summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig26
-rw-r--r--kernel/trace/Makefile5
-rw-r--r--kernel/trace/blktrace.c144
-rw-r--r--kernel/trace/ftrace.c172
-rw-r--r--kernel/trace/kmemtrace.c70
-rw-r--r--kernel/trace/power-traces.c1
-rw-r--r--kernel/trace/ring_buffer.c258
-rw-r--r--kernel/trace/ring_buffer_benchmark.c6
-rw-r--r--kernel/trace/trace.c408
-rw-r--r--kernel/trace/trace.h67
-rw-r--r--kernel/trace/trace_branch.c27
-rw-r--r--kernel/trace/trace_clock.c5
-rw-r--r--kernel/trace/trace_entries.h12
-rw-r--r--kernel/trace/trace_event_perf.c184
-rw-r--r--kernel/trace/trace_event_profile.c122
-rw-r--r--kernel/trace/trace_events.c219
-rw-r--r--kernel/trace/trace_events_filter.c35
-rw-r--r--kernel/trace/trace_export.c103
-rw-r--r--kernel/trace/trace_functions_graph.c284
-rw-r--r--kernel/trace/trace_hw_branches.c312
-rw-r--r--kernel/trace/trace_irqsoff.c271
-rw-r--r--kernel/trace/trace_kprobe.c947
-rw-r--r--kernel/trace/trace_ksym.c27
-rw-r--r--kernel/trace/trace_mmiotrace.c1
-rw-r--r--kernel/trace/trace_output.c155
-rw-r--r--kernel/trace/trace_output.h2
-rw-r--r--kernel/trace/trace_sched_switch.c21
-rw-r--r--kernel/trace/trace_sched_wakeup.c29
-rw-r--r--kernel/trace/trace_selftest.c65
-rw-r--r--kernel/trace/trace_stack.c24
-rw-r--r--kernel/trace/trace_stat.c1
-rw-r--r--kernel/trace/trace_syscalls.c374
-rw-r--r--kernel/trace/trace_workqueue.c27
33 files changed, 2519 insertions, 1885 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6c22d8a2f28..8b1797c4545 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -27,9 +27,7 @@ config HAVE_FUNCTION_GRAPH_TRACER
config HAVE_FUNCTION_GRAPH_FP_TEST
bool
help
- An arch may pass in a unique value (frame pointer) to both the
- entering and exiting of a function. On exit, the value is compared
- and if it does not match, then it will panic the kernel.
+ See Documentation/trace/ftrace-design.txt
config HAVE_FUNCTION_TRACE_MCOUNT_TEST
bool
@@ -46,9 +44,6 @@ config HAVE_FTRACE_MCOUNT_RECORD
help
See Documentation/trace/ftrace-design.txt
-config HAVE_HW_BRANCH_TRACER
- bool
-
config HAVE_SYSCALL_TRACEPOINTS
bool
help
@@ -330,15 +325,6 @@ config BRANCH_TRACER
Say N if unsure.
-config POWER_TRACER
- bool "Trace power consumption behavior"
- depends on X86
- select GENERIC_TRACER
- help
- This tracer helps developers to analyze and optimize the kernel's
- power management decisions, specifically the C-state and P-state
- behavior.
-
config KSYM_TRACER
bool "Trace read and write access on kernel memory locations"
depends on HAVE_HW_BREAKPOINT
@@ -385,14 +371,6 @@ config STACK_TRACER
Say N if unsure.
-config HW_BRANCH_TRACER
- depends on HAVE_HW_BRANCH_TRACER
- bool "Trace hw branches"
- select GENERIC_TRACER
- help
- This tracer records all branches on the system in a circular
- buffer, giving access to the last N branches for each cpu.
-
config KMEMTRACE
bool "Trace SLAB allocations"
select GENERIC_TRACER
@@ -451,7 +429,7 @@ config BLK_DEV_IO_TRACE
config KPROBE_EVENT
depends on KPROBES
- depends on X86
+ depends on HAVE_REGS_AND_STACK_ACCESS_API
bool "Enable kprobes-based dynamic events"
select TRACING
default y
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index cd9ecd89ec7..ffb1a5b0550 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -41,7 +41,6 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
@@ -51,7 +50,9 @@ endif
obj-$(CONFIG_EVENT_TRACING) += trace_events.o
obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
-obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
+endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d9d6206e0b1..36ea2b65dcd 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -21,6 +21,7 @@
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/smp_lock.h>
#include <linux/time.h>
@@ -540,9 +541,10 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (ret)
return ret;
- if (copy_to_user(arg, &buts, sizeof(buts)))
+ if (copy_to_user(arg, &buts, sizeof(buts))) {
+ blk_trace_remove(q);
return -EFAULT;
-
+ }
return 0;
}
EXPORT_SYMBOL_GPL(blk_trace_setup);
@@ -673,28 +675,33 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
}
}
-static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_abort(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_ABORT);
}
-static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_INSERT);
}
-static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
}
-static void blk_add_trace_rq_requeue(struct request_queue *q,
+static void blk_add_trace_rq_requeue(void *ignore,
+ struct request_queue *q,
struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
}
-static void blk_add_trace_rq_complete(struct request_queue *q,
+static void blk_add_trace_rq_complete(void *ignore,
+ struct request_queue *q,
struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
@@ -722,34 +729,40 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
!bio_flagged(bio, BIO_UPTODATE), 0, NULL);
}
-static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_bounce(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
}
-static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_complete(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
}
-static void blk_add_trace_bio_backmerge(struct request_queue *q,
+static void blk_add_trace_bio_backmerge(void *ignore,
+ struct request_queue *q,
struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
}
-static void blk_add_trace_bio_frontmerge(struct request_queue *q,
+static void blk_add_trace_bio_frontmerge(void *ignore,
+ struct request_queue *q,
struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
}
-static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_queue(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
}
-static void blk_add_trace_getrq(struct request_queue *q,
+static void blk_add_trace_getrq(void *ignore,
+ struct request_queue *q,
struct bio *bio, int rw)
{
if (bio)
@@ -763,7 +776,8 @@ static void blk_add_trace_getrq(struct request_queue *q,
}
-static void blk_add_trace_sleeprq(struct request_queue *q,
+static void blk_add_trace_sleeprq(void *ignore,
+ struct request_queue *q,
struct bio *bio, int rw)
{
if (bio)
@@ -777,7 +791,7 @@ static void blk_add_trace_sleeprq(struct request_queue *q,
}
}
-static void blk_add_trace_plug(struct request_queue *q)
+static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -785,7 +799,7 @@ static void blk_add_trace_plug(struct request_queue *q)
__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
}
-static void blk_add_trace_unplug_io(struct request_queue *q)
+static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -798,7 +812,7 @@ static void blk_add_trace_unplug_io(struct request_queue *q)
}
}
-static void blk_add_trace_unplug_timer(struct request_queue *q)
+static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -811,7 +825,8 @@ static void blk_add_trace_unplug_timer(struct request_queue *q)
}
}
-static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+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;
@@ -837,8 +852,9 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
* it spans a stripe (or similar). Add a trace for that action.
*
**/
-static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from)
+static void blk_add_trace_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_io_trace_remap r;
@@ -867,7 +883,8 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
* Add a trace for that action.
*
**/
-static void blk_add_trace_rq_remap(struct request_queue *q,
+static void blk_add_trace_rq_remap(void *ignore,
+ struct request_queue *q,
struct request *rq, dev_t dev,
sector_t from)
{
@@ -919,64 +936,64 @@ static void blk_register_tracepoints(void)
{
int ret;
- ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+ ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+ ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+ ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+ ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+ ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+ ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
WARN_ON(ret);
- ret = register_trace_block_getrq(blk_add_trace_getrq);
+ ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
WARN_ON(ret);
- ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+ ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
WARN_ON(ret);
- ret = register_trace_block_plug(blk_add_trace_plug);
+ ret = register_trace_block_plug(blk_add_trace_plug, NULL);
WARN_ON(ret);
- ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
WARN_ON(ret);
- ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+ ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
WARN_ON(ret);
- ret = register_trace_block_split(blk_add_trace_split);
+ ret = register_trace_block_split(blk_add_trace_split, NULL);
WARN_ON(ret);
- ret = register_trace_block_remap(blk_add_trace_remap);
+ ret = register_trace_block_remap(blk_add_trace_remap, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+ ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
WARN_ON(ret);
}
static void blk_unregister_tracepoints(void)
{
- unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
- unregister_trace_block_remap(blk_add_trace_remap);
- unregister_trace_block_split(blk_add_trace_split);
- unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
- unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
- unregister_trace_block_plug(blk_add_trace_plug);
- unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
- unregister_trace_block_getrq(blk_add_trace_getrq);
- unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
- unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
- unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
- unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
- unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
- unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
- unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
- unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
- unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
- unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+ unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
+ unregister_trace_block_remap(blk_add_trace_remap, NULL);
+ unregister_trace_block_split(blk_add_trace_split, NULL);
+ unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+ unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+ unregister_trace_block_plug(blk_add_trace_plug, NULL);
+ unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
+ unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
+ unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
+ unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
+ unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
+ unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
+ unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
+ unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
+ unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+ unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
+ unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
+ unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
tracepoint_synchronize_unregister();
}
@@ -1319,7 +1336,7 @@ out:
}
static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
return print_one_line(iter, false);
}
@@ -1341,7 +1358,8 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
}
static enum print_line_t
-blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
+blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return blk_trace_synthesize_old_trace(iter) ?
TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
@@ -1379,12 +1397,16 @@ static struct tracer blk_tracer __read_mostly = {
.set_flag = blk_tracer_set_flag,
};
-static struct trace_event trace_blk_event = {
- .type = TRACE_BLK,
+static struct trace_event_functions trace_blk_event_funcs = {
.trace = blk_trace_event_print,
.binary = blk_trace_event_print_binary,
};
+static struct trace_event trace_blk_event = {
+ .type = TRACE_BLK,
+ .funcs = &trace_blk_event_funcs,
+};
+
static int __init init_blk_tracer(void)
{
if (!register_ftrace_event(&trace_blk_event)) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1e6640f8045..6d2cb14f944 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -22,12 +22,13 @@
#include <linux/hardirq.h>
#include <linux/kthread.h>
#include <linux/uaccess.h>
-#include <linux/kprobes.h>
#include <linux/ftrace.h>
#include <linux/sysctl.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/hash.h>
+#include <linux/rcupdate.h>
#include <trace/events/sched.h>
@@ -85,22 +86,22 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
-#endif
-
+/*
+ * Traverse the ftrace_list, invoking all entries. The reason that we
+ * can use rcu_dereference_raw() 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() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
- struct ftrace_ops *op = ftrace_list;
-
- /* in case someone actually ports this to alpha! */
- read_barrier_depends();
+ struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
while (op != &ftrace_list_end) {
- /* silly alpha */
- read_barrier_depends();
op->func(ip, parent_ip);
- op = op->next;
+ op = rcu_dereference_raw(op->next); /*see above*/
};
}
@@ -155,8 +156,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
* the ops->next pointer is valid before another CPU sees
* the ops pointer included into the ftrace_list.
