aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig1
-rw-r--r--kernel/trace/blktrace.c213
-rw-r--r--kernel/trace/bpf_trace.c6
-rw-r--r--kernel/trace/ftrace.c41
-rw-r--r--kernel/trace/ftrace_internal.h8
-rw-r--r--kernel/trace/ring_buffer.c2
-rw-r--r--kernel/trace/trace.c30
-rw-r--r--kernel/trace/trace.h29
-rw-r--r--kernel/trace/trace_events.c14
-rw-r--r--kernel/trace/trace_events_filter.c2
-rw-r--r--kernel/trace/trace_events_hist.c173
-rw-r--r--kernel/trace/trace_events_trigger.c36
-rw-r--r--kernel/trace/trace_hwlat.c5
-rw-r--r--kernel/trace/trace_kprobe.c29
-rw-r--r--kernel/trace/trace_sched_switch.c4
-rw-r--r--kernel/trace/trace_sched_wakeup.c4
-rw-r--r--kernel/trace/trace_stack.c5
-rw-r--r--kernel/trace/trace_stat.c31
-rw-r--r--kernel/trace/tracing_map.c4
19 files changed, 433 insertions, 204 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 564e5fdb025f..9669aaf0cd76 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -371,7 +371,6 @@ config PROFILE_ANNOTATED_BRANCHES
config PROFILE_ALL_BRANCHES
bool "Profile all if conditionals" if !FORTIFY_SOURCE
select TRACE_BRANCH_PROFILING
- imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives
help
This tracer profiles all branch conditions. Every if ()
taken in the kernel is recorded whether it hit or miss.
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index e1c6d79fb4cc..8f18311f9be5 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -3,6 +3,9 @@
* Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
*
*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/blktrace_api.h>
@@ -336,6 +339,7 @@ static void put_probe_ref(void)
static void blk_trace_cleanup(struct blk_trace *bt)
{
+ synchronize_rcu();
blk_trace_free(bt);
put_probe_ref();
}
@@ -344,7 +348,8 @@ static int __blk_trace_remove(struct request_queue *q)
{
struct blk_trace *bt;
- bt = xchg(&q->blk_trace, NULL);
+ bt = rcu_replace_pointer(q->blk_trace, NULL,
+ lockdep_is_held(&q->blk_trace_mutex));
if (!bt)
return -EINVAL;
@@ -479,6 +484,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct dentry *dir = NULL;
int ret;
+ lockdep_assert_held(&q->blk_trace_mutex);
+
if (!buts->buf_size || !buts->buf_nr)
return -EINVAL;
@@ -494,6 +501,17 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
*/
strreplace(buts->name, '/', '_');
+ /*
+ * bdev can be NULL, as with scsi-generic, this is a helpful as
+ * we can be.
+ */
+ if (rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex))) {
+ pr_warn("Concurrent blktraces are not allowed on %s\n",
+ buts->name);
+ return -EBUSY;
+ }
+
bt = kzalloc(sizeof(*bt), GFP_KERNEL);
if (!bt)
return -ENOMEM;
@@ -507,13 +525,31 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (!bt->msg_data)
goto err;
- ret = -ENOENT;
-
- dir = debugfs_lookup(buts->name, blk_debugfs_root);
- if (!dir)
+#ifdef CONFIG_BLK_DEBUG_FS
+ /*
+ * When tracing whole make_request drivers (multiqueue) block devices,
+ * reuse the existing debugfs directory created by the block layer on
+ * init. For request-based block devices, all partitions block devices,
+ * and scsi-generic block devices we create a temporary new debugfs
+ * directory that will be removed once the trace ends.
+ */
+ if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains)
+ dir = q->debugfs_dir;
+ else
+#endif
bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
- if (!dir)
+
+ /*
+ * As blktrace relies on debugfs for its interface the debugfs directory
+ * is required, contrary to the usual mantra of not checking for debugfs
+ * files or directories.
