aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/blktrace.c473
-rw-r--r--kernel/trace/ring_buffer.c117
-rw-r--r--kernel/trace/trace.c42
-rw-r--r--kernel/trace/trace.h76
-rw-r--r--kernel/trace/trace_events.c203
-rw-r--r--kernel/trace/trace_events_filter.c427
-rw-r--r--kernel/trace/trace_events_stage_2.h45
-rw-r--r--kernel/trace/trace_events_stage_3.h9
-rw-r--r--kernel/trace/trace_nop.c1
10 files changed, 1110 insertions, 284 deletions
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 0e45c206c2f..2630f5121ec 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -45,5 +45,6 @@ obj-$(CONFIG_EVENT_TRACER) += events.o
obj-$(CONFIG_EVENT_TRACER) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b171778e386..947c5b3f90c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -30,7 +30,7 @@
static unsigned int blktrace_seq __read_mostly = 1;
static struct trace_array *blk_tr;
-static int __read_mostly blk_tracer_enabled;
+static bool blk_tracer_enabled __read_mostly;
/* Select an alternative, minimalistic output than the original one */
#define TRACE_BLK_OPT_CLASSIC 0x1
@@ -47,10 +47,9 @@ static struct tracer_flags blk_tracer_flags = {
};
/* Global reference count of probes */
-static DEFINE_MUTEX(blk_probe_mutex);
static atomic_t blk_probes_ref = ATOMIC_INIT(0);
-static int blk_register_tracepoints(void);
+static void blk_register_tracepoints(void);
static void blk_unregister_tracepoints(void);
/*
@@ -60,22 +59,39 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
const void *data, size_t len)
{
struct blk_io_trace *t;
+ struct ring_buffer_event *event = NULL;
+ int pc = 0;
+ int cpu = smp_processor_id();
+ bool blk_tracer = blk_tracer_enabled;
+
+ if (blk_tracer) {
+ pc = preempt_count();
+ event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+ sizeof(*t) + len,
+ 0, pc);
+ if (!event)
+ return;
+ t = ring_buffer_event_data(event);
+ goto record_it;
+ }
if (!bt->rchan)
return;
t = relay_reserve(bt->rchan, sizeof(*t) + len);
if (t) {
- const int cpu = smp_processor_id();
-
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
t->time = ktime_to_ns(ktime_get());
+record_it:
t->device = bt->dev;
t->action = action;
t->pid = pid;
t->cpu = cpu;
t->pdu_len = len;
memcpy((void *) t + sizeof(*t), data, len);
+
+ if (blk_tracer)
+ trace_buffer_unlock_commit(blk_tr, event, 0, pc);
}
}
@@ -111,14 +127,8 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
unsigned long flags;
char *buf;
- if (blk_tr) {
- va_start(args, fmt);
- ftrace_vprintk(fmt, args);
- va_end(args);
- return;
- }
-
- if (!bt->msg_data)
+ if (unlikely(bt->trace_state != Blktrace_running &&
+ !blk_tracer_enabled))
return;
local_irq_save(flags);
@@ -148,8 +158,8 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
/*
* Data direction bit lookup
*/
-static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ),
- BLK_TC_ACT(BLK_TC_WRITE) };
+static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
+ BLK_TC_ACT(BLK_TC_WRITE) };
/* The ilog2() calls fall out because they're constant */
#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
@@ -169,9 +179,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
unsigned long *sequence;
pid_t pid;
int cpu, pc = 0;
+ bool blk_tracer = blk_tracer_enabled;
- if (unlikely(bt->trace_state != Blktrace_running ||
- !blk_tracer_enabled))
+ if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
return;
what |= ddir_act[rw & WRITE];
@@ -186,7 +196,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
return;
cpu = raw_smp_processor_id();
- if (blk_tr) {
+ if (blk_tracer) {
tracing_record_cmdline(current);
pc = preempt_count();
@@ -236,7 +246,7 @@ record_it:
if (pdu_len)
memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
- if (blk_tr) {
+ if (blk_tracer) {
trace_buffer_unlock_commit(blk_tr, event, 0, pc);
return;
}
@@ -248,7 +258,7 @@ record_it:
static struct dentry *blk_tree_root;
static DEFINE_MUTEX(blk_tree_mutex);
-static void blk_trace_cleanup(struct blk_trace *bt)
+static void blk_trace_free(struct blk_trace *bt)
{
debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
@@ -256,10 +266,13 @@ static void blk_trace_cleanup(struct blk_trace *bt)
free_percpu(bt->sequence);
free_percpu(bt->msg_data);
kfree(bt);
- mutex_lock(&blk_probe_mutex);
+}
+
+static void blk_trace_cleanup(struct blk_trace *bt)
+{
+ blk_trace_free(bt);
if (atomic_dec_and_test(&blk_probes_ref))
blk_unregister_tracepoints();
- mutex_unlock(&blk_probe_mutex);
}
int blk_trace_remove(struct request_queue *q)
@@ -270,8 +283,7 @@ int blk_trace_remove(struct request_queue *q)
if (!bt)
return -EINVAL;
- if (bt->trace_state == Blktrace_setup ||
- bt->trace_state == Blktrace_stopped)
+ if (bt->trace_state != Blktrace_running)
blk_trace_cleanup(bt);
return 0;
@@ -414,11 +426,11 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (buts->name[i] == '/')
buts->name[i] = '_';
- ret = -ENOMEM;
bt = kzalloc(sizeof(*bt), GFP_KERNEL);
if (!bt)
- goto err;
+ return -ENOMEM;
+ ret = -ENOMEM;
bt->sequence = alloc_percpu(unsigned long);
if (!bt->sequence)
goto err;
@@ -429,11 +441,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
ret = -ENOENT;
+ mutex_lock(&blk_tree_mutex);
if (!blk_tree_root) {
blk_tree_root = debugfs_create_dir("block", NULL);
- if (!blk_tree_root)
- return -ENOMEM;
+ if (!blk_tree_root) {
+ mutex_unlock(&blk_tree_mutex);
+ goto err;
+ }
}
+ mutex_unlock(&blk_tree_mutex);
dir = debugfs_create_dir(buts->name, blk_tree_root);
@@ -471,14 +487,6 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
- mutex_lock(&blk_probe_mutex);
- if (atomic_add_return(1, &blk_probes_ref) == 1) {
- ret = blk_register_tracepoints();
- if (ret)
- goto probe_err;
- }
- mutex_unlock(&blk_probe_mutex);
-
ret = -EBUSY;
old_bt = xchg(&q->blk_trace, bt);
if (old_bt) {
