+ if (global_trace.trace_buffer.buffer)
tracing_start_cmdline_record();
}
@@ -1675,7 +1910,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
local_save_flags(flags);
size = sizeof(*entry) + sizeof(u32) * len;
- buffer = tr->buffer;
+ buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
flags, pc);
if (!event)
@@ -1698,27 +1933,12 @@ out:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
-int trace_array_printk(struct trace_array *tr,
- unsigned long ip, const char *fmt, ...)
-{
- int ret;
- va_list ap;
-
- if (!(trace_flags & TRACE_ITER_PRINTK))
- return 0;
-
- va_start(ap, fmt);
- ret = trace_array_vprintk(tr, ip, fmt, ap);
- va_end(ap);
- return ret;
-}
-
-int trace_array_vprintk(struct trace_array *tr,
- unsigned long ip, const char *fmt, va_list args)
+static int
+__trace_array_vprintk(struct ring_buffer *buffer,
+ unsigned long ip, const char *fmt, va_list args)
{
struct ftrace_event_call *call = &event_print;
struct ring_buffer_event *event;
- struct ring_buffer *buffer;
int len = 0, size, pc;
struct print_entry *entry;
unsigned long flags;
@@ -1746,7 +1966,6 @@ int trace_array_vprintk(struct trace_array *tr,
local_save_flags(flags);
size = sizeof(*entry) + len + 1;
- buffer = tr->buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
flags, pc);
if (!event)
@@ -1767,6 +1986,42 @@ int trace_array_vprintk(struct trace_array *tr,
return len;
}
+int trace_array_vprintk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, va_list args)
+{
+ return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
+}
+
+int trace_array_printk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ va_start(ap, fmt);
+ ret = trace_array_vprintk(tr, ip, fmt, ap);
+ va_end(ap);
+ return ret;
+}
+
+int trace_array_printk_buf(struct ring_buffer *buffer,
+ unsigned long ip, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ va_start(ap, fmt);
+ ret = __trace_array_vprintk(buffer, ip, fmt, ap);
+ va_end(ap);
+ return ret;
+}
+
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -1792,7 +2047,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
if (buf_iter)
event = ring_buffer_iter_peek(buf_iter, ts);
else
- event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+ event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts,
lost_events);
if (event) {
@@ -1807,7 +2062,7 @@ static struct trace_entry *
__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
unsigned long *missing_events, u64 *ent_ts)
{
- struct ring_buffer *buffer = iter->tr->buffer;
+ struct ring_buffer *buffer = iter->trace_buffer->buffer;
struct trace_entry *ent, *next = NULL;
unsigned long lost_events = 0, next_lost = 0;
int cpu_file = iter->cpu_file;
@@ -1820,7 +2075,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
* If we are in a per_cpu trace file, don't bother by iterating over
* all cpu and peek directly.
*/
- if (cpu_file > TRACE_PIPE_ALL_CPU) {
+ if (cpu_file > RING_BUFFER_ALL_CPUS) {
if (ring_buffer_empty_cpu(buffer, cpu_file))
return NULL;
ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
@@ -1884,7 +2139,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter)
static void trace_consume(struct trace_iterator *iter)
{
- ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+ ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts,
&iter->lost_events);
}
@@ -1917,13 +2172,12 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
void tracing_iter_reset(struct trace_iterator *iter, int cpu)
{
- struct trace_array *tr = iter->tr;
struct ring_buffer_event *event;
struct ring_buffer_iter *buf_iter;
unsigned long entries = 0;
u64 ts;
- tr->data[cpu]->skipped_entries = 0;
+ per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0;
buf_iter = trace_buffer_iter(iter, cpu);
if (!buf_iter)
@@ -1937,13 +2191,13 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
* by the timestamp being before the start of the buffer.
*/
while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
- if (ts >= iter->tr->time_start)
+ if (ts >= iter->trace_buffer->time_start)
break;
entries++;
ring_buffer_read(buf_iter, NULL);
}
- tr->data[cpu]->skipped_entries = entries;
+ per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries;
}
/*
@@ -1953,6 +2207,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
static void *s_start(struct seq_file *m, loff_t *pos)
{
struct trace_iterator *iter = m->private;
+ struct trace_array *tr = iter->tr;
int cpu_file = iter->cpu_file;
void *p = NULL;
loff_t l = 0;
@@ -1965,12 +2220,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
* will point to the same string as current_trace->name.
*/
mutex_lock(&trace_types_lock);
- if (unlikely(current_trace && iter->trace->name != current_trace->name))
- *iter->trace = *current_trace;
+ if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
+ *iter->trace = *tr->current_trace;
mutex_unlock(&trace_types_lock);
+#ifdef CONFIG_TRACER_MAX_TRACE
if (iter->snapshot && iter->trace->use_max_tr)
return ERR_PTR(-EBUSY);
+#endif
if (!iter->snapshot)
atomic_inc(&trace_record_cmdline_disabled);
@@ -1980,7 +2237,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
iter->cpu = 0;
iter->idx = -1;
- if (cpu_file == TRACE_PIPE_ALL_CPU) {
+ if (cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu)
tracing_iter_reset(iter, cpu);
} else
@@ -2012,17 +2269,21 @@ static void s_stop(struct seq_file *m, void *p)
{
struct trace_iterator *iter = m->private;
+#ifdef CONFIG_TRACER_MAX_TRACE
if (iter->snapshot && iter->trace->use_max_tr)
return;
+#endif
if (!iter->snapshot)
atomic_dec(&trace_record_cmdline_disabled);
+
trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
}
static void
-get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries)
+get_total_entries(struct trace_buffer *buf,
+ unsigned long *total, unsigned long *entries)
{
unsigned long count;
int cpu;
@@ -2031,19 +2292,19 @@ get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *e
*entries = 0;
for_each_tracing_cpu(cpu) {
- count = ring_buffer_entries_cpu(tr->buffer, cpu);
+ count = ring_buffer_entries_cpu(buf->buffer, cpu);
/*
* If this buffer has skipped entries, then we hold all
* entries for the trace and we need to ignore the
* ones before the time stamp.
*/
- if (tr->data[cpu]->skipped_entries) {
- count -= tr->data[cpu]->skipped_entries;
+ if (per_cpu_ptr(buf->data, cpu)->skipped_entries) {
+ count -= per_cpu_ptr(buf->data, cpu)->skipped_entries;
/* total is the same as the entries */
*total += count;
} else
*total += count +
- ring_buffer_overrun_cpu(tr->buffer, cpu);
+ ring_buffer_overrun_cpu(buf->buffer, cpu);
*entries += count;
}
}
@@ -2060,27 +2321,27 @@ static void print_lat_help_header(struct seq_file *m)
seq_puts(m, "# \\ / ||||| \\ | / \n");
}
-static void print_event_info(struct trace_array *tr, struct seq_file *m)
+static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
{
unsigned long total;
unsigned long entries;
- get_total_entries(tr, &total, &entries);
+ get_total_entries(buf, &total, &entries);
seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n",
entries, total, num_online_cpus());
seq_puts(m, "#\n");
}
-static void print_func_help_header(struct trace_array *tr, struct seq_file *m)
+static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
{
- print_event_info(tr, m);
+ print_event_info(buf, m);
seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n");
seq_puts(m, "# | | | | |\n");
}
-static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m)
+static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
- print_event_info(tr, m);
+ print_event_info(buf, m);
seq_puts(m, "# _-----=> irqs-off\n");
seq_puts(m, "# / _----=> need-resched\n");
seq_puts(m, "# | / _---=> hardirq/softirq\n");
@@ -2094,16 +2355,16 @@ void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
- struct trace_array *tr = iter->tr;
- struct trace_array_cpu *data = tr->data[tr->cpu];
- struct tracer *type = current_trace;
+ struct trace_buffer *buf = iter->trace_buffer;
+ struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu);
+ struct tracer *type = iter->trace;
unsigned long entries;
unsigned long total;
const char *name = "preemption";
name = type->name;
- get_total_entries(tr, &total, &entries);
+ get_total_entries(buf, &total, &entries);
seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
name, UTS_RELEASE);
@@ -2114,7 +2375,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
nsecs_to_usecs(data->saved_latency),
entries,
total,
- tr->cpu,
+ buf->cpu,
#if defined(CONFIG_PREEMPT_NONE)
"server",
#elif defined(CONFIG_PREEMPT_VOLUNTARY)
@@ -2165,7 +2426,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
if (cpumask_test_cpu(iter->cpu, iter->started))
return;
- if (iter->tr->data[iter->cpu]->skipped_entries)
+ if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
return;
cpumask_set_cpu(iter->cpu, iter->started);
@@ -2288,14 +2549,14 @@ int trace_empty(struct trace_iterator *iter)
int cpu;
/* If we are looking at one CPU buffer, only check that one */
- if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
+ if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
cpu = iter->cpu_file;
buf_iter = trace_buffer_iter(iter, cpu);
if (buf_iter) {
if (!ring_buffer_iter_empty(buf_iter))
return 0;
} else {
- if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+ if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
return 0;
}
return 1;
@@ -2307,7 +2568,7 @@ int trace_empty(struct trace_iterator *iter)
if (!ring_buffer_iter_empty(buf_iter))
return 0;
} else {
- if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+ if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
return 0;
}
}
@@ -2331,6 +2592,11 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
return ret;
}
+ if (iter->ent->type == TRACE_BPUTS &&
+ trace_flags & TRACE_ITER_PRINTK &&
+ trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+ return trace_print_bputs_msg_only(iter);
+
if (iter->ent->type == TRACE_BPRINT &&
trace_flags & TRACE_ITER_PRINTK &&
trace_flags & TRACE_ITER_PRINTK_MSGONLY)
@@ -2385,9 +2651,9 @@ void trace_default_header(struct seq_file *m)
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->tr, m);
+ print_func_help_header_irq(iter->trace_buffer, m);
else
- print_func_help_header(iter->tr, m);
+ print_func_help_header(iter->trace_buffer, m);
}
}
}
@@ -2401,14 +2667,8 @@ static void test_ftrace_alive(struct seq_file *m)
}
#ifdef CONFIG_TRACER_MAX_TRACE
-static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+static void show_snapshot_main_help(struct seq_file *m)
{
- if (iter->trace->allocated_snapshot)
- seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
- else
- seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
-
- seq_printf(m, "# Snapshot commands:\n");
seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
seq_printf(m, "# Takes a snapshot of the main buffer.\n");
@@ -2416,6 +2676,35 @@ static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
seq_printf(m, "# (Doesn't have to be '2' works with any number that\n");
seq_printf(m, "# is not a '0' or '1')\n");
}
+
+static void show_snapshot_percpu_help(struct seq_file *m)
+{
+ seq_printf(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n");
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+ seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+ seq_printf(m, "# Takes a snapshot of the main buffer for this cpu.\n");
+#else
+ seq_printf(m, "# echo 1 > snapshot : Not supported with this kernel.\n");
+ seq_printf(m, "# Must use main snapshot file to allocate.\n");
+#endif
+ seq_printf(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n");
+ seq_printf(m, "# (Doesn't have to be '2' works with any number that\n");
+ seq_printf(m, "# is not a '0' or '1')\n");
+}
+
+static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+{
+ if (iter->tr->allocated_snapshot)
+ seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
+ else
+ seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
+
+ seq_printf(m, "# Snapshot commands:\n");
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+ show_snapshot_main_help(m);
+ else
+ show_snapshot_percpu_help(m);
+}
#else
/* Should never be called */
static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
@@ -2475,7 +2764,8 @@ static const struct seq_operations tracer_seq_ops = {
static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, bool snapshot)
{
- long cpu_file = (long) inode->i_private;
+ struct trace_cpu *tc = inode->i_private;
+ struct trace_array *tr = tc->tr;
struct trace_iterator *iter;
int cpu;
@@ -2500,26 +2790,31 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
if (!iter->trace)
goto fail;
- *iter->trace = *current_trace;
+ *iter->trace = *tr->current_trace;
if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
goto fail;
- if (current_trace->print_max || snapshot)
- iter->tr = &max_tr;
+ iter->tr = tr;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ /* Currently only the top directory has a snapshot */
+ if (tr->current_trace->print_max || snapshot)
+ iter->trace_buffer = &tr->max_buffer;
else
- iter->tr = &global_trace;
+#endif
+ iter->trace_buffer = &tr->trace_buffer;
iter->snapshot = snapshot;
iter->pos = -1;
mutex_init(&iter->mutex);
- iter->cpu_file = cpu_file;
+ iter->cpu_file = tc->cpu;
/* Notify the tracer early; before we stop tracing. */
if (iter->trace && iter->trace->open)
iter->trace->open(iter);
/* Annotate start of buffers if we had overruns */
- if (ring_buffer_overruns(iter->tr->buffer))
+ if (ring_buffer_overruns(iter->trace_buffer->buffer))
iter->iter_flags |= TRACE_FILE_ANNOTATE;
/* Output in nanoseconds only if we are using a clock in nanoseconds. */
@@ -2528,12 +2823,12 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
/* stop the trace while dumping if we are not opening "snapshot" */
if (!iter->snapshot)
- tracing_stop();
+ tracing_stop_tr(tr);
- if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->tr->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
}
ring_buffer_read_prepare_sync();
for_each_tracing_cpu(cpu) {
@@ -2543,12 +2838,14 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->tr->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
ring_buffer_read_prepare_sync();
ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
}
+ tr->ref++;
+
mutex_unlock(&trace_types_lock);
return iter;
@@ -2575,14 +2872,20 @@ static int tracing_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
struct trace_iterator *iter;
+ struct trace_array *tr;
int cpu;
if (!(file->f_mode & FMODE_READ))
return 0;
iter = m->private;
+ tr = iter->tr;
mutex_lock(&trace_types_lock);
+
+ WARN_ON(!tr->ref);
+ tr->ref--;
+
for_each_tracing_cpu(cpu) {
if (iter->buffer_iter[cpu])
ring_buffer_read_finish(iter->buffer_iter[cpu]);
@@ -2593,7 +2896,7 @@ static int tracing_release(struct inode *inode, struct file *file)
if (!iter->snapshot)
/* reenable tracing if it was previously enabled */
- tracing_start();
+ tracing_start_tr(tr);
mutex_unlock(&trace_types_lock);
mutex_destroy(&iter->mutex);
@@ -2612,12 +2915,13 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
- long cpu = (long) inode->i_private;
+ struct trace_cpu *tc = inode->i_private;
+ struct trace_array *tr = tc->tr;
- if (cpu == TRACE_PIPE_ALL_CPU)
- tracing_reset_online_cpus(&global_trace);
+ if (tc->cpu == RING_BUFFER_ALL_CPUS)
+ tracing_reset_online_cpus(&tr->trace_buffer);
else
- tracing_reset(&global_trace, cpu);
+ tracing_reset(&tr->trace_buffer, tc->cpu);
}
if (file->f_mode & FMODE_READ) {
@@ -2764,8 +3068,9 @@ static ssize_t
tracing_cpumask_write(struct file *filp, const char __user *ubuf,
size_t count, loff_t *ppos)
{
- int err, cpu;
+ struct trace_array *tr = filp->private_data;
cpumask_var_t tracing_cpumask_new;
+ int err, cpu;
if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
return -ENOMEM;
@@ -2785,13 +3090,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
*/
if (cpumask_test_cpu(cpu, tracing_cpumask) &&
!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
- atomic_inc(&global_trace.data[cpu]->disabled);
- ring_buffer_record_disable_cpu(global_trace.buffer, cpu);
+ atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
+ ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu);
}
if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
cpumask_test_cpu(cpu, tracing_cpumask_new)) {
- atomic_dec(&global_trace.data[cpu]->disabled);
- ring_buffer_record_enable_cpu(global_trace.buffer, cpu);
+ atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
+ ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
}
}
arch_spin_unlock(&ftrace_max_lock);
@@ -2820,12 +3125,13 @@ static const struct file_operations tracing_cpumask_fops = {
static int tracing_trace_options_show(struct seq_file *m, void *v)
{
struct tracer_opt *trace_opts;
+ struct trace_array *tr = m->private;
u32 tracer_flags;
int i;
mutex_lock(&trace_types_lock);
- tracer_flags = current_trace->flags->val;
- trace_opts = current_trace->flags->opts;
+ tracer_flags = tr->current_trace->flags->val;
+ trace_opts = tr->current_trace->flags->opts;
for (i = 0; trace_options[i]; i++) {
if (trace_flags & (1 << i))
@@ -2880,11 +3186,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
return -EINVAL;
}
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+ if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+ return -1;
+
+ return 0;
+}
+
+int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
/* do nothing if flag is already set */
if (!!(trace_flags & mask) == !!enabled)
- return;
+ return 0;
+
+ /* Give the tracer a chance to approve the change */
+ if (tr->current_trace->flag_changed)
+ if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
+ return -EINVAL;
if (enabled)
trace_flags |= mask;
@@ -2894,18 +3214,24 @@ static void set_tracer_flags(unsigned int mask, int enabled)
if (mask == TRACE_ITER_RECORD_CMD)
trace_event_enable_cmd_record(enabled);
- if (mask == TRACE_ITER_OVERWRITE)
- ring_buffer_change_overwrite(global_trace.buffer, enabled);
+ if (mask == TRACE_ITER_OVERWRITE) {
+ ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled);
+#endif
+ }
if (mask == TRACE_ITER_PRINTK)
trace_printk_start_stop_comm(enabled);
+
+ return 0;
}
-static int trace_set_options(char *option)
+static int trace_set_options(struct trace_array *tr, char *option)
{
char *cmp;
int neg = 0;
- int ret = 0;
+ int ret = -ENODEV;
int i;
cmp = strstrip(option);
@@ -2915,19 +3241,20 @@ static int trace_set_options(char *option)
cmp += 2;
}
+ mutex_lock(&trace_types_lock);
+
for (i = 0; trace_options[i]; i++) {
if (strcmp(cmp, trace_options[i]) == 0) {
- set_tracer_flags(1 << i, !neg);
+ ret = set_tracer_flag(tr, 1 << i, !neg);
break;
}
}
/* If no option could be set, test the specific tracer options */
- if (!trace_options[i]) {
- mutex_lock(&trace_types_lock);
- ret = set_tracer_option(current_trace, cmp, neg);
- mutex_unlock(&trace_types_lock);
- }
+ if (!trace_options[i])
+ ret = set_tracer_option(tr->current_trace, cmp, neg);
+
+ mutex_unlock(&trace_types_lock);
return ret;
}
@@ -2936,7 +3263,10 @@ static ssize_t
tracing_trace_options_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ struct seq_file *m = filp->private_data;
+ struct trace_array *tr = m->private;
char buf[64];
+ int ret;
if (cnt >= sizeof(buf))
return -EINVAL;
@@ -2946,7 +3276,9 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
buf[cnt] = 0;
- trace_set_options(buf);
+ ret = trace_set_options(tr, buf);
+ if (ret < 0)
+ return ret;
*ppos += cnt;
@@ -2957,7 +3289,8 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
{
if (tracing_disabled)
return -ENODEV;
- return single_open(file, tracing_trace_options_show, NULL);
+
+ return single_open(file, tracing_trace_options_show, inode->i_private);
}
static const struct file_operations tracing_iter_fops = {
@@ -2970,20 +3303,84 @@ static const struct file_operations tracing_iter_fops = {
static const char readme_msg[] =
"tracing mini-HOWTO:\n\n"
- "# mount -t debugfs nodev /sys/kernel/debug\n\n"
- "# cat /sys/kernel/debug/tracing/available_tracers\n"
- "wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
- "# cat /sys/kernel/debug/tracing/current_tracer\n"
- "nop\n"
- "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
- "# cat /sys/kernel/debug/tracing/current_tracer\n"
- "wakeup\n"
- "# cat /sys/kernel/debug/tracing/trace_options\n"
- "noprint-parent nosym-offset nosym-addr noverbose\n"
- "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
- "# echo 1 > /sys/kernel/debug/tracing/tracing_on\n"
- "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n"
- "# echo 0 > /sys/kernel/debug/tracing/tracing_on\n"
+ "# echo 0 > tracing_on : quick way to disable tracing\n"
+ "# echo 1 > tracing_on : quick way to re-enable tracing\n\n"
+ " Important files:\n"
+ " trace\t\t\t- The static contents of the buffer\n"
+ "\t\t\t To clear the buffer write into this file: echo > trace\n"
+ " trace_pipe\t\t- A consuming read to see the contents of the buffer\n"
+ " current_tracer\t- function and latency tracers\n"
+ " available_tracers\t- list of configured tracers for current_tracer\n"
+ " buffer_size_kb\t- view and modify size of per cpu buffer\n"
+ " buffer_total_size_kb - view total size of all cpu buffers\n\n"
+ " trace_clock\t\t-change the clock used to order events\n"
+ " local: Per cpu clock but may not be synced across CPUs\n"
+ " global: Synced across CPUs but slows tracing down.\n"
+ " counter: Not a clock, but just an increment\n"
+ " uptime: Jiffy counter from time of boot\n"
+ " perf: Same clock that perf events use\n"
+#ifdef CONFIG_X86_64
+ " x86-tsc: TSC cycle counter\n"
+#endif
+ "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
+ " tracing_cpumask\t- Limit which CPUs to trace\n"
+ " instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
+ "\t\t\t Remove sub-buffer with rmdir\n"
+ " trace_options\t\t- Set format or modify how tracing happens\n"
+ "\t\t\t Disable an option by adding a suffix 'no' to the option name\n"
+#ifdef CONFIG_DYNAMIC_FTRACE
+ "\n available_filter_functions - list of functions that can be filtered on\n"
+ " set_ftrace_filter\t- echo function name in here to only trace these functions\n"
+ " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+ " modules: Can select a group via module\n"
+ " Format: :mod:<module-name>\n"
+ " example: echo :mod:ext3 > set_ftrace_filter\n"
+ " triggers: a command to perform when function is hit\n"
+ " Format: <function>:<trigger>[:count]\n"
+ " trigger: traceon, traceoff\n"
+ " enable_event:<system>:<event>\n"
+ " disable_event:<system>:<event>\n"
+#ifdef CONFIG_STACKTRACE
+ " stacktrace\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+ " snapshot\n"
+#endif
+ " example: echo do_fault:traceoff > set_ftrace_filter\n"
+ " echo do_trap:traceoff:3 > set_ftrace_filter\n"
+ " The first one will disable tracing every time do_fault is hit\n"
+ " The second will disable tracing at most 3 times when do_trap is hit\n"
+ " The first time do trap is hit and it disables tracing, the counter\n"
+ " will decrement to 2. If tracing is already disabled, the counter\n"
+ " will not decrement. It only decrements when the trigger did work\n"
+ " To remove trigger without count:\n"
+ " echo '!<function>:<trigger> > set_ftrace_filter\n"
+ " To remove trigger with a count:\n"
+ " echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
+ " set_ftrace_notrace\t- echo function name in here to never trace.\n"
+ " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+ " modules: Can select a group via module command :mod:\n"
+ " Does not accept triggers\n"
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#ifdef CONFIG_FUNCTION_TRACER
+ " set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n"
+#endif
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ " set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
+ " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+ "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
+ "\t\t\t Read the contents for more information\n"
+#endif
+#ifdef CONFIG_STACKTRACE
+ " stack_trace\t\t- Shows the max stack trace when active\n"
+ " stack_max_size\t- Shows current max stack size that was traced\n"
+ "\t\t\t Write into this file to reset the max size (trigger a new trace)\n"
+#ifdef CONFIG_DYNAMIC_FTRACE
+ " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
+#endif
+#endif /* CONFIG_STACKTRACE */
;
static ssize_t
@@ -3055,11 +3452,12 @@ static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ struct trace_array *tr = filp->private_data;
char buf[MAX_TRACER_SIZE+2];
int r;
mutex_lock(&trace_types_lock);
- r = sprintf(buf, "%s\n", current_trace->name);
+ r = sprintf(buf, "%s\n", tr->current_trace->name);
mutex_unlock(&trace_types_lock);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -3067,43 +3465,48 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
int tracer_init(struct tracer *t, struct trace_array *tr)
{
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
return t->init(tr);
}
-static void set_buffer_entries(struct trace_array *tr, unsigned long val)
+static void set_buffer_entries(struct trace_buffer *buf, unsigned long val)
{
int cpu;
+
for_each_tracing_cpu(cpu)
- tr->data[cpu]->entries = val;
+ per_cpu_ptr(buf->data, cpu)->entries = val;
}
+#ifdef CONFIG_TRACER_MAX_TRACE
/* resize @tr's buffer to the size of @size_tr's entries */
-static int resize_buffer_duplicate_size(struct trace_array *tr,
- struct trace_array *size_tr, int cpu_id)
+static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
+ struct trace_buffer *size_buf, int cpu_id)
{
int cpu, ret = 0;
if (cpu_id == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
- ret = ring_buffer_resize(tr->buffer,
- size_tr->data[cpu]->entries, cpu);
+ ret = ring_buffer_resize(trace_buf->buffer,
+ per_cpu_ptr(size_buf->data, cpu)->entries, cpu);
if (ret < 0)
break;
- tr->data[cpu]->entries = size_tr->data[cpu]->entries;
+ per_cpu_ptr(trace_buf->data, cpu)->entries =
+ per_cpu_ptr(size_buf->data, cpu)->entries;
}
} else {
- ret = ring_buffer_resize(tr->buffer,
- size_tr->data[cpu_id]->entries, cpu_id);
+ ret = ring_buffer_resize(trace_buf->buffer,
+ per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id);
if (ret == 0)
- tr->data[cpu_id]->entries =
- size_tr->data[cpu_id]->entries;
+ per_cpu_ptr(trace_buf->data, cpu_id)->entries =
+ per_cpu_ptr(size_buf->data, cpu_id)->entries;
}
return ret;
}
+#endif /* CONFIG_TRACER_MAX_TRACE */
-static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
+static int __tracing_resize_ring_buffer(struct trace_array *tr,
+ unsigned long size, int cpu)
{
int ret;
@@ -3112,23 +3515,25 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
* we use the size that was given, and we can forget about
* expanding it later.