+ */
+ if (IS_ERR_OR_NULL(dir)) {
+ pr_warn("debugfs_dir not present for %s so skipping\n",
+ buts->name);
+ ret = -ENOENT;
goto err;
+ }
bt->dev = dev;
atomic_set(&bt->dropped, 0);
@@ -522,12 +558,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
ret = -EIO;
bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
&blk_dropped_fops);
- if (!bt->dropped_file)
- goto err;
bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
- if (!bt->msg_file)
- goto err;
bt->rchan = relay_open("trace", dir, buts->buf_size,
buts->buf_nr, &blk_relay_callbacks, bt);
@@ -549,16 +581,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
- ret = -EBUSY;
- if (cmpxchg(&q->blk_trace, NULL, bt))
- goto err;
-
+ rcu_assign_pointer(q->blk_trace, bt);
get_probe_ref();
ret = 0;
err:
- if (dir && !bt->dir)
- dput(dir);
if (ret)
blk_trace_free(bt);
return ret;
@@ -636,8 +663,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
static int __blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (bt == NULL)
return -EINVAL;
@@ -747,8 +776,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
void blk_trace_shutdown(struct request_queue *q)
{
mutex_lock(&q->blk_trace_mutex);
-
- if (q->blk_trace) {
+ if (rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex))) {
__blk_trace_startstop(q, 0);
__blk_trace_remove(q);
}
@@ -760,8 +789,10 @@ void blk_trace_shutdown(struct request_queue *q)
static union kernfs_node_id *
blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ /* We don't use the 'bt' value here except as an optimization... */
+ bt = rcu_dereference_protected(q->blk_trace, 1);
if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
return NULL;
@@ -806,10 +837,14 @@ static void blk_add_trace_rq(struct request *rq, int error,
unsigned int nr_bytes, u32 what,
union kernfs_node_id *cgid)
{
- struct blk_trace *bt = rq->q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(rq->q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
if (blk_rq_is_passthrough(rq))
what |= BLK_TC_ACT(BLK_TC_PC);
@@ -818,6 +853,7 @@ static void blk_add_trace_rq(struct request *rq, int error,
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
rq->cmd_flags, what, error, 0, NULL, cgid);
+ rcu_read_unlock();
}
static void blk_add_trace_rq_insert(void *ignore,
@@ -863,14 +899,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
u32 what, int error)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio_op(bio), bio->bi_opf, what, error, 0, NULL,
blk_trace_bio_get_cgid(q, bio));
+ rcu_read_unlock();
}
static void blk_add_trace_bio_bounce(void *ignore,
@@ -915,11 +956,14 @@ static void blk_add_trace_getrq(void *ignore,
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
NULL, NULL);
+ rcu_read_unlock();
}
}
@@ -931,27 +975,35 @@ static void blk_add_trace_sleeprq(void *ignore,
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
0, 0, NULL, NULL);
+ rcu_read_unlock();
}
}
static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL);
+ rcu_read_unlock();
}
static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
unsigned int depth, bool explicit)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(depth);
u32 what;
@@ -963,22 +1015,28 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL);
}
+ rcu_read_unlock();
}
static void blk_add_trace_split(void *ignore,
struct request_queue *q, struct bio *bio,
unsigned int pdu)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(pdu);
__blk_add_trace(bt, bio->bi_iter.bi_sector,
bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
- BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
- &rpdu, blk_trace_bio_get_cgid(q, bio));
+ BLK_TA_SPLIT,
+ blk_status_to_errno(bio->bi_status),
+ sizeof(rpdu), &rpdu,
+ blk_trace_bio_get_cgid(q, bio));
}
+ rcu_read_unlock();
}
/**
@@ -998,19 +1056,25 @@ static void blk_add_trace_bio_remap(void *ignore,
struct request_queue *q, struct bio *bio,
dev_t dev, sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(bio_dev(bio));
r.sector_from = cpu_to_be64(from);
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
+ bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+ blk_status_to_errno(bio->bi_status),
sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
+ rcu_read_unlock();
}
/**
@@ -1031,11 +1095,15 @@ static void blk_add_trace_rq_remap(void *ignore,
struct request *rq, dev_t dev,
sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(disk_devt(rq->rq_disk));
@@ -1044,6 +1112,7 @@ static void blk_add_trace_rq_remap(void *ignore,
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+ rcu_read_unlock();
}
/**
@@ -1061,14 +1130,19 @@ void blk_add_driver_data(struct request_queue *q,
struct request *rq,
void *data, size_t len)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
BLK_TA_DRV_DATA, 0, len, data,
blk_trace_request_get_cgid(q, rq));
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1220,21 +1294,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
{
- const __u64 *val = pdu_start(ent, has_cg);
+ const __be64 *val = pdu_start(ent, has_cg);
return be64_to_cpu(*val);
}
-static void get_pdu_remap(const struct trace_entry *ent,
- struct blk_io_trace_remap *r, bool has_cg)
-{
- const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
- __u64 sector_from = __r->sector_from;
-
- r->device_from = be32_to_cpu(__r->device_from);
- r->device_to = be32_to_cpu(__r->device_to);
- r->sector_from = be64_to_cpu(sector_from);
-}
-
typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
bool has_cg);
@@ -1360,13 +1423,13 @@ static void blk_log_with_error(struct trace_seq *s,
static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
{
- struct blk_io_trace_remap r = { .device_from = 0, };
+ const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
- get_pdu_remap(ent, &r, has_cg);
trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
t_sector(ent), t_sec(ent),
- MAJOR(r.device_from), MINOR(r.device_from),
- (unsigned long long)r.sector_from);
+ MAJOR(be32_to_cpu(__r->device_from)),
+ MINOR(be32_to_cpu(__r->device_from)),
+ be64_to_cpu(__r->sector_from));
}
static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
@@ -1590,11 +1653,13 @@ static int blk_trace_remove_queue(struct request_queue *q)
{
struct blk_trace *bt;
- bt = xchg(&q->blk_trace, NULL);
+ bt = rcu_replace_pointer(q->blk_trace, NULL,