*/
- smp_wmb();
- ftrace_list = ops;
+ rcu_assign_pointer(ftrace_list, ops);
if (ftrace_enabled) {
ftrace_func_t func;
@@ -264,6 +264,7 @@ struct ftrace_profile {
unsigned long counter;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long long time;
+ unsigned long long time_squared;
#endif
};
@@ -366,9 +367,9 @@ static int function_stat_headers(struct seq_file *m)
{
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_printf(m, " Function "
- "Hit Time Avg\n"
+ "Hit Time Avg s^2\n"
" -------- "
- "--- ---- ---\n");
+ "--- ---- --- ---\n");
#else
seq_printf(m, " Function Hit\n"
" -------- ---\n");
@@ -384,6 +385,7 @@ static int function_stat_show(struct seq_file *m, void *v)
static DEFINE_MUTEX(mutex);
static struct trace_seq s;
unsigned long long avg;
+ unsigned long long stddev;
#endif
kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -394,11 +396,25 @@ static int function_stat_show(struct seq_file *m, void *v)
avg = rec->time;
do_div(avg, rec->counter);
+ /* Sample standard deviation (s^2) */
+ if (rec->counter <= 1)
+ stddev = 0;
+ else {
+ stddev = rec->time_squared - rec->counter * avg * avg;
+ /*
+ * Divide only 1000 for ns^2 -> us^2 conversion.
+ * trace_print_graph_duration will divide 1000 again.
+ */
+ do_div(stddev, (rec->counter - 1) * 1000);
+ }
+
mutex_lock(&mutex);
trace_seq_init(&s);
trace_print_graph_duration(rec->time, &s);
trace_seq_puts(&s, " ");
trace_print_graph_duration(avg, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(stddev, &s);
trace_print_seq(m, &s);
mutex_unlock(&mutex);
#endif
@@ -650,6 +666,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
if (!stat->hash || !ftrace_profile_enabled)
goto out;
+ /* If the calltime was zero'd ignore it */
+ if (!trace->calltime)
+ goto out;
+
calltime = trace->rettime - trace->calltime;
if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
@@ -668,8 +688,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
}
rec = ftrace_find_profiled_func(stat, trace->func);
- if (rec)
+ if (rec) {
rec->time += calltime;
+ rec->time_squared += calltime * calltime;
+ }
out:
local_irq_restore(flags);
@@ -898,36 +920,6 @@ static struct dyn_ftrace *ftrace_free_records;
} \
}
-#ifdef CONFIG_KPROBES
-
-static int frozen_record_count;
-
-static inline void freeze_record(struct dyn_ftrace *rec)
-{
- if (!(rec->flags & FTRACE_FL_FROZEN)) {
- rec->flags |= FTRACE_FL_FROZEN;
- frozen_record_count++;
- }
-}
-
-static inline void unfreeze_record(struct dyn_ftrace *rec)
-{
- if (rec->flags & FTRACE_FL_FROZEN) {
- rec->flags &= ~FTRACE_FL_FROZEN;
- frozen_record_count--;
- }
-}
-
-static inline int record_frozen(struct dyn_ftrace *rec)
-{
- return rec->flags & FTRACE_FL_FROZEN;
-}
-#else
-# define freeze_record(rec) ({ 0; })
-# define unfreeze_record(rec) ({ 0; })
-# define record_frozen(rec) ({ 0; })
-#endif /* CONFIG_KPROBES */
-
static void ftrace_free_rec(struct dyn_ftrace *rec)
{
rec->freelist = ftrace_free_records;
@@ -1025,6 +1017,21 @@ static void ftrace_bug(int failed, unsigned long ip)
}
+/* Return 1 if the address range is reserved for ftrace */
+int ftrace_text_reserved(void *start, void *end)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+
+ do_for_each_ftrace_rec(pg, rec) {
+ if (rec->ip <= (unsigned long)end &&
+ rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start)
+ return 1;
+ } while_for_each_ftrace_rec();
+ return 0;
+}
+
+
static int
__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
{
@@ -1076,14 +1083,6 @@ static void ftrace_replace_code(int enable)
!(rec->flags & FTRACE_FL_CONVERTED))
continue;
- /* ignore updates to this record's mcount site */
- if (get_kprobe((void *)rec->ip)) {
- freeze_record(rec);
- continue;
- } else {
- unfreeze_record(rec);
- }
-
failed = __ftrace_replace_code(rec, enable);
if (failed) {
rec->flags |= FTRACE_FL_FAILED;
@@ -2300,6 +2299,8 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -2426,6 +2427,7 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
int ftrace_graph_count;
+int ftrace_graph_filter_enabled;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
static void *
@@ -2448,7 +2450,7 @@ static void *g_start(struct seq_file *m, loff_t *pos)
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
- if (!ftrace_graph_count && !*pos)
+ if (!ftrace_graph_filter_enabled && !*pos)
return (void *)1;
return __g_next(m, pos);
@@ -2494,6 +2496,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
+ ftrace_graph_filter_enabled = 0;
ftrace_graph_count = 0;
memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
}
@@ -2519,7 +2522,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
struct dyn_ftrace *rec;
struct ftrace_page *pg;
int search_len;
- int found = 0;
+ int fail = 1;
int type, not;
char *search;
bool exists;
@@ -2530,37 +2533,51 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
/* decode regex */
type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
- if (not)
- return -EINVAL;
+ if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+ return -EBUSY;
search_len = strlen(search);
mutex_lock(&ftrace_lock);
do_for_each_ftrace_rec(pg, rec) {
- if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
- break;
-
if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
continue;
if (ftrace_match_record(rec, search, search_len, type)) {
- /* ensure it is not already in the array */
+ /* if it is in the array */
exists = false;
- for (i = 0; i < *idx; i++)
+ for (i = 0; i < *idx; i++) {
if (array[i] == rec->ip) {
exists = true;
break;
}
- if (!exists)
- array[(*idx)++] = rec->ip;
- found = 1;
+ }
+
+ if (!not) {
+ fail = 0;
+ if (!exists) {
+ array[(*idx)++] = rec->ip;
+ if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+ goto out;
+ }
+ } else {
+ if (exists) {
+ array[i] = array[--(*idx)];
+ array[*idx] = 0;
+ fail = 0;
+ }
+ }
}
} while_for_each_ftrace_rec();
-
+out:
mutex_unlock(&ftrace_lock);
- return found ? 0 : -EINVAL;
+ if (fail)
+ return -EINVAL;
+
+ ftrace_graph_filter_enabled = 1;
+ return 0;
}
static ssize_t
@@ -2570,16 +2587,11 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
struct trace_parser parser;
ssize_t read, ret;
- if (!cnt || cnt < 0)
+ if (!cnt)
return 0;
mutex_lock(&graph_lock);
- if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
- ret = -EBUSY;
- goto out_unlock;
- }
-
if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
ret = -ENOMEM;
goto out_unlock;
@@ -3222,8 +3234,8 @@ free:
}
static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
- struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+ struct task_struct *prev, struct task_struct *next)
{
unsigned long long timestamp;
int index;
@@ -3277,7 +3289,7 @@ static int start_graph_tracing(void)
} while (ret == -EAGAIN);
if (!ret) {
- ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+ ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
if (ret)
pr_info("ftrace_graph: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
@@ -3349,11 +3361,11 @@ void unregister_ftrace_graph(void)
goto out;
ftrace_graph_active--;
- unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
ftrace_shutdown(FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
+ unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
out:
mutex_unlock(&ftrace_lock);
@@ -3364,6 +3376,7 @@ void ftrace_graph_init_task(struct task_struct *t)
{
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
+ t->curr_ret_stack = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
@@ -3373,7 +3386,6 @@ void ftrace_graph_init_task(struct task_struct *t)
GFP_KERNEL);
if (!ret_stack)
return;
- t->curr_ret_stack = -1;
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index a91da69f153..bbfc1bb1660 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -95,7 +95,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
trace_wake_up();
}
-static void kmemtrace_kmalloc(unsigned long call_site,
+static void kmemtrace_kmalloc(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -105,7 +106,8 @@ static void kmemtrace_kmalloc(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, -1);
}
-static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -115,7 +117,8 @@ static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, -1);
}
-static void kmemtrace_kmalloc_node(unsigned long call_site,
+static void kmemtrace_kmalloc_node(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -126,7 +129,8 @@ static void kmemtrace_kmalloc_node(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, node);
}
-static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc_node(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -137,12 +141,14 @@ static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, node);
}
-static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+static void
+kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr)
{
kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
}
-static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+static void kmemtrace_kmem_cache_free(void *ignore,
+ unsigned long call_site, const void *ptr)
{
kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
}
@@ -151,34 +157,34 @@ static int kmemtrace_start_probes(void)
{
int err;
- err = register_trace_kmalloc(kmemtrace_kmalloc);
+ err = register_trace_kmalloc(kmemtrace_kmalloc, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
if (err)
return err;
- err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
if (err)
return err;
- err = register_trace_kfree(kmemtrace_kfree);
+ err = register_trace_kfree(kmemtrace_kfree, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+ err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
return err;
}
static void kmemtrace_stop_probes(void)
{
- unregister_trace_kmalloc(kmemtrace_kmalloc);
- unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
- unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
- unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
- unregister_trace_kfree(kmemtrace_kfree);
- unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+ unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
+ unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
+ unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
+ unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
+ unregister_trace_kfree(kmemtrace_kfree, NULL);
+ unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
}
static int kmem_trace_init(struct trace_array *tr)
@@ -237,7 +243,8 @@ struct kmemtrace_user_event_alloc {
};
static enum print_line_t
-kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_alloc_entry *entry;
@@ -257,7 +264,8 @@ kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags)
+kmemtrace_print_free(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_free_entry *entry;
@@ -275,7 +283,8 @@ kmemtrace_print_free(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_alloc_entry *entry;
@@ -309,7 +318,8 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_free_entry *entry;
@@ -463,18 +473,26 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
}
}
-static struct trace_event kmem_trace_alloc = {
- .type = TRACE_KMEM_ALLOC,
+static struct trace_event_functions kmem_trace_alloc_funcs = {
.trace = kmemtrace_print_alloc,
.binary = kmemtrace_print_alloc_user,
};
-static struct trace_event kmem_trace_free = {
- .type = TRACE_KMEM_FREE,
+static struct trace_event kmem_trace_alloc = {
+ .type = TRACE_KMEM_ALLOC,
+ .funcs = &kmem_trace_alloc_funcs,
+};
+
+static struct trace_event_functions kmem_trace_free_funcs = {
.trace = kmemtrace_print_free,
.binary = kmemtrace_print_free_user,
};
+static struct trace_event kmem_trace_free = {
+ .type = TRACE_KMEM_FREE,
+ .funcs = &kmem_trace_free_funcs,
+};
+
static struct tracer kmem_tracer __read_mostly = {
.name = "kmemtrace",
.init = kmem_trace_init,
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index 9f4f565b01e..a22582a0616 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -9,7 +9,6 @@
#include <linux/workqueue.h>
#include <linux/sched.h>