*/
- ring_buffer_expanded = 1;
+ ring_buffer_expanded = true;
/* May be called before buffers are initialized */
- if (!global_trace.buffer)
+ if (!tr->trace_buffer.buffer)
return 0;
- ret = ring_buffer_resize(global_trace.buffer, size, cpu);
+ ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu);
if (ret < 0)
return ret;
- if (!current_trace->use_max_tr)
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
+ !tr->current_trace->use_max_tr)
goto out;
- ret = ring_buffer_resize(max_tr.buffer, size, cpu);
+ ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
if (ret < 0) {
- int r = resize_buffer_duplicate_size(&global_trace,
- &global_trace, cpu);
+ int r = resize_buffer_duplicate_size(&tr->trace_buffer,
+ &tr->trace_buffer, cpu);
if (r < 0) {
/*
* AARGH! We are left with different
@@ -3151,20 +3556,23 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
}
if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&max_tr, size);
+ set_buffer_entries(&tr->max_buffer, size);
else
- max_tr.data[cpu]->entries = size;
+ per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;
out:
+#endif /* CONFIG_TRACER_MAX_TRACE */
+
if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&global_trace, size);
+ set_buffer_entries(&tr->trace_buffer, size);
else
- global_trace.data[cpu]->entries = size;
+ per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size;
return ret;
}
-static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
+static ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
+ unsigned long size, int cpu_id)
{
int ret = size;
@@ -3178,7 +3586,7 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
}
}
- ret = __tracing_resize_ring_buffer(size, cpu_id);
+ ret = __tracing_resize_ring_buffer(tr, size, cpu_id);
if (ret < 0)
ret = -ENOMEM;
@@ -3205,7 +3613,7 @@ int tracing_update_buffers(void)
mutex_lock(&trace_types_lock);
if (!ring_buffer_expanded)
- ret = __tracing_resize_ring_buffer(trace_buf_size,
+ ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size,
RING_BUFFER_ALL_CPUS);
mutex_unlock(&trace_types_lock);
@@ -3215,7 +3623,7 @@ int tracing_update_buffers(void)
struct trace_option_dentry;
static struct trace_option_dentry *
-create_trace_option_files(struct tracer *tracer);
+create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
static void
destroy_trace_option_files(struct trace_option_dentry *topts);
@@ -3225,13 +3633,15 @@ static int tracing_set_tracer(const char *buf)
static struct trace_option_dentry *topts;
struct trace_array *tr = &global_trace;
struct tracer *t;
+#ifdef CONFIG_TRACER_MAX_TRACE
bool had_max_tr;
+#endif
int ret = 0;
mutex_lock(&trace_types_lock);
if (!ring_buffer_expanded) {
- ret = __tracing_resize_ring_buffer(trace_buf_size,
+ ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
RING_BUFFER_ALL_CPUS);
if (ret < 0)
goto out;
@@ -3246,15 +3656,21 @@ static int tracing_set_tracer(const char *buf)
ret = -EINVAL;
goto out;
}
- if (t == current_trace)
+ if (t == tr->current_trace)
goto out;
trace_branch_disable();
- if (current_trace->reset)
- current_trace->reset(tr);
- had_max_tr = current_trace->allocated_snapshot;
- current_trace = &nop_trace;
+ tr->current_trace->enabled = false;
+
+ if (tr->current_trace->reset)
+ tr->current_trace->reset(tr);
+
+ /* Current trace needs to be nop_trace before synchronize_sched */
+ tr->current_trace = &nop_trace;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ had_max_tr = tr->allocated_snapshot;
if (had_max_tr && !t->use_max_tr) {
/*
@@ -3265,27 +3681,20 @@ static int tracing_set_tracer(const char *buf)
* so a synchronized_sched() is sufficient.
*/
synchronize_sched();
- /*
- * We don't free the ring buffer. instead, resize it because
- * The max_tr ring buffer has some state (e.g. ring->clock) and
- * we want preserve it.
- */
- ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
- set_buffer_entries(&max_tr, 1);
- tracing_reset_online_cpus(&max_tr);
- current_trace->allocated_snapshot = false;
+ free_snapshot(tr);
}
+#endif
destroy_trace_option_files(topts);
- topts = create_trace_option_files(t);
+ topts = create_trace_option_files(tr, t);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
- /* we need to make per cpu buffer sizes equivalent */
- ret = resize_buffer_duplicate_size(&max_tr, &global_trace,
- RING_BUFFER_ALL_CPUS);
+ ret = alloc_snapshot(tr);
if (ret < 0)
goto out;
- t->allocated_snapshot = true;
}
+#endif
if (t->init) {
ret = tracer_init(t, tr);
@@ -3293,7 +3702,8 @@ static int tracing_set_tracer(const char *buf)
goto out;
}
- current_trace = t;
+ tr->current_trace = t;
+ tr->current_trace->enabled = true;
trace_branch_enable(tr);
out:
mutex_unlock(&trace_types_lock);
@@ -3367,7 +3777,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
- long cpu_file = (long) inode->i_private;
+ struct trace_cpu *tc = inode->i_private;
+ struct trace_array *tr = tc->tr;
struct trace_iterator *iter;
int ret = 0;
@@ -3392,7 +3803,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
ret = -ENOMEM;
goto fail;
}
- *iter->trace = *current_trace;
+ *iter->trace = *tr->current_trace;
if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
ret = -ENOMEM;
@@ -3409,8 +3820,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
if (trace_clocks[trace_clock_id].in_ns)
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
- iter->cpu_file = cpu_file;
- iter->tr = &global_trace;
+ iter->cpu_file = tc->cpu;
+ iter->tr = tc->tr;
+ iter->trace_buffer = &tc->tr->trace_buffer;
mutex_init(&iter->mutex);
filp->private_data = iter;
@@ -3449,24 +3861,28 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
}
static unsigned int
-tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table)
{
- struct trace_iterator *iter = filp->private_data;
+ /* Iterators are static, they should be filled or empty */
+ if (trace_buffer_iter(iter, iter->cpu_file))
+ return POLLIN | POLLRDNORM;
- if (trace_flags & TRACE_ITER_BLOCK) {
+ if (trace_flags & TRACE_ITER_BLOCK)
/*
* Always select as readable when in blocking mode
*/
return POLLIN | POLLRDNORM;
- } else {
- if (!trace_empty(iter))
- return POLLIN | POLLRDNORM;
- poll_wait(filp, &trace_wait, poll_table);
- if (!trace_empty(iter))
- return POLLIN | POLLRDNORM;
+ else
+ return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file,
+ filp, poll_table);
+}
- return 0;
- }
+static unsigned int
+tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+{
+ struct trace_iterator *iter = filp->private_data;
+
+ return trace_poll(iter, filp, poll_table);
}
/*
@@ -3532,6 +3948,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_iterator *iter = filp->private_data;
+ struct trace_array *tr = iter->tr;
ssize_t sret;
/* return any leftover data */
@@ -3543,8 +3960,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
/* copy the tracer to avoid using a global lock all around */
mutex_lock(&trace_types_lock);
- if (unlikely(iter->trace->name != current_trace->name))
- *iter->trace = *current_trace;
+ if (unlikely(iter->trace->name != tr->current_trace->name))
+ *iter->trace = *tr->current_trace;
mutex_unlock(&trace_types_lock);
/*
@@ -3700,6 +4117,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
.ops = &tracing_pipe_buf_ops,
.spd_release = tracing_spd_release_pipe,
};
+ struct trace_array *tr = iter->tr;
ssize_t ret;
size_t rem;
unsigned int i;
@@ -3709,8 +4127,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
/* copy the tracer to avoid using a global lock all around */
mutex_lock(&trace_types_lock);
- if (unlikely(iter->trace->name != current_trace->name))
- *iter->trace = *current_trace;
+ if (unlikely(iter->trace->name != tr->current_trace->name))
+ *iter->trace = *tr->current_trace;
mutex_unlock(&trace_types_lock);
mutex_lock(&iter->mutex);
@@ -3772,43 +4190,19 @@ out_err:
goto out;
}
-struct ftrace_entries_info {
- struct trace_array *tr;
- int cpu;
-};
-
-static int tracing_entries_open(struct inode *inode, struct file *filp)
-{
- struct ftrace_entries_info *info;
-
- if (tracing_disabled)
- return -ENODEV;
-
- info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info)
- return -ENOMEM;
-
- info->tr = &global_trace;
- info->cpu = (unsigned long)inode->i_private;
-
- filp->private_data = info;
-
- return 0;
-}
-
static ssize_t
tracing_entries_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ftrace_entries_info *info = filp->private_data;
- struct trace_array *tr = info->tr;
+ struct trace_cpu *tc = filp->private_data;
+ struct trace_array *tr = tc->tr;
char buf[64];
int r = 0;
ssize_t ret;
mutex_lock(&trace_types_lock);
- if (info->cpu == RING_BUFFER_ALL_CPUS) {
+ if (tc->cpu == RING_BUFFER_ALL_CPUS) {
int cpu, buf_size_same;
unsigned long size;
@@ -3818,8 +4212,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
for_each_tracing_cpu(cpu) {
/* fill in the size from first enabled cpu */
if (size == 0)
- size = tr->data[cpu]->entries;
- if (size != tr->data[cpu]->entries) {
+ size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries;
+ if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) {
buf_size_same = 0;
break;
}
@@ -3835,7 +4229,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
} else
r = sprintf(buf, "X\n");
} else
- r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10);
+ r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
mutex_unlock(&trace_types_lock);
@@ -3847,7 +4241,7 @@ static ssize_t
tracing_entries_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ftrace_entries_info *info = filp->private_data;
+ struct trace_cpu *tc = filp->private_data;
unsigned long val;
int ret;
@@ -3862,7 +4256,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
/* value is in KB */
val <<= 10;
- ret = tracing_resize_ring_buffer(val, info->cpu);
+ ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
if (ret < 0)
return ret;
@@ -3871,16 +4265,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
return cnt;
}
-static int
-tracing_entries_release(struct inode *inode, struct file *filp)
-{
- struct ftrace_entries_info *info = filp->private_data;
-
- kfree(info);
-
- return 0;
-}
-
static ssize_t
tracing_total_entries_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
@@ -3892,7 +4276,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
mutex_lock(&trace_types_lock);
for_each_tracing_cpu(cpu) {
- size += tr->data[cpu]->entries >> 10;
+ size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10;
if (!ring_buffer_expanded)
expanded_size += trace_buf_size >> 10;
}
@@ -3922,11 +4306,13 @@ tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
static int
tracing_free_buffer_release(struct inode *inode, struct file *filp)
{
+ struct trace_array *tr = inode->i_private;
+
/* disable tracing ? */
if (trace_flags & TRACE_ITER_STOP_ON_FREE)
tracing_off();
/* resize the ring buffer to 0 */
- tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS);
+ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS);
return 0;
}
@@ -3995,7 +4381,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
local_save_flags(irq_flags);
size = sizeof(*entry) + cnt + 2; /* possible \n added */
- buffer = global_trace.buffer;
+ buffer = global_trace.trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
irq_flags, preempt_count());
if (!event) {
@@ -4037,13 +4423,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
static int tracing_clock_show(struct seq_file *m, void *v)
{
+ struct trace_array *tr = m->private;
int i;
for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
seq_printf(m,
"%s%s%s%s", i ? " " : "",
- i == trace_clock_id ? "[" : "", trace_clocks[i].name,
- i == trace_clock_id ? "]" : "");
+ i == tr->clock_id ? "[" : "", trace_clocks[i].name,
+ i == tr->clock_id ? "]" : "");
seq_putc(m, '\n');
return 0;
@@ -4052,6 +4439,8 @@ static int tracing_clock_show(struct seq_file *m, void *v)
static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
{
+ struct seq_file *m = filp->private_data;
+ struct trace_array *tr = m->private;
char buf[64];
const char *clockstr;
int i;
@@ -4073,20 +4462,23 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
if (i == ARRAY_SIZE(trace_clocks))
return -EINVAL;
- trace_clock_id = i;
-
mutex_lock(&trace_types_lock);
- ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
- if (max_tr.buffer)
- ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+ tr->clock_id = i;
+
+ ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func);
/*
* New clock may not be consistent with the previous clock.
* Reset the buffer so that it doesn't have incomparable timestamps.
*/
- tracing_reset_online_cpus(&global_trace);
- tracing_reset_online_cpus(&max_tr);
+ tracing_reset_online_cpus(&global_trace.trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
+ ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
+ tracing_reset_online_cpus(&global_trace.max_buffer);
+#endif
mutex_unlock(&trace_types_lock);
@@ -4099,20 +4491,45 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
{
if (tracing_disabled)
return -ENODEV;
- return single_open(file, tracing_clock_show, NULL);
+
+ return single_open(file, tracing_clock_show, inode->i_private);
}
+struct ftrace_buffer_info {
+ struct trace_iterator iter;
+ void *spare;
+ unsigned int read;
+};
+
#ifdef CONFIG_TRACER_SNAPSHOT
static int tracing_snapshot_open(struct inode *inode, struct file *file)
{
+ struct trace_cpu *tc = inode->i_private;
struct trace_iterator *iter;
+ struct seq_file *m;
int ret = 0;
if (file->f_mode & FMODE_READ) {
iter = __tracing_open(inode, file, true);
if (IS_ERR(iter))
ret = PTR_ERR(iter);
+ } else {
+ /* Writes still need the seq_file to hold the private data */
+ m = kzalloc(sizeof(*m), GFP_KERNEL);
+ if (!m)
+ return -ENOMEM;
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter) {
+ kfree(m);
+ return -ENOMEM;
+ }
+ iter->tr = tc->tr;
+ iter->trace_buffer = &tc->tr->max_buffer;
+ iter->cpu_file = tc->cpu;
+ m->private = iter;
+ file->private_data = m;
}
+
return ret;
}
@@ -4120,6 +4537,9 @@ static ssize_t
tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
+ struct seq_file *m = filp->private_data;
+ struct trace_iterator *iter = m->private;
+ struct trace_array *tr = iter->tr;
unsigned long val;
int ret;
@@ -4133,40 +4553,48 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
mutex_lock(&trace_types_lock);
- if (current_trace->use_max_tr) {
+ if (tr->current_trace->use_max_tr) {
ret = -EBUSY;
goto out;
}
switch (val) {
case 0:
- if (current_trace->allocated_snapshot) {
- /* free spare buffer */
- ring_buffer_resize(max_tr.buffer, 1,
- RING_BUFFER_ALL_CPUS);
- set_buffer_entries(&max_tr, 1);
- tracing_reset_online_cpus(&max_tr);
- current_trace->allocated_snapshot = false;
+ if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
+ ret = -EINVAL;
+ break;
}
+ if (tr->allocated_snapshot)
+ free_snapshot(tr);
break;
case 1:
- if (!current_trace->allocated_snapshot) {
- /* allocate spare buffer */
- ret = resize_buffer_duplicate_size(&max_tr,
- &global_trace, RING_BUFFER_ALL_CPUS);
+/* Only allow per-cpu swap if the ring buffer supports it */
+#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP
+ if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
+ ret = -EINVAL;
+ break;
+ }
+#endif
+ if (!tr->allocated_snapshot) {
+ ret = alloc_snapshot(tr);
if (ret < 0)
break;
- current_trace->allocated_snapshot = true;
}
-
local_irq_disable();
/* Now, we're going to swap */
- update_max_tr(&global_trace, current, smp_processor_id());
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+ update_max_tr(tr, current, smp_processor_id());
+ else
+ update_max_tr_single(tr, current, iter->cpu_file);
local_irq_enable();
break;
default:
- if (current_trace->allocated_snapshot)
- tracing_reset_online_cpus(&max_tr);
+ if (tr->allocated_snapshot) {
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+ tracing_reset_online_cpus(&tr->max_buffer);
+ else
+ tracing_reset(&tr->max_buffer, iter->cpu_file);
+ }
break;
}
@@ -4178,6 +4606,51 @@ out:
mutex_unlock(&trace_types_lock);
return ret;
}
+
+static int tracing_snapshot_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *m = file->private_data;
+
+ if (file->f_mode & FMODE_READ)
+ return tracing_release(inode, file);
+
+ /* If write only, the seq_file is just a stub */
+ if (m)
+ kfree(m->private);
+ kfree(m);
+
+ return 0;
+}
+
+static int tracing_buffers_open(struct inode *inode, struct file *filp);
+static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos);
+static int tracing_buffers_release(struct inode *inode, struct file *file);
+static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len, unsigned int flags);
+
+static int snapshot_raw_open(struct inode *inode, struct file *filp)
+{
+ struct ftrace_buffer_info *info;
+ int ret;
+
+ ret = tracing_buffers_open(inode, filp);
+ if (ret < 0)
+ return ret;
+
+ info = filp->private_data;
+
+ if (info->iter.trace->use_max_tr) {
+ tracing_buffers_release(inode, filp);
+ return -EBUSY;
+ }
+
+ info->iter.snapshot = true;
+ info->iter.trace_buffer = &info->iter.tr->max_buffer;
+
+ return ret;
+}
+
#endif /* CONFIG_TRACER_SNAPSHOT */
@@ -4205,10 +4678,9 @@ static const struct file_operations tracing_pipe_fops = {
};
static const struct file_operations tracing_entries_fops = {
- .open = tracing_entries_open,
+ .open = tracing_open_generic,
.read = tracing_entries_read,
.write = tracing_entries_write,
- .release = tracing_entries_release,
.llseek = generic_file_llseek,
};
@@ -4243,20 +4715,23 @@ static const struct file_operations snapshot_fops = {
.read = seq_read,
.write = tracing_snapshot_write,
.llseek = tracing_seek,
- .release = tracing_release,
+ .release = tracing_snapshot_release,
};
-#endif /* CONFIG_TRACER_SNAPSHOT */
-struct ftrace_buffer_info {
- struct trace_array *tr;
- void *spare;
- int cpu;
- unsigned int read;
+static const struct file_operations snapshot_raw_fops = {
+ .open = snapshot_raw_open,
+ .read = tracing_buffers_read,
+ .release = tracing_buffers_release,
+ .splice_read = tracing_buffers_splice_read,
+ .llseek = no_llseek,
};
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
static int tracing_buffers_open(struct inode *inode, struct file *filp)
{
- int cpu = (int)(long)inode->i_private;
+ struct trace_cpu *tc = inode->i_private;
+ struct trace_array *tr = tc->tr;
struct ftrace_buffer_info *info;
if (tracing_disabled)
@@ -4266,72 +4741,131 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
if (!info)
return -ENOMEM;
- info->tr = &global_trace;
- info->cpu = cpu;
- info->spare = NULL;
+ mutex_lock(&trace_types_lock);
+
+ tr->ref++;
+
+ info->iter.tr = tr;
+ info->iter.cpu_file = tc->cpu;
+ info->iter.trace = tr->current_trace;
+ info->iter.trace_buffer = &tr->trace_buffer;
+ info->spare = NULL;
/* Force reading ring buffer for first read */
- info->read = (unsigned int)-1;
+ info->read = (unsigned int)-1;
filp->private_data = info;
+ mutex_unlock(&trace_types_lock);
+
return nonseekable_open(inode, filp);
}
+static unsigned int
+tracing_buffers_poll(struct file *filp, poll_table *poll_table)
+{
+ struct ftrace_buffer_info *info = filp->private_data;
+ struct trace_iterator *iter = &info->iter;
+
+ return trace_poll(iter, filp, poll_table);
+}
+
static ssize_t
tracing_buffers_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct ftrace_buffer_info *info = filp->private_data;
+ struct trace_iterator *iter = &info->iter;
ssize_t ret;
- size_t size;
+ ssize_t size;
if (!count)
return 0;
+ mutex_lock(&trace_types_lock);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
+ size = -EBUSY;
+ goto out_unlock;
+ }
+#endif
+
if (!info->spare)
- info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu);
+ info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
+ iter->cpu_file);
+ size = -ENOMEM;
if (!info->spare)
- return -ENOMEM;
+ goto out_unlock;
/* Do we have previous read data to read? */
if (info->read < PAGE_SIZE)
goto read;
- trace_access_lock(info->cpu);
- ret = ring_buffer_read_page(info->tr->buffer,
+ again:
+ trace_access_lock(iter->cpu_file);
+ ret = ring_buffer_read_page(iter->trace_buffer->buffer,
&info->spare,
count,
- info->cpu, 0);
- trace_access_unlock(info->cpu);
- if (ret < 0)
- return 0;
+ iter->cpu_file, 0);
+ trace_access_unlock(iter->cpu_file);
- info->read = 0;
+ if (ret < 0) {
+ if (trace_empty(iter)) {
+ if ((filp->f_flags & O_NONBLOCK)) {
+ size = -EAGAIN;
+ goto out_unlock;
+ }
+ mutex_unlock(&trace_types_lock);
+ iter->trace->wait_pipe(iter);
+ mutex_lock(&trace_types_lock);
+ if (signal_pending(current)) {
+ size = -EINTR;
+ goto out_unlock;
+ }
+ goto again;
+ }
+ size = 0;
+ goto out_unlock;
+ }
-read:
+ info->read = 0;
+ read:
size = PAGE_SIZE - info->read;
if (size > count)
size = count;
ret = copy_to_user(ubuf, info->spare + info->read, size);
- if (ret == size)
- return -EFAULT;
+ if (ret == size) {
+ size = -EFAULT;
+ goto out_unlock;
+ }
size -= ret;
*ppos += size;
info->read += size;
+ out_unlock:
+ mutex_unlock(&trace_types_lock);
+
return size;
}
static int tracing_buffers_release(struct inode *inode, struct file *file)
{
struct ftrace_buffer_info *info = file->private_data;
+ struct trace_iterator *iter = &info->iter;
+
+ mutex_lock(&trace_types_lock);
+
+ WARN_ON(!iter->tr->ref);
+ iter->tr->ref--;
if (info->spare)
- ring_buffer_free_read_page(info->tr->buffer, info->spare);
+ ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
kfree(info);
+ mutex_unlock(&trace_types_lock);
+
return 0;
}
@@ -4396,6 +4930,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
unsigned int flags)
{
struct ftrace_buffer_info *info = file->private_data;
+ struct trace_iterator *iter = &info->iter;
struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct page *pages_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
@@ -4408,10 +4943,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
};
struct buffer_ref *ref;
int entries, size, i;
- size_t ret;
+ ssize_t ret;
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
+ mutex_lock(&trace_types_lock);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (iter->snapshot && iter->tr->current_trace->use_max_tr) {
+ ret = -EBUSY;
+ goto out;
+ }
+#endif
+
+ if (splice_grow_spd(pipe, &spd)) {
+ ret = -ENOMEM;
+ goto out;
+ }
if (*ppos & (PAGE_SIZE - 1)) {
ret = -EINVAL;
@@ -4426,8 +4972,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
len &= PAGE_MASK;
}
- trace_access_lock(info->cpu);
- entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+ again:
+ trace_access_lock(iter->cpu_file);
+ entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
@@ -4438,15 +4985,15 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
ref->ref = 1;
- ref->buffer = info->tr->buffer;
- ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu);
+ ref->buffer = iter->trace_buffer->buffer;
+ ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
if (!ref->page) {
kfree(ref);
break;
}
r = ring_buffer_read_page(ref->buffer, &ref->page,
- len, info->cpu, 1);
+ len, iter->cpu_file, 1);
if (r < 0) {
ring_buffer_free_read_page(ref->buffer, ref->page);
kfree(ref);
@@ -4470,31 +5017,40 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
spd.nr_pages++;
*ppos += PAGE_SIZE;
- entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+ entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
}
- trace_access_unlock(info->cpu);
+ trace_access_unlock(iter->cpu_file);
spd.nr_pages = i;
/* did we read anything? */
if (!spd.nr_pages) {
- if (flags & SPLICE_F_NONBLOCK)
+ if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
ret = -EAGAIN;
- else
- ret = 0;
- /* TODO: block */
- goto out;
+ goto out;
+ }
+ mutex_unlock(&trace_types_lock);
+ iter->trace->wait_pipe(iter);
+ mutex_lock(&trace_types_lock);
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
+ goto again;
}
ret = splice_to_pipe(pipe, &spd);
splice_shrink_spd(&spd);
out:
+ mutex_unlock(&trace_types_lock);
+
return ret;
}
static const struct file_operations tracing_buffers_fops = {
.open = tracing_buffers_open,
.read = tracing_buffers_read,
+ .poll = tracing_buffers_poll,
.release = tracing_buffers_release,
.splice_read = tracing_buffers_splice_read,
.llseek = no_llseek,
@@ -4504,12 +5060,14 @@ static ssize_t
tracing_stats_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
- unsigned long cpu = (unsigned long)filp->private_data;
- struct trace_array *tr = &global_trace;
+ struct trace_cpu *tc = filp->private_data;
+ struct trace_array *tr = tc->tr;
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
struct trace_seq *s;
unsigned long cnt;
unsigned long long t;
unsigned long usec_rem;
+ int cpu = tc->cpu;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
@@ -4517,41 +5075,41 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
trace_seq_init(s);
- cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "entries: %ld\n", cnt);
- cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "overrun: %ld\n", cnt);
- cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "commit overrun: %ld\n", cnt);
- cnt = ring_buffer_bytes_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "bytes: %ld\n", cnt);
if (trace_clocks[trace_clock_id].in_ns) {
/* local or global for trace_clock */
- t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
+ t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
usec_rem = do_div(t, USEC_PER_SEC);
trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n",
t, usec_rem);
- t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
+ t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu));
usec_rem = do_div(t, USEC_PER_SEC);
trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
} else {
/* counter or tsc mode for trace_clock */
trace_seq_printf(s, "oldest event ts: %llu\n",
- ring_buffer_oldest_event_ts(tr->buffer, cpu));
+ ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
trace_seq_printf(s, "now ts: %llu\n",
- ring_buffer_time_stamp(tr->buffer, cpu));
+ ring_buffer_time_stamp(trace_buf->buffer, cpu));
}
- cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "dropped events: %ld\n", cnt);
- cnt = ring_buffer_read_events_cpu(tr->buffer, cpu);
+ cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "read events: %ld\n", cnt);
count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
@@ -4603,60 +5161,161 @@ static const struct file_operations tracing_dyn_info_fops = {
.read = tracing_read_dyn_info,
.llseek = generic_file_llseek,
};
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
-static struct dentry *d_tracer;
+#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE)
+static void
+ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ tracing_snapshot();
+}
-struct dentry *tracing_init_dentry(void)
+static void
+ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ unsigned long *count = (long *)data;
+
+ if (!*count)
+ return;
+
+ if (*count != -1)
+ (*count)--;
+
+ tracing_snapshot();
+}
+
+static int
+ftrace_snapshot_print(struct seq_file *m, unsigned long ip,
+ struct ftrace_probe_ops *ops, void *data)
+{
+ long count = (long)data;
+
+ seq_printf(m, "%ps:", (void *)ip);
+
+ seq_printf(m, "snapshot");
+
+ if (count == -1)
+ seq_printf(m, ":unlimited\n");
+ else
+ seq_printf(m, ":count=%ld\n", count);
+
+ return 0;
+}
+
+static struct ftrace_probe_ops snapshot_probe_ops = {
+ .func = ftrace_snapshot,
+ .print = ftrace_snapshot_print,
+};
+
+static struct ftrace_probe_ops snapshot_count_probe_ops = {
+ .func = ftrace_count_snapshot,
+ .print = ftrace_snapshot_print,
+};
+
+static int
+ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
+ char *glob, char *cmd, char *param, int enable)
{
- static int once;
+ struct ftrace_probe_ops *ops;
+ void *count = (void *)-1;
+ char *number;
+ int ret;
+
+ /* hash funcs only work with set_ftrace_filter */
+ if (!enable)
+ return -EINVAL;
+
+ ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops;
+
+ if (glob[0] == '!') {
+ unregister_ftrace_function_probe_func(glob+1, ops);
+ return 0;
+ }
+
+ if (!param)
+ goto out_reg;
- if (d_tracer)
- return d_tracer;
+ number = strsep(&param, ":");
+
+ if (!strlen(number))
+ goto out_reg;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, (unsigned long *)&count);
+ if (ret)
+ return ret;
+
+ out_reg:
+ ret = register_ftrace_function_probe(glob, ops, count);
+
+ if (ret >= 0)
+ alloc_snapshot(&global_trace);
+
+ return ret < 0 ? ret : 0;
+}
+
+static struct ftrace_func_command ftrace_snapshot_cmd = {
+ .name = "snapshot",
+ .func = ftrace_trace_snapshot_callback,
+};
+
+static int register_snapshot_cmd(void)
+{
+ return register_ftrace_command(&ftrace_snapshot_cmd);
+}
+#else
+static inline int register_snapshot_cmd(void) { return 0; }
+#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */
+
+struct dentry *tracing_init_dentry_tr(struct trace_array *tr)
+{
+ if (tr->dir)
+ return tr->dir;
if (!debugfs_initialized())
return NULL;
- d_tracer = debugfs_create_dir("tracing", NULL);
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ tr->dir = debugfs_create_dir("tracing", NULL);
- if (!d_tracer && !once) {
- once = 1;
- pr_warning("Could not create debugfs directory 'tracing'\n");
- return NULL;
- }
+ if (!tr->dir)
+ pr_warn_once("Could not create debugfs directory 'tracing'\n");
- return d_tracer;
+ return tr->dir;
}
-static struct dentry *d_percpu;
+struct dentry *tracing_init_dentry(void)
+{
+ return tracing_init_dentry_tr(&global_trace);
+}
-static struct dentry *tracing_dentry_percpu(void)
+static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
{
- static int once;
struct dentry *d_tracer;
- if (d_percpu)
- return d_percpu;
-
- d_tracer = tracing_init_dentry();
+ if (tr->percpu_dir)
+ return tr->percpu_dir;
+ d_tracer = tracing_init_dentry_tr(tr);
if (!d_tracer)
return NULL;
- d_percpu = debugfs_create_dir("per_cpu", d_tracer);
+ tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer);
- if (!d_percpu && !once) {
- once = 1;
- pr_warning("Could not create debugfs directory 'per_cpu'\n");
- return NULL;
- }
+ WARN_ONCE(!tr->percpu_dir,
+ "Could not create debugfs directory 'per_cpu/%d'\n", cpu);
- return d_percpu;
+ return tr->percpu_dir;
}
-static void tracing_init_debugfs_percpu(long cpu)
+static void
+tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
{
- struct dentry *d_percpu = tracing_dentry_percpu();
+ struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+ struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
struct dentry *d_cpu;
char cpu_dir[30]; /* 30 characters should be more than enough */
@@ -4672,20 +5331,28 @@ static void tracing_init_debugfs_percpu(long cpu)
/* per cpu trace_pipe */
trace_create_file("trace_pipe", 0444, d_cpu,
- (void *) cpu, &tracing_pipe_fops);
+ (void *)&data->trace_cpu, &tracing_pipe_fops);
/* per cpu trace */
trace_create_file("trace", 0644, d_cpu,
- (void *) cpu, &tracing_fops);
+ (void *)&data->trace_cpu, &tracing_fops);
trace_create_file("trace_pipe_raw", 0444, d_cpu,
- (void *) cpu, &tracing_buffers_fops);
+ (void *)&data->trace_cpu, &tracing_buffers_fops);
trace_create_file("stats", 0444, d_cpu,
- (void *) cpu, &tracing_stats_fops);
+ (void *)&data->trace_cpu, &tracing_stats_fops);
trace_create_file("buffer_size_kb", 0444, d_cpu,
- (void *) cpu, &tracing_entries_fops);
+ (void *)&data->trace_cpu, &tracing_entries_fops);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+ trace_create_file("snapshot", 0644, d_cpu,
+ (void *)&data->trace_cpu, &snapshot_fops);
+
+ trace_create_file("snapshot_raw", 0444, d_cpu,
+ (void *)&data->trace_cpu, &snapshot_raw_fops);
+#endif
}
#ifdef CONFIG_FTRACE_SELFTEST
@@ -4696,6 +5363,7 @@ static void tracing_init_debugfs_percpu(long cpu)
struct trace_option_dentry {
struct tracer_opt *opt;
struct tracer_flags *flags;
+ struct trace_array *tr;
struct dentry *entry;
};
@@ -4731,7 +5399,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (!!(topt->flags->val & topt->opt->bit) != val) {
mutex_lock(&trace_types_lock);
- ret = __set_tracer_option(current_trace, topt->flags,
+ ret = __set_tracer_option(topt->tr->current_trace, topt->flags,
topt->opt, !val);
mutex_unlock(&trace_types_lock);
if (ret)
@@ -4770,6 +5438,7 @@ static ssize_t
trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
+ struct trace_array *tr = &global_trace;
long index = (long)filp->private_data;
unsigned long val;
int ret;
@@ -4780,7 +5449,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (val != 0 && val != 1)
return -EINVAL;
- set_tracer_flags(1 << index, val);
+
+ mutex_lock(&trace_types_lock);
+ ret = set_tracer_flag(tr, 1 << index, val);
+ mutex_unlock(&trace_types_lock);
+
+ if (ret < 0)
+ return ret;
*ppos += cnt;
@@ -4810,40 +5485,41 @@ struct dentry *trace_create_file(const char *name,
}
-static struct dentry *trace_options_init_dentry(void)
+static struct dentry *trace_options_init_dentry(struct trace_array *tr)
{
struct dentry *d_tracer;
- static struct dentry *t_options;
- if (t_options)
- return t_options;
+ if (tr->options)
+ return tr->options;
- d_tracer = tracing_init_dentry();
+ d_tracer = tracing_init_dentry_tr(tr);
if (!d_tracer)
return NULL;
- t_options = debugfs_create_dir("options", d_tracer);
- if (!t_options) {
+ tr->options = debugfs_create_dir("options", d_tracer);
+ if (!tr->options) {
pr_warning("Could not create debugfs directory 'options'\n");
return NULL;
}
- return t_options;
+ return tr->options;
}
static void
-create_trace_option_file(struct trace_option_dentry *topt,
+create_trace_option_file(struct trace_array *tr,
+ struct trace_option_dentry *topt,
struct tracer_flags *flags,
struct tracer_opt *opt)
{
struct dentry *t_options;
- t_options = trace_options_init_dentry();
+ t_options = trace_options_init_dentry(tr);
if (!t_options)
return;
topt->flags = flags;
topt->opt = opt;
+ topt->tr = tr;
topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
&trace_options_fops);
@@ -4851,7 +5527,7 @@ create_trace_option_file(struct trace_option_dentry *topt,
}
static struct trace_option_dentry *
-create_trace_option_files(struct tracer *tracer)
+create_trace_option_files(struct trace_array *tr, struct tracer *tracer)
{
struct trace_option_dentry *topts;
struct tracer_flags *flags;
@@ -4876,7 +5552,7 @@ create_trace_option_files(struct tracer *tracer)
return NULL;
for (cnt = 0; opts[cnt].name; cnt++)
- create_trace_option_file(&topts[cnt], flags,
+ create_trace_option_file(tr, &topts[cnt], flags,
&opts[cnt]);
return topts;
@@ -4899,11 +5575,12 @@ destroy_trace_option_files(struct trace_option_dentry *topts)
}
static struct dentry *
-create_trace_option_core_file(const char *option, long index)
+create_trace_option_core_file(struct trace_array *tr,
+ const char *option, long index)
{
struct dentry *t_options;
- t_options = trace_options_init_dentry();
+ t_options = trace_options_init_dentry(tr);
if (!t_options)
return NULL;
@@ -4911,17 +5588,17 @@ create_trace_option_core_file(const char *option, long index)
&trace_options_core_fops);
}
-static __init void create_trace_options_dir(void)
+static __init void create_trace_options_dir(struct trace_array *tr)
{
struct dentry *t_options;
int i;
- t_options = trace_options_init_dentry();
+ t_options = trace_options_init_dentry(tr);
if (!t_options)
return;
for (i = 0; trace_options[i]; i++)
- create_trace_option_core_file(trace_options[i], i);
+ create_trace_option_core_file(tr, trace_options[i], i);
}
static ssize_t
@@ -4929,7 +5606,7 @@ rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_array *tr = filp->private_data;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
char buf[64];
int r;
@@ -4948,7 +5625,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_array *tr = filp->private_data;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
unsigned long val;
int ret;
@@ -4960,12 +5637,12 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
mutex_lock(&trace_types_lock);
if (val) {
ring_buffer_record_on(buffer);
- if (current_trace->start)
- current_trace->start(tr);
+ if (tr->current_trace->start)
+ tr->current_trace->start(tr);
} else {
ring_buffer_record_off(buffer);
- if (current_trace->stop)
- current_trace->stop(tr);
+ if (tr->current_trace->stop)
+ tr->current_trace->stop(tr);
}
mutex_unlock(&trace_types_lock);
}
@@ -4982,23 +5659,310 @@ static const struct file_operations rb_simple_fops = {
.llseek = default_llseek,
};
+struct dentry *trace_instance_dir;
+
+static void
+init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
+
+static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf)
+{
+ int cpu;
+
+ for_each_tracing_cpu(cpu) {
+ memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu));
+ per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu;
+ per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr;
+ }
+}
+
+static int
+allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
+{
+ enum ring_buffer_flags rb_flags;
+
+ rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
+ buf->buffer = ring_buffer_alloc(size, rb_flags);
+ if (!buf->buffer)
+ return -ENOMEM;
+
+ buf->data = alloc_percpu(struct trace_array_cpu);
+ if (!buf->data) {
+ ring_buffer_free(buf->buffer);
+ return -ENOMEM;
+ }
+
+ init_trace_buffers(tr, buf);
+
+ /* Allocate the first page for all buffers */
+ set_buffer_entries(&tr->trace_buffer,
+ ring_buffer_size(tr->trace_buffer.buffer, 0));
+
+ return 0;
+}
+
+static int allocate_trace_buffers(struct trace_array *tr, int size)
+{
+ int ret;
+
+ ret = allocate_trace_buffer(tr, &tr->trace_buffer, size);
+ if (ret)
+ return ret;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ret = allocate_trace_buffer(tr, &tr->max_buffer,
+ allocate_snapshot ? size : 1);
+ if (WARN_ON(ret)) {
+ ring_buffer_free(tr->trace_buffer.buffer);
+ free_percpu(tr->trace_buffer.data);
+ return -ENOMEM;
+ }
+ tr->allocated_snapshot = allocate_snapshot;
+
+ /*
+ * Only the top level trace array gets its snapshot allocated
+ * from the kernel command line.
+ */
+ allocate_snapshot = false;
+#endif
+ return 0;
+}
+
+static int new_instance_create(const char *name)
+{
+ struct trace_array *tr;
+ int ret;
+
+ mutex_lock(&trace_types_lock);
+
+ ret = -EEXIST;
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr->name && strcmp(tr->name, name) == 0)
+ goto out_unlock;
+ }
+
+ ret = -ENOMEM;
+ tr = kzalloc(sizeof(*tr), GFP_KERNEL);
+ if (!tr)
+ goto out_unlock;
+
+ tr->name = kstrdup(name, GFP_KERNEL);
+ if (!tr->name)
+ goto out_free_tr;
+
+ raw_spin_lock_init(&tr->start_lock);
+
+ tr->current_trace = &nop_trace;
+
+ INIT_LIST_HEAD(&tr->systems);
+ INIT_LIST_HEAD(&tr->events);
+
+ if (allocate_trace_buffers(tr, trace_buf_size) < 0)
+ goto out_free_tr;
+
+ /* Holder for file callbacks */
+ tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
+ tr->trace_cpu.tr = tr;
+
+ tr->dir = debugfs_create_dir(name, trace_instance_dir);
+ if (!tr->dir)
+ goto out_free_tr;
+
+ ret = event_trace_add_tracer(tr->dir, tr);
+ if (ret)
+ goto out_free_tr;
+
+ init_tracer_debugfs(tr, tr->dir);
+
+ list_add(&tr->list, &ftrace_trace_arrays);
+
+ mutex_unlock(&trace_types_lock);
+
+ return 0;
+
+ out_free_tr:
+ if (tr->trace_buffer.buffer)
+ ring_buffer_free(tr->trace_buffer.buffer);
+ kfree(tr->name);
+ kfree(tr);
+
+ out_unlock:
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+
+}
+
+static int instance_delete(const char *name)
+{
+ struct trace_array *tr;
+ int found = 0;
+ int ret;
+
+ mutex_lock(&trace_types_lock);
+
+ ret = -ENODEV;
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr->name && strcmp(tr->name, name) == 0) {
+ found = 1;
+ break;
+ }
+ }
+ if (!found)
+ goto out_unlock;
+
+ ret = -EBUSY;
+ if (tr->ref)
+ goto out_unlock;
+
+ list_del(&tr->list);
+
+ event_trace_del_tracer(tr);
+ debugfs_remove_recursive(tr->dir);
+ free_percpu(tr->trace_buffer.data);
+ ring_buffer_free(tr->trace_buffer.buffer);
+
+ kfree(tr->name);
+ kfree(tr);
+
+ ret = 0;
+
+ out_unlock:
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+}
+
+static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode)
+{
+ struct dentry *parent;
+ int ret;
+
+ /* Paranoid: Make sure the parent is the "instances" directory */
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ if (WARN_ON_ONCE(parent != trace_instance_dir))
+ return -ENOENT;
+
+ /*
+ * The inode mutex is locked, but debugfs_create_dir() will also
+ * take the mutex. As the instances directory can not be destroyed
+ * or changed in any other way, it is safe to unlock it, and
+ * let the dentry try. If two users try to make the same dir at
+ * the same time, then the new_instance_create() will determine the
+ * winner.
+ */
+ mutex_unlock(&inode->i_mutex);
+
+ ret = new_instance_create(dentry->d_iname);
+
+ mutex_lock(&inode->i_mutex);
+
+ return ret;
+}
+
+static int instance_rmdir(struct inode *inode, struct dentry *dentry)
+{
+ struct dentry *parent;
+ int ret;
+
+ /* Paranoid: Make sure the parent is the "instances" directory */
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ if (WARN_ON_ONCE(parent != trace_instance_dir))
+ return -ENOENT;
+
+ /* The caller did a dget() on dentry */
+ mutex_unlock(&dentry->d_inode->i_mutex);
+
+ /*
+ * The inode mutex is locked, but debugfs_create_dir() will also
+ * take the mutex. As the instances directory can not be destroyed
+ * or changed in any other way, it is safe to unlock it, and
+ * let the dentry try. If two users try to make the same dir at
+ * the same time, then the instance_delete() will determine the
+ * winner.
+ */
+ mutex_unlock(&inode->i_mutex);
+
+ ret = instance_delete(dentry->d_iname);
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock(&dentry->d_inode->i_mutex);
+
+ return ret;
+}
+
+static const struct inode_operations instance_dir_inode_operations = {
+ .lookup = simple_lookup,
+ .mkdir = instance_mkdir,
+ .rmdir = instance_rmdir,
+};
+
+static __init void create_trace_instances(struct dentry *d_tracer)
+{
+ trace_instance_dir = debugfs_create_dir("instances", d_tracer);
+ if (WARN_ON(!trace_instance_dir))
+ return;
+
+ /* Hijack the dir inode operations, to allow mkdir */
+ trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations;
+}
+
+static void
+init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
+{
+ int cpu;
+
+ trace_create_file("trace_options", 0644, d_tracer,
+ tr, &tracing_iter_fops);
+
+ trace_create_file("trace", 0644, d_tracer,
+ (void *)&tr->trace_cpu, &tracing_fops);
+
+ trace_create_file("trace_pipe", 0444, d_tracer,
+ (void *)&tr->trace_cpu, &tracing_pipe_fops);
+
+ trace_create_file("buffer_size_kb", 0644, d_tracer,
+ (void *)&tr->trace_cpu, &tracing_entries_fops);
+
+ trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+ tr, &tracing_total_entries_fops);
+
+ trace_create_file("free_buffer", 0644, d_tracer,
+ tr, &tracing_free_buffer_fops);
+
+ trace_create_file("trace_marker", 0220, d_tracer,
+ tr, &tracing_mark_fops);
+
+ trace_create_file("trace_clock", 0644, d_tracer, tr,
+ &trace_clock_fops);
+
+ trace_create_file("tracing_on", 0644, d_tracer,
+ tr, &rb_simple_fops);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+ trace_create_file("snapshot", 0644, d_tracer,
+ (void *)&tr->trace_cpu, &snapshot_fops);
+#endif
+
+ for_each_tracing_cpu(cpu)
+ tracing_init_debugfs_percpu(tr, cpu);
+
+}
+
static __init int tracer_init_debugfs(void)
{
struct dentry *d_tracer;
- int cpu;
trace_access_lock_init();
d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
- trace_create_file("trace_options", 0644, d_tracer,
- NULL, &tracing_iter_fops);
+ init_tracer_debugfs(&global_trace, d_tracer);
trace_create_file("tracing_cpumask", 0644, d_tracer,
- NULL, &tracing_cpumask_fops);
-
- trace_create_file("trace", 0644, d_tracer,
- (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
+ &global_trace, &tracing_cpumask_fops);
trace_create_file("available_tracers", 0444, d_tracer,
&global_trace, &show_traces_fops);
@@ -5017,44 +5981,17 @@ static __init int tracer_init_debugfs(void)
trace_create_file("README", 0444, d_tracer,
NULL, &tracing_readme_fops);
- trace_create_file("trace_pipe", 0444, d_tracer,
- (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
-
- trace_create_file("buffer_size_kb", 0644, d_tracer,
- (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops);
-
- trace_create_file("buffer_total_size_kb", 0444, d_tracer,
- &global_trace, &tracing_total_entries_fops);
-
- trace_create_file("free_buffer", 0644, d_tracer,
- &global_trace, &tracing_free_buffer_fops);
-
- trace_create_file("trace_marker", 0220, d_tracer,
- NULL, &tracing_mark_fops);
-
trace_create_file("saved_cmdlines", 0444, d_tracer,
NULL, &tracing_saved_cmdlines_fops);
- trace_create_file("trace_clock", 0644, d_tracer, NULL,
- &trace_clock_fops);
-
- trace_create_file("tracing_on", 0644, d_tracer,
- &global_trace, &rb_simple_fops);
-
#ifdef CONFIG_DYNAMIC_FTRACE
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
#endif
-#ifdef CONFIG_TRACER_SNAPSHOT
- trace_create_file("snapshot", 0644, d_tracer,
- (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops);
-#endif
-
- create_trace_options_dir();
+ create_trace_instances(d_tracer);
- for_each_tracing_cpu(cpu)
- tracing_init_debugfs_percpu(cpu);
+ create_trace_options_dir(&global_trace);
return 0;
}
@@ -5110,8 +6047,8 @@ void
trace_printk_seq(struct trace_seq *s)
{
/* Probably should print a warning here. */
- if (s->len >= 1000)
- s->len = 1000;
+ if (s->len >= TRACE_MAX_PRINT)
+ s->len = TRACE_MAX_PRINT;
/* should be zero ended, but we are paranoid. */
s->buffer[s->len] = 0;
@@ -5124,46 +6061,43 @@ trace_printk_seq(struct trace_seq *s)
void trace_init_global_iter(struct trace_iterator *iter)
{
iter->tr = &global_trace;
- iter->trace = current_trace;
- iter->cpu_file = TRACE_PIPE_ALL_CPU;
+ iter->trace = iter->tr->current_trace;
+ iter->cpu_file = RING_BUFFER_ALL_CPUS;
+ iter->trace_buffer = &global_trace.trace_buffer;
}
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
{
- static arch_spinlock_t ftrace_dump_lock =
- (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
+ static atomic_t dump_running;
unsigned int old_userobj;
- static int dump_ran;
unsigned long flags;
int cnt = 0, cpu;
- /* only one dump */
- local_irq_save(flags);
- arch_spin_lock(&ftrace_dump_lock);
- if (dump_ran)
- goto out;
-
- dump_ran = 1;
+ /* Only allow one dump user at a time. */
+ if (atomic_inc_return(&dump_running) != 1) {
+ atomic_dec(&dump_running);
+ return;
+ }
+ /*
+ * Always turn off tracing when we dump.