+ lockdep_is_held(&q->blk_trace_mutex));
if (bt == NULL)
return -EINVAL;
put_probe_ref();
+ synchronize_rcu();
blk_trace_free(bt);
return 0;
}
@@ -1621,10 +1686,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
blk_trace_setup_lba(bt, bdev);
- ret = -EBUSY;
- if (cmpxchg(&q->blk_trace, NULL, bt))
- goto free_bt;
-
+ rcu_assign_pointer(q->blk_trace, bt);
get_probe_ref();
return 0;
@@ -1756,6 +1818,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct hd_struct *p = dev_to_part(dev);
struct request_queue *q;
struct block_device *bdev;
+ struct blk_trace *bt;
ssize_t ret = -ENXIO;
bdev = bdget(part_devt(p));
@@ -1768,21 +1831,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ ret = sprintf(buf, "%u\n", !!bt);
goto out_unlock_bdev;
}
- if (q->blk_trace == NULL)
+ if (bt == NULL)
ret = sprintf(buf, "disabled\n");
else if (attr == &dev_attr_act_mask)
- ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+ ret = blk_trace_mask2str(buf, bt->act_mask);
else if (attr == &dev_attr_pid)
- ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+ ret = sprintf(buf, "%u\n", bt->pid);
else if (attr == &dev_attr_start_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+ ret = sprintf(buf, "%llu\n", bt->start_lba);
else if (attr == &dev_attr_end_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+ ret = sprintf(buf, "%llu\n", bt->end_lba);
out_unlock_bdev:
mutex_unlock(&q->blk_trace_mutex);
@@ -1799,6 +1864,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
struct block_device *bdev;
struct request_queue *q;
struct hd_struct *p;
+ struct blk_trace *bt;
u64 value;
ssize_t ret = -EINVAL;
@@ -1829,8 +1895,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- if (!!value == !!q->blk_trace) {
+ if (!!value == !!bt) {
ret = 0;
goto out_unlock_bdev;
}
@@ -1842,18 +1910,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
}
ret = 0;
- if (q->blk_trace == NULL)
+ if (bt == NULL) {
ret = blk_trace_setup_queue(q, bdev);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
+ }
if (ret == 0) {
if (attr == &dev_attr_act_mask)
- q->blk_trace->act_mask = value;
+ bt->act_mask = value;
else if (attr == &dev_attr_pid)
- q->blk_trace->pid = value;
+ bt->pid = value;
else if (attr == &dev_attr_start_lba)
- q->blk_trace->start_lba = value;
+ bt->start_lba = value;
else if (attr == &dev_attr_end_lba)
- q->blk_trace->end_lba = value;
+ bt->end_lba = value;
}
out_unlock_bdev:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index aaf66cd9daa6..a2c30e1eb7e4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -155,7 +155,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
.arg3_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
+BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
u32, size)
{
/*
@@ -178,10 +178,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
- if (!access_ok(unsafe_ptr, size))
- return -EPERM;
- return probe_kernel_write(unsafe_ptr, src, size);
+ return probe_user_write(unsafe_ptr, src, size);
}
static const struct bpf_func_proto bpf_probe_write_user_proto = {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index baa54a76c6aa..98751023c05a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -523,8 +523,7 @@ static int function_stat_show(struct seq_file *m, void *v)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- avg = rec->time;
- do_div(avg, rec->counter);
+ avg = div64_ul(rec->time, rec->counter);
if (tracing_thresh && (avg < tracing_thresh))
goto out;
#endif
@@ -550,7 +549,8 @@ static int function_stat_show(struct seq_file *m, void *v)
* Divide only 1000 for ns^2 -> us^2 conversion.
* trace_print_graph_duration will divide 1000 again.
*/
- do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev,
+ rec->counter * (rec->counter - 1) * 1000);
}
trace_seq_init(&s);
@@ -5085,8 +5085,8 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
-struct ftrace_hash *ftrace_graph_hash = EMPTY_HASH;
-struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_notrace_hash = EMPTY_HASH;
enum graph_filter_type {
GRAPH_FILTER_NOTRACE = 0,
@@ -5357,8 +5357,15 @@ ftrace_graph_release(struct inode *inode, struct file *file)
mutex_unlock(&graph_lock);
- /* Wait till all users are no longer using the old hash */
- synchronize_rcu();
+ /*
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
+ schedule_on_each_cpu(ftrace_sync);
free_ftrace_hash(old_hash);
}
@@ -5671,8 +5678,11 @@ static int referenced_filters(struct dyn_ftrace *rec)
int cnt = 0;
for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
- if (ops_references_rec(ops, rec))
- cnt++;
+ if (ops_references_rec(ops, rec)) {
+ cnt++;
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+ rec->flags |= FTRACE_FL_REGS;
+ }
}
return cnt;
@@ -5849,8 +5859,8 @@ void ftrace_module_enable(struct module *mod)
if (ftrace_start_up)
cnt += referenced_filters(rec);
- /* This clears FTRACE_FL_DISABLED */
- rec->flags = cnt;
+ rec->flags &= ~FTRACE_FL_DISABLED;
+ rec->flags += cnt;
if (ftrace_start_up && cnt) {
int failed = __ftrace_replace_code(rec, 1);
@@ -6435,12 +6445,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
if (enable) {
register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
tr);
- register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
tr);
} else {
unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
tr);
- unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
tr);
}
}
@@ -6513,9 +6523,10 @@ static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
struct trace_array *tr = m->private;
struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids);
- if (v == FTRACE_NO_PIDS)
+ if (v == FTRACE_NO_PIDS) {
+ (*pos)++;
return NULL;
-
+ }
return trace_pid_next(pid_list, v, pos);
}
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0515a2096f90..0456e0a3dab1 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -6,22 +6,22 @@
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
- * can use rcu_dereference_raw_notrace() is that elements removed from this list
+ * can use rcu_dereference_raw_check() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
- * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle
+ * mechanism. The rcu_dereference_raw_check() calls are needed to handle
* concurrent insertions into the ftrace_global_list.