#include <linux/module.h>
-#include <linux/slab.h>
#define CREATE_TRACE_POINTS
#include <trace/events/power.h>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index edefe3b2801..1da7b6ea8b8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,12 +14,14 @@
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/list.h>
#include <linux/cpu.h>
#include <linux/fs.h>
+#include <asm/local.h>
#include "trace.h"
/*
@@ -206,6 +208,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */
+#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+# define RB_FORCE_8BYTE_ALIGNMENT 0
+# define RB_ARCH_ALIGNMENT RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT 1
+# define RB_ARCH_ALIGNMENT 8U
+#endif
+
/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
@@ -309,6 +319,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
#define TS_MASK ((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST (~TS_MASK)
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS (1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED (1 << 30)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -328,6 +343,7 @@ struct buffer_page {
local_t write; /* index for next write */
unsigned read; /* index for next read */
local_t entries; /* entries on this page */
+ unsigned long real_end; /* real end of data */
struct buffer_data_page *page; /* Actual data page */
};
@@ -407,6 +423,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
(unsigned int)sizeof(field.commit),
(unsigned int)is_signed_type(long));
+ ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ 1,
+ (unsigned int)is_signed_type(long));
+
ret = trace_seq_printf(s, "\tfield: char data;\t"
"offset:%u;\tsize:%u;\tsigned:%u;\n",
(unsigned int)offsetof(typeof(field), data),
@@ -430,6 +452,8 @@ struct ring_buffer_per_cpu {
struct buffer_page *tail_page; /* write to tail */
struct buffer_page *commit_page; /* committed pages */
struct buffer_page *reader_page;
+ unsigned long lost_events;
+ unsigned long last_overrun;
local_t commit_overrun;
local_t overrun;
local_t entries;
@@ -464,6 +488,8 @@ struct ring_buffer_iter {
struct ring_buffer_per_cpu *cpu_buffer;
unsigned long head;
struct buffer_page *head_page;
+ struct buffer_page *cache_reader_page;
+ unsigned long cache_read;
u64 read_stamp;
};
@@ -1198,18 +1224,19 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
for (i = 0; i < nr_pages; i++) {
if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
- return;
+ goto out;
p = cpu_buffer->pages->next;
bpage = list_entry(p, struct buffer_page, list);
list_del_init(&bpage->list);
free_buffer_page(bpage);
}
if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
- return;
+ goto out;
rb_reset_cpu(cpu_buffer);
rb_check_pages(cpu_buffer);
+out:
spin_unlock_irq(&cpu_buffer->reader_lock);
}
@@ -1226,7 +1253,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
for (i = 0; i < nr_pages; i++) {
if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
- return;
+ goto out;
p = pages->next;
bpage = list_entry(p, struct buffer_page, list);
list_del_init(&bpage->list);
@@ -1235,6 +1262,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
rb_reset_cpu(cpu_buffer);
rb_check_pages(cpu_buffer);
+out:
spin_unlock_irq(&cpu_buffer->reader_lock);
}
@@ -1544,7 +1572,7 @@ rb_update_event(struct ring_buffer_event *event,
case 0:
length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA)
+ if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
event->array[0] = length;
else
event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
@@ -1719,11 +1747,11 @@ static unsigned rb_calculate_event_length(unsigned length)
if (!length)
length = 1;
- if (length > RB_MAX_SMALL_DATA)
+ if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
length += sizeof(event.array[0]);
length += RB_EVNT_HDR_SIZE;
- length = ALIGN(length, RB_ALIGNMENT);
+ length = ALIGN(length, RB_ARCH_ALIGNMENT);
return length;
}
@@ -1740,6 +1768,14 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* must fill the old tail_page with padding.
*/
if (tail >= BUF_PAGE_SIZE) {
+ /*
+ * If the page was filled, then we still need
+ * to update the real_end. Reset it to zero
+ * and the reader will ignore it.
+ */
+ if (tail == BUF_PAGE_SIZE)
+ tail_page->real_end = 0;
+
local_sub(length, &tail_page->write);
return;
}
@@ -1748,6 +1784,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
kmemcheck_annotate_bitfield(event, bitfield);
/*
+ * Save the original length to the meta data.
+ * This will be used by the reader to add lost event
+ * counter.
+ */
+ tail_page->real_end = tail;
+
+ /*
* If this event is bigger than the minimum size, then
* we need to be careful that we don't subtract the
* write counter enough to allow another writer to slip
@@ -1965,17 +2008,13 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
u64 *ts, u64 *delta)
{
struct ring_buffer_event *event;
- static int once;
int ret;
- if (unlikely(*delta > (1ULL << 59) && !once++)) {
- printk(KERN_WARNING "Delta way too big! %llu"
- " ts=%llu write stamp = %llu\n",
- (unsigned long long)*delta,
- (unsigned long long)*ts,
- (unsigned long long)cpu_buffer->write_stamp);
- WARN_ON(1);
- }
+ WARN_ONCE(*delta > (1ULL << 59),
+ KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+ (unsigned long long)*delta,
+ (unsigned long long)*ts,
+ (unsigned long long)cpu_buffer->write_stamp);
/*
* The delta is too big, we to add a
@@ -2230,12 +2269,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
if (ring_buffer_flags != RB_BUFFERS_ON)
return NULL;
- if (atomic_read(&buffer->record_disabled))
- return NULL;
-
/* If we are tracing schedule, we don't want to recurse */
resched = ftrace_preempt_disable();
+ if (atomic_read(&buffer->record_disabled))
+ goto out_nocheck;
+
if (trace_recursive_lock())
goto out_nocheck;
@@ -2467,11 +2506,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
if (ring_buffer_flags != RB_BUFFERS_ON)
return -EBUSY;
- if (atomic_read(&buffer->record_disabled))
- return -EBUSY;
-
resched = ftrace_preempt_disable();
+ if (atomic_read(&buffer->record_disabled))
+ goto out;
+
cpu = raw_smp_processor_id();
if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -2539,7 +2578,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
* @buffer: The ring buffer to enable writes
*
* Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
*/
void ring_buffer_record_enable(struct ring_buffer *buffer)
{
@@ -2575,7 +2614,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
* @cpu: The CPU to enable.
*
* Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
*/
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
{
@@ -2716,6 +2755,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
iter->read_stamp = cpu_buffer->read_stamp;
else
iter->read_stamp = iter->head_page->page->time_stamp;
+ iter->cache_reader_page = cpu_buffer->reader_page;
+ iter->cache_read = cpu_buffer->read;
}
/**
@@ -2822,6 +2863,7 @@ static struct buffer_page *
rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
struct buffer_page *reader = NULL;
+ unsigned long overwrite;
unsigned long flags;
int nr_loops = 0;
int ret;
@@ -2863,6 +2905,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
local_set(&cpu_buffer->reader_page->write, 0);
local_set(&cpu_buffer->reader_page->entries, 0);
local_set(&cpu_buffer->reader_page->page->commit, 0);
+ cpu_buffer->reader_page->real_end = 0;
spin:
/*
@@ -2883,6 +2926,18 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
/*
+ * We want to make sure we read the overruns after we set up our
+ * pointers to the next object. The writer side does a
+ * cmpxchg to cross pages which acts as the mb on the writer
+ * side. Note, the reader will constantly fail the swap
+ * while the writer is updating the pointers, so this
+ * guarantees that the overwrite recorded here is the one we
+ * want to compare with the last_overrun.
+ */
+ smp_mb();
+ overwrite = local_read(&(cpu_buffer->overrun));
+
+ /*
* Here's the tricky part.
*
* We need to move the pointer past the header page.
@@ -2913,6 +2968,11 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page = reader;
rb_reset_reader_page(cpu_buffer);
+ if (overwrite != cpu_buffer->last_overrun) {
+ cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+ cpu_buffer->last_overrun = overwrite;
+ }
+
goto again;
out:
@@ -2989,8 +3049,14 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
rb_advance_iter(iter);
}
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return cpu_buffer->lost_events;
+}
+
static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+ unsigned long *lost_events)
{
struct ring_buffer_event *event;
struct buffer_page *reader;
@@ -3042,6 +3108,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
cpu_buffer->cpu, ts);
}
+ if (lost_events)
+ *lost_events = rb_lost_events(cpu_buffer);
return event;
default:
@@ -3060,13 +3128,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_event *event;
int nr_loops = 0;
- if (ring_buffer_iter_empty(iter))
- return NULL;
-
cpu_buffer = iter->cpu_buffer;
buffer = cpu_buffer->buffer;
+ /*
+ * Check if someone performed a consuming read to
+ * the buffer. A consuming read invalidates the iterator
+ * and we need to reset the iterator in this case.
+ */
+ if (unlikely(iter->cache_read != cpu_buffer->read ||
+ iter->cache_reader_page != cpu_buffer->reader_page))
+ rb_iter_reset(iter);
+
again:
+ if (ring_buffer_iter_empty(iter))
+ return NULL;
+
/*
* We repeat when a timestamp is encountered.
* We can get multiple timestamps by nested interrupts or also
@@ -3081,6 +3158,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
if (rb_per_cpu_empty(cpu_buffer))
return NULL;
+ if (iter->head >= local_read(&iter->head_page->page->commit)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+
event = rb_iter_head_event(iter);
switch (event->type_len) {
@@ -3138,12 +3220,14 @@ static inline int rb_ok_to_lock(void)
* @buffer: The ring buffer to read
* @cpu: The cpu to peak at
* @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
*
* This will return the event that will be read next, but does
* not consume the data.
*/
struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+ unsigned long *lost_events)
{
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct ring_buffer_event *event;
@@ -3158,7 +3242,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
local_irq_save(flags);
if (dolock)
spin_lock(&cpu_buffer->reader_lock);
- event = rb_buffer_peek(cpu_buffer, ts);
+ event = rb_buffer_peek(cpu_buffer, ts, lost_events);
if (event && event->type_len == RINGBUF_TYPE_PADDING)
rb_advance_reader(cpu_buffer);
if (dolock)
@@ -3200,13 +3284,17 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
/**
* ring_buffer_consume - return an event and consume it
* @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
*
* Returns the next event in the ring buffer, and that event is consumed.
* Meaning, that sequential reads will keep returning a different event,
* and eventually empty the ring buffer if the producer is slower.
*/
struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+ unsigned long *lost_events)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event = NULL;
@@ -3227,9 +3315,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
if (dolock)
spin_lock(&cpu_buffer->reader_lock);
- event = rb_buffer_peek(cpu_buffer, ts);
- if (event)
+ event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+ if (event) {
+ cpu_buffer->lost_events = 0;
rb_advance_reader(cpu_buffer);
+ }
if (dolock)
spin_unlock(&cpu_buffer->reader_lock);
@@ -3246,23 +3336,30 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
EXPORT_SYMBOL_GPL(ring_buffer_consume);
/**
- * ring_buffer_read_start - start a non consuming read of the buffer
+ * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
* @buffer: The ring buffer to read from
* @cpu: The cpu buffer to iterate over
*
- * This starts up an iteration through the buffer. It also disables
- * the recording to the buffer until the reading is finished.