+ * We don't need to show trace output of what happens
+ * between multiple crashes.
+ *
+ * If the user does a sysrq-z, then they can re-enable
+ * tracing with echo 1 > tracing_on.
+ */
tracing_off();
- /* Did function tracer already get disabled? */
- if (ftrace_is_dead()) {
- printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
- printk("# MAY BE MISSING FUNCTION EVENTS\n");
- }
-
- if (disable_tracing)
- ftrace_kill();
+ local_irq_save(flags);
/* Simulate the iterator */
trace_init_global_iter(&iter);
for_each_tracing_cpu(cpu) {
- atomic_inc(&iter.tr->data[cpu]->disabled);
+ atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled);
}
old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
@@ -5173,7 +6107,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
switch (oops_dump_mode) {
case DUMP_ALL:
- iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ iter.cpu_file = RING_BUFFER_ALL_CPUS;
break;
case DUMP_ORIG:
iter.cpu_file = raw_smp_processor_id();
@@ -5182,11 +6116,17 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
goto out_enable;
default:
printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
- iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ iter.cpu_file = RING_BUFFER_ALL_CPUS;
}
printk(KERN_TRACE "Dumping ftrace buffer:\n");
+ /* Did function tracer already get disabled? */
+ if (ftrace_is_dead()) {
+ printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+ printk("# MAY BE MISSING FUNCTION EVENTS\n");
+ }
+
/*
* We need to stop all tracing on all CPUS to read the
* the next buffer. This is a bit expensive, but is
@@ -5226,33 +6166,19 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
printk(KERN_TRACE "---------------------------------\n");
out_enable:
- /* Re-enable tracing if requested */
- if (!disable_tracing) {
- trace_flags |= old_userobj;
+ trace_flags |= old_userobj;
- for_each_tracing_cpu(cpu) {
- atomic_dec(&iter.tr->data[cpu]->disabled);
- }
- tracing_on();
+ for_each_tracing_cpu(cpu) {
+ atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
}
-
- out:
- arch_spin_unlock(&ftrace_dump_lock);
+ atomic_dec(&dump_running);
local_irq_restore(flags);
}
-
-/* By default: disable tracing after the dump */
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
-{
- __ftrace_dump(true, oops_dump_mode);
-}
EXPORT_SYMBOL_GPL(ftrace_dump);
__init static int tracer_alloc_buffers(void)
{
int ring_buf_size;
- enum ring_buffer_flags rb_flags;
- int i;
int ret = -ENOMEM;
@@ -5273,49 +6199,27 @@ __init static int tracer_alloc_buffers(void)
else
ring_buf_size = 1;
- rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
-
cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
cpumask_copy(tracing_cpumask, cpu_all_mask);
+ raw_spin_lock_init(&global_trace.start_lock);
+
/* TODO: make the number of buffers hot pluggable with CPUS */
- global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
- if (!global_trace.buffer) {
+ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
WARN_ON(1);
goto out_free_cpumask;
}
+
if (global_trace.buffer_disabled)
tracing_off();
-
-#ifdef CONFIG_TRACER_MAX_TRACE
- max_tr.buffer = ring_buffer_alloc(1, rb_flags);
- if (!max_tr.buffer) {
- printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
- WARN_ON(1);
- ring_buffer_free(global_trace.buffer);
- goto out_free_cpumask;
- }
-#endif
-
- /* Allocate the first page for all buffers */
- for_each_tracing_cpu(i) {
- global_trace.data[i] = &per_cpu(global_trace_cpu, i);
- max_tr.data[i] = &per_cpu(max_tr_data, i);
- }
-
- set_buffer_entries(&global_trace,
- ring_buffer_size(global_trace.buffer, 0));
-#ifdef CONFIG_TRACER_MAX_TRACE
- set_buffer_entries(&max_tr, 1);
-#endif
-
trace_init_cmdlines();
- init_irq_work(&trace_work_wakeup, trace_wake_up);
register_tracer(&nop_trace);
+ global_trace.current_trace = &nop_trace;
+
/* All seems OK, enable tracing */
tracing_disabled = 0;
@@ -5324,16 +6228,32 @@ __init static int tracer_alloc_buffers(void)
register_die_notifier(&trace_die_notifier);
+ global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
+
+ /* Holder for file callbacks */
+ global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS;
+ global_trace.trace_cpu.tr = &global_trace;
+
+ INIT_LIST_HEAD(&global_trace.systems);
+ INIT_LIST_HEAD(&global_trace.events);
+ list_add(&global_trace.list, &ftrace_trace_arrays);
+
while (trace_boot_options) {
char *option;
option = strsep(&trace_boot_options, ",");
- trace_set_options(option);
+ trace_set_options(&global_trace, option);
}
+ register_snapshot_cmd();
+
return 0;
out_free_cpumask:
+ free_percpu(global_trace.trace_buffer.data);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ free_percpu(global_trace.max_buffer.data);
+#endif
free_cpumask_var(tracing_cpumask);
out_free_buffer_mask:
free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57d7e5397d56..711ca7d3e7f1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -13,6 +13,11 @@
#include <linux/trace_seq.h>
#include <linux/ftrace_event.h>
+#ifdef CONFIG_FTRACE_SYSCALLS
+#include <asm/unistd.h> /* For NR_SYSCALLS */
+#include <asm/syscall.h> /* some archs define it here */
+#endif
+
enum trace_type {
__TRACE_FIRST_TYPE = 0,
@@ -29,6 +34,7 @@ enum trace_type {
TRACE_GRAPH_ENT,
TRACE_USER_STACK,
TRACE_BLK,
+ TRACE_BPUTS,
__TRACE_LAST_TYPE,
};
@@ -103,11 +109,6 @@ struct kretprobe_trace_entry_head {
unsigned long ret_ip;
};
-struct uprobe_trace_entry_head {
- struct trace_entry ent;
- unsigned long ip;
-};
-
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
@@ -127,12 +128,21 @@ enum trace_flag_type {
#define TRACE_BUF_SIZE 1024
+struct trace_array;
+
+struct trace_cpu {
+ struct trace_array *tr;
+ struct dentry *dir;
+ int cpu;
+};
+
/*
* The CPU trace array - it consists of thousands of trace entries
* plus some other descriptor data: (for example which task started
* the trace, etc.)
*/
struct trace_array_cpu {
+ struct trace_cpu trace_cpu;
atomic_t disabled;
void *buffer_page; /* ring buffer spare */
@@ -151,20 +161,83 @@ struct trace_array_cpu {
char comm[TASK_COMM_LEN];
};
+struct tracer;
+
+struct trace_buffer {
+ struct trace_array *tr;
+ struct ring_buffer *buffer;
+ struct trace_array_cpu __percpu *data;
+ cycle_t time_start;
+ int cpu;
+};
+
/*
* The trace array - an array of per-CPU trace arrays. This is the
* highest level data structure that individual tracers deal with.
* They have on/off state as well:
*/
struct trace_array {
- struct ring_buffer *buffer;
- int cpu;
+ struct list_head list;
+ char *name;
+ struct trace_buffer trace_buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+ /*
+ * The max_buffer is used to snapshot the trace when a maximum
+ * latency is reached, or when the user initiates a snapshot.
+ * Some tracers will use this to store a maximum trace while
+ * it continues examining live traces.
+ *
+ * The buffers for the max_buffer are set up the same as the trace_buffer
+ * When a snapshot is taken, the buffer of the max_buffer is swapped
+ * with the buffer of the trace_buffer and the buffers are reset for
+ * the trace_buffer so the tracing can continue.
+ */
+ struct trace_buffer max_buffer;
+ bool allocated_snapshot;
+#endif
int buffer_disabled;
- cycle_t time_start;
+ struct trace_cpu trace_cpu; /* place holder */
+#ifdef CONFIG_FTRACE_SYSCALLS
+ int sys_refcount_enter;
+ int sys_refcount_exit;
+ DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
+ DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+#endif
+ int stop_count;
+ int clock_id;
+ struct tracer *current_trace;
+ unsigned int flags;
+ raw_spinlock_t start_lock;
+ struct dentry *dir;
+ struct dentry *options;
+ struct dentry *percpu_dir;
+ struct dentry *event_dir;
+ struct list_head systems;
+ struct list_head events;
struct task_struct *waiter;
- struct trace_array_cpu *data[NR_CPUS];
+ int ref;
+};
+
+enum {
+ TRACE_ARRAY_FL_GLOBAL = (1 << 0)
};
+extern struct list_head ftrace_trace_arrays;
+
+/*
+ * The global tracer (top) should be the first trace array added,
+ * but we check the flag anyway.
+ */
+static inline struct trace_array *top_trace_array(void)
+{
+ struct trace_array *tr;
+
+ tr = list_entry(ftrace_trace_arrays.prev,
+ typeof(*tr), list);
+ WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
+ return tr;
+}
+
#define FTRACE_CMP_TYPE(var, type) \
__builtin_types_compatible_p(typeof(var), type *)
@@ -200,6 +273,7 @@ extern void __ftrace_bad_type(void);
IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \
+ IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
TRACE_MMIO_RW); \
IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
@@ -283,11 +357,16 @@ struct tracer {
enum print_line_t (*print_line)(struct trace_iterator *iter);
/* If you handled the flag setting, return 0 */
int (*set_flag)(u32 old_flags, u32 bit, int set);
+ /* Return 0 if OK with change, else return non-zero */
+ int (*flag_changed)(struct tracer *tracer,
+ u32 mask, int set);
struct tracer *next;
struct tracer_flags *flags;
bool print_max;
+ bool enabled;
+#ifdef CONFIG_TRACER_MAX_TRACE
bool use_max_tr;
- bool allocated_snapshot;
+#endif
};
@@ -423,8 +502,6 @@ static __always_inline void trace_clear_recursion(int bit)
current->trace_recursion = val;
}
-#define TRACE_PIPE_ALL_CPU -1
-
static inline struct ring_buffer_iter *
trace_buffer_iter(struct trace_iterator *iter, int cpu)
{
@@ -435,10 +512,10 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
-void tracing_reset(struct trace_array *tr, int cpu);
-void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset(struct trace_buffer *buf, int cpu);
+void tracing_reset_online_cpus(struct trace_buffer *buf);
void tracing_reset_current(int cpu);
-void tracing_reset_current_online_cpus(void);
+void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
struct dentry *trace_create_file(const char *name,
umode_t mode,
@@ -446,6 +523,7 @@ struct dentry *trace_create_file(const char *name,
void *data,
const struct file_operations *fops);
+struct dentry *tracing_init_dentry_tr(struct trace_array *tr);
struct dentry *tracing_init_dentry(void);
struct ring_buffer_event;
@@ -579,7 +657,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
-extern int ring_buffer_expanded;
+extern bool ring_buffer_expanded;
extern bool tracing_selftest_disabled;
DECLARE_PER_CPU(int, ftrace_cpu_disabled);
@@ -615,6 +693,8 @@ trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args);
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...);
+int trace_array_printk_buf(struct ring_buffer *buffer,
+ unsigned long ip, const char *fmt, ...);
void trace_printk_seq(struct trace_seq *s);
enum print_line_t print_trace_line(struct trace_iterator *iter);
@@ -782,6 +862,7 @@ enum trace_iterator_flags {
TRACE_ITER_STOP_ON_FREE = 0x400000,
TRACE_ITER_IRQ_INFO = 0x800000,
TRACE_ITER_MARKERS = 0x1000000,
+ TRACE_ITER_FUNCTION = 0x2000000,
};
/*
@@ -828,8 +909,8 @@ enum {
struct ftrace_event_field {
struct list_head link;
- char *name;
- char *type;
+ const char *name;
+ const char *type;
int filter_type;
int offset;
int size;
@@ -847,12 +928,19 @@ struct event_filter {
struct event_subsystem {
struct list_head list;
const char *name;
- struct dentry *entry;
struct event_filter *filter;
- int nr_events;
int ref_count;
};
+struct ftrace_subsystem_dir {
+ struct list_head list;
+ struct event_subsystem *subsystem;
+ struct trace_array *tr;
+ struct dentry *entry;
+ int ref_count;
+ int nr_events;
+};
+
#define FILTER_PRED_INVALID ((unsigned short)-1)
#define FILTER_PRED_IS_RIGHT (1 << 15)
#define FILTER_PRED_FOLD (1 << 15)
@@ -902,22 +990,20 @@ struct filter_pred {
unsigned short right;
};
-extern struct list_head ftrace_common_fields;
-
extern enum regex_type
filter_parse_regex(char *buff, int len, char **search, int *not);
extern void print_event_filter(struct ftrace_event_call *call,
struct trace_seq *s);
extern int apply_event_filter(struct ftrace_event_call *call,
char *filter_string);
-extern int apply_subsystem_event_filter(struct event_subsystem *system,
+extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
char *filter_string);
extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
-struct list_head *
-trace_get_fields(struct ftrace_event_call *event_call);
+struct ftrace_event_field *
+trace_find_event_field(struct ftrace_event_call *call, char *name);
static inline int
filter_check_discard(struct ftrace_event_call *call, void *rec,
@@ -934,6 +1020,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
}
extern void trace_event_enable_cmd_record(bool enable);
+extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
+extern int event_trace_del_tracer(struct trace_array *tr);
extern struct mutex event_mutex;
extern struct list_head ftrace_events;
@@ -943,6 +1031,19 @@ extern const char *__stop___trace_bprintk_fmt[];
void trace_printk_init_buffers(void);
void trace_printk_start_comm(void);
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
+
+/*
+ * Normal trace_printk() and friends allocates special buffers
+ * to do the manipulation, as well as saves the print formats
+ * into sections to display. But the trace infrastructure wants
+ * to use these without the added overhead at the price of being
+ * a bit slower (used mainly for warnings, where we don't care
+ * about performance). The internal_trace_puts() is for such
+ * a purpose.
+ */
+#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str))
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 95e96842ed29..d594da0dc03c 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -32,6 +32,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
struct ftrace_event_call *call = &event_branch;
struct trace_array *tr = branch_tracer;
+ struct trace_array_cpu *data;
struct ring_buffer_event *event;
struct trace_branch *entry;
struct ring_buffer *buffer;
@@ -51,11 +52,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
local_irq_save(flags);
cpu = raw_smp_processor_id();
- if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+ if (atomic_inc_return(&data->disabled) != 1)
goto out;
pc = preempt_count();
- buffer = tr->buffer;
+ buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
sizeof(*entry), flags, pc);
if (!event)
@@ -80,7 +82,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
__buffer_unlock_commit(buffer, event);
out:
- atomic_dec(&tr->data[cpu]->disabled);
+ atomic_dec(&data->disabled);
local_irq_restore(flags);
}
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index aa8f5f48dae6..26dc348332b7 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -57,6 +57,16 @@ u64 notrace trace_clock(void)
return local_clock();
}
+/*
+ * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ */
+u64 notrace trace_clock_jiffies(void)
+{
+ u64 jiffy = jiffies - INITIAL_JIFFIES;
+
+ /* Return nsecs */
+ return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+}
/*
* trace_clock_global(): special globally coherent trace clock
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 4108e1250ca2..e2d027ac66a2 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -223,8 +223,8 @@ FTRACE_ENTRY(bprint, bprint_entry,
__dynamic_array( u32, buf )
),
- F_printk("%08lx fmt:%p",
- __entry->ip, __entry->fmt),
+ F_printk("%pf: %s",
+ (void *)__entry->ip, __entry->fmt),
FILTER_OTHER
);
@@ -238,8 +238,23 @@ FTRACE_ENTRY(print, print_entry,
__dynamic_array( char, buf )
),
- F_printk("%08lx %s",
- __entry->ip, __entry->buf),
+ F_printk("%pf: %s",
+ (void *)__entry->ip, __entry->buf),
+
+ FILTER_OTHER
+);
+
+FTRACE_ENTRY(bputs, bputs_entry,
+
+ TRACE_BPUTS,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( const char *, str )
+ ),
+
+ F_printk("%pf: %s",
+ (void *)__entry->ip, __entry->str),
FILTER_OTHER
);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 57e9b284250c..53582e982e51 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -34,9 +34,27 @@ char event_storage[EVENT_STORAGE_SIZE];
EXPORT_SYMBOL_GPL(event_storage);
LIST_HEAD(ftrace_events);
-LIST_HEAD(ftrace_common_fields);
+static LIST_HEAD(ftrace_common_fields);
-struct list_head *
+#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
+
+static struct kmem_cache *field_cachep;
+static struct kmem_cache *file_cachep;
+
+/* Double loops, do not use break, only goto's work */
+#define do_for_each_event_file(tr, file) \
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \
+ list_for_each_entry(file, &tr->events, list)
+
+#define do_for_each_event_file_safe(tr, file) \
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \
+ struct ftrace_event_file *___n; \
+ list_for_each_entry_safe(file, ___n, &tr->events, list)
+
+#define while_for_each_event_file() \
+ }
+
+static struct list_head *
trace_get_fields(struct ftrace_event_call *event_call)
{
if (!event_call->class->get_fields)
@@ -44,23 +62,45 @@ trace_get_fields(struct ftrace_event_call *event_call)
return event_call->class->get_fields(event_call);
}
+static struct ftrace_event_field *
+__find_event_field(struct list_head *head, char *name)
+{
+ struct ftrace_event_field *field;
+
+ list_for_each_entry(field, head, link) {
+ if (!strcmp(field->name, name))
+ return field;
+ }
+
+ return NULL;
+}
+
+struct ftrace_event_field *
+trace_find_event_field(struct ftrace_event_call *call, char *name)
+{
+ struct ftrace_event_field *field;
+ struct list_head *head;
+
+ field = __find_event_field(&ftrace_common_fields, name);
+ if (field)
+ return field;
+
+ head = trace_get_fields(call);
+ return __find_event_field(head, name);
+}
+
static int __trace_define_field(struct list_head *head, const char *type,
const char *name, int offset, int size,
int is_signed, int filter_type)
{
struct ftrace_event_field *field;
- field = kzalloc(sizeof(*field), GFP_KERNEL);
+ field = kmem_cache_alloc(field_cachep, GFP_TRACE);
if (!field)
goto err;
- field->name = kstrdup(name, GFP_KERNEL);
- if (!field->name)
- goto err;
-
- field->type = kstrdup(type, GFP_KERNEL);
- if (!field->type)
- goto err;
+ field->name = name;
+ field->type = type;
if (filter_type == FILTER_OTHER)
field->filter_type = filter_assign_type(type);
@@ -76,9 +116,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
return 0;
err:
- if (field)
- kfree(field->name);
- kfree(field);
+ kmem_cache_free(field_cachep, field);
return -ENOMEM;
}
@@ -120,7 +158,7 @@ static int trace_define_common_fields(void)
return ret;
}
-void trace_destroy_fields(struct ftrace_event_call *call)
+static void trace_destroy_fields(struct ftrace_event_call *call)
{
struct ftrace_event_field *field, *next;
struct list_head *head;
@@ -128,9 +166,7 @@ void trace_destroy_fields(struct ftrace_event_call *call)
head = trace_get_fields(call);
list_for_each_entry_safe(field, next, head, link) {
list_del(&field->link);
- kfree(field->type);
- kfree(field->name);
- kfree(field);
+ kmem_cache_free(field_cachep, field);
}
}
@@ -149,15 +185,17 @@ EXPORT_SYMBOL_GPL(trace_event_raw_init);
int ftrace_event_reg(struct ftrace_event_call *call,
enum trace_reg type, void *data)
{
+ struct ftrace_event_file *file = data;
+
switch (type) {
case TRACE_REG_REGISTER:
return tracepoint_probe_register(call->name,
call->class->probe,
- call);
+ file);
case TRACE_REG_UNREGISTER:
tracepoint_probe_unregister(call->name,
call->class->probe,
- call);
+ file);
return 0;
#ifdef CONFIG_PERF_EVENTS
@@ -183,54 +221,100 @@ EXPORT_SYMBOL_GPL(ftrace_event_reg);
void trace_event_enable_cmd_record(bool enable)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
+ struct trace_array *tr;
mutex_lock(&event_mutex);
- list_for_each_entry(call, &ftrace_events, list) {
- if (!(call->flags & TRACE_EVENT_FL_ENABLED))
+ do_for_each_event_file(tr, file) {
+
+ if (!(file->flags & FTRACE_EVENT_FL_ENABLED))
continue;
if (enable) {
tracing_start_cmdline_record();
- call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+ set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
} else {
tracing_stop_cmdline_record();
- call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+ clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
}
- }
+ } while_for_each_event_file();
mutex_unlock(&event_mutex);
}
-static int ftrace_event_enable_disable(struct ftrace_event_call *call,
- int enable)
+static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable)
{
+ struct ftrace_event_call *call = file->event_call;
int ret = 0;
+ int disable;
switch (enable) {
case 0:
- if (call->flags & TRACE_EVENT_FL_ENABLED) {
- call->flags &= ~TRACE_EVENT_FL_ENABLED;
- if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) {
+ /*
+ * When soft_disable is set and enable is cleared, we want
+ * to clear the SOFT_DISABLED flag but leave the event in the
+ * state that it was. That is, if the event was enabled and
+ * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED
+ * is set we do not want the event to be enabled before we
+ * clear the bit.
+ *
+ * When soft_disable is not set but the SOFT_MODE flag is,
+ * we do nothing. Do not disable the tracepoint, otherwise
+ * "soft enable"s (clearing the SOFT_DISABLED bit) wont work.
+ */
+ if (soft_disable) {
+ disable = file->flags & FTRACE_EVENT_FL_SOFT_DISABLED;
+ clear_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags);
+ } else
+ disable = !(file->flags & FTRACE_EVENT_FL_SOFT_MODE);
+
+ if (disable && (file->flags & FTRACE_EVENT_FL_ENABLED)) {
+ clear_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags);
+ if (file->flags & FTRACE_EVENT_FL_RECORDED_CMD) {
tracing_stop_cmdline_record();
- call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+ clear_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
}
- call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
+ call->class->reg(call, TRACE_REG_UNREGISTER, file);
}
+ /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT */
+ if (file->flags & FTRACE_EVENT_FL_SOFT_MODE)
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
break;
case 1:
- if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
+ /*
+ * When soft_disable is set and enable is set, we want to
+ * register the tracepoint for the event, but leave the event
+ * as is. That means, if the event was already enabled, we do
+ * nothing (but set SOFT_MODE). If the event is disabled, we
+ * set SOFT_DISABLED before enabling the event tracepoint, so
+ * it still seems to be disabled.