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
#define do_for_each_ftrace_op(op, list) \
- op = rcu_dereference_raw_notrace(list); \
+ op = rcu_dereference_raw_check(list); \
do
/*
* Optimized for just a single item in the list (as that is the normal case).
*/
#define while_for_each_ftrace_op(op) \
- while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \
+ while (likely(op = rcu_dereference_raw_check((op)->next)) && \
unlikely((op) != &ftrace_list_end))
extern struct ftrace_ops __rcu *ftrace_ops_list;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05b0b3139ebc..0e4af9941a23 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2366,7 +2366,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
if (unlikely(info->add_timestamp)) {
bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
- event = rb_add_time_stamp(event, info->delta, abs);
+ event = rb_add_time_stamp(event, abs ? info->delta : delta, abs);
length -= RB_LEN_TIME_EXTEND;
delta = 0;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1a65ca0a91f6..c4c3daeba5c0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1726,6 +1726,7 @@ static __init int init_trace_selftests(void)
pr_info("Running postponed tracer tests:\n");
+ tracing_selftest_running = true;
list_for_each_entry_safe(p, n, &postponed_selftests, list) {
/* This loop can take minutes when sanitizers are enabled, so
* lets make sure we allow RCU processing.
@@ -1748,6 +1749,7 @@ static __init int init_trace_selftests(void)
list_del(&p->list);
kfree(p);
}
+ tracing_selftest_running = false;
out:
mutex_unlock(&trace_types_lock);
@@ -2642,10 +2644,10 @@ static void ftrace_exports(struct ring_buffer_event *event)
preempt_disable_notrace();
- export = rcu_dereference_raw_notrace(ftrace_exports_list);
+ export = rcu_dereference_raw_check(ftrace_exports_list);
while (export) {
trace_process_export(export, event);
- export = rcu_dereference_raw_notrace(export->next);
+ export = rcu_dereference_raw_check(export->next);
}
preempt_enable_notrace();
@@ -4569,6 +4571,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
+ if ((mask == TRACE_ITER_RECORD_TGID) ||
+ (mask == TRACE_ITER_RECORD_CMD))
+ lockdep_assert_held(&event_mutex);
+
/* do nothing if flag is already set */
if (!!(tr->trace_flags & mask) == !!enabled)
return 0;
@@ -4588,7 +4594,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
if (mask == TRACE_ITER_RECORD_TGID) {
if (!tgid_map)
- tgid_map = kcalloc(PID_MAX_DEFAULT + 1,
+ tgid_map = kvcalloc(PID_MAX_DEFAULT + 1,
sizeof(*tgid_map),
GFP_KERNEL);
if (!tgid_map) {
@@ -4636,6 +4642,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
cmp += len;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = match_string(trace_options, -1, cmp);
@@ -4646,6 +4653,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
ret = set_tracer_flag(tr, 1 << ret, !neg);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
/*
* If the first trailing whitespace is replaced with '\0' by strstrip,
@@ -6009,6 +6017,7 @@ waitagain:
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
cpumask_clear(iter->started);
+ trace_seq_init(&iter->seq);
iter->pos = -1;
trace_event_read_lock();
@@ -7947,9 +7956,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (val != 0 && val != 1)
return -EINVAL;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = set_tracer_flag(tr, 1 << index, val);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
if (ret < 0)
return ret;
@@ -8277,6 +8288,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
*/
allocate_snapshot = false;
#endif
+
+ /*
+ * Because of some magic with the way alloc_percpu() works on
+ * x86_64, we need to synchronize the pgd of all the tables,
+ * otherwise the trace events that happen in x86_64 page fault
+ * handlers can't cope with accessing the chance that a
+ * alloc_percpu()'d memory might be touched in the page fault trace
+ * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
+ * calls in tracing, because something might get triggered within a
+ * page fault trace event!
+ */
+ vmalloc_sync_mappings();
+
return 0;
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 005f08629b8b..08088cafbb88 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -931,22 +931,31 @@ extern void __trace_graph_return(struct trace_array *tr,
unsigned long flags, int pc);
#ifdef CONFIG_DYNAMIC_FTRACE
-extern struct ftrace_hash *ftrace_graph_hash;
-extern struct ftrace_hash *ftrace_graph_notrace_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash;
static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
unsigned long addr = trace->func;
int ret = 0;
+ struct ftrace_hash *hash;
preempt_disable_notrace();
- if (ftrace_hash_empty(ftrace_graph_hash)) {
+ /*
+ * Have to open code "rcu_dereference_sched()" because the
+ * function graph tracer can be called when RCU is not
+ * "watching".
+ * Protected with schedule_on_each_cpu(ftrace_sync)
+ */
+ hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
+
+ if (ftrace_hash_empty(hash)) {
ret = 1;
goto out;
}
- if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
+ if (ftrace_lookup_ip(hash, addr)) {
/*
* This needs to be cleared on the return functions
@@ -982,10 +991,20 @@ static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
int ret = 0;
+ struct ftrace_hash *notrace_hash;
preempt_disable_notrace();
- if (ftrace_lookup_ip(ftrace_graph_notrace_hash, addr))
+ /*
+ * Have to open code "rcu_dereference_sched()" because the
+ * function graph tracer can be called when RCU is not
+ * "watching".