- * This prevents the reading from being corrupted. This is not
- * a consuming read, so a producer is not expected.
+ * This performs the initial preparations necessary to iterate
+ * through the buffer. Memory is allocated, buffer recording
+ * is disabled, and the iterator pointer is returned to the caller.
*
- * Must be paired with ring_buffer_finish.
+ * Disabling buffer recordng prevents the reading from being
+ * corrupted. This is not a consuming read, so a producer is not
+ * expected.
+ *
+ * After a sequence of ring_buffer_read_prepare calls, the user is
+ * expected to make at least one call to ring_buffer_prepare_sync.
+ * Afterwards, ring_buffer_read_start is invoked to get things going
+ * for real.
+ *
+ * This overall must be paired with ring_buffer_finish.
*/
struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_iter *iter;
- unsigned long flags;
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
@@ -3276,15 +3373,52 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
iter->cpu_buffer = cpu_buffer;
atomic_inc(&cpu_buffer->record_disabled);
+
+ return iter;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
+
+/**
+ * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
+ *
+ * All previously invoked ring_buffer_read_prepare calls to prepare
+ * iterators will be synchronized. Afterwards, read_buffer_read_start
+ * calls on those iterators are allowed.
+ */
+void
+ring_buffer_read_prepare_sync(void)
+{
synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @iter: The iterator returned by ring_buffer_read_prepare
+ *
+ * This finalizes the startup of an iteration through the buffer.
+ * The iterator comes from a call to ring_buffer_read_prepare and
+ * an intervening ring_buffer_read_prepare_sync must have been
+ * performed.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+void
+ring_buffer_read_start(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+
+ if (!iter)
+ return;
+
+ cpu_buffer = iter->cpu_buffer;
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
arch_spin_lock(&cpu_buffer->lock);
rb_iter_reset(iter);
arch_spin_unlock(&cpu_buffer->lock);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
- return iter;
}
EXPORT_SYMBOL_GPL(ring_buffer_read_start);
@@ -3378,6 +3512,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->write_stamp = 0;
cpu_buffer->read_stamp = 0;
+ cpu_buffer->lost_events = 0;
+ cpu_buffer->last_overrun = 0;
+
rb_head_page_activate(cpu_buffer);
}
@@ -3653,6 +3790,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
struct ring_buffer_event *event;
struct buffer_data_page *bpage;
struct buffer_page *reader;
+ unsigned long missed_events;
unsigned long flags;
unsigned int commit;
unsigned int read;
@@ -3689,6 +3827,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
read = reader->read;
commit = rb_page_commit(reader);
+ /* Check if any events were dropped */
+ missed_events = cpu_buffer->lost_events;
+
/*
* If this page has been partially read or
* if len is not big enough to read the rest of the page or
@@ -3749,9 +3890,42 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
local_set(&reader->entries, 0);
reader->read = 0;
*data_page = bpage;
+
+ /*
+ * Use the real_end for the data size,
+ * This gives us a chance to store the lost events
+ * on the page.
+ */
+ if (reader->real_end)
+ local_set(&bpage->commit, reader->real_end);
}
ret = read;
+ cpu_buffer->lost_events = 0;
+
+ commit = local_read(&bpage->commit);
+ /*
+ * Set a flag in the commit field if we lost events
+ */
+ if (missed_events) {
+ /* If there is room at the end of the page to save the
+ * missed events, then record it there.
+ */
+ if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+ memcpy(&bpage->data[commit], &missed_events,
+ sizeof(missed_events));
+ local_add(RB_MISSED_STORED, &bpage->commit);
+ commit += sizeof(missed_events);
+ }
+ local_add(RB_MISSED_EVENTS, &bpage->commit);
+ }
+
+ /*
+ * This page may be off to user land. Zero it out here.
+ */
+ if (commit < BUF_PAGE_SIZE)
+ memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+
out_unlock:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index b2477caf09c..302f8a61463 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -8,6 +8,7 @@
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/time.h>
+#include <asm/local.h>
struct rb_page {
u64 ts;
@@ -80,7 +81,7 @@ static enum event_status read_event(int cpu)
int *entry;
u64 ts;
- event = ring_buffer_consume(buffer, cpu, &ts);
+ event = ring_buffer_consume(buffer, cpu, &ts, NULL);
if (!event)
return EVENT_DROPPED;
@@ -112,7 +113,8 @@ static enum event_status read_page(int cpu)
ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
if (ret >= 0) {
rpage = bpage;
- commit = local_read(&rpage->commit);
+ /* The commit may have missed event flags set, clear them */
+ commit = local_read(&rpage->commit) & 0xfffff;
for (i = 0; i < commit && !kill_test; i += inc) {
if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f2cb9..086d3631680 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -32,10 +32,11 @@
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
-#include <linux/gfp.h>
#include <linux/fs.h>
#include "trace.h"
@@ -91,20 +92,17 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
{
preempt_disable();
- __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_inc(ftrace_cpu_disabled);
}
static inline void ftrace_enable_cpu(void)
{
- __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_dec(ftrace_cpu_disabled);
preempt_enable();
}
static cpumask_var_t __read_mostly tracing_buffer_mask;
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t tracing_reader_cpumask;
-
#define for_each_tracing_cpu(cpu) \
for_each_cpu(cpu, tracing_buffer_mask)
@@ -119,9 +117,12 @@ static cpumask_var_t tracing_reader_cpumask;
*
* It is default off, but you can enable it with either specifying
* "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
*/
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
static int tracing_set_tracer(const char *buf);
@@ -141,8 +142,17 @@ __setup("ftrace=", set_cmdline_ftrace);
static int __init set_ftrace_dump_on_oops(char *str)
{
- ftrace_dump_on_oops = 1;
- return 1;
+ if (*str++ != '=' || !*str) {
+ ftrace_dump_on_oops = DUMP_ALL;
+ return 1;
+ }
+
+ if (!strcmp("orig_cpu", str)) {
+ ftrace_dump_on_oops = DUMP_ORIG;
+ return 1;
+ }
+
+ return 0;
}
__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
@@ -243,12 +253,91 @@ static struct tracer *current_trace __read_mostly;
/*
* trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
*/
static DEFINE_MUTEX(trace_types_lock);
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ * A) the page of the consumed events may become a normal page
+ * (not reader page) in ring buffer, and this page will be rewrited
+ * by events producer.
+ * B) The page of the consumed events may become a page for splice_read,
+ * and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ /* gain it for accessing the whole ring buffer. */
+ down_write(&all_cpu_access_lock);
+ } else {
+ /* gain it for accessing a cpu ring buffer. */
+
+ /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+ down_read(&all_cpu_access_lock);
+
+ /* Secondly block other access to this @cpu ring buffer. */
+ mutex_lock(&per_cpu(cpu_access_lock, cpu));
+ }
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ up_write(&all_cpu_access_lock);
+ } else {
+ mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+ up_read(&all_cpu_access_lock);
+ }
+}
+
+static inline void trace_access_lock_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ (void)cpu;
+ mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ (void)cpu;
+ mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
/* trace_wait is a waitqueue for tasks blocked on trace_poll */
static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
@@ -297,6 +386,21 @@ static int __init set_buf_size(char *str)
}
__setup("trace_buf_size=", set_buf_size);
+static int __init set_tracing_thresh(char *str)
+{
+ unsigned long threshhold;
+ int ret;
+
+ if (!str)
+ return 0;
+ ret = strict_strtoul(str, 0, &threshhold);
+ if (ret < 0)
+ return 0;
+ tracing_thresh = threshhold * 1000;
+ return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
unsigned long nsecs_to_usecs(unsigned long nsecs)
{
return nsecs / 1000;
@@ -502,9 +606,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
static arch_spinlock_t ftrace_max_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+unsigned long __read_mostly tracing_thresh;
+
#ifdef CONFIG_TRACER_MAX_TRACE
unsigned long __read_mostly tracing_max_latency;
-unsigned long __read_mostly tracing_thresh;
/*
* Copy the new maximum trace into the separate maximum-trace
@@ -515,7 +620,7 @@ static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
struct trace_array_cpu *data = tr->data[cpu];
- struct trace_array_cpu *max_data = tr->data[cpu];
+ struct trace_array_cpu *max_data;
max_tr.cpu = cpu;
max_tr.time_start = data->preempt_timestamp;
@@ -525,7 +630,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
max_data->critical_start = data->critical_start;
max_data->critical_end = data->critical_end;
- memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+ memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
max_data->pid = tsk->pid;
max_data->uid = task_uid(tsk);
max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
@@ -747,10 +852,10 @@ out:
mutex_unlock(&trace_types_lock);
}
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
{
ftrace_disable_cpu();
- ring_buffer_reset_cpu(tr->buffer, cpu);
+ ring_buffer_reset_cpu(buffer, cpu);
ftrace_enable_cpu();
}
@@ -762,7 +867,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
/* Make sure all commits have finished */
synchronize_sched();
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
@@ -780,7 +885,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
tr->time_start = ftrace_now(tr->cpu);
for_each_online_cpu(cpu)
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
@@ -857,6 +962,8 @@ void tracing_start(void)
goto out;
}
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
buffer = global_trace.buffer;
if (buffer)
@@ -866,6 +973,8 @@ void tracing_start(void)
if (buffer)
ring_buffer_record_enable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
ftrace_start();
out:
spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -887,6 +996,9 @@ void tracing_stop(void)
if (trace_stop_count++)
goto out;
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
+
buffer = global_trace.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
@@ -895,6 +1007,8 @@ void tracing_stop(void)
if (buffer)
ring_buffer_record_disable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
out:
spin_unlock_irqrestore(&tracing_start_lock, flags);
}
@@ -951,6 +1065,11 @@ void trace_find_cmdline(int pid, char comm[])
return;
}
+ if (WARN_ON_ONCE(pid < 0)) {
+ strcpy(comm, "<XXX>");
+ return;
+ }
+
if (pid > PID_MAX_DEFAULT) {
strcpy(comm, "<...>");
return;
@@ -1084,7 +1203,7 @@ trace_function(struct trace_array *tr,
struct ftrace_entry *entry;
/* If we are reading the ring buffer, don't trace */
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -1177,6 +1296,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
+ /*
+ * NMIs can not handle page faults, even with fix ups.
+ * The save user stack can (and often does) fault.