+ */
+ if (!soft_disable)
+ clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
+ else
+ set_bit(FTRACE_EVENT_FL_SOFT_MODE_BIT, &file->flags);
+
+ if (!(file->flags & FTRACE_EVENT_FL_ENABLED)) {
+
+ /* Keep the event disabled, when going to SOFT_MODE. */
+ if (soft_disable)
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
+
if (trace_flags & TRACE_ITER_RECORD_CMD) {
tracing_start_cmdline_record();
- call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+ set_bit(FTRACE_EVENT_FL_RECORDED_CMD_BIT, &file->flags);
}
- ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
+ ret = call->class->reg(call, TRACE_REG_REGISTER, file);
if (ret) {
tracing_stop_cmdline_record();
pr_info("event trace: Could not enable event "
"%s\n", call->name);
break;
}
- call->flags |= TRACE_EVENT_FL_ENABLED;
+ set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags);
+
+ /* WAS_ENABLED gets set but never cleared. */
+ call->flags |= TRACE_EVENT_FL_WAS_ENABLED;
}
break;
}
@@ -238,13 +322,19 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
return ret;
}
-static void ftrace_clear_events(void)
+static int ftrace_event_enable_disable(struct ftrace_event_file *file,
+ int enable)
{
- struct ftrace_event_call *call;
+ return __ftrace_event_enable_disable(file, enable, 0);
+}
+
+static void ftrace_clear_events(struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
mutex_lock(&event_mutex);
- list_for_each_entry(call, &ftrace_events, list) {
- ftrace_event_enable_disable(call, 0);
+ list_for_each_entry(file, &tr->events, list) {
+ ftrace_event_enable_disable(file, 0);
}
mutex_unlock(&event_mutex);
}
@@ -257,11 +347,12 @@ static void __put_system(struct event_subsystem *system)
if (--system->ref_count)
return;
+ list_del(&system->list);
+
if (filter) {
kfree(filter->filter_string);
kfree(filter);
}
- kfree(system->name);
kfree(system);
}
@@ -271,24 +362,45 @@ static void __get_system(struct event_subsystem *system)
system->ref_count++;
}
-static void put_system(struct event_subsystem *system)
+static void __get_system_dir(struct ftrace_subsystem_dir *dir)
+{
+ WARN_ON_ONCE(dir->ref_count == 0);
+ dir->ref_count++;
+ __get_system(dir->subsystem);
+}
+
+static void __put_system_dir(struct ftrace_subsystem_dir *dir)
+{
+ WARN_ON_ONCE(dir->ref_count == 0);
+ /* If the subsystem is about to be freed, the dir must be too */
+ WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1);
+
+ __put_system(dir->subsystem);
+ if (!--dir->ref_count)
+ kfree(dir);
+}
+
+static void put_system(struct ftrace_subsystem_dir *dir)
{
mutex_lock(&event_mutex);
- __put_system(system);
+ __put_system_dir(dir);
mutex_unlock(&event_mutex);
}
/*
* __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
*/
-static int __ftrace_set_clr_event(const char *match, const char *sub,
- const char *event, int set)
+static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
+ const char *sub, const char *event, int set)
{
+ struct ftrace_event_file *file;
struct ftrace_event_call *call;
int ret = -EINVAL;
mutex_lock(&event_mutex);
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
+
+ call = file->event_call;
if (!call->name || !call->class || !call->class->reg)
continue;
@@ -307,7 +419,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
if (event && strcmp(event, call->name) != 0)
continue;
- ftrace_event_enable_disable(call, set);
+ ftrace_event_enable_disable(file, set);
ret = 0;
}
@@ -316,7 +428,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
return ret;
}
-static int ftrace_set_clr_event(char *buf, int set)
+static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
@@ -344,7 +456,7 @@ static int ftrace_set_clr_event(char *buf, int set)
event = NULL;
}
- return __ftrace_set_clr_event(match, sub, event, set);
+ return __ftrace_set_clr_event(tr, match, sub, event, set);
}
/**
@@ -361,7 +473,9 @@ static int ftrace_set_clr_event(char *buf, int set)
*/
int trace_set_clr_event(const char *system, const char *event, int set)
{
- return __ftrace_set_clr_event(NULL, system, event, set);
+ struct trace_array *tr = top_trace_array();
+
+ return __ftrace_set_clr_event(tr, NULL, system, event, set);
}
EXPORT_SYMBOL_GPL(trace_set_clr_event);
@@ -373,6 +487,8 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
+ struct seq_file *m = file->private_data;
+ struct trace_array *tr = m->private;
ssize_t read, ret;
if (!cnt)
@@ -395,7 +511,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
parser.buffer[parser.idx] = 0;
- ret = ftrace_set_clr_event(parser.buffer + !set, set);
+ ret = ftrace_set_clr_event(tr, parser.buffer + !set, set);
if (ret)
goto out_put;
}
@@ -411,17 +527,20 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = v;
+ struct ftrace_event_file *file = v;
+ struct ftrace_event_call *call;
+ struct trace_array *tr = m->private;
(*pos)++;
- list_for_each_entry_continue(call, &ftrace_events, list) {
+ list_for_each_entry_continue(file, &tr->events, list) {
+ call = file->event_call;
/*
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
*/
if (call->class && call->class->reg)
- return call;
+ return file;
}
return NULL;
@@ -429,30 +548,32 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
+ struct trace_array *tr = m->private;
loff_t l;
mutex_lock(&event_mutex);
- call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+ file = list_entry(&tr->events, struct ftrace_event_file, list);
for (l = 0; l <= *pos; ) {
- call = t_next(m, call, &l);
- if (!call)
+ file = t_next(m, file, &l);
+ if (!file)
break;
}
- return call;
+ return file;
}
static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = v;
+ struct ftrace_event_file *file = v;
+ struct trace_array *tr = m->private;
(*pos)++;
- list_for_each_entry_continue(call, &ftrace_events, list) {
- if (call->flags & TRACE_EVENT_FL_ENABLED)
- return call;
+ list_for_each_entry_continue(file, &tr->events, list) {
+ if (file->flags & FTRACE_EVENT_FL_ENABLED)
+ return file;
}
return NULL;
@@ -460,23 +581,25 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
static void *s_start(struct seq_file *m, loff_t *pos)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
+ struct trace_array *tr = m->private;
loff_t l;
mutex_lock(&event_mutex);
- call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+ file = list_entry(&tr->events, struct ftrace_event_file, list);
for (l = 0; l <= *pos; ) {
- call = s_next(m, call, &l);
- if (!call)
+ file = s_next(m, file, &l);
+ if (!file)
break;
}
- return call;
+ return file;
}
static int t_show(struct seq_file *m, void *v)
{
- struct ftrace_event_call *call = v;
+ struct ftrace_event_file *file = v;
+ struct ftrace_event_call *call = file->event_call;
if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
seq_printf(m, "%s:", call->class->system);
@@ -494,25 +617,31 @@ static ssize_t
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_file *file = filp->private_data;
char *buf;
- if (call->flags & TRACE_EVENT_FL_ENABLED)
- buf = "1\n";
- else
+ if (file->flags & FTRACE_EVENT_FL_ENABLED) {
+ if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)
+ buf = "0*\n";
+ else
+ buf = "1\n";
+ } else
buf = "0\n";
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf));
}
static ssize_t
event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_file *file = filp->private_data;
unsigned long val;
int ret;
+ if (!file)
+ return -EINVAL;
+
ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
if (ret)
return ret;
@@ -525,7 +654,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
case 0:
case 1:
mutex_lock(&event_mutex);
- ret = ftrace_event_enable_disable(call, val);
+ ret = ftrace_event_enable_disable(file, val);
mutex_unlock(&event_mutex);
break;
@@ -543,14 +672,18 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
const char set_to_char[4] = { '?', '0', '1', 'X' };
- struct event_subsystem *system = filp->private_data;
+ struct ftrace_subsystem_dir *dir = filp->private_data;
+ struct event_subsystem *system = dir->subsystem;
struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
+ struct trace_array *tr = dir->tr;
char buf[2];
int set = 0;
int ret;
mutex_lock(&event_mutex);
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
+ call = file->event_call;
if (!call->name || !call->class || !call->class->reg)
continue;
@@ -562,7 +695,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
* or if all events or cleared, or if we have
* a mixture.
*/
- set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
+ set |= (1 << !!(file->flags & FTRACE_EVENT_FL_ENABLED));
/*
* If we have a mixture, no need to look further.
@@ -584,7 +717,8 @@ static ssize_t
system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct event_subsystem *system = filp->private_data;
+ struct ftrace_subsystem_dir *dir = filp->private_data;
+ struct event_subsystem *system = dir->subsystem;
const char *name = NULL;
unsigned long val;
ssize_t ret;
@@ -607,7 +741,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (system)
name = system->name;
- ret = __ftrace_set_clr_event(NULL, name, NULL, val);
+ ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val);
if (ret)
goto out;
@@ -845,43 +979,75 @@ static LIST_HEAD(event_subsystems);
static int subsystem_open(struct inode *inode, struct file *filp)
{
struct event_subsystem *system = NULL;
+ struct ftrace_subsystem_dir *dir = NULL; /* Initialize for gcc */
+ struct trace_array *tr;
int ret;
- if (!inode->i_private)
- goto skip_search;
-
/* Make sure the system still exists */
mutex_lock(&event_mutex);
- list_for_each_entry(system, &event_subsystems, list) {
- if (system == inode->i_private) {
- /* Don't open systems with no events */
- if (!system->nr_events) {
- system = NULL;
- break;
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ list_for_each_entry(dir, &tr->systems, list) {
+ if (dir == inode->i_private) {
+ /* Don't open systems with no events */
+ if (dir->nr_events) {
+ __get_system_dir(dir);
+ system = dir->subsystem;
+ }
+ goto exit_loop;
}
- __get_system(system);
- break;
}
}
+ exit_loop:
mutex_unlock(&event_mutex);
- if (system != inode->i_private)
+ if (!system)
return -ENODEV;
- skip_search:
+ /* Some versions of gcc think dir can be uninitialized here */
+ WARN_ON(!dir);
+
ret = tracing_open_generic(inode, filp);
- if (ret < 0 && system)
- put_system(system);
+ if (ret < 0)
+ put_system(dir);
+
+ return ret;
+}
+
+static int system_tr_open(struct inode *inode, struct file *filp)
+{
+ struct ftrace_subsystem_dir *dir;
+ struct trace_array *tr = inode->i_private;
+ int ret;
+
+ /* Make a temporary dir that has no system but points to tr */
+ dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+ if (!dir)
+ return -ENOMEM;
+
+ dir->tr = tr;
+
+ ret = tracing_open_generic(inode, filp);
+ if (ret < 0)
+ kfree(dir);
+
+ filp->private_data = dir;
return ret;
}
static int subsystem_release(struct inode *inode, struct file *file)
{
- struct event_subsystem *system = inode->i_private;
+ struct ftrace_subsystem_dir *dir = file->private_data;
- if (system)
- put_system(system);
+ /*
+ * If dir->subsystem is NULL, then this is a temporary
+ * descriptor that was made for a trace_array to enable
+ * all subsystems.
+ */
+ if (dir->subsystem)
+ put_system(dir);
+ else
+ kfree(dir);
return 0;
}
@@ -890,7 +1056,8 @@ static ssize_t
subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct event_subsystem *system = filp->private_data;
+ struct ftrace_subsystem_dir *dir = filp->private_data;
+ struct event_subsystem *system = dir->subsystem;
struct trace_seq *s;
int r;
@@ -915,7 +1082,7 @@ static ssize_t
subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct event_subsystem *system = filp->private_data;
+ struct ftrace_subsystem_dir *dir = filp->private_data;
char *buf;
int err;
@@ -932,7 +1099,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
}
buf[cnt] = '\0';
- err = apply_subsystem_event_filter(system, buf);
+ err = apply_subsystem_event_filter(dir, buf);
free_page((unsigned long) buf);
if (err < 0)
return err;
@@ -1041,30 +1208,35 @@ static const struct file_operations ftrace_system_enable_fops = {
.release = subsystem_release,
};
+static const struct file_operations ftrace_tr_enable_fops = {
+ .open = system_tr_open,
+ .read = system_enable_read,
+ .write = system_enable_write,
+ .llseek = default_llseek,
+ .release = subsystem_release,
+};
+
static const struct file_operations ftrace_show_header_fops = {
.open = tracing_open_generic,
.read = show_header,
.llseek = default_llseek,
};
-static struct dentry *event_trace_events_dir(void)
+static int
+ftrace_event_open(struct inode *inode, struct file *file,
+ const struct seq_operations *seq_ops)
{
- static struct dentry *d_tracer;
- static struct dentry *d_events;
-
- if (d_events)
- return d_events;
-
- d_tracer = tracing_init_dentry();
- if (!d_tracer)
- return NULL;
+ struct seq_file *m;
+ int ret;
- d_events = debugfs_create_dir("events", d_tracer);
- if (!d_events)
- pr_warning("Could not create debugfs "
- "'events' directory\n");
+ ret = seq_open(file, seq_ops);
+ if (ret < 0)
+ return ret;
+ m = file->private_data;
+ /* copy tr over to seq ops */
+ m->private = inode->i_private;
- return d_events;
+ return ret;
}
static int
@@ -1072,117 +1244,165 @@ ftrace_event_avail_open(struct inode *inode, struct file *file)
{
const struct seq_operations *seq_ops = &show_event_seq_ops;
- return seq_open(file, seq_ops);
+ return ftrace_event_open(inode, file, seq_ops);
}
static int
ftrace_event_set_open(struct inode *inode, struct file *file)
{
const struct seq_operations *seq_ops = &show_set_event_seq_ops;
+ struct trace_array *tr = inode->i_private;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
- ftrace_clear_events();
+ ftrace_clear_events(tr);
- return seq_open(file, seq_ops);
+ return ftrace_event_open(inode, file, seq_ops);
+}
+
+static struct event_subsystem *
+create_new_subsystem(const char *name)
+{
+ struct event_subsystem *system;
+
+ /* need to create new entry */
+ system = kmalloc(sizeof(*system), GFP_KERNEL);
+ if (!system)
+ return NULL;
+
+ system->ref_count = 1;
+ system->name = name;
+
+ system->filter = NULL;
+
+ system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+ if (!system->filter)
+ goto out_free;
+
+ list_add(&system->list, &event_subsystems);
+
+ return system;
+
+ out_free:
+ kfree(system);
+ return NULL;
}
static struct dentry *
-event_subsystem_dir(const char *name, struct dentry *d_events)
+event_subsystem_dir(struct trace_array *tr, const char *name,
+ struct ftrace_event_file *file, struct dentry *parent)
{
+ struct ftrace_subsystem_dir *dir;
struct event_subsystem *system;
struct dentry *entry;
/* First see if we did not already create this dir */
- list_for_each_entry(system, &event_subsystems, list) {
+ list_for_each_entry(dir, &tr->systems, list) {
+ system = dir->subsystem;
if (strcmp(system->name, name) == 0) {
- system->nr_events++;
- return system->entry;
+ dir->nr_events++;
+ file->system = dir;
+ return dir->entry;
}
}
- /* need to create new entry */
- system = kmalloc(sizeof(*system), GFP_KERNEL);
- if (!system) {
- pr_warning("No memory to create event subsystem %s\n",
- name);
- return d_events;
+ /* Now see if the system itself exists. */
+ list_for_each_entry(system, &event_subsystems, list) {
+ if (strcmp(system->name, name) == 0)
+ break;
}
+ /* Reset system variable when not found */
+ if (&system->list == &event_subsystems)
+ system = NULL;
- system->entry = debugfs_create_dir(name, d_events);
- if (!system->entry) {
- pr_warning("Could not create event subsystem %s\n",
- name);
- kfree(system);
- return d_events;
- }
+ dir = kmalloc(sizeof(*dir), GFP_KERNEL);
+ if (!dir)
+ goto out_fail;
- system->nr_events = 1;
- system->ref_count = 1;
- system->name = kstrdup(name, GFP_KERNEL);
- if (!system->name) {
- debugfs_remove(system->entry);
- kfree(system);
- return d_events;
+ if (!system) {
+ system = create_new_subsystem(name);
+ if (!system)
+ goto out_free;
+ } else
+ __get_system(system);
+
+ dir->entry = debugfs_create_dir(name, parent);
+ if (!dir->entry) {
+ pr_warning("Failed to create system directory %s\n", name);
+ __put_system(system);
+ goto out_free;
}
- list_add(&system->list, &event_subsystems);
-
- system->filter = NULL;
-
- system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
- if (!system->filter) {
- pr_warning("Could not allocate filter for subsystem "
- "'%s'\n", name);
- return system->entry;
- }
+ dir->tr = tr;
+ dir->ref_count = 1;
+ dir->nr_events = 1;
+ dir->subsystem = system;
+ file->system = dir;
- entry = debugfs_create_file("filter", 0644, system->entry, system,
+ entry = debugfs_create_file("filter", 0644, dir->entry, dir,
&ftrace_subsystem_filter_fops);
if (!entry) {
kfree(system->filter);
system->filter = NULL;
- pr_warning("Could not create debugfs "
- "'%s/filter' entry\n", name);
+ pr_warning("Could not create debugfs '%s/filter' entry\n", name);
}
- trace_create_file("enable", 0644, system->entry, system,
+ trace_create_file("enable", 0644, dir->entry, dir,
&ftrace_system_enable_fops);
- return system->entry;
+ list_add(&dir->list, &tr->systems);
+
+ return dir->entry;
+
+ out_free:
+ kfree(dir);
+ out_fail:
+ /* Only print this message if failed on memory allocation */
+ if (!dir || !system)
+ pr_warning("No memory to create event subsystem %s\n",
+ name);
+ return NULL;
}
static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+event_create_dir(struct dentry *parent,
+ struct ftrace_event_file *file,
const struct file_operations *id,
const struct file_operations *enable,
const struct file_operations *filter,
const struct file_operations *format)
{
+ struct ftrace_event_call *call = file->event_call;
+ struct trace_array *tr = file->tr;
struct list_head *head;
+ struct dentry *d_events;
int ret;
/*
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
- if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
- d_events = event_subsystem_dir(call->class->system, d_events);
-
- call->dir = debugfs_create_dir(call->name, d_events);
- if (!call->dir) {
- pr_warning("Could not create debugfs "
- "'%s' directory\n", call->name);
+ if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
+ d_events = event_subsystem_dir(tr, call->class->system, file, parent);
+ if (!d_events)
+ return -ENOMEM;
+ } else
+ d_events = parent;
+
+ file->dir = debugfs_create_dir(call->name, d_events);
+ if (!file->dir) {
+ pr_warning("Could not create debugfs '%s' directory\n",
+ call->name);
return -1;
}
if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
- trace_create_file("enable", 0644, call->dir, call,
+ trace_create_file("enable", 0644, file->dir, file,
enable);
#ifdef CONFIG_PERF_EVENTS
if (call->event.type && call->class->reg)
- trace_create_file("id", 0444, call->dir, call,
+ trace_create_file("id", 0444, file->dir, call,
id);
#endif
@@ -1196,23 +1416,76 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
if (ret < 0) {
pr_warning("Could not initialize trace point"
" events/%s\n", call->name);
- return ret;
+ return -1;
}
}
- trace_create_file("filter", 0644, call->dir, call,
+ trace_create_file("filter", 0644, file->dir, call,
filter);
- trace_create_file("format", 0444, call->dir, call,
+ trace_create_file("format", 0444, file->dir, call,
format);
return 0;
}
+static void remove_subsystem(struct ftrace_subsystem_dir *dir)
+{
+ if (!dir)
+ return;
+
+ if (!--dir->nr_events) {
+ debugfs_remove_recursive(dir->entry);
+ list_del(&dir->list);
+ __put_system_dir(dir);
+ }
+}
+
+static void remove_event_from_tracers(struct ftrace_event_call *call)
+{
+ struct ftrace_event_file *file;
+ struct trace_array *tr;
+
+ do_for_each_event_file_safe(tr, file) {
+
+ if (file->event_call != call)
+ continue;
+
+ list_del(&file->list);
+ debugfs_remove_recursive(file->dir);
+ remove_subsystem(file->system);
+ kmem_cache_free(file_cachep, file);
+
+ /*
+ * The do_for_each_event_file_safe() is
+ * a double loop. After finding the call for this
+ * trace_array, we use break to jump to the next
+ * trace_array.
+ */
+ break;
+ } while_for_each_event_file();
+}
+
static void event_remove(struct ftrace_event_call *call)
{
- ftrace_event_enable_disable(call, 0);
+ struct trace_array *tr;
+ struct ftrace_event_file *file;
+
+ do_for_each_event_file(tr, file) {
+ if (file->event_call != call)
+ continue;
+ ftrace_event_enable_disable(file, 0);
+ /*
+ * The do_for_each_event_file() is
+ * a double loop. After finding the call for this
+ * trace_array, we use break to jump to the next
+ * trace_array.
+ */
+ break;
+ } while_for_each_event_file();
+
if (call->event.funcs)
__unregister_ftrace_event(&call->event);
+ remove_event_from_tracers(call);
list_del(&call->list);
}
@@ -1234,82 +1507,99 @@ static int event_init(struct ftrace_event_call *call)
}
static int
-__trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
- const struct file_operations *id,
- const struct file_operations *enable,
- const struct file_operations *filter,
- const struct file_operations *format)
+__register_event(struct ftrace_event_call *call, struct module *mod)
{
- struct dentry *d_events;
int ret;
ret = event_init(call);
if (ret < 0)
return ret;
- d_events = event_trace_events_dir();
- if (!d_events)
- return -ENOENT;
-
- ret = event_create_dir(call, d_events, id, enable, filter, format);
- if (!ret)
- list_add(&call->list, &ftrace_events);
+ list_add(&call->list, &ftrace_events);
call->mod = mod;
- return ret;
+ return 0;
+}
+
+/* Add an event to a trace directory */
+static int
+__trace_add_new_event(struct ftrace_event_call *call,
+ struct trace_array *tr,
+ const struct file_operations *id,
+ const struct file_operations *enable,
+ const struct file_operations *filter,
+ const struct file_operations *format)
+{
+ struct ftrace_event_file *file;
+
+ file = kmem_cache_alloc(file_cachep, GFP_TRACE);
+ if (!file)
+ return -ENOMEM;
+
+ file->event_call = call;
+ file->tr = tr;
+ list_add(&file->list, &tr->events);
+
+ return event_create_dir(tr->event_dir, file, id, enable, filter, format);
}
+/*
+ * Just create a decriptor for early init. A descriptor is required
+ * for enabling events at boot. We want to enable events before
+ * the filesystem is initialized.
+ */
+static __init int
+__trace_early_add_new_event(struct ftrace_event_call *call,
+ struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
+
+ file = kmem_cache_alloc(file_cachep, GFP_TRACE);
+ if (!file)
+ return -ENOMEM;
+
+ file->event_call = call;
+ file->tr = tr;
+ list_add(&file->list, &tr->events);
+
+ return 0;
+}
+
+struct ftrace_module_file_ops;
+static void __add_event_to_tracers(struct ftrace_event_call *call,
+ struct ftrace_module_file_ops *file_ops);
+
/* Add an additional event_call dynamically */
int trace_add_event_call(struct ftrace_event_call *call)
{
int ret;
mutex_lock(&event_mutex);
- ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
- &ftrace_enable_fops,
- &ftrace_event_filter_fops,
- &ftrace_event_format_fops);
- mutex_unlock(&event_mutex);
- return ret;
-}
-static void remove_subsystem_dir(const char *name)
-{
- struct event_subsystem *system;
-
- if (strcmp(name, TRACE_SYSTEM) == 0)
- return;
+ ret = __register_event(call, NULL);
+ if (ret >= 0)
+ __add_event_to_tracers(call, NULL);
- list_for_each_entry(system, &event_subsystems, list) {
- if (strcmp(system->name, name) == 0) {
- if (!--system->nr_events) {
- debugfs_remove_recursive(system->entry);
- list_del(&system->list);
- __put_system(system);
- }
- break;
- }
- }
+ mutex_unlock(&event_mutex);
+ return ret;
}
/*
- * Must be called under locking both of event_mutex and trace_event_mutex.
+ * Must be called under locking both of event_mutex and trace_event_sem.
*/
static void __trace_remove_event_call(struct ftrace_event_call *call)
{
event_remove(call);
trace_destroy_fields(call);
destroy_preds(call);
- debugfs_remove_recursive(call->dir);
- remove_subsystem_dir(call->class->system);
}
/* Remove an event_call */
void trace_remove_event_call(struct ftrace_event_call *call)
{
mutex_lock(&event_mutex);
- down_write(&trace_event_mutex);
+ down_write(&trace_event_sem);
__trace_remove_event_call(call);
- up_write(&trace_event_mutex);
+ up_write(&trace_event_sem);
mutex_unlock(&event_mutex);
}
@@ -1336,6 +1626,26 @@ struct ftrace_module_file_ops {
};
static struct ftrace_module_file_ops *
+find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
+{
+ /*
+ * As event_calls are added in groups by module,
+ * when we find one file_ops, we don't need to search for
+ * each call in that module, as the rest should be the
+ * same. Only search for a new one if the last one did
+ * not match.