+ * Protected with schedule_on_each_cpu(ftrace_sync)
+ */
+ notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
+ !preemptible());
+
+ if (ftrace_lookup_ip(notrace_hash, addr))
ret = 1;
preempt_enable_notrace();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0ce3db67f556..42d4afd2fc4f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -327,7 +327,8 @@ void trace_event_enable_cmd_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
@@ -341,7 +342,6 @@ void trace_event_enable_cmd_record(bool enable)
clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
void trace_event_enable_tgid_record(bool enable)
@@ -349,7 +349,8 @@ void trace_event_enable_tgid_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
continue;
@@ -363,7 +364,6 @@ void trace_event_enable_tgid_record(bool enable)
&file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
static int __ftrace_event_enable_disable(struct trace_event_file *file,
@@ -534,12 +534,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
if (enable) {
register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
tr, INT_MIN);
- register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+ register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
tr, INT_MAX);
} else {
unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
tr);
- unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+ unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
tr);
}
}
@@ -795,7 +795,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
return ret;
}
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
int ret;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index d5a4bda9ce7b..b878d0ec8181 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1659,7 +1659,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0);
return -EINVAL;
fail_mem:
- kfree(filter);
+ __free_filter(filter);
/* If any call succeeded, we still need to sync */
if (!fail)
tracepoint_synchronize_unregister();
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index dd310d3b5843..21caeb2052ef 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -111,6 +111,7 @@ struct hist_field {
struct ftrace_event_field *field;
unsigned long flags;
hist_field_fn_t fn;
+ unsigned int ref;
unsigned int size;
unsigned int offset;
unsigned int is_signed;
@@ -464,11 +465,12 @@ struct action_data {
* When a histogram trigger is hit, the values of any
* references to variables, including variables being passed
* as parameters to synthetic events, are collected into a
- * var_ref_vals array. This var_ref_idx is the index of the
- * first param in the array to be passed to the synthetic
- * event invocation.
+ * var_ref_vals array. This var_ref_idx array is an array of
+ * indices into the var_ref_vals array, one for each synthetic
+ * event param, and is passed to the synthetic event
+ * invocation.
*/
- unsigned int var_ref_idx;
+ unsigned int var_ref_idx[TRACING_MAP_VARS_MAX];
struct synth_event *synth_event;
bool use_trace_keyword;
char *synth_event_name;
@@ -674,6 +676,8 @@ static bool synth_field_signed(char *type)
{
if (str_has_prefix(type, "u"))
return false;
+ if (strcmp(type, "gfp_t") == 0)
+ return false;
return true;
}
@@ -852,14 +856,14 @@ static struct trace_event_functions synth_event_funcs = {
static notrace void trace_event_raw_event_synth(void *__data,
u64 *var_ref_vals,
- unsigned int var_ref_idx)
+ unsigned int *var_ref_idx)
{
struct trace_event_file *trace_file = __data;
struct synth_trace_event *entry;
struct trace_event_buffer fbuffer;
struct ring_buffer *buffer;
struct synth_event *event;
- unsigned int i, n_u64;
+ unsigned int i, n_u64, val_idx;
int fields_size = 0;
event = trace_file->event_call->data;
@@ -882,14 +886,34 @@ static notrace void trace_event_raw_event_synth(void *__data,
goto out;
for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+ val_idx = var_ref_idx[i];
if (event->fields[i]->is_string) {
- char *str_val = (char *)(long)var_ref_vals[var_ref_idx + i];
+ char *str_val = (char *)(long)var_ref_vals[val_idx];
char *str_field = (char *)&entry->fields[n_u64];
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
- entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
+ struct synth_field *field = event->fields[i];
+ u64 val = var_ref_vals[val_idx];
+
+ switch (field->size) {
+ case 1:
+ *(u8 *)&entry->fields[n_u64] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&entry->fields[n_u64] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&entry->fields[n_u64] = (u32)val;
+ break;
+
+ default:
+ entry->fields[n_u64] = val;
+ break;
+ }
n_u64++;
}
}
@@ -1071,10 +1095,10 @@ static struct tracepoint *alloc_synth_tracepoint(char *name)
}
typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
- unsigned int var_ref_idx);
+ unsigned int *var_ref_idx);
static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
- unsigned int var_ref_idx)
+ unsigned int *var_ref_idx)
{
struct tracepoint *tp = event->tp;
@@ -1985,12 +2009,6 @@ static int parse_map_size(char *str)
unsigned long size, map_bits;
int ret;
- strsep(&str, "=");