@@ -486,22 +494,12 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
goto err;
}
+ if (atomic_inc_return(&blk_probes_ref) == 1)
+ blk_register_tracepoints();
+
return 0;
-probe_err:
- atomic_dec(&blk_probes_ref);
- mutex_unlock(&blk_probe_mutex);
err:
- if (bt) {
- if (bt->msg_file)
- debugfs_remove(bt->msg_file);
- if (bt->dropped_file)
- debugfs_remove(bt->dropped_file);
- free_percpu(bt->sequence);
- free_percpu(bt->msg_data);
- if (bt->rchan)
- relay_close(bt->rchan);
- kfree(bt);
- }
+ blk_trace_free(bt);
return ret;
}
@@ -863,7 +861,7 @@ void blk_add_driver_data(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
-static int blk_register_tracepoints(void)
+static void blk_register_tracepoints(void)
{
int ret;
@@ -901,7 +899,6 @@ static int blk_register_tracepoints(void)
WARN_ON(ret);
ret = register_trace_block_remap(blk_add_trace_remap);
WARN_ON(ret);
- return 0;
}
static void blk_unregister_tracepoints(void)
@@ -934,25 +931,31 @@ static void blk_unregister_tracepoints(void)
static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
{
int i = 0;
+ int tc = t->action >> BLK_TC_SHIFT;
+
+ if (t->action == BLK_TN_MESSAGE) {
+ rwbs[i++] = 'N';
+ goto out;
+ }
- if (t->action & BLK_TC_DISCARD)
+ if (tc & BLK_TC_DISCARD)
rwbs[i++] = 'D';
- else if (t->action & BLK_TC_WRITE)
+ else if (tc & BLK_TC_WRITE)
rwbs[i++] = 'W';
else if (t->bytes)
rwbs[i++] = 'R';
else
rwbs[i++] = 'N';
- if (t->action & BLK_TC_AHEAD)
+ if (tc & BLK_TC_AHEAD)
rwbs[i++] = 'A';
- if (t->action & BLK_TC_BARRIER)
+ if (tc & BLK_TC_BARRIER)
rwbs[i++] = 'B';
- if (t->action & BLK_TC_SYNC)
+ if (tc & BLK_TC_SYNC)
rwbs[i++] = 'S';
- if (t->action & BLK_TC_META)
+ if (tc & BLK_TC_META)
rwbs[i++] = 'M';
-
+out:
rwbs[i] = '\0';
}
@@ -979,7 +982,7 @@ static inline unsigned long long t_sector(const struct trace_entry *ent)
static inline __u16 t_error(const struct trace_entry *ent)
{
- return te_blk_io_trace(ent)->sector;
+ return te_blk_io_trace(ent)->error;
}
static __u64 get_pdu_int(const struct trace_entry *ent)
@@ -999,29 +1002,31 @@ static void get_pdu_remap(const struct trace_entry *ent,
r->sector = be64_to_cpu(sector);
}
-static int blk_log_action_iter(struct trace_iterator *iter, const char *act)
+typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+
+static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
{
char rwbs[6];
- unsigned long long ts = ns2usecs(iter->ts);
- unsigned long usec_rem = do_div(ts, USEC_PER_SEC);
+ unsigned long long ts = iter->ts;
+ unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
unsigned secs = (unsigned long)ts;
- const struct trace_entry *ent = iter->ent;
- const struct blk_io_trace *t = (const struct blk_io_trace *)ent;
+ const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
fill_rwbs(rwbs, t);
return trace_seq_printf(&iter->seq,
- "%3d,%-3d %2d %5d.%06lu %5u %2s %3s ",
+ "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
MAJOR(t->device), MINOR(t->device), iter->cpu,
- secs, usec_rem, ent->pid, act, rwbs);
+ secs, nsec_rem, iter->ent->pid, act, rwbs);
}
-static int blk_log_action_seq(struct trace_seq *s, const struct blk_io_trace *t,
- const char *act)
+static int blk_log_action(struct trace_iterator *iter, const char *act)
{
char rwbs[6];
+ const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+
fill_rwbs(rwbs, t);
- return trace_seq_printf(s, "%3d,%-3d %2s %3s ",
+ return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
MAJOR(t->device), MINOR(t->device), act, rwbs);
}
@@ -1085,6 +1090,17 @@ static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
get_pdu_int(ent), cmd);
}
+static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+{
+ int ret;
+ const struct blk_io_trace *t = te_blk_io_trace(ent);
+
+ ret = trace_seq_putmem(s, t + 1, t->pdu_len);
+ if (ret)
+ return trace_seq_putc(s, '\n');
+ return ret;
+}
+
/*
* struct tracer operations
*/
@@ -1099,11 +1115,7 @@ static void blk_tracer_print_header(struct seq_file *m)
static void blk_tracer_start(struct trace_array *tr)
{
- mutex_lock(&blk_probe_mutex);
- if (atomic_add_return(1, &blk_probes_ref) == 1)
- if (blk_register_tracepoints())
- atomic_dec(&blk_probes_ref);
- mutex_unlock(&blk_probe_mutex);
+ blk_tracer_enabled = true;
trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
}
@@ -1111,38 +1123,24 @@ static int blk_tracer_init(struct trace_array *tr)
{
blk_tr = tr;
blk_tracer_start(tr);
- mutex_lock(&blk_probe_mutex);
- blk_tracer_enabled++;
- mutex_unlock(&blk_probe_mutex);
return 0;
}
static void blk_tracer_stop(struct trace_array *tr)
{
+ blk_tracer_enabled = false;
trace_flags |= TRACE_ITER_CONTEXT_INFO;
- mutex_lock(&blk_probe_mutex);
- if (atomic_dec_and_test(&blk_probes_ref))
- blk_unregister_tracepoints();
- mutex_unlock(&blk_probe_mutex);
}
static void blk_tracer_reset(struct trace_array *tr)
{
- if (!atomic_read(&blk_probes_ref))
- return;
-
- mutex_lock(&blk_probe_mutex);
- blk_tracer_enabled--;
- WARN_ON(blk_tracer_enabled < 0);
- mutex_unlock(&blk_probe_mutex);
-
blk_tracer_stop(tr);
}
-static struct {
+static const struct {
const char *act[2];
int (*print)(struct trace_seq *s, const struct trace_entry *ent);
-} what2act[] __read_mostly = {
+} what2act[] = {
[__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic },
[__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic },
[__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic },
@@ -1160,29 +1158,48 @@ static struct {
[__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap },
};
-static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
- int flags)
+static enum print_line_t print_one_line(struct trace_iterator *iter,
+ bool classic)
{
struct trace_seq *s = &iter->seq;
- const struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
- const u16 what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+ const struct blk_io_trace *t;