+ */
+ if (file_ops && mod == file_ops->mod)
+ return file_ops;
+
+ list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+ if (file_ops->mod == mod)
+ return file_ops;
+ }
+ return NULL;
+}
+
+static struct ftrace_module_file_ops *
trace_create_file_ops(struct module *mod)
{
struct ftrace_module_file_ops *file_ops;
@@ -1386,9 +1696,8 @@ static void trace_module_add_events(struct module *mod)
return;
for_each_event(call, start, end) {
- __trace_add_event_call(*call, mod,
- &file_ops->id, &file_ops->enable,
- &file_ops->filter, &file_ops->format);
+ __register_event(*call, mod);
+ __add_event_to_tracers(*call, file_ops);
}
}
@@ -1396,12 +1705,13 @@ static void trace_module_remove_events(struct module *mod)
{
struct ftrace_module_file_ops *file_ops;
struct ftrace_event_call *call, *p;
- bool found = false;
+ bool clear_trace = false;
- down_write(&trace_event_mutex);
+ down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
if (call->mod == mod) {
- found = true;
+ if (call->flags & TRACE_EVENT_FL_WAS_ENABLED)
+ clear_trace = true;
__trace_remove_event_call(call);
}
}
@@ -1415,14 +1725,18 @@ static void trace_module_remove_events(struct module *mod)
list_del(&file_ops->list);
kfree(file_ops);
}
+ up_write(&trace_event_sem);
/*
* It is safest to reset the ring buffer if the module being unloaded
- * registered any events.
+ * registered any events that were used. The only worry is if
+ * a new module gets loaded, and takes on the same id as the events
+ * of this module. When printing out the buffer, traced events left
+ * over from this module may be passed to the new module events and
+ * unexpected results may occur.
*/
- if (found)
- tracing_reset_current_online_cpus();
- up_write(&trace_event_mutex);
+ if (clear_trace)
+ tracing_reset_all_online_cpus();
}
static int trace_module_notify(struct notifier_block *self,
@@ -1443,14 +1757,433 @@ static int trace_module_notify(struct notifier_block *self,
return 0;
}
+
+static int
+__trace_add_new_mod_event(struct ftrace_event_call *call,
+ struct trace_array *tr,
+ struct ftrace_module_file_ops *file_ops)
+{
+ return __trace_add_new_event(call, tr,
+ &file_ops->id, &file_ops->enable,
+ &file_ops->filter, &file_ops->format);
+}
+
#else
-static int trace_module_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static inline struct ftrace_module_file_ops *
+find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
+{
+ return NULL;
+}
+static inline int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
{
return 0;
}
+static inline int
+__trace_add_new_mod_event(struct ftrace_event_call *call,
+ struct trace_array *tr,
+ struct ftrace_module_file_ops *file_ops)
+{
+ return -ENODEV;
+}
#endif /* CONFIG_MODULES */
+/* Create a new event directory structure for a trace directory. */
+static void
+__trace_add_event_dirs(struct trace_array *tr)
+{
+ struct ftrace_module_file_ops *file_ops = NULL;
+ struct ftrace_event_call *call;
+ int ret;
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (call->mod) {
+ /*
+ * Directories for events by modules need to
+ * keep module ref counts when opened (as we don't
+ * want the module to disappear when reading one
+ * of these files). The file_ops keep account of
+ * the module ref count.
+ */
+ file_ops = find_ftrace_file_ops(file_ops, call->mod);
+ if (!file_ops)
+ continue; /* Warn? */
+ ret = __trace_add_new_mod_event(call, tr, file_ops);
+ if (ret < 0)
+ pr_warning("Could not create directory for event %s\n",
+ call->name);
+ continue;
+ }
+ ret = __trace_add_new_event(call, tr,
+ &ftrace_event_id_fops,
+ &ftrace_enable_fops,
+ &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (ret < 0)
+ pr_warning("Could not create directory for event %s\n",
+ call->name);
+ }
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct event_probe_data {
+ struct ftrace_event_file *file;
+ unsigned long count;
+ int ref;
+ bool enable;
+};
+
+static struct ftrace_event_file *
+find_event_file(struct trace_array *tr, const char *system, const char *event)
+{
+ struct ftrace_event_file *file;
+ struct ftrace_event_call *call;
+
+ list_for_each_entry(file, &tr->events, list) {
+
+ call = file->event_call;
+
+ if (!call->name || !call->class || !call->class->reg)
+ continue;
+
+ if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
+ continue;
+
+ if (strcmp(event, call->name) == 0 &&
+ strcmp(system, call->class->system) == 0)
+ return file;
+ }
+ return NULL;
+}
+
+static void
+event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_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(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags);
+ else
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &data->file->flags);
+}
+
+static void
+event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+{
+ struct event_probe_data **pdata = (struct event_probe_data **)_data;
+ struct event_probe_data *data = *pdata;
+
+ if (!data)
+ return;
+
+ if (!data->count)
+ return;
+
+ /* Skip if the event is in a state we want to switch to */
+ if (data->enable == !(data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ event_enable_probe(ip, parent_ip, _data);
+}
+
+static int
+event_enable_print(struct seq_file *m, unsigned long ip,
+ struct ftrace_probe_ops *ops, void *_data)
+{
+ struct event_probe_data *data = _data;
+
+ 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,
+ data->file->event_call->name);
+
+ if (data->count == -1)
+ seq_printf(m, ":unlimited\n");
+ else
+ seq_printf(m, ":count=%ld\n", data->count);
+
+ return 0;
+}
+
+static int
+event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip,
+ void **_data)
+{
+ struct event_probe_data **pdata = (struct event_probe_data **)_data;
+ struct event_probe_data *data = *pdata;
+
+ data->ref++;
+ return 0;
+}
+
+static void
+event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip,
+ void **_data)
+{
+ struct event_probe_data **pdata = (struct event_probe_data **)_data;
+ struct event_probe_data *data = *pdata;
+
+ if (WARN_ON_ONCE(data->ref <= 0))
+ 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;
+}
+
+static struct ftrace_probe_ops event_enable_probe_ops = {
+ .func = event_enable_probe,
+ .print = event_enable_print,
+ .init = event_enable_init,
+ .free = event_enable_free,
+};
+
+static struct ftrace_probe_ops event_enable_count_probe_ops = {
+ .func = event_enable_count_probe,
+ .print = event_enable_print,
+ .init = event_enable_init,
+ .free = event_enable_free,
+};
+
+static struct ftrace_probe_ops event_disable_probe_ops = {
+ .func = event_enable_probe,
+ .print = event_enable_print,
+ .init = event_enable_init,
+ .free = event_enable_free,
+};
+
+static struct ftrace_probe_ops event_disable_count_probe_ops = {
+ .func = event_enable_count_probe,
+ .print = event_enable_print,
+ .init = event_enable_init,
+ .free = event_enable_free,
+};
+
+static int
+event_enable_func(struct ftrace_hash *hash,
+ char *glob, char *cmd, char *param, int enabled)
+{
+ struct trace_array *tr = top_trace_array();
+ struct ftrace_event_file *file;
+ struct ftrace_probe_ops *ops;
+ struct event_probe_data *data;
+ const char *system;
+ const char *event;
+ char *number;
+ bool enable;
+ int ret;
+
+ /* hash funcs only work with set_ftrace_filter */
+ if (!enabled)
+ return -EINVAL;
+
+ if (!param)
+ return -EINVAL;
+
+ system = strsep(&param, ":");
+ if (!param)
+ return -EINVAL;
+
+ event = strsep(&param, ":");
+
+ mutex_lock(&event_mutex);
+
+ ret = -EINVAL;
+ file = find_event_file(tr, system, event);
+ if (!file)
+ goto out;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ if (enable)
+ ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops;
+ else
+ ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops;
+
+ if (glob[0] == '!') {
+ unregister_ftrace_function_probe_func(glob+1, ops);
+ ret = 0;
+ goto out;
+ }
+
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out;
+
+ data->enable = enable;
+ data->count = -1;
+ data->file = file;
+
+ if (!param)
+ goto out_reg;
+
+ number = strsep(&param, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &data->count);
+ if (ret)
+ goto out_free;
+
+ out_reg:
+ /* Don't let event modules unload while probe registered */
+ ret = try_module_get(file->event_call->mod);
+ if (!ret)
+ goto out_free;
+
+ ret = __ftrace_event_enable_disable(file, 1, 1);
+ if (ret < 0)
+ goto out_put;
+ ret = register_ftrace_function_probe(glob, ops, data);
+ if (!ret)
+ goto out_disable;
+ out:
+ mutex_unlock(&event_mutex);
+ return ret;
+
+ out_disable:
+ __ftrace_event_enable_disable(file, 0, 1);
+ out_put:
+ module_put(file->event_call->mod);
+ out_free:
+ kfree(data);
+ goto out;
+}
+
+static struct ftrace_func_command event_enable_cmd = {
+ .name = ENABLE_EVENT_STR,
+ .func = event_enable_func,
+};
+
+static struct ftrace_func_command event_disable_cmd = {
+ .name = DISABLE_EVENT_STR,
+ .func = event_enable_func,
+};
+
+static __init int register_event_cmds(void)
+{
+ int ret;
+
+ ret = register_ftrace_command(&event_enable_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_ftrace_command(&event_disable_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_ftrace_command(&event_enable_cmd);
+ return ret;
+}
+#else
+static inline int register_event_cmds(void) { return 0; }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * The top level array has already had its ftrace_event_file
+ * descriptors created in order to allow for early events to
+ * be recorded. This function is called after the debugfs has been
+ * initialized, and we now have to create the files associated
+ * to the events.
+ */
+static __init void
+__trace_early_add_event_dirs(struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
+ int ret;
+
+
+ list_for_each_entry(file, &tr->events, list) {
+ ret = event_create_dir(tr->event_dir, file,
+ &ftrace_event_id_fops,
+ &ftrace_enable_fops,
+ &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (ret < 0)
+ pr_warning("Could not create directory for event %s\n",
+ file->event_call->name);
+ }
+}
+
+/*
+ * For early boot up, the top trace array requires to have
+ * a list of events that can be enabled. This must be done before
+ * the filesystem is set up in order to allow events to be traced
+ * early.
+ */
+static __init void
+__trace_early_add_events(struct trace_array *tr)
+{
+ struct ftrace_event_call *call;
+ int ret;
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ /* Early boot up should not have any modules loaded */
+ if (WARN_ON_ONCE(call->mod))
+ continue;
+
+ ret = __trace_early_add_new_event(call, tr);
+ if (ret < 0)
+ pr_warning("Could not create early event %s\n",
+ call->name);
+ }
+}
+
+/* Remove the event directory structure for a trace directory. */
+static void
+__trace_remove_event_dirs(struct trace_array *tr)
+{
+ struct ftrace_event_file *file, *next;
+
+ list_for_each_entry_safe(file, next, &tr->events, list) {
+ list_del(&file->list);
+ debugfs_remove_recursive(file->dir);
+ remove_subsystem(file->system);
+ kmem_cache_free(file_cachep, file);
+ }
+}
+
+static void
+__add_event_to_tracers(struct ftrace_event_call *call,
+ struct ftrace_module_file_ops *file_ops)
+{
+ struct trace_array *tr;
+
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (file_ops)
+ __trace_add_new_mod_event(call, tr, file_ops);
+ else
+ __trace_add_new_event(call, tr,
+ &ftrace_event_id_fops,
+ &ftrace_enable_fops,
+ &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ }
+}
+
static struct notifier_block trace_module_nb = {
.notifier_call = trace_module_notify,
.priority = 0,
@@ -1464,15 +2197,135 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
static __init int setup_trace_event(char *str)
{
strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
- ring_buffer_expanded = 1;
- tracing_selftest_disabled = 1;
+ ring_buffer_expanded = true;
+ tracing_selftest_disabled = true;
return 1;
}
__setup("trace_event=", setup_trace_event);
+/* Expects to have event_mutex held when called */
+static int
+create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
+{
+ struct dentry *d_events;
+ struct dentry *entry;
+
+ entry = debugfs_create_file("set_event", 0644, parent,
+ tr, &ftrace_set_event_fops);
+ if (!entry) {
+ pr_warning("Could not create debugfs 'set_event' entry\n");
+ return -ENOMEM;
+ }
+
+ d_events = debugfs_create_dir("events", parent);
+ if (!d_events) {
+ pr_warning("Could not create debugfs 'events' directory\n");
+ return -ENOMEM;
+ }
+
+ /* ring buffer internal formats */
+ trace_create_file("header_page", 0444, d_events,
+ ring_buffer_print_page_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("header_event", 0444, d_events,
+ ring_buffer_print_entry_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("enable", 0644, d_events,
+ tr, &ftrace_tr_enable_fops);
+
+ tr->event_dir = d_events;
+
+ return 0;
+}
+
+/**
+ * event_trace_add_tracer - add a instance of a trace_array to events
+ * @parent: The parent dentry to place the files/directories for events in
+ * @tr: The trace array associated with these events
+ *
+ * When a new instance is created, it needs to set up its events
+ * directory, as well as other files associated with events. It also
+ * creates the event hierachry in the @parent/events directory.
+ *
+ * Returns 0 on success.
+ */
+int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
+{
+ int ret;
+
+ mutex_lock(&event_mutex);
+
+ ret = create_event_toplevel_files(parent, tr);
+ if (ret)
+ goto out_unlock;
+
+ down_write(&trace_event_sem);
+ __trace_add_event_dirs(tr);
+ up_write(&trace_event_sem);
+
+ out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+/*
+ * The top trace array already had its file descriptors created.
+ * Now the files themselves need to be created.
+ */
+static __init int
+early_event_add_tracer(struct dentry *parent, struct trace_array *tr)
+{
+ int ret;
+
+ mutex_lock(&event_mutex);
+
+ ret = create_event_toplevel_files(parent, tr);
+ if (ret)
+ goto out_unlock;
+
+ down_write(&trace_event_sem);
+ __trace_early_add_event_dirs(tr);
+ up_write(&trace_event_sem);
+
+ out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+int event_trace_del_tracer(struct trace_array *tr)
+{
+ /* Disable any running events */
+ __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
+
+ mutex_lock(&event_mutex);
+
+ down_write(&trace_event_sem);
+ __trace_remove_event_dirs(tr);
+ debugfs_remove_recursive(tr->event_dir);
+ up_write(&trace_event_sem);
+
+ tr->event_dir = NULL;
+
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+
+static __init int event_trace_memsetup(void)
+{
+ field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC);
+ file_cachep = KMEM_CACHE(ftrace_event_file, SLAB_PANIC);
+ return 0;
+}
+
static __init int event_trace_enable(void)
{
+ struct trace_array *tr = top_trace_array();
struct ftrace_event_call **iter, *call;
char *buf = bootup_event_buf;
char *token;
@@ -1486,6 +2339,14 @@ static __init int event_trace_enable(void)
list_add(&call->list, &ftrace_events);
}
+ /*
+ * We need the top trace array to have a working set of trace
+ * points at early init, before the debug files and directories
+ * are created. Create the file entries now, and attach them
+ * to the actual file dentries later.
+ */
+ __trace_early_add_events(tr);
+
while (true) {
token = strsep(&buf, ",");
@@ -1494,73 +2355,43 @@ static __init int event_trace_enable(void)
if (!*token)
continue;
- ret = ftrace_set_clr_event(token, 1);
+ ret = ftrace_set_clr_event(tr, token, 1);
if (ret)
pr_warn("Failed to enable trace event: %s\n", token);
}
trace_printk_start_comm();
+ register_event_cmds();
+
return 0;
}
static __init int event_trace_init(void)
{
- struct ftrace_event_call *call;
+ struct trace_array *tr;
struct dentry *d_tracer;
struct dentry *entry;
- struct dentry *d_events;
int ret;
+ tr = top_trace_array();
+
d_tracer = tracing_init_dentry();
if (!d_tracer)
return 0;
entry = debugfs_create_file("available_events", 0444, d_tracer,
- NULL, &ftrace_avail_fops);
+ tr, &ftrace_avail_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'available_events' entry\n");
- entry = debugfs_create_file("set_event", 0644, d_tracer,
- NULL, &ftrace_set_event_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_event' entry\n");
-
- d_events = event_trace_events_dir();
- if (!d_events)
- return 0;
-
- /* ring buffer internal formats */
- trace_create_file("header_page", 0444, d_events,
- ring_buffer_print_page_header,
- &ftrace_show_header_fops);
-
- trace_create_file("header_event", 0444, d_events,
- ring_buffer_print_entry_header,
- &ftrace_show_header_fops);
-
- trace_create_file("enable", 0644, d_events,
- NULL, &ftrace_system_enable_fops);
-
if (trace_define_common_fields())
pr_warning("tracing: Failed to allocate common fields");
- /*
- * Early initialization already enabled ftrace event.
- * Now it's only necessary to create the event directory.
- */
- list_for_each_entry(call, &ftrace_events, list) {
-
- ret = event_create_dir(call, d_events,
- &ftrace_event_id_fops,
- &ftrace_enable_fops,
- &ftrace_event_filter_fops,
- &ftrace_event_format_fops);
- if (ret < 0)
- event_remove(call);
- }
+ ret = early_event_add_tracer(d_tracer, tr);
+ if (ret)
+ return ret;
ret = register_module_notifier(&trace_module_nb);
if (ret)
@@ -1568,6 +2399,7 @@ static __init int event_trace_init(void)
return 0;
}
+early_initcall(event_trace_memsetup);
core_initcall(event_trace_enable);
fs_initcall(event_trace_init);
@@ -1627,13 +2459,20 @@ static __init void event_test_stuff(void)
*/
static __init void event_trace_self_tests(void)
{
+ struct ftrace_subsystem_dir *dir;
+ struct ftrace_event_file *file;
struct ftrace_event_call *call;
struct event_subsystem *system;
+ struct trace_array *tr;
int ret;
+ tr = top_trace_array();
+
pr_info("Running tests on trace events:\n");
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
+
+ call = file->event_call;
/* Only test those that have a probe */
if (!call->class || !call->class->probe)
@@ -1657,15 +2496,15 @@ static __init void event_trace_self_tests(void)
* If an event is already enabled, someone is using
* it and the self test should not be on.
*/
- if (call->flags & TRACE_EVENT_FL_ENABLED) {
+ if (file->flags & FTRACE_EVENT_FL_ENABLED) {
pr_warning("Enabled event during self test!\n");
WARN_ON_ONCE(1);
continue;
}
- ftrace_event_enable_disable(call, 1);
+ ftrace_event_enable_disable(file, 1);
event_test_stuff();
- ftrace_event_enable_disable(call, 0);
+ ftrace_event_enable_disable(file, 0);
pr_cont("OK\n");
}
@@ -1674,7 +2513,9 @@ static __init void event_trace_self_tests(void)
pr_info("Running tests on trace event systems:\n");
- list_for_each_entry(system, &event_subsystems, list) {
+ list_for_each_entry(dir, &tr->systems, list) {
+
+ system = dir->subsystem;
/* the ftrace system is special, skip it */
if (strcmp(system->name, "ftrace") == 0)
@@ -1682,7 +2523,7 @@ static __init void event_trace_self_tests(void)
pr_info("Testing event system %s: ", system->name);
- ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+ ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1);
if (WARN_ON_ONCE(ret)) {
pr_warning("error enabling system %s\n",
system->name);
@@ -1691,7 +2532,7 @@ static __init void event_trace_self_tests(void)
event_test_stuff();
- ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+ ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0);
if (WARN_ON_ONCE(ret)) {
pr_warning("error disabling system %s\n",
system->name);
@@ -1706,7 +2547,7 @@ static __init void event_trace_self_tests(void)
pr_info("Running tests on all trace events:\n");
pr_info("Testing all events: ");
- ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+ ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1);
if (WARN_ON_ONCE(ret)) {
pr_warning("error enabling all events\n");
return;
@@ -1715,7 +2556,7 @@ static __init void event_trace_self_tests(void)
event_test_stuff();
/* reset sysname */
- ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+ ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
if (WARN_ON_ONCE(ret)) {
pr_warning("error disabling all events\n");
return;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e5b0ca8b8d4d..a6361178de5a 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -658,33 +658,6 @@ void print_subsystem_event_filter(struct event_subsystem *system,
mutex_unlock(&event_mutex);
}
-static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
-{
- struct ftrace_event_field *field;
-
- list_for_each_entry(field, head, link) {
- if (!strcmp(field->name, name))
- return field;
- }
-
- return NULL;
-}
-
-static struct ftrace_event_field *
-find_event_field(struct ftrace_event_call *call, char *name)
-{
- struct ftrace_event_field *field;
- struct list_head *head;
-
- field = __find_event_field(&ftrace_common_fields, name);
- if (field)
- return field;
-
- head = trace_get_fields(call);
- return __find_event_field(head, name);
-}
-
static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
{
stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
@@ -1337,7 +1310,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
return NULL;
}
- field = find_event_field(call, operand1);
+ field = trace_find_event_field(call, operand1);
if (!field) {
parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
return NULL;
@@ -1907,16 +1880,17 @@ out_unlock:
return err;
}
-int apply_subsystem_event_filter(struct event_subsystem *system,
+int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
char *filter_string)
{
+ struct event_subsystem *system = dir->subsystem;
struct event_filter *filter;
int err = 0;
mutex_lock(&event_mutex);
/* Make sure the system still has events */
- if (!system->nr_events) {
+ if (!dir->nr_events) {
err = -ENODEV;
goto out_unlock;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e039906b037d..d21a74670088 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -129,7 +129,7 @@ static void __always_unused ____ftrace_check_##name(void) \
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
-int \
+static int __init \
ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
{ \
struct struct_name field; \
@@ -168,7 +168,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
regfn) \
\
-struct ftrace_event_class event_class_ftrace_##call = { \
+struct ftrace_event_class __refdata event_class_ftrace_##call = { \
.system = __stringify(TRACE_SYSTEM), \
.define_fields = ftrace_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 601152523326..c4d6d7191988 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -28,7 +28,7 @@ static void tracing_stop_function_trace(void);
static int function_trace_init(struct trace_array *tr)
{
func_trace = tr;
- tr->cpu = get_cpu();
+ tr->trace_buffer.cpu = get_cpu();
put_cpu();
tracing_start_cmdline_record();
@@ -44,7 +44,7 @@ static void function_trace_reset(struct trace_array *tr)
static void function_trace_start(struct trace_array *tr)
{
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
}
/* Our option */
@@ -76,7 +76,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
goto out;
cpu = smp_processor_id();
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
if (!atomic_read(&data->disabled)) {
local_save_flags(flags);
trace_function(tr, ip, parent_ip, flags, pc);
@@ -107,7 +107,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
*/
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
@@ -214,66 +214,89 @@ static struct tracer function_trace __read_mostly =
};
#ifdef CONFIG_DYNAMIC_FTRACE
-static void
-ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+static int update_count(void **data)
{
- long *count = (long *)data;
-
- if (tracing_is_on())
- return;
+ unsigned long *count = (long *)data;
if (!*count)
- return;
+ return 0;
if (*count != -1)
(*count)--;
- tracing_on();
+ return 1;
}
static void
-ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data)
{
- long *count = (long *)data;
+ if (tracing_is_on())
+ return;
+
+ if (update_count(data))
+ tracing_on();
+}
+static void
+ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data)
+{
if (!tracing_is_on())
return;
- if (!*count)
+ if (update_count(data))
+ tracing_off();
+}
+
+static void
+ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ if (tracing_is_on())
return;
- if (*count != -1)
- (*count)--;
+ tracing_on();
+}
+
+static void
+ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ if (!tracing_is_on())
+ return;
tracing_off();
}
-static int
-ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
- struct ftrace_probe_ops *ops, void *data);
+/*
+ * Skip 4:
+ * ftrace_stacktrace()
+ * function_trace_probe_call()
+ * ftrace_ops_list_func()
+ * ftrace_call()
+ */
+#define STACK_SKIP 4
-static struct ftrace_probe_ops traceon_probe_ops = {
- .func = ftrace_traceon,
- .print = ftrace_trace_onoff_print,
-};
+static void
+ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ trace_dump_stack(STACK_SKIP);
+}
-static struct ftrace_probe_ops traceoff_probe_ops = {
- .func = ftrace_traceoff,
- .print = ftrace_trace_onoff_print,
-};
+static void
+ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ if (!tracing_is_on())
+ return;
+
+ if (update_count(data))
+ trace_dump_stack(STACK_SKIP);
+}
static int
-ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
- struct ftrace_probe_ops *ops, void *data)
+ftrace_probe_print(const char *name, struct seq_file *m,
+ unsigned long ip, void *data)
{
long count = (long)data;
- seq_printf(m, "%ps:", (void *)ip);
-
- if (ops == &traceon_probe_ops)
- seq_printf(m, "traceon");
- else
- seq_printf(m, "traceoff");
+ seq_printf(m, "%ps:%s", (void *)ip, name);
if (count == -1)
seq_printf(m, ":unlimited\n");
@@ -284,26 +307,61 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
}
static int
-ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
+ftrace_traceon_print(struct seq_file *m, unsigned long ip,
+ struct ftrace_probe_ops *ops, void *data)
{
- struct ftrace_probe_ops *ops;
-
- /* we register both traceon and traceoff to this callback */
- if (strcmp(cmd, "traceon") == 0)
- ops = &traceon_probe_ops;
- else
- ops = &traceoff_probe_ops;
+ return ftrace_probe_print("traceon", m, ip, data);
+}
- unregister_ftrace_function_probe_func(glob, ops);
+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 0;
+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);
}
+static struct ftrace_probe_ops traceon_count_probe_ops = {
+ .func = ftrace_traceon_count,
+ .print = ftrace_traceon_print,
+};
+
+static struct ftrace_probe_ops traceoff_count_probe_ops = {
+ .func = ftrace_traceoff_count,
+ .print = ftrace_traceoff_print,
+};
+
+static struct ftrace_probe_ops stacktrace_count_probe_ops = {
+ .func = ftrace_stacktrace_count,
+ .print = ftrace_stacktrace_print,
+};
+
+static struct ftrace_probe_ops traceon_probe_ops = {
+ .func = ftrace_traceon,
+ .print = ftrace_traceon_print,
+};
+
+static struct ftrace_probe_ops traceoff_probe_ops = {
+ .func = ftrace_traceoff,
+ .print = ftrace_traceoff_print,
+};
+
+static struct ftrace_probe_ops stacktrace_probe_ops = {
+ .func = ftrace_stacktrace,
+ .print = ftrace_stacktrace_print,
+};
+
static int
-ftrace_trace_onoff_callback(struct ftrace_hash *hash,
- char *glob, char *cmd, char *param, int enable)
+ftrace_trace_probe_callback(struct ftrace_probe_ops *ops,
+ struct ftrace_hash *hash, char *glob,
+ char *cmd, char *param, int enable)
{
- struct ftrace_probe_ops *ops;
void *count = (void *)-1;
char *number;
int ret;
@@ -312,14 +370,10 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash,
if (!enable)
return -EINVAL;
- if (glob[0] == '!')