- if (!str) {
- ret = -EINVAL;
- goto out;
- }
-
ret = kstrtoul(str, 0, &size);
if (ret)
goto out;
@@ -2050,25 +2068,25 @@ static int parse_action(char *str, struct hist_trigger_attrs *attrs)
static int parse_assignment(struct trace_array *tr,
char *str, struct hist_trigger_attrs *attrs)
{
- int ret = 0;
+ int len, ret = 0;
- if ((str_has_prefix(str, "key=")) ||
- (str_has_prefix(str, "keys="))) {
- attrs->keys_str = kstrdup(str, GFP_KERNEL);
+ if ((len = str_has_prefix(str, "key=")) ||
+ (len = str_has_prefix(str, "keys="))) {
+ attrs->keys_str = kstrdup(str + len, GFP_KERNEL);
if (!attrs->keys_str) {
ret = -ENOMEM;
goto out;
}
- } else if ((str_has_prefix(str, "val=")) ||
- (str_has_prefix(str, "vals=")) ||
- (str_has_prefix(str, "values="))) {
- attrs->vals_str = kstrdup(str, GFP_KERNEL);
+ } else if ((len = str_has_prefix(str, "val=")) ||
+ (len = str_has_prefix(str, "vals=")) ||
+ (len = str_has_prefix(str, "values="))) {
+ attrs->vals_str = kstrdup(str + len, GFP_KERNEL);
if (!attrs->vals_str) {
ret = -ENOMEM;
goto out;
}
- } else if (str_has_prefix(str, "sort=")) {
- attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
+ } else if ((len = str_has_prefix(str, "sort="))) {
+ attrs->sort_key_str = kstrdup(str + len, GFP_KERNEL);
if (!attrs->sort_key_str) {
ret = -ENOMEM;
goto out;
@@ -2079,12 +2097,8 @@ static int parse_assignment(struct trace_array *tr,
ret = -ENOMEM;
goto out;
}
- } else if (str_has_prefix(str, "clock=")) {
- strsep(&str, "=");
- if (!str) {
- ret = -EINVAL;
- goto out;
- }
+ } else if ((len = str_has_prefix(str, "clock="))) {
+ str += len;
str = strstrip(str);
attrs->clock = kstrdup(str, GFP_KERNEL);
@@ -2092,8 +2106,8 @@ static int parse_assignment(struct trace_array *tr,
ret = -ENOMEM;
goto out;
}
- } else if (str_has_prefix(str, "size=")) {
- int map_bits = parse_map_size(str);
+ } else if ((len = str_has_prefix(str, "size="))) {
+ int map_bits = parse_map_size(str + len);
if (map_bits < 0) {
ret = map_bits;
@@ -2133,8 +2147,14 @@ parse_hist_trigger_attrs(struct trace_array *tr, char *trigger_str)
while (trigger_str) {
char *str = strsep(&trigger_str, ":");
+ char *rhs;
- if (strchr(str, '=')) {
+ rhs = strchr(str, '=');
+ if (rhs) {
+ if (!strlen(++rhs)) {
+ ret = -EINVAL;
+ goto free;
+ }
ret = parse_assignment(tr, str, attrs);
if (ret)
goto free;
@@ -2378,12 +2398,23 @@ static int contains_operator(char *str)
return field_op;
}
+static void get_hist_field(struct hist_field *hist_field)
+{
+ hist_field->ref++;
+}
+
static void __destroy_hist_field(struct hist_field *hist_field)
{
+ if (--hist_field->ref > 1)
+ return;
+
kfree(hist_field->var.name);
kfree(hist_field->name);
kfree(hist_field->type);
+ kfree(hist_field->system);
+ kfree(hist_field->event_name);
+
kfree(hist_field);
}
@@ -2421,6 +2452,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (!hist_field)
return NULL;
+ hist_field->ref = 1;
+
hist_field->hist_data = hist_data;
if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
@@ -2595,6 +2628,22 @@ static int init_var_ref(struct hist_field *ref_field,
goto out;
}
+static int find_var_ref_idx(struct hist_trigger_data *hist_data,
+ struct hist_field *var_field)
+{
+ struct hist_field *ref_field;
+ int i;
+
+ for (i = 0; i < hist_data->n_var_refs; i++) {
+ ref_field = hist_data->var_refs[i];
+ if (ref_field->var.idx == var_field->var.idx &&
+ ref_field->var.hist_data == var_field->hist_data)
+ return i;
+ }
+
+ return -ENOENT;
+}
+
/**
* create_var_ref - Create a variable reference and attach it to trigger
* @hist_data: The trigger that will be referencing the variable
@@ -2616,6 +2665,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
{
unsigned long flags = HIST_FIELD_FL_VAR_REF;
struct hist_field *ref_field;
+ int i;
+
+ /* Check if the variable already exists */
+ for (i = 0; i < hist_data->n_var_refs; i++) {
+ ref_field = hist_data->var_refs[i];
+ if (ref_field->var.idx == var_field->var.idx &&
+ ref_field->var.hist_data == var_field->hist_data) {
+ get_hist_field(ref_field);
+ return ref_field;
+ }
+ }
ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
if (ref_field) {
@@ -3413,6 +3473,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
goto out;
}
+ var->ref = 1;
var->flags = HIST_FIELD_FL_VAR;
var->var.idx = idx;
var->var.hist_data = var->hist_data = hist_data;
@@ -4042,6 +4103,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
for (i = 0; i < hist_data->n_field_vars; i++)
destroy_field_var(hist_data->field_vars[i]);
+
+ for (i = 0; i < hist_data->n_save_vars; i++)
+ destroy_field_var(hist_data->save_vars[i]);
}
static void save_field_var(struct hist_trigger_data *hist_data,
@@ -4153,11 +4217,11 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
struct trace_array *tr = hist_data->event_file->tr;
char *event_name, *param, *system = NULL;
struct hist_field *hist_field, *var_ref;
- unsigned int i, var_ref_idx;
+ unsigned int i;
unsigned int field_pos = 0;
struct synth_event *event;
char *synth_event_name;
- int ret = 0;
+ int var_ref_idx, ret = 0;
lockdep_assert_held(&event_mutex);