+ */
+ if (unlikely(in_nmi()))
+ return;
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
@@ -1315,8 +1441,10 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
entry->fmt = fmt;
memcpy(entry->buf, trace_buf, sizeof(u32) * len);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, flags, 6, pc);
+ }
out_unlock:
arch_spin_unlock(&trace_buf_lock);
@@ -1389,8 +1517,10 @@ int trace_array_vprintk(struct trace_array *tr,
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = '\0';
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, irq_flags, 6, pc);
+ }
out_unlock:
arch_spin_unlock(&trace_buf_lock);
@@ -1427,7 +1557,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
}
static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+ unsigned long *lost_events)
{
struct ring_buffer_event *event;
struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1438,7 +1569,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
if (buf_iter)
event = ring_buffer_iter_peek(buf_iter, ts);
else
- event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+ event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+ lost_events);
ftrace_enable_cpu();
@@ -1446,10 +1578,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
}
static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+ unsigned long *missing_events, u64 *ent_ts)
{
struct ring_buffer *buffer = iter->tr->buffer;
struct trace_entry *ent, *next = NULL;
+ unsigned long lost_events = 0, next_lost = 0;
int cpu_file = iter->cpu_file;
u64 next_ts = 0, ts;
int next_cpu = -1;
@@ -1462,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
if (cpu_file > TRACE_PIPE_ALL_CPU) {
if (ring_buffer_empty_cpu(buffer, cpu_file))
return NULL;
- ent = peek_next_entry(iter, cpu_file, ent_ts);
+ ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
if (ent_cpu)
*ent_cpu = cpu_file;
@@ -1474,7 +1608,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
if (ring_buffer_empty_cpu(buffer, cpu))
continue;
- ent = peek_next_entry(iter, cpu, &ts);
+ ent = peek_next_entry(iter, cpu, &ts, &lost_events);
/*
* Pick the entry with the smallest timestamp:
@@ -1483,6 +1617,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
next = ent;
next_cpu = cpu;
next_ts = ts;
+ next_lost = lost_events;
}
}
@@ -1492,6 +1627,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
if (ent_ts)
*ent_ts = next_ts;
+ if (missing_events)
+ *missing_events = next_lost;
+
return next;
}
@@ -1499,13 +1637,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
int *ent_cpu, u64 *ent_ts)
{
- return __find_next_entry(iter, ent_cpu, ent_ts);
+ return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
}
/* Find the next real entry, and increment the iterator to the next entry */
static void *find_next_entry_inc(struct trace_iterator *iter)
{
- iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+ iter->ent = __find_next_entry(iter, &iter->cpu,
+ &iter->lost_events, &iter->ts);
if (iter->ent)
trace_iterator_increment(iter);
@@ -1517,7 +1656,8 @@ static void trace_consume(struct trace_iterator *iter)
{
/* Don't allow ftrace to trace into the ring buffers */
ftrace_disable_cpu();
- ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+ &iter->lost_events);
ftrace_enable_cpu();
}
@@ -1580,12 +1720,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
}
/*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
* The current tracer is copied to avoid a global locking
* all around.
*/
@@ -1623,6 +1757,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
ftrace_enable_cpu();
+ iter->leftover = 0;
for (p = iter; p && l < *pos; p = s_next(m, p, &l))
;
@@ -1640,12 +1775,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
}
trace_event_read_lock();
+ trace_access_lock(cpu_file);
return p;
}
static void s_stop(struct seq_file *m, void *p)
{
+ struct trace_iterator *iter = m->private;
+
atomic_dec(&trace_record_cmdline_disabled);
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
}
@@ -1669,7 +1808,7 @@ static void print_func_help_header(struct seq_file *m)
}
-static void
+void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1797,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
}
if (event)
- return event->trace(iter, sym_flags);
+ return event->funcs->trace(iter, sym_flags, event);
if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
goto partial;
@@ -1823,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
event = ftrace_find_event(entry->type);
if (event)
- return event->raw(iter, 0);
+ return event->funcs->raw(iter, 0, event);
if (!trace_seq_printf(s, "%d ?\n", entry->type))
goto partial;
@@ -1850,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
event = ftrace_find_event(entry->type);
if (event) {
- enum print_line_t ret = event->hex(iter, 0);
+ enum print_line_t ret = event->funcs->hex(iter, 0, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
@@ -1875,10 +2014,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
}
event = ftrace_find_event(entry->type);
- return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+ return event ? event->funcs->binary(iter, 0, event) :
+ TRACE_TYPE_HANDLED;
}
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
{
int cpu;
@@ -1913,6 +2053,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
{
enum print_line_t ret;
+ if (iter->lost_events)
+ trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+ iter->cpu, iter->lost_events);
+
if (iter->trace && iter->trace->print_line) {
ret = iter->trace->print_line(iter);
if (ret != TRACE_TYPE_UNHANDLED)
@@ -1941,6 +2085,23 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
return print_trace_fmt(iter);
}
+void trace_default_header(struct seq_file *m)
+{
+ struct trace_iterator *iter = m->private;
+
+ if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+ /* print nothing if the buffers are empty */
+ if (trace_empty(iter))
+ return;
+ print_trace_header(m, iter);
+ if (!(trace_flags & TRACE_ITER_VERBOSE))
+ print_lat_help_header(m);
+ } else {
+ if (!(trace_flags & TRACE_ITER_VERBOSE))
+ print_func_help_header(m);
+ }
+}
+
static int s_show(struct seq_file *m, void *v)
{
struct trace_iterator *iter = v;
@@ -1953,17 +2114,9 @@ static int s_show(struct seq_file *m, void *v)
}
if (iter->trace && iter->trace->print_header)
iter->trace->print_header(m);
- else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
- /* print nothing if the buffers are empty */
- if (trace_empty(iter))
- return 0;
- print_trace_header(m, iter);
- if (!(trace_flags & TRACE_ITER_VERBOSE))
- print_lat_help_header(m);
- } else {
- if (!(trace_flags & TRACE_ITER_VERBOSE))
- print_func_help_header(m);
- }
+ else
+ trace_default_header(m);
+
} else if (iter->leftover) {
/*
* If we filled the seq_file buffer earlier, we
@@ -2049,15 +2202,20 @@ __tracing_open(struct inode *inode, struct file *file)
if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
for_each_tracing_cpu(cpu) {
-
iter->buffer_iter[cpu] =
- ring_buffer_read_start(iter->tr->buffer, cpu);
+ ring_buffer_read_prepare(iter->tr->buffer, cpu);
+ }
+ ring_buffer_read_prepare_sync();
+ for_each_tracing_cpu(cpu) {
+ ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
}
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_start(iter->tr->buffer, cpu);
+ ring_buffer_read_prepare(iter->tr->buffer, cpu);
+ ring_buffer_read_prepare_sync();
+ ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
}
@@ -2836,22 +2994,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
mutex_lock(&trace_types_lock);
- /* We only allow one reader per cpu */
- if (cpu_file == TRACE_PIPE_ALL_CPU) {
- if (!cpumask_empty(tracing_reader_cpumask)) {
- ret = -EBUSY;
- goto out;
- }
- cpumask_setall(tracing_reader_cpumask);
- } else {
- if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
- cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
- else {
- ret = -EBUSY;
- goto out;
- }
- }
-
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
@@ -2907,12 +3049,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
mutex_lock(&trace_types_lock);
- if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
- cpumask_clear(tracing_reader_cpumask);
- else
- cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
-
-
if (iter->trace->pipe_close)
iter->trace->pipe_close(iter);
@@ -3074,6 +3210,7 @@ waitagain:
iter->pos = -1;
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
while (find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
int len = iter->seq.len;
@@ -3090,6 +3227,7 @@ waitagain:
if (iter->seq.len >= cnt)
break;
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
/* Now copy what we have to the user */
@@ -3172,12 +3310,12 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
size_t len,
unsigned int flags)
{
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct trace_iterator *iter = filp->private_data;
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
.flags = flags,
.ops = &tracing_pipe_buf_ops,
@@ -3188,6 +3326,9 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
size_t rem;
unsigned int i;
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
/* copy the tracer to avoid using a global lock all around */
mutex_lock(&trace_types_lock);
if (unlikely(old_tracer != current_trace && current_trace)) {
@@ -3215,40 +3356,44 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
}
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
/* Fill as many pages as possible. */
- for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
- pages[i] = alloc_page(GFP_KERNEL);
- if (!pages[i])
+ for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+ spd.pages[i] = alloc_page(GFP_KERNEL);
+ if (!spd.pages[i])
break;
rem = tracing_fill_pipe_page(rem, iter);
/* Copy the data into the page, so we can start over. */
ret = trace_seq_to_buffer(&iter->seq,
- page_address(pages[i]),
+ page_address(spd.pages[i]),
iter->seq.len);
if (ret < 0) {
- __free_page(pages[i]);
+ __free_page(spd.pages[i]);
break;
}
- partial[i].offset = 0;
- partial[i].len = iter->seq.len;
+ spd.partial[i].offset = 0;
+ spd.partial[i].len = iter->seq.len;
trace_seq_init(&iter->seq);
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
mutex_unlock(&iter->mutex);
spd.nr_pages = i;
- return splice_to_pipe(pipe, &spd);
+ ret = splice_to_pipe(pipe, &spd);
+out:
+ splice_shrink_spd(pipe, &spd);
+ return ret;
out_err:
mutex_unlock(&iter->mutex);
-
- return ret;
+ goto out;
}
static ssize_t
@@ -3521,7 +3666,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct ftrace_buffer_info *info = filp->private_data;
- unsigned int pos;
ssize_t ret;
size_t size;
@@ -3539,18 +3683,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
info->read = 0;
+ trace_access_lock(info->cpu);
ret = ring_buffer_read_page(info->tr->buffer,
&info->spare,
count,
info->cpu, 0);
+ trace_access_unlock(info->cpu);
if (ret < 0)
return 0;
- pos = ring_buffer_page_len(info->spare);
-
- if (pos < PAGE_SIZE)
- memset(info->spare + pos, 0, PAGE_SIZE - pos);
-
read:
size = PAGE_SIZE - info->read;
if (size > count)
@@ -3645,11 +3786,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
unsigned int flags)
{