+ u16 what;
int ret;
+ bool long_act;
+ blk_log_action_t *log_action;
- if (!trace_print_context(iter))
- return TRACE_TYPE_PARTIAL_LINE;
+ t = te_blk_io_trace(iter->ent);
+ what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+ long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
+ log_action = classic ? &blk_log_action_classic : &blk_log_action;
- if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
+ if (t->action == BLK_TN_MESSAGE) {
+ ret = log_action(iter, long_act ? "message" : "m");
+ if (ret)
+ ret = blk_log_msg(s, iter->ent);
+ goto out;
+ }
+
+ if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
ret = trace_seq_printf(s, "Bad pc action %x\n", what);
else {
- const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
- ret = blk_log_action_seq(s, t, what2act[what].act[long_act]);
+ ret = log_action(iter, what2act[what].act[long_act]);
if (ret)
ret = what2act[what].print(s, iter->ent);
}
-
+out:
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
}
+static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
+ int flags)
+{
+ if (!trace_print_context(iter))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return print_one_line(iter, false);
+}
+
static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
@@ -1190,7 +1207,7 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
const int offset = offsetof(struct blk_io_trace, sector);
struct blk_io_trace old = {
.magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION,
- .time = ns2usecs(iter->ts),
+ .time = iter->ts,
};
if (!trace_seq_putmem(s, &old, offset))
@@ -1208,26 +1225,10 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
{
- const struct blk_io_trace *t;
- u16 what;
- int ret;
-
if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
return TRACE_TYPE_UNHANDLED;
- t = (const struct blk_io_trace *)iter->ent;
- what = t->action & ((1 << BLK_TC_SHIFT) - 1);
-
- if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
- ret = trace_seq_printf(&iter->seq, "Bad pc action %x\n", what);
- else {
- const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
- ret = blk_log_action_iter(iter, what2act[what].act[long_act]);
- if (ret)
- ret = what2act[what].print(&iter->seq, iter->ent);
- }
-
- return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+ return print_one_line(iter, true);
}
static struct tracer blk_tracer __read_mostly = {
@@ -1273,7 +1274,10 @@ static int blk_trace_remove_queue(struct request_queue *q)
if (bt == NULL)
return -EINVAL;
- kfree(bt);
+ if (atomic_dec_and_test(&blk_probes_ref))
+ blk_unregister_tracepoints();
+
+ blk_trace_free(bt);
return 0;
}
@@ -1283,26 +1287,33 @@ static int blk_trace_remove_queue(struct request_queue *q)
static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
{
struct blk_trace *old_bt, *bt = NULL;
- int ret;
+ int ret = -ENOMEM;
- ret = -ENOMEM;
bt = kzalloc(sizeof(*bt), GFP_KERNEL);
if (!bt)
- goto err;
+ return -ENOMEM;
+
+ bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+ if (!bt->msg_data)
+ goto free_bt;
bt->dev = dev;
bt->act_mask = (u16)-1;
bt->end_lba = -1ULL;
- bt->trace_state = Blktrace_running;
old_bt = xchg(&q->blk_trace, bt);
if (old_bt != NULL) {
(void)xchg(&q->blk_trace, old_bt);
- kfree(bt);
ret = -EBUSY;
+ goto free_bt;
}
+
+ if (atomic_inc_return(&blk_probes_ref) == 1)
+ blk_register_tracepoints();
return 0;
-err:
+
+free_bt:
+ blk_trace_free(bt);
return ret;
}
@@ -1310,72 +1321,6 @@ err:
* sysfs interface to enable and configure tracing
*/
-static ssize_t sysfs_blk_trace_enable_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct hd_struct *p = dev_to_part(dev);
- struct block_device *bdev;
- ssize_t ret = -ENXIO;
-
- lock_kernel();
- bdev = bdget(part_devt(p));
- if (bdev != NULL) {
- struct request_queue *q = bdev_get_queue(bdev);
-
- if (q != NULL) {
- mutex_lock(&bdev->bd_mutex);
- ret = sprintf(buf, "%u\n", !!q->blk_trace);
- mutex_unlock(&bdev->bd_mutex);
- }
-
- bdput(bdev);
- }
-
- unlock_kernel();
- return ret;
-}
-
-static ssize_t sysfs_blk_trace_enable_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct block_device *bdev;
- struct request_queue *q;
- struct hd_struct *p;
- int value;
- ssize_t ret = -ENXIO;
-
- if (count == 0 || sscanf(buf, "%d", &value) != 1)
- goto out;
-
- lock_kernel();
- p = dev_to_part(dev);
- bdev = bdget(part_devt(p));
- if (bdev == NULL)
- goto out_unlock_kernel;
-
- q = bdev_get_queue(bdev);
- if (q == NULL)
- goto out_bdput;
-
- mutex_lock(&bdev->bd_mutex);
- if (value)
- ret = blk_trace_setup_queue(q, bdev->bd_dev);
- else
- ret = blk_trace_remove_queue(q);
- mutex_unlock(&bdev->bd_mutex);
-
- if (ret == 0)
- ret = count;
-out_bdput:
- bdput(bdev);
-out_unlock_kernel:
- unlock_kernel();
-out:
- return ret;
-}
-
static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct device_attribute *attr,
char *buf);
@@ -1387,8 +1332,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
sysfs_blk_trace_attr_show, \
sysfs_blk_trace_attr_store)
-static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR,
- sysfs_blk_trace_enable_show, sysfs_blk_trace_enable_store);
+static BLK_TRACE_DEVICE_ATTR(enable);
static BLK_TRACE_DEVICE_ATTR(act_mask);
static BLK_TRACE_DEVICE_ATTR(pid);
static BLK_TRACE_DEVICE_ATTR(start_lba);
@@ -1408,53 +1352,85 @@ struct attribute_group blk_trace_attr_group = {
.attrs = blk_trace_attrs,
};
-static int blk_str2act_mask(const char *str)
+static const struct {
+ int mask;
+ const char *str;
+} mask_maps[] = {
+ { BLK_TC_READ, "read" },
+ { BLK_TC_WRITE, "write" },
+ { BLK_TC_BARRIER, "barrier" },
+ { BLK_TC_SYNC, "sync" },
+ { BLK_TC_QUEUE, "queue" },
+ { BLK_TC_REQUEUE, "requeue" },
+ { BLK_TC_ISSUE, "issue" },
+ { BLK_TC_COMPLETE, "complete" },
+ { BLK_TC_FS, "fs" },
+ { BLK_TC_PC, "pc" },
+ { BLK_TC_AHEAD, "ahead" },