@@ -4174,8 +4238,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
event->ref++;
- var_ref_idx = hist_data->n_var_refs;
-
for (i = 0; i < data->n_params; i++) {
char *p;
@@ -4224,6 +4286,14 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
goto err;
}
+ var_ref_idx = find_var_ref_idx(hist_data, var_ref);
+ if (WARN_ON(var_ref_idx < 0)) {
+ ret = var_ref_idx;
+ goto err;
+ }
+
+ data->var_ref_idx[i] = var_ref_idx;
+
field_pos++;
kfree(p);
continue;
@@ -4242,7 +4312,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
}
data->synth_event = event;
- data->var_ref_idx = var_ref_idx;
out:
return ret;
err:
@@ -4461,10 +4530,6 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
if (!fields_str)
goto out;
- strsep(&fields_str, "=");
- if (!fields_str)
- goto out;
-
for (i = 0, j = 1; i < TRACING_MAP_VALS_MAX &&
j < TRACING_MAP_VALS_MAX; i++) {
field_str = strsep(&fields_str, ",");
@@ -4559,10 +4624,6 @@ static int create_key_fields(struct hist_trigger_data *hist_data,
if (!fields_str)
goto out;
- strsep(&fields_str, "=");
- if (!fields_str)
- goto out;
-
for (i = n_vals; i < n_vals + TRACING_MAP_KEYS_MAX; i++) {
field_str = strsep(&fields_str, ",");
if (!field_str)
@@ -4720,12 +4781,6 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
if (!fields_str)
goto out;
- strsep(&fields_str, "=");
- if (!fields_str) {
- ret = -EINVAL;
- goto out;
- }
-
for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) {
struct hist_field *hist_field;
char *field_str, *field_name;
@@ -4734,9 +4789,11 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
sort_key = &hist_data->sort_keys[i];
field_str = strsep(&fields_str, ",");
- if (!field_str) {
- if (i == 0)
- ret = -EINVAL;
+ if (!field_str)
+ break;
+
+ if (!*field_str) {
+ ret = -EINVAL;
break;
}
@@ -4746,7 +4803,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
}
field_name = strsep(&field_str, ".");
- if (!field_name) {
+ if (!field_name || !*field_name) {
ret = -EINVAL;
break;
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2a2912cb4533..586ea94e0db1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -115,9 +115,10 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
{
struct trace_event_file *event_file = event_file_data(m->private);
- if (t == SHOW_AVAILABLE_TRIGGERS)
+ if (t == SHOW_AVAILABLE_TRIGGERS) {
+ (*pos)++;
return NULL;
-
+ }
return seq_list_next(t, &event_file->triggers, pos);
}
@@ -210,11 +211,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
static int trigger_process_regex(struct trace_event_file *file, char *buff)
{
- char *command, *next = buff;
+ char *command, *next;
struct event_command *p;
int ret = -EINVAL;
+ next = buff = skip_spaces(buff);
command = strsep(&next, ": \t");
+ if (next) {
+ next = skip_spaces(next);
+ if (!*next)
+ next = NULL;
+ }
command = (command[0] != '!') ? command : command + 1;
mutex_lock(&trigger_cmd_mutex);
@@ -617,8 +624,14 @@ event_trigger_callback(struct event_command *cmd_ops,
int ret;
/* separate the trigger from the filter (t:n [if filter]) */
- if (param && isdigit(param[0]))
+ if (param && isdigit(param[0])) {
trigger = strsep(&param, " \t");
+ if (param) {
+ param = skip_spaces(param);
+ if (!*param)
+ param = NULL;
+ }
+ }
trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
@@ -1075,14 +1088,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *data,
struct trace_event_file *file)
{
- int ret = register_trigger(glob, ops, data, file);
-
- if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
- unregister_trigger(glob, ops, data, file);
- ret = 0;
- }
+ if (tracing_alloc_snapshot_instance(file->tr) != 0)
+ return 0;
- return ret;
+ return register_trigger(glob, ops, data, file);
}
static int
@@ -1359,6 +1368,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
trigger = strsep(&param, " \t");
if (!trigger)
return -EINVAL;
+ if (param) {
+ param = skip_spaces(param);
+ if (!*param)
+ param = NULL;
+ }
system = strsep(&trigger, ":");
if (!trigger)
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 8030e24dbf14..568918fae8d4 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -270,6 +270,7 @@ static bool disable_migrate;
static void move_to_next_cpu(void)
{
struct cpumask *current_mask = &save_cpumask;
+ struct trace_array *tr = hwlat_trace;
int next_cpu;
if (disable_migrate)
@@ -283,7 +284,7 @@ static void move_to_next_cpu(void)
goto disable;
get_online_cpus();
- cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+ cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
next_cpu = cpumask_next(smp_processor_id(), current_mask);
put_online_cpus();
@@ -360,7 +361,7 @@ static int start_kthread(struct trace_array *tr)
/* Just pick the first CPU on first iteration */
current_mask = &save_cpumask;
get_online_cpus();
- cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+ cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
put_online_cpus();
next_cpu = cpumask_first(current_mask);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7d736248a070..4666bceb1383 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -389,11 +389,10 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