- return ftrace_trace_onoff_unreg(glob+1, cmd, param);
-
- /* we register both traceon and traceoff to this callback */
- if (strcmp(cmd, "traceon") == 0)
- ops = &traceon_probe_ops;
- else
- ops = &traceoff_probe_ops;
+ if (glob[0] == '!') {
+ unregister_ftrace_function_probe_func(glob+1, ops);
+ return 0;
+ }
if (!param)
goto out_reg;
@@ -343,6 +397,34 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash,
return ret < 0 ? ret : 0;
}
+static int
+ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+ char *glob, char *cmd, char *param, int enable)
+{
+ struct ftrace_probe_ops *ops;
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = param ? &traceon_count_probe_ops : &traceon_probe_ops;
+ else
+ ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops;
+
+ return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+ param, enable);
+}
+
+static int
+ftrace_stacktrace_callback(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,
+ param, enable);
+}
+
static struct ftrace_func_command ftrace_traceon_cmd = {
.name = "traceon",
.func = ftrace_trace_onoff_callback,
@@ -353,6 +435,11 @@ static struct ftrace_func_command ftrace_traceoff_cmd = {
.func = ftrace_trace_onoff_callback,
};
+static struct ftrace_func_command ftrace_stacktrace_cmd = {
+ .name = "stacktrace",
+ .func = ftrace_stacktrace_callback,
+};
+
static int __init init_func_cmd_traceon(void)
{
int ret;
@@ -364,6 +451,12 @@ static int __init init_func_cmd_traceon(void)
ret = register_ftrace_command(&ftrace_traceon_cmd);
if (ret)
unregister_ftrace_command(&ftrace_traceoff_cmd);
+
+ ret = register_ftrace_command(&ftrace_stacktrace_cmd);
+ if (ret) {
+ unregister_ftrace_command(&ftrace_traceoff_cmd);
+ unregister_ftrace_command(&ftrace_traceon_cmd);
+ }
return ret;
}
#else
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 39ada66389cc..8388bc99f2ee 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -218,7 +218,7 @@ int __trace_graph_entry(struct trace_array *tr,
{
struct ftrace_event_call *call = &event_funcgraph_entry;
struct ring_buffer_event *event;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ftrace_graph_ent_entry *entry;
if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
@@ -265,7 +265,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
@@ -323,7 +323,7 @@ void __trace_graph_return(struct trace_array *tr,
{
struct ftrace_event_call *call = &event_funcgraph_exit;
struct ring_buffer_event *event;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ftrace_graph_ret_entry *entry;
if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
@@ -350,7 +350,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
@@ -560,9 +560,9 @@ get_return_for_leaf(struct trace_iterator *iter,
* We need to consume the current entry to see
* the next one.
*/
- ring_buffer_consume(iter->tr->buffer, iter->cpu,
+ ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu,
NULL, NULL);
- event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+ event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu,
NULL, NULL);
}
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 713a2cac4881..b19d065a28cb 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,8 @@ enum {
static int trace_type __read_mostly;
-static int save_lat_flag;
+static int save_flags;
+static bool function_enabled;
static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -121,7 +122,7 @@ static int func_prolog_dec(struct trace_array *tr,
if (!irqs_disabled_flags(*flags))
return 0;
- *data = tr->data[cpu];
+ *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&(*data)->disabled);
if (likely(disabled == 1))
@@ -175,7 +176,7 @@ static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
per_cpu(tracing_cpu, cpu) = 0;
tracing_max_latency = 0;
- tracing_reset_online_cpus(irqsoff_trace);
+ tracing_reset_online_cpus(&irqsoff_trace->trace_buffer);
return start_irqsoff_tracer(irqsoff_trace, set);
}
@@ -380,7 +381,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
if (per_cpu(tracing_cpu, cpu))
return;
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
if (unlikely(!data) || atomic_read(&data->disabled))
return;
@@ -418,7 +419,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
if (!tracer_enabled)
return;
- data = tr->data[cpu];
+ data = per_cpu_ptr(tr->trace_buffer.data, cpu);
if (unlikely(!data) ||
!data->critical_start || atomic_read(&data->disabled))
@@ -528,15 +529,60 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
}
#endif /* CONFIG_PREEMPT_TRACER */
-static int start_irqsoff_tracer(struct trace_array *tr, int graph)
+static int register_irqsoff_function(int graph, int set)
{
- int ret = 0;
+ int ret;
- if (!graph)
- ret = register_ftrace_function(&trace_ops);
- else
+ /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+ if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+ return 0;
+
+ if (graph)
ret = register_ftrace_graph(&irqsoff_graph_return,
&irqsoff_graph_entry);
+ else
+ ret = register_ftrace_function(&trace_ops);
+
+ if (!ret)
+ function_enabled = true;
+
+ return ret;
+}
+
+static void unregister_irqsoff_function(int graph)
+{
+ if (!function_enabled)
+ return;
+
+ if (graph)
+ unregister_ftrace_graph();
+ else
+ unregister_ftrace_function(&trace_ops);
+
+ function_enabled = false;
+}
+
+static void irqsoff_function_set(int set)
+{
+ if (set)
+ register_irqsoff_function(is_graph(), 1);
+ else
+ unregister_irqsoff_function(is_graph());
+}
+
+static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set)
+{
+ if (mask & TRACE_ITER_FUNCTION)
+ irqsoff_function_set(set);
+
+ return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
+{
+ int ret;
+
+ ret = register_irqsoff_function(graph, 0);
if (!ret && tracing_is_enabled())
tracer_enabled = 1;
@@ -550,22 +596,22 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
{
tracer_enabled = 0;
- if (!graph)
- unregister_ftrace_function(&trace_ops);
- else
- unregister_ftrace_graph();
+ unregister_irqsoff_function(graph);
}
static void __irqsoff_tracer_init(struct trace_array *tr)
{
- save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
- trace_flags |= TRACE_ITER_LATENCY_FMT;
+ save_flags = trace_flags;
+
+ /* non overwrite screws up the latency tracers */
+ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+ set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
tracing_max_latency = 0;
irqsoff_trace = tr;
/* make sure that the tracer is visible */
smp_wmb();
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
if (start_irqsoff_tracer(tr, is_graph()))
printk(KERN_ERR "failed to start irqsoff tracer\n");
@@ -573,10 +619,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
static void irqsoff_tracer_reset(struct trace_array *tr)
{
+ int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+ int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
stop_irqsoff_tracer(tr, is_graph());
- if (!save_lat_flag)
- trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+ set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
}
static void irqsoff_tracer_start(struct trace_array *tr)
@@ -609,6 +658,7 @@ static struct tracer irqsoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = irqsoff_flag_changed,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_irqsoff,
#endif
@@ -642,6 +692,7 @@ static struct tracer preemptoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = irqsoff_flag_changed,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptoff,
#endif
@@ -677,6 +728,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
.print_line = irqsoff_print_line,
.flags = &tracer_flags,
.set_flag = irqsoff_set_flag,
+ .flag_changed = irqsoff_flag_changed,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptirqsoff,
#endif
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 3c5c5dfea0b3..bd90e1b06088 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -26,7 +26,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
trace_init_global_iter(&iter);
for_each_tracing_cpu(cpu) {
- atomic_inc(&iter.tr->data[cpu]->disabled);
+ atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
}
old_userobj = trace_flags;
@@ -43,17 +43,17 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
iter.iter_flags |= TRACE_FILE_LAT_FMT;
iter.pos = -1;
- if (cpu_file == TRACE_PIPE_ALL_CPU) {
+ if (cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter.buffer_iter[cpu] =
- ring_buffer_read_prepare(iter.tr->buffer, cpu);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu);
ring_buffer_read_start(iter.buffer_iter[cpu]);
tracing_iter_reset(&iter, cpu);
}
} else {
iter.cpu_file = cpu_file;
iter.buffer_iter[cpu_file] =
- ring_buffer_read_prepare(iter.tr->buffer, cpu_file);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file);
ring_buffer_read_start(iter.buffer_iter[cpu_file]);
tracing_iter_reset(&iter, cpu_file);
}
@@ -83,7 +83,7 @@ out:
trace_flags = old_userobj;
for_each_tracing_cpu(cpu) {
- atomic_dec(&iter.tr->data[cpu]->disabled);
+ atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
}
for_each_tracing_cpu(cpu)
@@ -115,7 +115,7 @@ static int kdb_ftdump(int argc, const char **argv)
!cpu_online(cpu_file))
return KDB_BADINT;
} else {
- cpu_file = TRACE_PIPE_ALL_CPU;
+ cpu_file = RING_BUFFER_ALL_CPUS;
}
kdb_trap_printk++;
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index fd3c8aae55e5..a5e8f4878bfa 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -31,7 +31,7 @@ static void mmio_reset_data(struct trace_array *tr)
overrun_detected = false;
prev_overruns = 0;
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
}
static int mmio_trace_init(struct trace_array *tr)
@@ -128,7 +128,7 @@ static void mmio_close(struct trace_iterator *iter)
static unsigned long count_overruns(struct trace_iterator *iter)
{
unsigned long cnt = atomic_xchg(&dropped_count, 0);
- unsigned long over = ring_buffer_overruns(iter->tr->buffer);
+ unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer);
if (over > prev_overruns)
cnt += over - prev_overruns;
@@ -309,7 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
struct mmiotrace_rw *rw)
{
struct ftrace_event_call *call = &event_mmiotrace_rw;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ring_buffer_event *event;
struct trace_mmiotrace_rw *entry;
int pc = preempt_count();
@@ -330,7 +330,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
void mmio_trace_rw(struct mmiotrace_rw *rw)
{
struct trace_array *tr = mmio_trace_array;
- struct trace_array_cpu *data = tr->data[smp_processor_id()];
+ struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
__trace_mmiotrace_rw(tr, data, rw);
}
@@ -339,7 +339,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
struct mmiotrace_map *map)
{
struct ftrace_event_call *call = &event_mmiotrace_map;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ring_buffer_event *event;
struct trace_mmiotrace_map *entry;
int pc = preempt_count();
@@ -363,7 +363,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
struct trace_array_cpu *data;
preempt_disable();
- data = tr->data[smp_processor_id()];
+ data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
__trace_mmiotrace_map(tr, data, map);
preempt_enable();
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 697e88d13907..bb922d9ee51b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -14,7 +14,7 @@
/* must be a power of 2 */
#define EVENT_HASHSIZE 128
-DECLARE_RWSEM(trace_event_mutex);
+DECLARE_RWSEM(trace_event_sem);
static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
@@ -37,6 +37,22 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s)
return ret;
}
+enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct bputs_entry *field;
+ int ret;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_puts(s, field->str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
@@ -397,6 +413,32 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
}
EXPORT_SYMBOL(ftrace_print_hex_seq);
+int ftrace_raw_output_prep(struct trace_iterator *iter,
+ struct trace_event *trace_event)
+{
+ struct ftrace_event_call *event;
+ struct trace_seq *s = &iter->seq;
+ struct trace_seq *p = &iter->tmp_seq;
+ struct trace_entry *entry;
+ int ret;
+
+ event = container_of(trace_event, struct ftrace_event_call, event);
+ entry = iter->ent;
+
+ if (entry->type != event->event.type) {
+ WARN_ON_ONCE(1);
+ return TRACE_TYPE_UNHANDLED;
+ }
+
+ trace_seq_init(p);
+ ret = trace_seq_printf(s, "%s: ", event->name);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return 0;
+}
+EXPORT_SYMBOL(ftrace_raw_output_prep);
+
#ifdef CONFIG_KRETPROBES
static inline const char *kretprobed(const char *name)
{
@@ -617,7 +659,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
{
unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE;
unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
- unsigned long long abs_ts = iter->ts - iter->tr->time_start;
+ unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start;
unsigned long long rel_ts = next_ts - iter->ts;
struct trace_seq *s = &iter->seq;
@@ -783,12 +825,12 @@ static int trace_search_list(struct list_head **list)
void trace_event_read_lock(void)
{
- down_read(&trace_event_mutex);
+ down_read(&trace_event_sem);
}
void trace_event_read_unlock(void)
{
- up_read(&trace_event_mutex);
+ up_read(&trace_event_sem);
}
/**
@@ -811,7 +853,7 @@ int register_ftrace_event(struct trace_event *event)
unsigned key;
int ret = 0;
- down_write(&trace_event_mutex);
+ down_write(&trace_event_sem);
if (WARN_ON(!event))
goto out;
@@ -866,14 +908,14 @@ int register_ftrace_event(struct trace_event *event)
ret = event->type;
out:
- up_write(&trace_event_mutex);
+ up_write(&trace_event_sem);
return ret;
}
EXPORT_SYMBOL_GPL(register_ftrace_event);
/*
- * Used by module code with the trace_event_mutex held for write.
+ * Used by module code with the trace_event_sem held for write.
*/
int __unregister_ftrace_event(struct trace_event *event)
{
@@ -888,9 +930,9 @@ int __unregister_ftrace_event(struct trace_event *event)
*/
int unregister_ftrace_event(struct trace_event *event)
{
- down_write(&trace_event_mutex);
+ down_write(&trace_event_sem);
__unregister_ftrace_event(event);
- up_write(&trace_event_mutex);
+ up_write(&trace_event_sem);
return 0;
}
@@ -1217,6 +1259,64 @@ static struct trace_event trace_user_stack_event = {
.funcs = &trace_user_stack_funcs,
};
+/* TRACE_BPUTS */
+static enum print_line_t
+trace_bputs_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct bputs_entry *field;
+
+ trace_assign_type(field, entry);
+
+ if (!seq_print_ip_sym(s, field->ip, flags))
+ goto partial;
+
+ if (!trace_seq_puts(s, ": "))
+ goto partial;
+
+ if (!trace_seq_puts(s, field->str))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+
+static enum print_line_t
+trace_bputs_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct bputs_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(s, ": %lx : ", field->ip))
+ goto partial;
+
+ if (!trace_seq_puts(s, field->str))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct trace_event_functions trace_bputs_funcs = {
+ .trace = trace_bputs_print,
+ .raw = trace_bputs_raw,
+};
+
+static struct trace_event trace_bputs_event = {
+ .type = TRACE_BPUTS,
+ .funcs = &trace_bputs_funcs,
+};
+
/* TRACE_BPRINT */
static enum print_line_t
trace_bprint_print(struct trace_iterator *iter, int flags,
@@ -1329,6 +1429,7 @@ static struct trace_event *events[] __initdata = {
&trace_wake_event,
&trace_stack_event,
&trace_user_stack_event,
+ &trace_bputs_event,
&trace_bprint_event,
&trace_print_event,
NULL
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index c038eba0492b..127a9d8c8357 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -5,6 +5,8 @@
#include "trace.h"
extern enum print_line_t
+trace_print_bputs_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
trace_print_bprintk_msg_only(struct trace_iterator *iter);
extern enum print_line_t
trace_print_printk_msg_only(struct trace_iterator *iter);
@@ -31,7 +33,7 @@ trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
/* used by module unregistering */
extern int __unregister_ftrace_event(struct trace_event *event);
-extern struct rw_semaphore trace_event_mutex;
+extern struct rw_semaphore trace_event_sem;
#define MAX_MEMHEX_BYTES 8
#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 3374c792ccd8..4e98e3b257a3 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -28,7 +28,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
unsigned long flags, int pc)
{
struct ftrace_event_call *call = &event_context_switch;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
@@ -69,7 +69,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = ctx_trace->data[cpu];
+ data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
if (likely(!atomic_read(&data->disabled)))
tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc);
@@ -86,7 +86,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
struct ftrace_event_call *call = &event_wakeup;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
- struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
sizeof(*entry), flags, pc);
@@ -123,7 +123,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = ctx_trace->data[cpu];
+ data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
if (likely(!atomic_read(&data->disabled)))
tracing_sched_wakeup_trace(ctx_trace, wakee, current,
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 75aa97fbe1a1..fee77e15d815 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,8 @@ static void __wakeup_reset(struct trace_array *tr);
static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
static void wakeup_graph_return(struct ftrace_graph_ret *trace);
-static int save_lat_flag;
+static int save_flags;
+static bool function_enabled;
#define TRACE_DISPLAY_GRAPH 1
@@ -89,7 +90,7 @@ func_prolog_preempt_disable(struct trace_array *tr,
if (cpu != wakeup_current_cpu)
goto out_enable;
- *data = tr->data[cpu];
+ *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&(*data)->disabled);
if (unlikely(disabled != 1))
goto out;
@@ -134,15 +135,60 @@ static struct ftrace_ops trace_ops __read_mostly =
};
#endif /* CONFIG_FUNCTION_TRACER */
-static int start_func_tracer(int graph)
+static int register_wakeup_function(int graph, int set)
{
int ret;
- if (!graph)
- ret = register_ftrace_function(&trace_ops);
- else
+ /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+ if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+ return 0;
+
+ if (graph)
ret = register_ftrace_graph(&wakeup_graph_return,
&wakeup_graph_entry);
+ else
+ ret = register_ftrace_function(&trace_ops);
+
+ if (!ret)
+ function_enabled = true;
+
+ return ret;
+}
+
+static void unregister_wakeup_function(int graph)
+{
+ if (!function_enabled)
+ return;
+
+ if (graph)
+ unregister_ftrace_graph();
+ else
+ unregister_ftrace_function(&trace_ops);
+
+ function_enabled = false;
+}
+
+static void wakeup_function_set(int set)
+{
+ if (set)
+ register_wakeup_function(is_graph(), 1);
+ else
+ unregister_wakeup_function(is_graph());
+}
+
+static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set)
+{
+ if (mask & TRACE_ITER_FUNCTION)
+ wakeup_function_set(set);
+
+ return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_func_tracer(int graph)
+{
+ int ret;
+
+ ret = register_wakeup_function(graph, 0);
if (!ret && tracing_is_enabled())
tracer_enabled = 1;
@@ -156,10 +202,7 @@ static void stop_func_tracer(int graph)
{
tracer_enabled = 0;
- if (!graph)
- unregister_ftrace_function(&trace_ops);
- else
- unregister_ftrace_graph();
+ unregister_wakeup_function(graph);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -353,7 +396,7 @@ probe_wakeup_sched_switch(void *ignore,
/* disable local data, not wakeup_cpu data */
cpu = raw_smp_processor_id();
- disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+ disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
if (likely(disabled != 1))
goto out;
@@ -365,7 +408,7 @@ probe_wakeup_sched_switch(void *ignore,
goto out_unlock;
/* The task we are waiting for is waking up */
- data = wakeup_trace->data[wakeup_cpu];
+ data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
@@ -387,7 +430,7 @@ out_unlock:
arch_spin_unlock(&wakeup_lock);
local_irq_restore(flags);
out:
- atomic_dec(&wakeup_trace->data[cpu]->disabled);
+ atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
}
static void __wakeup_reset(struct trace_array *tr)
@@ -405,7 +448,7 @@ static void wakeup_reset(struct trace_array *tr)
{
unsigned long flags;
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
local_irq_save(flags);
arch_spin_lock(&wakeup_lock);
@@ -435,7 +478,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
return;
pc = preempt_count();
- disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+ disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
if (unlikely(disabled != 1))
goto out;
@@ -458,7 +501,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
local_save_flags(flags);
- data = wakeup_trace->data[wakeup_cpu];
+ data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
data->preempt_timestamp = ftrace_now(cpu);
tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
@@ -472,7 +515,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
out_locked:
arch_spin_unlock(&wakeup_lock);
out:
- atomic_dec(&wakeup_trace->data[cpu]->disabled);
+ atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
}
static void start_wakeup_tracer(struct trace_array *tr)
@@ -540,8 +583,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
static int __wakeup_tracer_init(struct trace_array *tr)
{
- save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
- trace_flags |= TRACE_ITER_LATENCY_FMT;
+ save_flags = trace_flags;
+
+ /* non overwrite screws up the latency tracers */
+ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+ set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
tracing_max_latency = 0;
wakeup_trace = tr;
@@ -563,12 +609,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
static void wakeup_tracer_reset(struct trace_array *tr)
{
+ int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+ int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
stop_wakeup_tracer(tr);
/* make sure we put back any tasks we are tracing */
wakeup_reset(tr);
- if (!save_lat_flag)
- trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+ set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
}
static void wakeup_tracer_start(struct trace_array *tr)
@@ -594,6 +643,7 @@ static struct tracer wakeup_tracer __read_mostly =
.print_line = wakeup_print_line,
.flags = &tracer_flags,
.set_flag = wakeup_set_flag,
+ .flag_changed = wakeup_flag_changed,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_wakeup,
#endif
@@ -615,6 +665,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
.print_line = wakeup_print_line,
.flags = &tracer_flags,
.set_flag = wakeup_set_flag,
+ .flag_changed = wakeup_flag_changed,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_wakeup,
#endif
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 51c819c12c29..55e2cf66967b 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -21,13 +21,13 @@ static inline int trace_valid_entry(struct trace_entry *entry)
return 0;
}
-static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
+static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu)
{
struct ring_buffer_event *event;
struct trace_entry *entry;
unsigned int loops = 0;
- while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
+ while ((event = ring_buffer_consume(buf->buffer, cpu, NULL, NULL))) {
entry = ring_buffer_event_data(event);
/*
@@ -58,7 +58,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
* Test the trace buffer to see if all the elements
* are still sane.
*/
-static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
+static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
{
unsigned long flags, cnt = 0;
int cpu, ret = 0;
@@ -67,7 +67,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
local_irq_save(flags);
arch_spin_lock(&ftrace_max_lock);
- cnt = ring_buffer_entries(tr->buffer);
+ cnt = ring_buffer_entries(buf->buffer);
/*
* The trace_test_buffer_cpu runs a while loop to consume all data.