+ { BLK_TC_META, "meta" },
+ { BLK_TC_DISCARD, "discard" },
+ { BLK_TC_DRV_DATA, "drv_data" },
+};
+
+static int blk_trace_str2mask(const char *str)
{
+ int i;
int mask = 0;
- char *copy = kstrdup(str, GFP_KERNEL), *s;
+ char *s, *token;
- if (copy == NULL)
+ s = kstrdup(str, GFP_KERNEL);
+ if (s == NULL)
return -ENOMEM;
-
- s = strstrip(copy);
+ s = strstrip(s);
while (1) {
- char *sep = strchr(s, ',');
-
- if (sep != NULL)
- *sep = '\0';
-
- if (strcasecmp(s, "barrier") == 0)
- mask |= BLK_TC_BARRIER;
- else if (strcasecmp(s, "complete") == 0)
- mask |= BLK_TC_COMPLETE;
- else if (strcasecmp(s, "fs") == 0)
- mask |= BLK_TC_FS;
- else if (strcasecmp(s, "issue") == 0)
- mask |= BLK_TC_ISSUE;
- else if (strcasecmp(s, "pc") == 0)
- mask |= BLK_TC_PC;
- else if (strcasecmp(s, "queue") == 0)
- mask |= BLK_TC_QUEUE;
- else if (strcasecmp(s, "read") == 0)
- mask |= BLK_TC_READ;
- else if (strcasecmp(s, "requeue") == 0)
- mask |= BLK_TC_REQUEUE;
- else if (strcasecmp(s, "sync") == 0)
- mask |= BLK_TC_SYNC;
- else if (strcasecmp(s, "write") == 0)
- mask |= BLK_TC_WRITE;
-
- if (sep == NULL)
+ token = strsep(&s, ",");
+ if (token == NULL)
break;
- s = sep + 1;
+ if (*token == '\0')
+ continue;
+
+ for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+ if (strcasecmp(token, mask_maps[i].str) == 0) {
+ mask |= mask_maps[i].mask;
+ break;
+ }
+ }
+ if (i == ARRAY_SIZE(mask_maps)) {
+ mask = -EINVAL;
+ break;
+ }
}
- kfree(copy);
+ kfree(s);
return mask;
}
+static ssize_t blk_trace_mask2str(char *buf, int mask)
+{
+ int i;
+ char *p = buf;
+
+ for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+ if (mask & mask_maps[i].mask) {
+ p += sprintf(p, "%s%s",
+ (p == buf) ? "" : ",", mask_maps[i].str);
+ }
+ }
+ *p++ = '\n';
+
+ return p - buf;
+}
+
+static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
+{
+ if (bdev->bd_disk == NULL)
+ return NULL;
+
+ return bdev_get_queue(bdev);
+}
+
static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -1469,20 +1445,29 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
if (bdev == NULL)
goto out_unlock_kernel;
- q = bdev_get_queue(bdev);
+ q = blk_trace_get_queue(bdev);
if (q == NULL)
goto out_bdput;
+
mutex_lock(&bdev->bd_mutex);
+
+ if (attr == &dev_attr_enable) {
+ ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ goto out_unlock_bdev;
+ }
+
if (q->blk_trace == NULL)
ret = sprintf(buf, "disabled\n");
else if (attr == &dev_attr_act_mask)
- ret = sprintf(buf, "%#x\n", q->blk_trace->act_mask);
+ ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
else if (attr == &dev_attr_pid)
ret = sprintf(buf, "%u\n", q->blk_trace->pid);
else if (attr == &dev_attr_start_lba)
ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
else if (attr == &dev_attr_end_lba)
ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+
+out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
out_bdput:
bdput(bdev);
@@ -1499,7 +1484,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
struct request_queue *q;
struct hd_struct *p;
u64 value;
- ssize_t ret = -ENXIO;
+ ssize_t ret = -EINVAL;
if (count == 0)
goto out;
@@ -1507,24 +1492,36 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
if (attr == &dev_attr_act_mask) {
if (sscanf(buf, "%llx", &value) != 1) {
/* Assume it is a list of trace category names */
- value = blk_str2act_mask(buf);
- if (value < 0)
+ ret = blk_trace_str2mask(buf);
+ if (ret < 0)
goto out;
+ value = ret;
}
} else if (sscanf(buf, "%llu", &value) != 1)
goto out;
+ ret = -ENXIO;
+
lock_kernel();
p = dev_to_part(dev);
bdev = bdget(part_devt(p));
if (bdev == NULL)
goto out_unlock_kernel;
- q = bdev_get_queue(bdev);
+ q = blk_trace_get_queue(bdev);
if (q == NULL)
goto out_bdput;
mutex_lock(&bdev->bd_mutex);
+
+ if (attr == &dev_attr_enable) {
+ if (value)
+ ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ else
+ ret = blk_trace_remove_queue(q);
+ goto out_unlock_bdev;
+ }
+
ret = 0;
if (q->blk_trace == NULL)
ret = blk_trace_setup_queue(q, bdev->bd_dev);
@@ -1538,13 +1535,15 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
q->blk_trace->start_lba = value;
else if (attr == &dev_attr_end_lba)
q->blk_trace->end_lba = value;
- ret = count;
}
+
+out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
out_bdput:
bdput(bdev);
out_unlock_kernel:
unlock_kernel();
out:
- return ret;
+ return ret ? ret : count;
}
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 808b14bbf07..edce2ff3894 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -189,16 +189,65 @@ enum {
RB_LEN_TIME_STAMP = 16,
};
-/* inline for ring buffer fast paths */
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+ return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+}
+
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+ return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+}
+
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+ event->type = RINGBUF_TYPE_PADDING;
+ event->time_delta = 0;
+}
+
+/**
+ * ring_buffer_event_discard - discard an event in the ring buffer
+ * @buffer: the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+ event->type = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ if (!event->time_delta)
+ event->time_delta = 1;
+}
+
static unsigned
-rb_event_length(struct ring_buffer_event *event)
+rb_event_data_length(struct ring_buffer_event *event)
{
unsigned length;
+ if (event->len)
+ length = event->len * RB_ALIGNMENT;
+ else
+ length = event->array[0];
+ return length + RB_EVNT_HDR_SIZE;
+}
+
+/* inline for ring buffer fast paths */
+static unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
switch (event->type) {
case RINGBUF_TYPE_PADDING:
- /* undefined */
- return -1;
+ if (rb_null_event(event))
+ /* undefined */
+ return -1;
+ return rb_event_data_length(event);
case RINGBUF_TYPE_TIME_EXTEND:
return RB_LEN_TIME_EXTEND;
@@ -207,11 +256,7 @@ rb_event_length(struct ring_buffer_event *event)
return RB_LEN_TIME_STAMP;
case RINGBUF_TYPE_DATA:
- if (event->len)
- length = event->len * RB_ALIGNMENT;
- else
- length = event->array[0];
- return length + RB_EVNT_HDR_SIZE;
+ return rb_event_data_length(event);
default:
BUG();
}
@@ -845,11 +890,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
}
EXPORT_SYMBOL_GPL(ring_buffer_resize);
-static inline int rb_null_event(struct ring_buffer_event *event)
-{
- return event->type == RINGBUF_TYPE_PADDING;
-}
-
static inline void *
__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
{
@@ -1219,7 +1259,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
if (tail < BUF_PAGE_SIZE) {
/* Mark the rest of the page with padding */
event = __rb_page_index(tail_page, tail);
- event->type = RINGBUF_TYPE_PADDING;
+ rb_event_set_padding(event);
}
if (tail <= BUF_PAGE_SIZE)
@@ -1969,7 +2009,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
event = rb_reader_event(cpu_buffer);
- if (event->type == RINGBUF_TYPE_DATA)
+ if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
cpu_buffer->entries--;
rb_update_read_stamp(cpu_buffer, event);
@@ -2052,9 +2092,18 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
switch (event->type) {
case RINGBUF_TYPE_PADDING:
- RB_WARN_ON(cpu_buffer, 1);
+ if (rb_null_event(event))
+ RB_WARN_ON(cpu_buffer, 1);
+ /*
+ * Because the writer could be discarding every
+ * event it creates (which would probably be bad)
+ * if we were to go back to "again" then we may never
+ * catch up, and will trigger the warn on, or lock
+ * the box. Return the padding, and we will release
+ * the current locks, and try again.
+ */
rb_advance_reader(cpu_buffer);
- return NULL;
+ return event;
case RINGBUF_TYPE_TIME_EXTEND:
/* Internal data, OK to advance */
@@ -2115,8 +2164,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
switch (event->type) {
case RINGBUF_TYPE_PADDING:
- rb_inc_iter(iter);
- goto again;
+ if (rb_null_event(event)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+ rb_advance_iter(iter);
+ return event;
case RINGBUF_TYPE_TIME_EXTEND:
/* Internal data, OK to advance */
@@ -2163,10 +2216,16 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_buffer_peek(buffer, cpu, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
@@ -2185,10 +2244,16 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_event *event;
unsigned long flags;
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_iter_peek(iter, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
@@ -2207,6 +2272,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
struct ring_buffer_event *event = NULL;
unsigned long flags;
+ again:
/* might be called in atomic */
preempt_disable();
@@ -2228,6 +2294,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
out:
preempt_enable();
+ if (event && event->type == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
EXPORT_SYMBOL_GPL(ring_buffer_consume);
@@ -2306,6 +2377,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
unsigned long flags;
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_iter_peek(iter, ts);
if (!event)
@@ -2315,6 +2387,11 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
out:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
EXPORT_SYMBOL_GPL(ring_buffer_read);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 67c6a21dd42..a0174a40c56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -861,15 +861,25 @@ static void ftrace_trace_stack(struct trace_array *tr,
static void ftrace_trace_userstack(struct trace_array *tr,
unsigned long flags, int pc);
-void trace_buffer_unlock_commit(struct trace_array *tr,
- struct ring_buffer_event *event,
- unsigned long flags, int pc)
+static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc,
+ int wake)
{
ring_buffer_unlock_commit(tr->buffer, event);
ftrace_trace_stack(tr, flags, 6, pc);
ftrace_trace_userstack(tr, flags, pc);
- trace_wake_up();
+
+ if (wake)
+ trace_wake_up();
+}
+
+void trace_buffer_unlock_commit(struct trace_array *tr,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ __trace_buffer_unlock_commit(tr, event, flags, pc, 1);
}
struct ring_buffer_event *
@@ -883,7 +893,13 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc)
{
- return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
+ return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+}
+
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
}
void
@@ -909,7 +925,7 @@ trace_function(struct trace_array *tr,
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __trace_graph_entry(struct trace_array *tr,
+static int __trace_graph_entry(struct trace_array *tr,
struct ftrace_graph_ent *trace,
unsigned long flags,
int pc)
@@ -918,15 +934,17 @@ static void __trace_graph_entry(struct trace_array *tr,
struct ftrace_graph_ent_entry *entry;
if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
- return;
+ return 0;
event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
sizeof(*entry), flags, pc);
if (!event)
- return;
+ return 0;
entry = ring_buffer_event_data(event);
entry->graph_ent = *trace;
ring_buffer_unlock_commit(global_trace.buffer, event);
+
+ return 1;
}
static void __trace_graph_return(struct trace_array *tr,
@@ -1147,6 +1165,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
struct trace_array_cpu *data;
unsigned long flags;
long disabled;
+ int ret;
int cpu;
int pc;
@@ -1162,15 +1181,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
- __trace_graph_entry(tr, trace, flags, pc);
+ ret = __trace_graph_entry(tr, trace, flags, pc);
+ } else {
+ ret = 0;
}
/* Only do the atomic if it is not already set */
if (!test_tsk_trace_graph(current))
set_tsk_trace_graph(current);
+
atomic_dec(&data->disabled);
local_irq_restore(flags);