#if defined(CONFIG_KPROBES_ON_FTRACE) && \
!defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
-static bool within_notrace_func(struct trace_kprobe *tk)
+static bool __within_notrace_func(unsigned long addr)
{
- unsigned long offset, size, addr;
+ unsigned long offset, size;
- addr = trace_kprobe_address(tk);
if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset))
return false;
@@ -406,6 +405,28 @@ static bool within_notrace_func(struct trace_kprobe *tk)
*/
return !ftrace_location_range(addr, addr + size - 1);
}
+
+static bool within_notrace_func(struct trace_kprobe *tk)
+{
+ unsigned long addr = trace_kprobe_address(tk);
+ char symname[KSYM_NAME_LEN], *p;
+
+ if (!__within_notrace_func(addr))
+ return false;
+
+ /* Check if the address is on a suffixed-symbol */
+ if (!lookup_symbol_name(addr, symname)) {
+ p = strchr(symname, '.');
+ if (!p)
+ return true;
+ *p = '\0';
+ addr = (unsigned long)kprobe_lookup_name(symname, 0);
+ if (addr)
+ return __within_notrace_func(addr);
+ }
+
+ return true;
+}
#else
#define within_notrace_func(tk) (false)
#endif
@@ -767,6 +788,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev)
int i;
seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p');
+ if (trace_kprobe_is_return(tk) && tk->rp.maxactive)
+ seq_printf(m, "%d", tk->rp.maxactive);
seq_printf(m, ":%s/%s", tk->tp.call.class->system,
trace_event_name(&tk->tp.call));
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e288168661e1..e304196d7c28 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -89,8 +89,10 @@ static void tracing_sched_unregister(void)
static void tracing_start_sched_switch(int ops)
{
- bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
+ bool sched_register;
+
mutex_lock(&sched_register_mutex);
+ sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
switch (ops) {
case RECORD_CMDLINE:
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 743b2b520d34..7152062d6af6 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -631,7 +631,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_migrate_task\n");
- return;
+ goto fail_deprobe_sched_switch;
}
wakeup_reset(tr);
@@ -649,6 +649,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
printk(KERN_ERR "failed to start wakeup tracer\n");
return;
+fail_deprobe_sched_switch:
+ unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 642a850af81a..5b4f50932478 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -184,6 +184,11 @@ static void check_stack(unsigned long ip, unsigned long *stack)
local_irq_restore(flags);
}
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75bf1bcb4a8a..92b76f9e25ed 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -278,18 +278,22 @@ static int tracing_stat_init(void)
d_tracing = tracing_init_dentry();
if (IS_ERR(d_tracing))
- return 0;
+ return -ENODEV;
stat_dir = tracefs_create_dir("trace_stat", d_tracing);
- if (!stat_dir)
+ if (!stat_dir) {
pr_warn("Could not create tracefs 'trace_stat' entry\n");
+ return -ENOMEM;
+ }
return 0;
}
static int init_stat_file(struct stat_session *session)
{
- if (!stat_dir && tracing_stat_init())
- return -ENODEV;
+ int ret;
+
+ if (!stat_dir && (ret = tracing_stat_init()))
+ return ret;
session->file = tracefs_create_file(session->ts->name, 0644,
stat_dir,
@@ -302,7 +306,7 @@ static int init_stat_file(struct stat_session *session)
int register_stat_tracer(struct tracer_stat *trace)
{
struct stat_session *session, *node;
- int ret;
+ int ret = -EINVAL;
if (!trace)
return -EINVAL;
@@ -313,17 +317,15 @@ int register_stat_tracer(struct tracer_stat *trace)
/* Already registered? */
mutex_lock(&all_stat_sessions_mutex);
list_for_each_entry(node, &all_stat_sessions, session_list) {
- if (node->ts == trace) {
- mutex_unlock(&all_stat_sessions_mutex);
- return -EINVAL;
- }
+ if (node->ts == trace)
+ goto out;
}
- mutex_unlock(&all_stat_sessions_mutex);
+ ret = -ENOMEM;
/* Init the session */
session = kzalloc(sizeof(*session), GFP_KERNEL);
if (!session)
- return -ENOMEM;
+ goto out;
session->ts = trace;
INIT_LIST_HEAD(&session->session_list);
@@ -332,15 +334,16 @@ int register_stat_tracer(struct tracer_stat *trace)
ret = init_stat_file(session);
if (ret) {
destroy_session(session);
- return ret;
+ goto out;
}
+ ret = 0;
/* Register */
- mutex_lock(&all_stat_sessions_mutex);
list_add_tail(&session->session_list, &all_stat_sessions);
+ out:
mutex_unlock(&all_stat_sessions_mutex);
- return 0;
+ return ret;
}
void unregister_stat_tracer(struct tracer_stat *trace)
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9a1c22310323..9e31bfc818ff 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b)
#define DEFINE_TRACING_MAP_CMP_FN(type) \
static int tracing_map_cmp_##type(void *val_a, void *val_b) \
{ \
- type a = *(type *)val_a; \
- type b = *(type *)val_b; \
+ type a = (type)(*(u64 *)val_a); \
+ type b = (type)(*(u64 *)val_b); \
\
return (a > b) ? 1 : ((a < b) ? -1 : 0); \
}
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-28 10:06:54 +0000