struct ftrace_buffer_info *info = file->private_data;
- struct partial_page partial[PIPE_BUFFERS];
- struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
@@ -3658,21 +3799,28 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
int entries, size, i;
size_t ret;
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
if (*ppos & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: previous read must page-align\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
if (len & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
- if (len < PAGE_SIZE)
- return -EINVAL;
+ if (len < PAGE_SIZE) {
+ ret = -EINVAL;
+ goto out;
+ }
len &= PAGE_MASK;
}
+ trace_access_lock(info->cpu);
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
- for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+ for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
int r;
@@ -3717,6 +3865,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
}
+ trace_access_unlock(info->cpu);
spd.nr_pages = i;
/* did we read anything? */
@@ -3726,11 +3875,12 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
else
ret = 0;
/* TODO: block */
- return ret;
+ goto out;
}
ret = splice_to_pipe(pipe, &spd);
-
+ splice_shrink_spd(pipe, &spd);
+out:
return ret;
}
@@ -4153,6 +4303,8 @@ static __init int tracer_init_debugfs(void)
struct dentry *d_tracer;
int cpu;
+ trace_access_lock_init();
+
d_tracer = tracing_init_dentry();
trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4176,10 +4328,10 @@ static __init int tracer_init_debugfs(void)
#ifdef CONFIG_TRACER_MAX_TRACE
trace_create_file("tracing_max_latency", 0644, d_tracer,
&tracing_max_latency, &tracing_max_lat_fops);
+#endif
trace_create_file("tracing_thresh", 0644, d_tracer,
&tracing_thresh, &tracing_max_lat_fops);
-#endif
trace_create_file("README", 0444, d_tracer,
NULL, &tracing_readme_fops);
@@ -4219,7 +4371,7 @@ static int trace_panic_handler(struct notifier_block *this,
unsigned long event, void *unused)
{
if (ftrace_dump_on_oops)
- ftrace_dump();
+ ftrace_dump(ftrace_dump_on_oops);
return NOTIFY_OK;
}
@@ -4236,7 +4388,7 @@ static int trace_die_handler(struct notifier_block *self,
switch (val) {
case DIE_OOPS:
if (ftrace_dump_on_oops)
- ftrace_dump();
+ ftrace_dump(ftrace_dump_on_oops);
break;
default:
break;
@@ -4277,7 +4429,8 @@ trace_printk_seq(struct trace_seq *s)
trace_seq_init(s);
}
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
{
static arch_spinlock_t ftrace_dump_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -4310,12 +4463,25 @@ static void __ftrace_dump(bool disable_tracing)
/* don't look at user memory in panic mode */
trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
- printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
/* Simulate the iterator */
iter.tr = &global_trace;
iter.trace = current_trace;
- iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+ switch (oops_dump_mode) {
+ case DUMP_ALL:
+ iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ break;
+ case DUMP_ORIG:
+ iter.cpu_file = raw_smp_processor_id();
+ break;
+ case DUMP_NONE:
+ goto out_enable;
+ default:
+ printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+ iter.cpu_file = TRACE_PIPE_ALL_CPU;
+ }
+
+ printk(KERN_TRACE "Dumping ftrace buffer:\n");
/*
* We need to stop all tracing on all CPUS to read the
@@ -4354,6 +4520,7 @@ static void __ftrace_dump(bool disable_tracing)
else
printk(KERN_TRACE "---------------------------------\n");
+ out_enable:
/* Re-enable tracing if requested */
if (!disable_tracing) {
trace_flags |= old_userobj;
@@ -4370,9 +4537,9 @@ static void __ftrace_dump(bool disable_tracing)
}
/* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
{
- __ftrace_dump(true);
+ __ftrace_dump(true, oops_dump_mode);
}
__init static int tracer_alloc_buffers(void)
@@ -4387,9 +4554,6 @@ __init static int tracer_alloc_buffers(void)
if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
goto out_free_buffer_mask;
- if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
- goto out_free_tracing_cpumask;
-
/* To save memory, keep the ring buffer size to its minimum */
if (ring_buffer_expanded)
ring_buf_size = trace_buf_size;
@@ -4447,8 +4611,6 @@ __init static int tracer_alloc_buffers(void)
return 0;
out_free_cpumask:
- free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
free_cpumask_var(tracing_cpumask);
out_free_buffer_mask:
free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4df6a77eb19..2cd96399463 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -34,7 +34,6 @@ enum trace_type {
TRACE_GRAPH_RET,
TRACE_GRAPH_ENT,
TRACE_USER_STACK,
- TRACE_HW_BRANCHES,
TRACE_KMEM_ALLOC,
TRACE_KMEM_FREE,
TRACE_BLK,
@@ -103,29 +102,17 @@ struct syscall_trace_exit {
long ret;
};
-struct kprobe_trace_entry {
+struct kprobe_trace_entry_head {
struct trace_entry ent;
unsigned long ip;
- int nargs;
- unsigned long args[];
};
-#define SIZEOF_KPROBE_TRACE_ENTRY(n) \
- (offsetof(struct kprobe_trace_entry, args) + \
- (sizeof(unsigned long) * (n)))
-
-struct kretprobe_trace_entry {
+struct kretprobe_trace_entry_head {
struct trace_entry ent;
unsigned long func;
unsigned long ret_ip;
- int nargs;
- unsigned long args[];
};
-#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \
- (offsetof(struct kretprobe_trace_entry, args) + \
- (sizeof(unsigned long) * (n)))
-
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
@@ -229,7 +216,6 @@ extern void __ftrace_bad_type(void);
TRACE_GRAPH_ENT); \
IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \
TRACE_GRAPH_RET); \
- IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \
TRACE_KMEM_ALLOC); \
IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
@@ -378,6 +364,9 @@ void trace_function(struct trace_array *tr,
unsigned long ip,
unsigned long parent_ip,
unsigned long flags, int pc);
+void trace_default_header(struct seq_file *m);
+void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
+int trace_empty(struct trace_iterator *iter);
void trace_graph_return(struct ftrace_graph_ret *trace);
int trace_graph_entry(struct ftrace_graph_ent *trace);
@@ -396,9 +385,10 @@ extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
+extern unsigned long tracing_thresh;
+
#ifdef CONFIG_TRACER_MAX_TRACE
extern unsigned long tracing_max_latency;
-extern unsigned long tracing_thresh;
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
void update_max_tr_single(struct trace_array *tr,
@@ -415,12 +405,12 @@ void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc);
#else
-static inline void ftrace_trace_stack(struct trace_array *tr,
+static inline void ftrace_trace_stack(struct ring_buffer *buffer,
unsigned long flags, int skip, int pc)
{
}
-static inline void ftrace_trace_userstack(struct trace_array *tr,
+static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
unsigned long flags, int pc)
{
}
@@ -466,8 +456,6 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
struct trace_array *tr);
extern int trace_selftest_startup_branch(struct tracer *trace,
struct trace_array *tr);
-extern int trace_selftest_startup_hw_branches(struct tracer *trace,
- struct trace_array *tr);
extern int trace_selftest_startup_ksym(struct tracer *trace,
struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
@@ -490,13 +478,34 @@ extern int trace_clock_id;
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN 0x1
+#define TRACE_GRAPH_PRINT_CPU 0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD 0x4
+#define TRACE_GRAPH_PRINT_PROC 0x8
+#define TRACE_GRAPH_PRINT_DURATION 0x10
+#define TRACE_GRAPH_PRINT_ABS_TIME 0x20
+
+extern enum print_line_t
+print_graph_function_flags(struct trace_iterator *iter, u32 flags);
+extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
extern enum print_line_t
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
+extern void graph_trace_open(struct trace_iterator *iter);
+extern void graph_trace_close(struct trace_iterator *iter);
+extern int __trace_graph_entry(struct trace_array *tr,
+ struct ftrace_graph_ent *trace,
+ unsigned long flags, int pc);
+extern void __trace_graph_return(struct trace_array *tr,
+ struct ftrace_graph_ret *trace,
+ unsigned long flags, int pc);
+
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS 32
+extern int ftrace_graph_filter_enabled;
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
@@ -504,7 +513,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
{
int i;
- if (!ftrace_graph_count || test_tsk_trace_graph(current))
+ if (!ftrace_graph_filter_enabled)
return 1;
for (i = 0; i < ftrace_graph_count; i++) {
@@ -522,7 +531,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
#endif /* CONFIG_DYNAMIC_FTRACE */
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
{
return TRACE_TYPE_UNHANDLED;
}
@@ -549,7 +558,7 @@ static inline int ftrace_trace_task(struct task_struct *task)
* struct trace_parser - servers for reading the user input separated by spaces
* @cont: set if the input is not complete - no final space char was found
* @buffer: holds the parsed user input
- * @idx: user input lenght
+ * @idx: user input length
* @size: buffer size
*/
struct trace_parser {
@@ -769,12 +778,15 @@ extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call);
+
static inline int
filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
{
- if (unlikely(call->filter_active) &&
+ if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
!filter_match_preds(call->filter, rec)) {
ring_buffer_discard_commit(buffer, event);
return 1;
@@ -791,7 +803,8 @@ extern const char *__stop___trace_bprintk_fmt[];
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
- extern struct ftrace_event_call event_##call;
+ extern struct ftrace_event_call \
+ __attribute__((__aligned__(4))) event_##call;
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4a194f08f88..8d3538b4ea5 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -143,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr)
}
static enum print_line_t trace_branch_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct trace_branch *field;
@@ -167,9 +167,13 @@ static void branch_print_header(struct seq_file *s)
" |\n");
}
+static struct trace_event_functions trace_branch_funcs = {
+ .trace = trace_branch_print,
+};
+
static struct trace_event trace_branch_event = {
.type = TRACE_BRANCH,
- .trace = trace_branch_print,
+ .funcs = &trace_branch_funcs,
};
static struct tracer branch_trace __read_mostly =
@@ -307,8 +311,23 @@ static int annotated_branch_stat_cmp(void *p1, void *p2)
return -1;
if (percent_a > percent_b)
return 1;
- else
- return 0;
+
+ if (a->incorrect < b->incorrect)
+ return -1;
+ if (a->incorrect > b->incorrect)
+ return 1;
+
+ /*
+ * Since the above shows worse (incorrect) cases
+ * first, we continue that by showing best (correct)
+ * cases last.
+ */
+ if (a->correct > b->correct)
+ return -1;
+ if (a->correct < b->correct)
+ return 1;
+
+ return 0;
}
static struct tracer_stat annotated_branch_stats = {
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 84a3a7ba072..9d589d8dcd1 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -13,6 +13,7 @@
* Tracer plugins will chose a default from these clocks.