- return 1;
+ return ret;
}
void trace_graph_return(struct ftrace_graph_ret *trace)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d7410bbb9a8..cb0ce3fc36d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -483,6 +483,8 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
unsigned long flags, int pc);
void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+ unsigned long flags, int pc);
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
struct trace_array_cpu *data);
@@ -776,16 +778,27 @@ enum {
TRACE_EVENT_TYPE_RAW = 2,
};
+struct ftrace_event_field {
+ struct list_head link;
+ char *name;
+ char *type;
+ int offset;
+ int size;
+};
+
struct ftrace_event_call {
- char *name;
- char *system;
- struct dentry *dir;
- int enabled;
- int (*regfunc)(void);
- void (*unregfunc)(void);
- int id;
- int (*raw_init)(void);
- int (*show_format)(struct trace_seq *s);
+ char *name;
+ char *system;
+ struct dentry *dir;
+ int enabled;
+ int (*regfunc)(void);
+ void (*unregfunc)(void);
+ int id;
+ int (*raw_init)(void);
+ int (*show_format)(struct trace_seq *s);
+ int (*define_fields)(void);
+ struct list_head fields;
+ struct filter_pred **preds;
#ifdef CONFIG_EVENT_PROFILE
atomic_t profile_count;
@@ -794,6 +807,51 @@ struct ftrace_event_call {
#endif
};
+struct event_subsystem {
+ struct list_head list;
+ const char *name;
+ struct dentry *entry;
+ struct filter_pred **preds;
+};
+
+#define events_for_each(event) \
+ for (event = __start_ftrace_events; \
+ (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+ event++)
+
+#define MAX_FILTER_PRED 8
+
+struct filter_pred;
+
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+
+struct filter_pred {
+ filter_pred_fn_t fn;
+ u64 val;
+ char *str_val;
+ int str_len;
+ char *field_name;
+ int offset;
+ int not;
+ int or;
+ int compound;
+ int clear;
+};
+
+int trace_define_field(struct ftrace_event_call *call, char *type,
+ char *name, int offset, int size);
+extern void filter_free_pred(struct filter_pred *pred);
+extern void filter_print_preds(struct filter_pred **preds,
+ struct trace_seq *s);
+extern int filter_parse(char **pbuf, struct filter_pred *pred);
+extern int filter_add_pred(struct ftrace_event_call *call,
+ struct filter_pred *pred);
+extern void filter_free_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern void filter_free_subsystem_preds(struct event_subsystem *system);
+extern int filter_add_subsystem_pred(struct event_subsystem *system,
+ struct filter_pred *pred);
+
void event_trace_printk(unsigned long ip, const char *fmt, ...);
extern struct ftrace_event_call __start_ftrace_events[];
extern struct ftrace_event_call __stop_ftrace_events[];
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3047b56f663..64ec4d278ff 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -19,6 +19,39 @@
static DEFINE_MUTEX(event_mutex);
+int trace_define_field(struct ftrace_event_call *call, char *type,
+ char *name, int offset, int size)
+{
+ struct ftrace_event_field *field;
+
+ field = kzalloc(sizeof(*field), GFP_KERNEL);
+ 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->offset = offset;
+ field->size = size;
+ list_add(&field->link, &call->fields);
+
+ return 0;
+
+err:
+ if (field) {
+ kfree(field->name);
+ kfree(field->type);
+ }
+ kfree(field);
+
+ return -ENOMEM;
+}
+
static void ftrace_clear_events(void)
{
struct ftrace_event_call *call = (void *)__start_ftrace_events;
@@ -343,7 +376,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
#undef FIELD
#define FIELD(type, name) \
- #type, #name, offsetof(typeof(field), name), sizeof(field.name)
+ #type, "common_" #name, offsetof(typeof(field), name), \
+ sizeof(field.name)
static int trace_write_header(struct trace_seq *s)
{
@@ -430,6 +464,139 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
return r;
}
+static ssize_t
+event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ filter_print_preds(call->preds, s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
+static ssize_t
+event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ char buf[64], *pbuf = buf;
+ struct filter_pred *pred;
+ int err;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return -ENOMEM;
+
+ err = filter_parse(&pbuf, pred);
+ if (err < 0) {
+ filter_free_pred(pred);
+ return err;
+ }
+
+ if (pred->clear) {
+ filter_free_preds(call);
+ filter_free_pred(pred);
+ return cnt;
+ }
+
+ if (filter_add_pred(call, pred)) {
+ filter_free_pred(pred);
+ return -EINVAL;
+ }
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+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 trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ filter_print_preds(system->preds, s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
+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;
+ char buf[64], *pbuf = buf;
+ struct filter_pred *pred;
+ int err;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return -ENOMEM;
+
+ err = filter_parse(&pbuf, pred);
+ if (err < 0) {
+ filter_free_pred(pred);
+ return err;
+ }
+
+ if (pred->clear) {
+ filter_free_subsystem_preds(system);
+ filter_free_pred(pred);
+ return cnt;
+ }
+
+ if (filter_add_subsystem_pred(system, pred)) {
+ filter_free_subsystem_preds(system);
+ filter_free_pred(pred);
+ return -EINVAL;
+ }
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
static const struct seq_operations show_event_seq_ops = {
.start = t_start,
.next = t_next,
@@ -475,6 +642,18 @@ static const struct file_operations ftrace_event_id_fops = {
.read = event_id_read,
};
+static const struct file_operations ftrace_event_filter_fops = {
+ .open = tracing_open_generic,
+ .read = event_filter_read,
+ .write = event_filter_write,
+};
+
+static const struct file_operations ftrace_subsystem_filter_fops = {
+ .open = tracing_open_generic,