@@ -78,7 +78,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
*/
tracing_off();
for_each_possible_cpu(cpu) {
- ret = trace_test_buffer_cpu(tr, cpu);
+ ret = trace_test_buffer_cpu(buf, cpu);
if (ret)
break;
}
@@ -355,7 +355,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
msleep(100);
/* we should have nothing in the buffer */
- ret = trace_test_buffer(tr, &count);
+ ret = trace_test_buffer(&tr->trace_buffer, &count);
if (ret)
goto out;
@@ -376,7 +376,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
ftrace_enabled = 0;
/* check the trace buffer */
- ret = trace_test_buffer(tr, &count);
+ ret = trace_test_buffer(&tr->trace_buffer, &count);
tracing_start();
/* we should only have one item */
@@ -666,7 +666,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
ftrace_enabled = 0;
/* check the trace buffer */
- ret = trace_test_buffer(tr, &count);
+ ret = trace_test_buffer(&tr->trace_buffer, &count);
trace->reset(tr);
tracing_start();
@@ -703,8 +703,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
/* Maximum number of functions to trace before diagnosing a hang */
#define GRAPH_MAX_FUNC_TEST 100000000
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
static unsigned int graph_hang_thresh;
/* Wrap the real function entry probe to avoid possible hanging */
@@ -714,8 +712,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
ftrace_graph_stop();
printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
- if (ftrace_dump_on_oops)
- __ftrace_dump(false, DUMP_ALL);
+ if (ftrace_dump_on_oops) {
+ ftrace_dump(DUMP_ALL);
+ /* ftrace_dump() disables tracing */
+ tracing_on();
+ }
return 0;
}
@@ -737,7 +738,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
* Simulate the init() callback but we attach a watchdog callback
* to detect and recover from possible hangs
*/
- tracing_reset_online_cpus(tr);
+ tracing_reset_online_cpus(&tr->trace_buffer);
set_graph_array(tr);
ret = register_ftrace_graph(&trace_graph_return,
&trace_graph_entry_watchdog);
@@ -760,7 +761,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
tracing_stop();
/* check the trace buffer */
- ret = trace_test_buffer(tr, &count);
+ ret = trace_test_buffer(&tr->trace_buffer, &count);
trace->reset(tr);
tracing_start();
@@ -815,9 +816,9 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
/* stop the tracing. */
tracing_stop();
/* check both trace buffers */
- ret = trace_test_buffer(tr, NULL);
+ ret = trace_test_buffer(&tr->trace_buffer, NULL);
if (!ret)
- ret = trace_test_buffer(&max_tr, &count);
+ ret = trace_test_buffer(&tr->max_buffer, &count);
trace->reset(tr);
tracing_start();
@@ -877,9 +878,9 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
/* stop the tracing. */
tracing_stop();
/* check both trace buffers */
- ret = trace_test_buffer(tr, NULL);
+ ret = trace_test_buffer(&tr->trace_buffer, NULL);
if (!ret)
- ret = trace_test_buffer(&max_tr, &count);
+ ret = trace_test_buffer(&tr->max_buffer, &count);
trace->reset(tr);
tracing_start();
@@ -943,11 +944,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
/* stop the tracing. */
tracing_stop();
/* check both trace buffers */
- ret = trace_test_buffer(tr, NULL);
+ ret = trace_test_buffer(&tr->trace_buffer, NULL);
if (ret)
goto out;
- ret = trace_test_buffer(&max_tr, &count);
+ ret = trace_test_buffer(&tr->max_buffer, &count);
if (ret)
goto out;
@@ -973,11 +974,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
/* stop the tracing. */
tracing_stop();
/* check both trace buffers */
- ret = trace_test_buffer(tr, NULL);
+ ret = trace_test_buffer(&tr->trace_buffer, NULL);
if (ret)
goto out;
- ret = trace_test_buffer(&max_tr, &count);
+ ret = trace_test_buffer(&tr->max_buffer, &count);
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
@@ -1084,10 +1085,10 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
/* stop the tracing. */
tracing_stop();
/* check both trace buffers */
- ret = trace_test_buffer(tr, NULL);
+ ret = trace_test_buffer(&tr->trace_buffer, NULL);
printk("ret = %d\n", ret);
if (!ret)
- ret = trace_test_buffer(&max_tr, &count);
+ ret = trace_test_buffer(&tr->max_buffer, &count);
trace->reset(tr);
@@ -1126,7 +1127,7 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
/* stop the tracing. */
tracing_stop();
/* check the trace buffer */
- ret = trace_test_buffer(tr, &count);
+ ret = trace_test_buffer(&tr->trace_buffer, &count);
trace->reset(tr);
tracing_start();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc701..b20428c5efe2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,13 +20,24 @@
#define STACK_TRACE_ENTRIES 500
+#ifdef CC_USING_FENTRY
+# define fentry 1
+#else
+# define fentry 0
+#endif
+
static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
{ [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
static struct stack_trace max_stack_trace = {
- .max_entries = STACK_TRACE_ENTRIES,
- .entries = stack_dump_trace,
+ .max_entries = STACK_TRACE_ENTRIES - 1,
+ .entries = &stack_dump_trace[1],
};
static unsigned long max_stack_size;
@@ -39,25 +50,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
static int last_stack_tracer_enabled;
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags;
unsigned long *p, *top, *start;
+ static int tracer_frame;
+ int frame_size = ACCESS_ONCE(tracer_frame);
int i;
- this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+ this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
this_size = THREAD_SIZE - this_size;
+ /* Remove the frame of the tracer */
+ this_size -= frame_size;
if (this_size <= max_stack_size)
return;
/* we do not handle interrupt stacks yet */
- if (!object_is_on_stack(&this_size))
+ if (!object_is_on_stack(stack))
return;
local_irq_save(flags);
arch_spin_lock(&max_stack_lock);
+ /* In case another CPU set the tracer_frame on us */
+ if (unlikely(!frame_size))
+ this_size -= tracer_frame;
+
/* a race could have already updated it */
if (this_size <= max_stack_size)
goto out;
@@ -70,10 +90,18 @@ static inline void check_stack(void)
save_stack_trace(&max_stack_trace);
/*
+ * Add the passed in ip from the function tracer.
+ * Searching for this on the stack will skip over
+ * most of the overhead from the stack tracer itself.
+ */
+ stack_dump_trace[0] = ip;
+ max_stack_trace.nr_entries++;
+
+ /*
* Now find where in the stack these are.
*/
i = 0;
- start = &this_size;
+ start = stack;
top = (unsigned long *)
(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
@@ -97,6 +125,18 @@ static inline void check_stack(void)
found = 1;
/* Start the search from here */
start = p + 1;
+ /*
+ * We do not want to show the overhead
+ * of the stack tracer stack in the
+ * max stack. If we haven't figured
+ * out what that is, then figure it out
+ * now.
+ */
+ if (unlikely(!tracer_frame) && i == 1) {
+ tracer_frame = (p - stack) *
+ sizeof(unsigned long);
+ max_stack_size -= tracer_frame;
+ }
}
}
@@ -113,6 +153,7 @@ static void
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();
@@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
if (per_cpu(trace_active, cpu)++ != 0)
goto out;
- check_stack();
+ /*
+ * When fentry is used, the traced function does not get
+ * its stack frame set up, and we lose the parent.
+ * The ip is pretty useless because the function tracer
+ * was called before that function set up its stack frame.
+ * In this case, we use the parent ip.
+ *
+ * By adding the return address of either the parent ip
+ * or the current ip we can disregard most of the stack usage
+ * caused by the stack tracer itself.
+ *
+ * The function tracer always reports the address of where the
+ * mcount call was, but the stack will hold the return address.
+ */
+ if (fentry)
+ ip = parent_ip;
+ else
+ ip += MCOUNT_INSN_SIZE;
+
+ check_stack(ip, &stack);
out:
per_cpu(trace_active, cpu)--;
@@ -322,7 +382,7 @@ static const struct file_operations stack_trace_filter_fops = {
.open = stack_trace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_regex_lseek,
+ .llseek = ftrace_filter_lseek,
.release = ftrace_regex_release,
};
@@ -371,6 +431,8 @@ static __init int stack_trace_init(void)
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
trace_create_file("stack_max_size", 0644, d_tracer,
&max_stack_size, &stack_max_size_fops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 96cffb269e73..847f88a6194b 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -307,6 +307,8 @@ static int tracing_stat_init(void)
struct dentry *d_tracing;
d_tracing = tracing_init_dentry();
+ if (!d_tracing)
+ return 0;
stat_dir = debugfs_create_dir("trace_stat", d_tracing);
if (!stat_dir)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7a809e321058..8f2ac73c7a5f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -12,10 +12,6 @@
#include "trace.h"
static DEFINE_MUTEX(syscall_trace_lock);
-static int sys_refcount_enter;
-static int sys_refcount_exit;
-static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
static int syscall_enter_register(struct ftrace_event_call *event,
enum trace_reg type, void *data);
@@ -41,7 +37,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
/*
* Only compare after the "sys" prefix. Archs that use
* syscall wrappers may have syscalls symbols aliases prefixed
- * with "SyS" instead of "sys", leading to an unwanted
+ * with ".SyS" or ".sys" instead of "sys", leading to an unwanted
* mismatch.
*/
return !strcmp(sym + 3, name + 3);
@@ -265,7 +261,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
kfree(call->print_fmt);
}
-static int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int __init syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
struct syscall_metadata *meta = call->data;
@@ -288,7 +284,7 @@ static int syscall_enter_define_fields(struct ftrace_event_call *call)
return ret;
}
-static int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_exit trace;
int ret;
@@ -303,8 +299,9 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call)
return ret;
}
-static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
{
+ struct trace_array *tr = data;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -315,7 +312,7 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, enabled_enter_syscalls))
+ if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -324,7 +321,8 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
- event = trace_current_buffer_lock_reserve(&buffer,
+ buffer = tr->trace_buffer.buffer;
+ event = trace_buffer_lock_reserve(buffer,
sys_data->enter_event->event.type, size, 0, 0);
if (!event)
return;
@@ -338,8 +336,9 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
{
+ struct trace_array *tr = data;
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -349,14 +348,15 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, enabled_exit_syscalls))
+ if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
- event = trace_current_buffer_lock_reserve(&buffer,
+ buffer = tr->trace_buffer.buffer;
+ event = trace_buffer_lock_reserve(buffer,
sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
if (!event)
return;
@@ -370,8 +370,10 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-static int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_file *file,
+ struct ftrace_event_call *call)
{
+ struct trace_array *tr = file->tr;
int ret = 0;
int num;
@@ -379,33 +381,37 @@ static int reg_event_syscall_enter(struct ftrace_event_call *call)
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
- if (!sys_refcount_enter)
- ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
+ if (!tr->sys_refcount_enter)
+ ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
if (!ret) {
- set_bit(num, enabled_enter_syscalls);
- sys_refcount_enter++;
+ set_bit(num, tr->enabled_enter_syscalls);
+ tr->sys_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-static void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_file *file,
+ struct ftrace_event_call *call)
{
+ struct trace_array *tr = file->tr;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
- sys_refcount_enter--;
- clear_bit(num, enabled_enter_syscalls);
- if (!sys_refcount_enter)
- unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
+ tr->sys_refcount_enter--;
+ clear_bit(num, tr->enabled_enter_syscalls);
+ if (!tr->sys_refcount_enter)
+ unregister_trace_sys_enter(ftrace_syscall_enter, tr);
mutex_unlock(&syscall_trace_lock);
}
-static int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_file *file,
+ struct ftrace_event_call *call)
{
+ struct trace_array *tr = file->tr;
int ret = 0;
int num;
@@ -413,28 +419,30 @@ static int reg_event_syscall_exit(struct ftrace_event_call *call)
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
- if (!sys_refcount_exit)
- ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
+ if (!tr->sys_refcount_exit)
+ ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
if (!ret) {
- set_bit(num, enabled_exit_syscalls);
- sys_refcount_exit++;
+ set_bit(num, tr->enabled_exit_syscalls);
+ tr->sys_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-static void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_file *file,
+ struct ftrace_event_call *call)
{
+ struct trace_array *tr = file->tr;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
- sys_refcount_exit--;
- clear_bit(num, enabled_exit_syscalls);
- if (!sys_refcount_exit)
- unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
+ tr->sys_refcount_exit--;
+ clear_bit(num, tr->enabled_exit_syscalls);
+ if (!tr->sys_refcount_exit)
+ unregister_trace_sys_exit(ftrace_syscall_exit, tr);
mutex_unlock(&syscall_trace_lock);
}
@@ -471,7 +479,7 @@ struct trace_event_functions exit_syscall_print_funcs = {
.trace = print_syscall_exit,
};
-struct ftrace_event_class event_class_syscall_enter = {
+struct ftrace_event_class __refdata event_class_syscall_enter = {
.system = "syscalls",
.reg = syscall_enter_register,
.define_fields = syscall_enter_define_fields,
@@ -479,7 +487,7 @@ struct ftrace_event_class event_class_syscall_enter = {
.raw_init = init_syscall_trace,
};
-struct ftrace_event_class event_class_syscall_exit = {
+struct ftrace_event_class __refdata event_class_syscall_exit = {
.system = "syscalls",
.reg = syscall_exit_register,
.define_fields = syscall_exit_define_fields,
@@ -685,11 +693,13 @@ static void perf_sysexit_disable(struct ftrace_event_call *call)
static int syscall_enter_register(struct ftrace_event_call *event,
enum trace_reg type, void *data)
{
+ struct ftrace_event_file *file = data;
+
switch (type) {
case TRACE_REG_REGISTER:
- return reg_event_syscall_enter(event);
+ return reg_event_syscall_enter(file, event);
case TRACE_REG_UNREGISTER:
- unreg_event_syscall_enter(event);
+ unreg_event_syscall_enter(file, event);
return 0;
#ifdef CONFIG_PERF_EVENTS
@@ -711,11 +721,13 @@ static int syscall_enter_register(struct ftrace_event_call *event,
static int syscall_exit_register(struct ftrace_event_call *event,
enum trace_reg type, void *data)
{
+ struct ftrace_event_file *file = data;
+
switch (type) {
case TRACE_REG_REGISTER:
- return reg_event_syscall_exit(event);
+ return reg_event_syscall_exit(file, event);
case TRACE_REG_UNREGISTER:
- unreg_event_syscall_exit(event);
+ unreg_event_syscall_exit(file, event);
return 0;
#ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8dad2a92dee9..32494fb0ee64 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -28,6 +28,18 @@
#define UPROBE_EVENT_SYSTEM "uprobes"
+struct uprobe_trace_entry_head {
+ struct trace_entry ent;
+ unsigned long vaddr[];
+};
+
+#define SIZEOF_TRACE_ENTRY(is_return) \
+ (sizeof(struct uprobe_trace_entry_head) + \
+ sizeof(unsigned long) * (is_return ? 2 : 1))
+
+#define DATAOF_TRACE_ENTRY(entry, is_return) \
+ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))
+
struct trace_uprobe_filter {
rwlock_t rwlock;
int nr_systemwide;
@@ -64,6 +76,8 @@ static DEFINE_MUTEX(uprobe_lock);
static LIST_HEAD(uprobe_list);
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
+static int uretprobe_dispatcher(struct uprobe_consumer *con,
+ unsigned long func, struct pt_regs *regs);
static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
@@ -77,11 +91,16 @@ static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
return !filter->nr_systemwide && list_empty(&filter->perf_events);
}
+static inline bool is_ret_probe(struct trace_uprobe *tu)
+{
+ return tu->consumer.ret_handler != NULL;
+}
+
/*
* Allocate new trace_uprobe and initialize it (including uprobes).
*/
static struct trace_uprobe *
-alloc_trace_uprobe(const char *group, const char *event, int nargs)
+alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
{
struct trace_uprobe *tu;
@@ -106,6 +125,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs)
INIT_LIST_HEAD(&tu->list);
tu->consumer.handler = uprobe_dispatcher;
+ if (is_ret)
+ tu->consumer.ret_handler = uretprobe_dispatcher;
init_trace_uprobe_filter(&tu->filter);
return tu;
@@ -180,7 +201,7 @@ end:
/*
* Argument syntax:
- * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]
+ * - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS]
*
* - Remove uprobe: -:[GRP/]EVENT
*/
@@ -192,20 +213,23 @@ static int create_trace_uprobe(int argc, char **argv)
char buf[MAX_EVENT_NAME_LEN];
struct path path;
unsigned long offset;
- bool is_delete;
+ bool is_delete, is_return;
int i, ret;
inode = NULL;
ret = 0;
is_delete = false;
+ is_return = false;
event = NULL;
group = NULL;
/* argc must be >= 1 */
if (argv[0][0] == '-')
is_delete = true;
+ else if (argv[0][0] == 'r')
+ is_return = true;
else if (argv[0][0] != 'p') {
- pr_info("Probe definition must be started with 'p' or '-'.\n");
+ pr_info("Probe definition must be started with 'p', 'r' or '-'.\n");
return -EINVAL;
}
@@ -303,7 +327,7 @@ static int create_trace_uprobe(int argc, char **argv)
kfree(tail);
}
- tu = alloc_trace_uprobe(group, event, argc);
+ tu = alloc_trace_uprobe(group, event, argc, is_return);
if (IS_ERR(tu)) {
pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu));
ret = PTR_ERR(tu);
@@ -414,9 +438,10 @@ static void probes_seq_stop(struct seq_file *m, void *v)
static int probes_seq_show(struct seq_file *m, void *v)
{
struct trace_uprobe *tu = v;
+ char c = is_ret_probe(tu) ? 'r' : 'p';
int i;
- seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name);
+ seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name);
seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
for (i = 0; i < tu->nr_args; i++)
@@ -485,65 +510,81 @@ static const struct file_operations uprobe_profile_ops = {
.release = seq_release,
};
-/* uprobe handler */
-static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static void uprobe_trace_print(struct trace_uprobe *tu,
+ unsigned long func, struct pt_regs *regs)
{
struct uprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
- u8 *data;
- int size, i, pc;
- unsigned long irq_flags;
+ void *data;
+ int size, i;
struct ftrace_event_call *call = &tu->call;
- local_save_flags(irq_flags);
- pc = preempt_count();
-
- size = sizeof(*entry) + tu->size;
-
+ size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
- size, irq_flags, pc);
+ size + tu->size, 0, 0);
if (!event)
- return 0;
+ return;
entry = ring_buffer_event_data(event);
- entry->ip = instruction_pointer(task_pt_regs(current));
- data = (u8 *)&entry[1];
+ if (is_ret_probe(tu)) {
+ entry->vaddr[0] = func;
+ entry->vaddr[1] = instruction_pointer(regs);
+ data = DATAOF_TRACE_ENTRY(entry, true);
+ } else {
+ entry->vaddr[0] = instruction_pointer(regs);
+ data = DATAOF_TRACE_ENTRY(entry, false);
+ }
+
for (i = 0; i < tu->nr_args; i++)
call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
if (!filter_current_check_discard(buffer, call, entry, event))
- trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ trace_buffer_unlock_commit(buffer, event, 0, 0);
+}
+/* uprobe handler */
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+ if (!is_ret_probe(tu))
+ uprobe_trace_print(tu, 0, regs);
return 0;
}
+static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
+ struct pt_regs *regs)
+{
+ uprobe_trace_print(tu, func, regs);
+}
+
/* Event entry printers */
static enum print_line_t
print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event)
{
- struct uprobe_trace_entry_head *field;
+ struct uprobe_trace_entry_head *entry;
struct trace_seq *s = &iter->seq;
struct trace_uprobe *tu;
u8 *data;
int i;
- field = (struct uprobe_trace_entry_head *)iter->ent;
+ entry = (struct uprobe_trace_entry_head *)iter->ent;
tu = container_of(event, struct trace_uprobe, call.event);
- if (!trace_seq_printf(s, "%s: (", tu->call.name))
- goto partial;
-
- if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
- goto partial;
-
- if (!trace_seq_puts(s, ")"))
- goto partial;
+ if (is_ret_probe(tu)) {
+ if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name,
+ entry->vaddr[1], entry->vaddr[0]))
+ goto partial;
+ data = DATAOF_TRACE_ENTRY(entry, true);
+ } else {
+ if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name,
+ entry->vaddr[0]))
+ goto partial;
+ data = DATAOF_TRACE_ENTRY(entry, false);
+ }
- data = (u8 *)&field[1];
for (i = 0; i < tu->nr_args; i++) {
if (!tu->args[i].type->print(s, tu->args[i].name,
- data + tu->args[i].offset, field))
+ data + tu->args[i].offset, entry))
goto partial;
}
@@ -595,16 +636,23 @@ static void probe_event_disable(struct trace_uprobe *tu, int flag)
static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
{
- int ret, i;
+ int ret, i, size;
struct uprobe_trace_entry_head field;
- struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data;
+ struct trace_uprobe *tu = event_call->data;
- DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ if (is_ret_probe(tu)) {
+ DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0);
+ size = SIZEOF_TRACE_ENTRY(true);
+ } else {
+ DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0);
+ size = SIZEOF_TRACE_ENTRY(false);
+ }
/* Set argument names as fields */
for (i = 0; i < tu->nr_args; i++) {
ret = trace_define_field(event_call, tu->args[i].type->fmttype,
tu->args[i].name,
- sizeof(field) + tu->args[i].offset,
+ size + tu->args[i].offset,
tu->args[i].type->size,
tu->args[i].type->is_signed,
FILTER_OTHER);
@@ -622,8 +670,13 @@ static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
int i;
int pos = 0;
- fmt = "(%lx)";
- arg = "REC->" FIELD_STRING_IP;
+ if (is_ret_probe(tu)) {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ } else {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ }
/* When len=0, we just calculate the needed length */
@@ -752,49 +805,68 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
return ret;
}
-/* uprobe profile handler */
-static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static void uprobe_perf_print(struct trace_uprobe *tu,
+ unsigned long func, struct pt_regs *regs)
{
struct ftrace_event_call *call = &tu->call;
struct uprobe_trace_entry_head *entry;
struct hlist_head *head;
- u8 *data;
- int size, __size, i;
- int rctx;
+ void *data;
+ int size, rctx, i;
- if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
- return UPROBE_HANDLER_REMOVE;
-
- __size = sizeof(*entry) + tu->size;
- size = ALIGN(__size + sizeof(u32), sizeof(u64));
- size -= sizeof(u32);
+ size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+ size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
- return 0;
+ return;
preempt_disable();
+ head = this_cpu_ptr(call->perf_events);
+ if (hlist_empty(head))
+ goto out;
entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
if (!entry)
goto out;
- entry->ip = instruction_pointer(task_pt_regs(current));
- data = (u8 *)&entry[1];
+ if (is_ret_probe(tu)) {
+ entry->vaddr[0] = func;
+ entry->vaddr[1] = instruction_pointer(regs);
+ data = DATAOF_TRACE_ENTRY(entry, true);
+ } else {
+ entry->vaddr[0] = instruction_pointer(regs);
+ data = DATAOF_TRACE_ENTRY(entry, false);
+ }
+
for (i = 0; i < tu->nr_args; i++)
call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
- head = this_cpu_ptr(call->perf_events);
- perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL);
-
+ perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
out:
preempt_enable();
+}
+
+/* uprobe profile handler */
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+ if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+ return UPROBE_HANDLER_REMOVE;
+
+ if (!is_ret_probe(tu))
+ uprobe_perf_print(tu, 0, regs);
return 0;
}
+
+static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
+ struct pt_regs *regs)
+{
+ uprobe_perf_print(tu, func, regs);
+}
#endif /* CONFIG_PERF_EVENTS */
static
int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data)
{
- struct trace_uprobe *tu = (struct trace_uprobe *)event->data;
+ struct trace_uprobe *tu = event->data;
switch (type) {
case TRACE_REG_REGISTER:
@@ -843,6 +915,23 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
return ret;
}
+static int uretprobe_dispatcher(struct uprobe_consumer *con,
+ unsigned long func, struct pt_regs *regs)
+{
+ struct trace_uprobe *tu;
+
+ tu = container_of(con, struct trace_uprobe, consumer);
+
+ if (tu->flags & TP_FLAG_TRACE)
+ uretprobe_trace_func(tu, func, regs);
+
+#ifdef CONFIG_PERF_EVENTS
+ if (tu->flags & TP_FLAG_PROFILE)
+ uretprobe_perf_func(tu, func, regs);
+#endif
+ return 0;
+}
+
static struct trace_event_functions uprobe_funcs = {
.trace = print_uprobe_event
};