*/
#include <linux/spinlock.h>
+#include <linux/irqflags.h>
#include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/percpu.h>
@@ -83,7 +84,7 @@ u64 notrace trace_clock_global(void)
int this_cpu;
u64 now;
- raw_local_irq_save(flags);
+ local_irq_save(flags);
this_cpu = raw_smp_processor_id();
now = cpu_clock(this_cpu);
@@ -109,7 +110,7 @@ u64 notrace trace_clock_global(void)
arch_spin_unlock(&trace_clock_struct.lock);
out:
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
return now;
}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c16a08f399d..dc008c1240d 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -318,18 +318,6 @@ FTRACE_ENTRY(branch, trace_branch,
__entry->func, __entry->file, __entry->correct)
);
-FTRACE_ENTRY(hw_branch, hw_branch_entry,
-
- TRACE_HW_BRANCHES,
-
- F_STRUCT(
- __field( u64, from )
- __field( u64, to )
- ),
-
- F_printk("from: %llx to: %llx", __entry->from, __entry->to)
-);
-
FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
TRACE_KMEM_ALLOC,
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
new file mode 100644
index 00000000000..cb6f365016e
--- /dev/null
+++ b/kernel/trace/trace_event_perf.c
@@ -0,0 +1,184 @@
+/*
+ * trace event based perf event profiling/tracing
+ *
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include "trace.h"
+
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
+
+static char *perf_trace_buf[4];
+
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+ perf_trace_t;
+
+/* Count the events in use (per event id, not per instance) */
+static int total_ref_count;
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
+{
+ struct hlist_head *list;
+ int ret = -ENOMEM;
+ int cpu;
+
+ p_event->tp_event = tp_event;
+ if (tp_event->perf_refcount++ > 0)
+ return 0;
+
+ list = alloc_percpu(struct hlist_head);
+ if (!list)
+ goto fail;
+
+ for_each_possible_cpu(cpu)
+ INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
+
+ tp_event->perf_events = list;
+
+ if (!total_ref_count) {
+ char *buf;
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ buf = (char *)alloc_percpu(perf_trace_t);
+ if (!buf)
+ goto fail;
+
+ perf_trace_buf[i] = buf;
+ }
+ }
+
+ if (tp_event->class->reg)
+ ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+ else
+ ret = tracepoint_probe_register(tp_event->name,
+ tp_event->class->perf_probe,
+ tp_event);
+
+ if (ret)
+ goto fail;
+
+ total_ref_count++;
+ return 0;
+
+fail:
+ if (!total_ref_count) {
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ free_percpu(perf_trace_buf[i]);
+ perf_trace_buf[i] = NULL;
+ }
+ }
+
+ if (!--tp_event->perf_refcount) {
+ free_percpu(tp_event->perf_events);
+ tp_event->perf_events = NULL;
+ }
+
+ return ret;
+}
+
+int perf_trace_init(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event;
+ int event_id = p_event->attr.config;
+ int ret = -EINVAL;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(tp_event, &ftrace_events, list) {
+ if (tp_event->event.type == event_id &&
+ tp_event->class && tp_event->class->perf_probe &&
+ try_module_get(tp_event->mod)) {
+ ret = perf_trace_event_init(tp_event, p_event);
+ break;
+ }
+ }
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+int perf_trace_enable(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ struct hlist_head *list;
+
+ list = tp_event->perf_events;
+ if (WARN_ON_ONCE(!list))
+ return -EINVAL;
+
+ list = per_cpu_ptr(list, smp_processor_id());
+ hlist_add_head_rcu(&p_event->hlist_entry, list);
+
+ return 0;
+}
+
+void perf_trace_disable(struct perf_event *p_event)
+{
+ hlist_del_rcu(&p_event->hlist_entry);
+}
+
+void perf_trace_destroy(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ int i;
+
+ if (--tp_event->perf_refcount > 0)
+ return;
+
+ if (tp_event->class->reg)
+ tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
+ else
+ tracepoint_probe_unregister(tp_event->name,
+ tp_event->class->perf_probe,
+ tp_event);
+
+ free_percpu(tp_event->perf_events);
+ tp_event->perf_events = NULL;
+
+ if (!--total_ref_count) {
+ for (i = 0; i < 4; i++) {
+ free_percpu(perf_trace_buf[i]);
+ perf_trace_buf[i] = NULL;
+ }
+ }
+}
+
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+ struct pt_regs *regs, int *rctxp)
+{
+ struct trace_entry *entry;
+ unsigned long flags;
+ char *raw_data;
+ int pc;
+
+ BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
+ pc = preempt_count();
+
+ *rctxp = perf_swevent_get_recursion_context();
+ if (*rctxp < 0)
+ return NULL;
+
+ raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id());
+
+ /* zero the dead bytes from align to not leak stack to user */
+ memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+
+ entry = (struct trace_entry *)raw_data;
+ local_save_flags(flags);
+ tracing_generic_entry_update(entry, flags, pc);
+ entry->type = type;
+
+ return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
deleted file mode 100644
index 9e25573242c..00000000000
--- a/kernel/trace/trace_event_profile.c
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- * trace event based perf counter profiling
- *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
- */
-
-#include <linux/module.h>
-#include "trace.h"
-
-
-char *perf_trace_buf;
-EXPORT_SYMBOL_GPL(perf_trace_buf);
-
-char *perf_trace_buf_nmi;
-EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
-
-typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
-
-/* Count the events in use (per event id, not per instance) */
-static int total_profile_count;
-
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
-{
- char *buf;
- int ret = -ENOMEM;
-
- if (event->profile_count++ > 0)
- return 0;
-
- if (!total_profile_count) {
- buf = (char *)alloc_percpu(perf_trace_t);
- if (!buf)
- goto fail_buf;
-
- rcu_assign_pointer(perf_trace_buf, buf);
-
- buf = (char *)alloc_percpu(perf_trace_t);
- if (!buf)
- goto fail_buf_nmi;
-
- rcu_assign_pointer(perf_trace_buf_nmi, buf);
- }
-
- ret = event->profile_enable(event);
- if (!ret) {
- total_profile_count++;
- return 0;
- }
-
-fail_buf_nmi:
- if (!total_profile_count) {
- free_percpu(perf_trace_buf_nmi);
- free_percpu(perf_trace_buf);
- perf_trace_buf_nmi = NULL;
- perf_trace_buf = NULL;
- }
-fail_buf:
- event->profile_count--;
-
- return ret;
-}
-
-int ftrace_profile_enable(int event_id)
-{
- struct ftrace_event_call *event;
- int ret = -EINVAL;
-
- mutex_lock(&event_mutex);
- list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id && event->profile_enable &&
- try_module_get(event->mod)) {
- ret = ftrace_profile_enable_event(event);
- break;
- }
- }
- mutex_unlock(&event_mutex);
-
- return ret;
-}
-
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
-{
- char *buf, *nmi_buf;
-
- if (--event->profile_count > 0)
- return;
-
- event->profile_disable(event);
-
- if (!--total_profile_count) {
- buf = perf_trace_buf;
- rcu_assign_pointer(perf_trace_buf, NULL);
-
- nmi_buf = perf_trace_buf_nmi;
- rcu_assign_pointer(perf_trace_buf_nmi, NULL);
-
- /*
- * Ensure every events in profiling have finished before
- * releasing the buffers
- */
- synchronize_sched();
-
- free_percpu(buf);
- free_percpu(nmi_buf);
- }
-}
-
-void ftrace_profile_disable(int event_id)
-{
- struct ftrace_event_call *event;
-
- mutex_lock(&event_mutex);
- list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id) {
- ftrace_profile_disable_event(event);
- module_put(event->mod);
- break;
- }
- }
- mutex_unlock(&event_mutex);
-}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 189b09baf4f..53cffc0b080 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,6 +15,7 @@
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/slab.h>
#include <linux/delay.h>
#include <asm/setup.h>
@@ -28,11 +29,23 @@ DEFINE_MUTEX(event_mutex);
LIST_HEAD(ftrace_events);
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call)
+{
+ if (!event_call->class->get_fields)
+ return &event_call->class->fields;
+ return event_call->class->get_fields(event_call);
+}
+
int trace_define_field(struct ftrace_event_call *call, const char *type,
const char *name, int offset, int size, int is_signed,
int filter_type)
{
struct ftrace_event_field *field;
+ struct list_head *head;
+
+ if (WARN_ON(!call->class))
+ return 0;
field = kzalloc(sizeof(*field), GFP_KERNEL);
if (!field)
@@ -55,15 +68,14 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
field->size = size;
field->is_signed = is_signed;
- list_add(&field->link, &call->fields);
+ head = trace_get_fields(call);
+ list_add(&field->link, head);
return 0;
err:
- if (field) {
+ if (field)
kfree(field->name);
- kfree(field->type);
- }
kfree(field);
return -ENOMEM;
@@ -95,8 +107,10 @@ static int trace_define_common_fields(struct ftrace_event_call *call)
void trace_destroy_fields(struct ftrace_event_call *call)
{
struct ftrace_event_field *field, *next;
+ struct list_head *head;
- list_for_each_entry_safe(field, next, &call->fields, link) {
+ head = trace_get_fields(call);
+ list_for_each_entry_safe(field, next, head, link) {
list_del(&field->link);
kfree(field->type);
kfree(field->name);
@@ -108,11 +122,9 @@ int trace_event_raw_init(struct ftrace_event_call *call)
{
int id;
- id = register_ftrace_event(call->event);
+ id = register_ftrace_event(&call->event);
if (!id)
return -ENODEV;
- call->id = id;
- INIT_LIST_HEAD(&call->fields);
return 0;
}
@@ -125,23 +137,33 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
switch (enable) {
case 0:
- if (call->enabled) {
- call->enabled = 0;
+ if (call->flags & TRACE_EVENT_FL_ENABLED) {
+ call->flags &= ~TRACE_EVENT_FL_ENABLED;
tracing_stop_cmdline_record();
- call->unregfunc(call);
+ if (call->class->reg)
+ call->class->reg(call, TRACE_REG_UNREGISTER);
+ else
+ tracepoint_probe_unregister(call->name,
+ call->class->probe,
+ call);
}
break;
case 1:
- if (!call->enabled) {
+ if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
tracing_start_cmdline_record();
- ret = call->regfunc(call);
+ if (call->class->reg)
+ ret = call->class->reg(call, TRACE_REG_REGISTER);
+ else
+ ret = tracepoint_probe_register(call->name,
+ call->class->probe,
+ call);
if (ret) {
tracing_stop_cmdline_record();
pr_info("event trace: Could not enable event "
"%s\n", call->name);
break;
}
- call->enabled = 1;
+ call->flags |= TRACE_EVENT_FL_ENABLED;
}
break;
}
@@ -172,15 +194,16 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->name || !call->regfunc)
+ if (!call->name || !call->class ||
+ (!call->class->probe && !call->class->reg))
continue;
if (match &&
strcmp(match, call->name) != 0 &&
- strcmp(match, call->system) != 0)
+ strcmp(match, call->class->system) != 0)
continue;
- if (sub && strcmp(sub, call->system) != 0)
+ if (sub && strcmp(sub, call->class->system) != 0)
continue;
if (event && strcmp(event, call->name) != 0)
@@ -298,7 +321,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
*/
- if (call->regfunc)
+ if (call->class && (call->class->probe || call->class->reg))
return call;
}
@@ -329,7 +352,7 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
(*pos)++;
list_for_each_entry_continue(call, &ftrace_events, list) {
- if (call->enabled)
+ if (call->flags & TRACE_EVENT_FL_ENABLED)
return call;
}
@@ -356,8 +379,8 @@ static int t_show(struct seq_file *m, void *v)
{
struct ftrace_event_call *call = v;
- if (strcmp(call->system, TRACE_SYSTEM) != 0)
- seq_printf(m, "%s:", call->system);
+ if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+ seq_printf(m, "%s:", call->class->system);
seq_printf(m, "%s\n", call->name);
return 0;
@@ -388,7 +411,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
struct ftrace_event_call *call = filp->private_data;
char *buf;
- if (call->enabled)
+ if (call->flags & TRACE_EVENT_FL_ENABLED)
buf = "1\n";
else
buf = "0\n";
@@ -451,10 +474,11 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->name || !call->regfunc)
+ if (!call->name || !call->class ||
+ (!call->class->probe && !call->class->reg))
continue;
- if (system && strcmp(call->system, system) != 0)
+ if (system && strcmp(call->class->system, system) != 0)
continue;
/*
@@ -462,7 +486,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
* or if all events or cleared, or if we have
* a mixture.