+ .read = subsystem_filter_read,
+ .write = subsystem_filter_write,
+};
+
static struct dentry *event_trace_events_dir(void)
{
static struct dentry *d_tracer;
@@ -495,12 +674,6 @@ static struct dentry *event_trace_events_dir(void)
return d_events;
}
-struct event_subsystem {
- struct list_head list;
- const char *name;
- struct dentry *entry;
-};
-
static LIST_HEAD(event_subsystems);
static struct dentry *
@@ -533,6 +706,8 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
system->name = name;
list_add(&system->list, &event_subsystems);
+ system->preds = NULL;
+
return system->entry;
}
@@ -581,6 +756,20 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
call->name);
}
+ if (call->define_fields) {
+ ret = call->define_fields();
+ if (ret < 0) {
+ pr_warning("Could not initialize trace point"
+ " events/%s\n", call->name);
+ return ret;
+ }
+ entry = debugfs_create_file("filter", 0644, call->dir, call,
+ &ftrace_event_filter_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'%s/filter' entry\n", call->name);
+ }
+
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
new file mode 100644
index 00000000000..026be412f35
--- /dev/null
+++ b/kernel/trace/trace_events_filter.c
@@ -0,0 +1,427 @@
+/*
+ * trace_events_filter - generic event filtering
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static int filter_pred_64(struct filter_pred *pred, void *event)
+{
+ u64 *addr = (u64 *)(event + pred->offset);
+ u64 val = (u64)pred->val;
+ int match;
+
+ match = (val == *addr) ^ pred->not;
+
+ return match;
+}
+
+static int filter_pred_32(struct filter_pred *pred, void *event)
+{
+ u32 *addr = (u32 *)(event + pred->offset);
+ u32 val = (u32)pred->val;
+ int match;
+
+ match = (val == *addr) ^ pred->not;
+
+ return match;
+}
+
+static int filter_pred_16(struct filter_pred *pred, void *event)
+{
+ u16 *addr = (u16 *)(event + pred->offset);
+ u16 val = (u16)pred->val;
+ int match;
+
+ match = (val == *addr) ^ pred->not;
+
+ return match;
+}
+
+static int filter_pred_8(struct filter_pred *pred, void *event)
+{
+ u8 *addr = (u8 *)(event + pred->offset);
+ u8 val = (u8)pred->val;
+ int match;
+
+ match = (val == *addr) ^ pred->not;
+
+ return match;
+}
+
+static int filter_pred_string(struct filter_pred *pred, void *event)
+{
+ char *addr = (char *)(event + pred->offset);
+ int cmp, match;
+
+ cmp = strncmp(addr, pred->str_val, pred->str_len);
+
+ match = (!cmp) ^ pred->not;
+
+ return match;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
+{
+ int i, matched, and_failed = 0;
+ struct filter_pred *pred;
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (call->preds[i]) {
+ pred = call->preds[i];
+ if (and_failed && !pred->or)
+ continue;
+ matched = pred->fn(pred, rec);
+ if (!matched && !pred->or) {
+ and_failed = 1;
+ continue;
+ } else if (matched && pred->or)
+ return 1;
+ } else
+ break;
+ }
+
+ if (and_failed)
+ return 0;
+
+ return 1;
+}
+
+void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+{
+ char *field_name;
+ struct filter_pred *pred;
+ int i;
+
+ if (!preds) {
+ trace_seq_printf(s, "none\n");
+ return;
+ }
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (preds[i]) {
+ pred = preds[i];
+ field_name = pred->field_name;
+ if (i)
+ trace_seq_printf(s, pred->or ? "|| " : "&& ");
+ trace_seq_printf(s, "%s ", field_name);
+ trace_seq_printf(s, pred->not ? "!= " : "== ");
+ if (pred->str_val)
+ trace_seq_printf(s, "%s\n", pred->str_val);
+ else
+ trace_seq_printf(s, "%llu\n", pred->val);
+ } else
+ break;
+ }
+}
+
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+ struct ftrace_event_field *field;
+
+ list_for_each_entry(field, &call->fields, link) {
+ if (!strcmp(field->name, name))
+ return field;
+ }
+
+ return NULL;
+}
+
+void filter_free_pred(struct filter_pred *pred)
+{
+ if (!pred)
+ return;
+
+ kfree(pred->field_name);
+ kfree(pred->str_val);
+ kfree(pred);
+}
+
+void filter_free_preds(struct ftrace_event_call *call)
+{
+ int i;
+
+ if (call->preds) {
+ for (i = 0; i < MAX_FILTER_PRED; i++)
+ filter_free_pred(call->preds[i]);
+ kfree(call->preds);
+ call->preds = NULL;
+ }
+}
+
+void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+ struct ftrace_event_call *call = __start_ftrace_events;
+ int i;
+
+ if (system->preds) {
+ for (i = 0; i < MAX_FILTER_PRED; i++)
+ filter_free_pred(system->preds[i]);
+ kfree(system->preds);
+ system->preds = NULL;
+ }
+
+ events_for_each(call) {
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (!strcmp(call->system, system->name))
+ filter_free_preds(call);
+ }
+}
+
+static int __filter_add_pred(struct ftrace_event_call *call,
+ struct filter_pred *pred)
+{
+ int i;
+
+ if (call->preds && !pred->compound)
+ filter_free_preds(call);
+
+ if (!call->preds) {
+ call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+ GFP_KERNEL);
+ if (!call->preds)
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (!call->preds[i]) {
+ call->preds[i] = pred;
+ return 0;
+ }
+ }
+
+ return -ENOMEM;
+}
+
+static int is_string_field(const char *type)
+{
+ if (strchr(type, '[') && strstr(type, "char"))
+ return 1;
+
+ return 0;
+}
+
+int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+{
+ struct ftrace_event_field *field;
+
+ field = find_event_field(call, pred->field_name);
+ if (!field)
+ return -EINVAL;
+
+ pred->offset = field->offset;
+
+ if (is_string_field(field->type)) {
+ if (!pred->str_val)
+ return -EINVAL;
+ pred->fn = filter_pred_string;
+ pred->str_len = field->size;
+ return __filter_add_pred(call, pred);
+ } else {
+ if (pred->str_val)
+ return -EINVAL;
+ }
+
+ switch (field->size) {
+ case 8:
+ pred->fn = filter_pred_64;
+ break;
+ case 4:
+ pred->fn = filter_pred_32;
+ break;
+ case 2:
+ pred->fn = filter_pred_16;
+ break;
+ case 1:
+ pred->fn = filter_pred_8;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return __filter_add_pred(call, pred);
+}
+
+static struct filter_pred *copy_pred(struct filter_pred *pred)
+{
+ struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
+ if (!new_pred)
+ return NULL;
+
+ memcpy(new_pred, pred, sizeof(*pred));
+
+ if (pred->field_name) {
+ new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+ if (!new_pred->field_name) {
+ kfree(new_pred);
+ return NULL;
+ }
+ }
+
+ if (pred->str_val) {
+ new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
+ if (!new_pred->str_val) {
+ filter_free_pred(new_pred);
+ return NULL;
+ }
+ }
+
+ return new_pred;
+}
+
+int filter_add_subsystem_pred(struct event_subsystem *system,
+ struct filter_pred *pred)
+{
+ struct ftrace_event_call *call = __start_ftrace_events;
+ struct filter_pred *event_pred;
+ int i;
+
+ if (system->preds && !pred->compound)
+ filter_free_subsystem_preds(system);
+
+ if (!system->preds) {
+ system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+ GFP_KERNEL);
+ if (!system->preds)
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (!system->preds[i]) {
+ system->preds[i] = pred;
+ break;
+ }
+ }
+
+ if (i == MAX_FILTER_PRED)
+ return -EINVAL;
+
+ events_for_each(call) {
+ int err;
+
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (strcmp(call->system, system->name))
+ continue;
+
+ if (!find_event_field(call, pred->field_name))
+ continue;
+
+ event_pred = copy_pred(pred);
+ if (!event_pred)
+ goto oom;
+
+ err = filter_add_pred(call, event_pred);
+ if (err)
+ filter_free_pred(event_pred);
+ if (err == -ENOMEM)
+ goto oom;
+ }
+
+ return 0;
+
+oom:
+ system->preds[i] = NULL;
+ return -ENOMEM;
+}
+
+int filter_parse(char **pbuf, struct filter_pred *pred)
+{
+ char *tmp, *tok, *val_str = NULL;
+ int tok_n = 0;
+
+ /* field ==/!= number, or/and field ==/!= number, number */
+ while ((tok = strsep(pbuf, " \n"))) {
+ if (tok_n == 0) {
+ if (!strcmp(tok, "0")) {
+ pred->clear = 1;
+ return 0;
+ } else if (!strcmp(tok, "&&")) {
+ pred->or = 0;
+ pred->compound = 1;
+ } else if (!strcmp(tok, "||")) {
+ pred->or = 1;
+ pred->compound = 1;
+ } else
+ pred->field_name = tok;
+ tok_n = 1;
+ continue;
+ }
+ if (tok_n == 1) {
+ if (!pred->field_name)
+ pred->field_name = tok;
+ else if (!strcmp(tok, "!="))
+ pred->not = 1;
+ else if (!strcmp(tok, "=="))
+ pred->not = 0;
+ else {
+ pred->field_name = NULL;
+ return -EINVAL;
+ }
+ tok_n = 2;
+ continue;
+ }
+ if (tok_n == 2) {
+ if (pred->compound) {
+ if (!strcmp(tok, "!="))
+ pred->not = 1;
+ else if (!strcmp(tok, "=="))
+ pred->not = 0;
+ else {
+ pred->field_name = NULL;
+ return -EINVAL;
+ }
+ } else {
+ val_str = tok;
+ break; /* done */
+ }
+ tok_n = 3;
+ continue;
+ }
+ if (tok_n == 3) {
+ val_str = tok;
+ break; /* done */
+ }
+ }
+
+ pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+ if (!pred->field_name)
+ return -ENOMEM;
+
+ pred->val = simple_strtoull(val_str, &tmp, 10);
+ if (tmp == val_str) {
+ pred->str_val = kstrdup(val_str, GFP_KERNEL);
+ if (!pred->str_val)
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
index 5117c43f5c6..30743f7d411 100644
--- a/kernel/trace/trace_events_stage_2.h
+++ b/kernel/trace/trace_events_stage_2.h
@@ -129,3 +129,48 @@ ftrace_format_##call(struct trace_seq *s) \
}
#include <trace/trace_event_types.h>
+
+#undef __field
+#define __field(type, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item)); \
+ if (ret) \
+ return ret;
+
+#undef __array
+#define __array(type, item, len) \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item)); \
+ if (ret) \
+ return ret;
+
+#define __common_field(type, item) \
+ ret = trace_define_field(event_call, #type, "common_" #item, \
+ offsetof(typeof(field.ent), item), \
+ sizeof(field.ent.item)); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
+int \
+ftrace_define_fields_##call(void) \
+{ \
+ struct ftrace_raw_##call field; \
+ struct ftrace_event_call *event_call = &event_##call; \
+ int ret; \
+ \
+ __common_field(unsigned char, type); \
+ __common_field(unsigned char, flags); \
+ __common_field(unsigned char, preempt_count); \
+ __common_field(int, pid); \
+ __common_field(int, tgid); \
+ \
+ tstruct; \
+ \
+ return ret; \
+}
+
+#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
index 6b3261ca988..9d2fa78cecc 100644
--- a/kernel/trace/trace_events_stage_3.h
+++ b/kernel/trace/trace_events_stage_3.h
@@ -204,6 +204,7 @@ static struct ftrace_event_call event_##call; \
\
static void ftrace_raw_event_##call(proto) \
{ \
+ struct ftrace_event_call *call = &event_##call; \
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
unsigned long irq_flags; \
@@ -221,7 +222,11 @@ static void ftrace_raw_event_##call(proto) \
\
assign; \
\
- trace_current_buffer_unlock_commit(event, irq_flags, pc); \
+ if (call->preds && !filter_match_preds(call, entry)) \
+ ring_buffer_event_discard(event); \
+ \
+ trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+ \
} \
\
static int ftrace_raw_reg_event_##call(void) \
@@ -252,6 +257,7 @@ static int ftrace_raw_init_event_##call(void) \
if (!id) \
return -ENODEV; \
event_##call.id = id; \
+ INIT_LIST_HEAD(&event_##call.fields); \
return 0; \
} \
\
@@ -264,6 +270,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.regfunc = ftrace_raw_reg_event_##call, \
.unregfunc = ftrace_raw_unreg_event_##call, \
.show_format = ftrace_format_##call, \
+ .define_fields = ftrace_define_fields_##call, \
_TRACE_PROFILE_INIT(call) \
}
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 9aa84bde23c..394f94417e2 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -91,6 +91,7 @@ struct tracer nop_trace __read_mostly =
.name = "nop",
.init = nop_trace_init,
.reset = nop_trace_reset,
+ .wait_pipe = poll_wait_pipe,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_nop,
#endif