*/
- set |= (1 << !!call->enabled);
+ set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
/*
* If we have a mixture, no need to look further.
@@ -520,41 +544,17 @@ out:
return ret;
}
-extern char *__bad_type_size(void);
-
-#undef FIELD
-#define FIELD(type, name) \
- sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
- #type, "common_" #name, offsetof(typeof(field), name), \
- sizeof(field.name), is_signed_type(type)
-
-static int trace_write_header(struct trace_seq *s)
-{
- struct trace_entry field;
-
- /* struct trace_entry */
- return trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\n",
- FIELD(unsigned short, type),
- FIELD(unsigned char, flags),
- FIELD(unsigned char, preempt_count),
- FIELD(int, pid),
- FIELD(int, lock_depth));
-}
-
static ssize_t
event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_field *field;
+ struct list_head *head;
struct trace_seq *s;
+ int common_field_count = 5;
char *buf;
- int r;
+ int r = 0;
if (*ppos)
return 0;
@@ -565,14 +565,49 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
- /* If any of the first writes fail, so will the show_format. */
-
trace_seq_printf(s, "name: %s\n", call->name);
- trace_seq_printf(s, "ID: %d\n", call->id);
+ trace_seq_printf(s, "ID: %d\n", call->event.type);
trace_seq_printf(s, "format:\n");
- trace_write_header(s);
- r = call->show_format(call, s);
+ head = trace_get_fields(call);
+ list_for_each_entry_reverse(field, head, link) {
+ /*
+ * Smartly shows the array type(except dynamic array).
+ * Normal:
+ * field:TYPE VAR
+ * If TYPE := TYPE[LEN], it is shown:
+ * field:TYPE VAR[LEN]
+ */
+ const char *array_descriptor = strchr(field->type, '[');
+
+ if (!strncmp(field->type, "__data_loc", 10))
+ array_descriptor = NULL;
+
+ if (!array_descriptor) {
+ r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+ "\tsize:%u;\tsigned:%d;\n",
+ field->type, field->name, field->offset,
+ field->size, !!field->is_signed);
+ } else {
+ r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+ "\tsize:%u;\tsigned:%d;\n",
+ (int)(array_descriptor - field->type),
+ field->type, field->name,
+ array_descriptor, field->offset,
+ field->size, !!field->is_signed);
+ }
+
+ if (--common_field_count == 0)
+ r = trace_seq_printf(s, "\n");
+
+ if (!r)
+ break;
+ }
+
+ if (r)
+ r = trace_seq_printf(s, "\nprint fmt: %s\n",
+ call->print_fmt);
+
if (!r) {
/*
* ug! The format output is bigger than a PAGE!!
@@ -605,7 +640,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
return -ENOMEM;
trace_seq_init(s);
- trace_seq_printf(s, "%d\n", call->id);
+ trace_seq_printf(s, "%d\n", call->event.type);
r = simple_read_from_buffer(ubuf, cnt, ppos,
s->buffer, s->len);
@@ -911,14 +946,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
const struct file_operations *filter,
const struct file_operations *format)
{
+ struct list_head *head;
int ret;
/*
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
- if (strcmp(call->system, TRACE_SYSTEM) != 0)
- d_events = event_subsystem_dir(call->system, d_events);
+ if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+ d_events = event_subsystem_dir(call->class->system, d_events);
call->dir = debugfs_create_dir(call->name, d_events);
if (!call->dir) {
@@ -927,31 +963,36 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
return -1;
}
- if (call->regfunc)
+ if (call->class->probe || call->class->reg)
trace_create_file("enable", 0644, call->dir, call,
enable);
- if (call->id && call->profile_enable)
+#ifdef CONFIG_PERF_EVENTS
+ if (call->event.type && (call->class->perf_probe || call->class->reg))
trace_create_file("id", 0444, call->dir, call,
id);
+#endif
- if (call->define_fields) {
- ret = trace_define_common_fields(call);
- if (!ret)
- ret = call->define_fields(call);
- if (ret < 0) {
- pr_warning("Could not initialize trace point"
- " events/%s\n", call->name);
- return ret;
+ if (call->class->define_fields) {
+ /*
+ * Other events may have the same class. Only update
+ * the fields if they are not already defined.
+ */
+ head = trace_get_fields(call);
+ if (list_empty(head)) {
+ ret = trace_define_common_fields(call);
+ if (!ret)
+ ret = call->class->define_fields(call);
+ if (ret < 0) {
+ pr_warning("Could not initialize trace point"
+ " events/%s\n", call->name);
+ return ret;
+ }
}
trace_create_file("filter", 0644, call->dir, call,
filter);
}
- /* A trace may not want to export its format */
- if (!call->show_format)
- return 0;
-
trace_create_file("format", 0444, call->dir, call,
format);
@@ -966,8 +1007,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
if (!call->name)
return -EINVAL;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1031,13 +1072,13 @@ static void remove_subsystem_dir(const char *name)
static void __trace_remove_event_call(struct ftrace_event_call *call)
{
ftrace_event_enable_disable(call, 0);
- if (call->event)
- __unregister_ftrace_event(call->event);
+ if (call->event.funcs)
+ __unregister_ftrace_event(&call->event);
debugfs_remove_recursive(call->dir);
list_del(&call->list);
trace_destroy_fields(call);
destroy_preds(call);
- remove_subsystem_dir(call->system);
+ remove_subsystem_dir(call->class->system);
}
/* Remove an event_call */
@@ -1128,8 +1169,8 @@ static void trace_module_add_events(struct module *mod)
/* The linker may leave blanks */
if (!call->name)
continue;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1282,8 +1323,8 @@ static __init int event_trace_init(void)
/* The linker may leave blanks */
if (!call->name)
continue;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1384,8 +1425,8 @@ static __init void event_trace_self_tests(void)
list_for_each_entry(call, &ftrace_events, list) {
- /* Only test those that have a regfunc */
- if (!call->regfunc)
+ /* Only test those that have a probe */
+ if (!call->class || !call->class->probe)
continue;
/*
@@ -1395,8 +1436,8 @@ static __init void event_trace_self_tests(void)
* syscalls as we test.
*/
#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
- if (call->system &&
- strcmp(call->system, "syscalls") == 0)
+ if (call->class->system &&
+ strcmp(call->class->system, "syscalls") == 0)
continue;
#endif
@@ -1406,7 +1447,7 @@ static __init void event_trace_self_tests(void)
* If an event is already enabled, someone is using
* it and the self test should not be on.
*/
- if (call->enabled) {
+ if (call->flags & TRACE_EVENT_FL_ENABLED) {
pr_warning("Enabled event during self test!\n");
WARN_ON_ONCE(1);
continue;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e42af9aad69..57bb1bb3299 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,6 +22,7 @@
#include <linux/ctype.h>
#include <linux/mutex.h>
#include <linux/perf_event.h>
+#include <linux/slab.h>
#include "trace.h"
#include "trace_output.h"
@@ -499,8 +500,10 @@ static struct ftrace_event_field *
find_event_field(struct ftrace_event_call *call, char *name)
{
struct ftrace_event_field *field;
+ struct list_head *head;
- list_for_each_entry(field, &call->fields, link) {
+ head = trace_get_fields(call);
+ list_for_each_entry(field, head, link) {
if (!strcmp(field->name, name))
return field;
}
@@ -544,7 +547,7 @@ static void filter_disable_preds(struct ftrace_event_call *call)
struct event_filter *filter = call->filter;
int i;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
filter->n_preds = 0;
for (i = 0; i < MAX_FILTER_PRED; i++)
@@ -571,7 +574,7 @@ void destroy_preds(struct ftrace_event_call *call)
{
__free_preds(call->filter);
call->filter = NULL;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
}
static struct event_filter *__alloc_preds(void)
@@ -610,7 +613,7 @@ static int init_preds(struct ftrace_event_call *call)
if (call->filter)
return 0;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
call->filter = __alloc_preds();
if (IS_ERR(call->filter))
return PTR_ERR(call->filter);
@@ -624,10 +627,10 @@ static int init_subsystem_preds(struct event_subsystem *system)
int err;
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
err = init_preds(call);
@@ -643,10 +646,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
struct ftrace_event_call *call;
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
filter_disable_preds(call);
@@ -1248,10 +1251,10 @@ static int replace_system_preds(struct event_subsystem *system,
list_for_each_entry(call, &ftrace_events, list) {
struct event_filter *filter = call->filter;
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
/* try to see if the filter can be applied */
@@ -1265,7 +1268,7 @@ static int replace_system_preds(struct event_subsystem *system,
if (err)
filter_disable_preds(call);
else {
- call->filter_active = 1;
+ call->flags |= TRACE_EVENT_FL_FILTERED;
replace_filter_string(filter, filter_string);
}
fail = false;
@@ -1314,7 +1317,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
if (err)
append_filter_err(ps, call->filter);
else
- call->filter_active = 1;
+ call->flags |= TRACE_EVENT_FL_FILTERED;
out:
filter_opstack_clear(ps);
postfix_clear(ps);
@@ -1371,7 +1374,7 @@ out_unlock:
return err;
}
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
void ftrace_profile_free_filter(struct perf_event *event)
{
@@ -1392,12 +1395,12 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (call->id == event_id)
+ if (call->event.type == event_id)
break;
}
err = -EINVAL;
- if (!call)
+ if (&call->list == &ftrace_events)
goto out_unlock;
err = -EEXIST;
@@ -1439,5 +1442,5 @@ out_unlock:
return err;
}
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d4fa5dc1ee4..8536e2a6596 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -62,78 +62,6 @@ static void __always_unused ____ftrace_check_##name(void) \
#include "trace_entries.h"
-
-#undef __field
-#define __field(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- sizeof(field.item), is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __field_desc
-#define __field_desc(type, container, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), container.item), \
- sizeof(field.container.item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- sizeof(field.item), is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __array_desc
-#define __array_desc(type, container, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), container.item), \
- sizeof(field.container.item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:0;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef F_printk
-#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef __entry
-#define __entry REC
-
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
-static int \
-ftrace_format_##name(struct ftrace_event_call *unused, \
- struct trace_seq *s) \
-{ \
- struct struct_name field __attribute__((unused)); \
- int ret = 0; \
- \
- tstruct; \
- \
- trace_seq_printf(s, "\nprint fmt: " print); \
- \
- return ret; \
-}
-
-#include "trace_entries.h"
-
#undef __field
#define __field(type, item) \
ret = trace_define_field(event_call, #type, #item, \
@@ -175,7 +103,12 @@ ftrace_format_##name(struct ftrace_event_call *unused, \
return ret;
#undef __dynamic_array
-#define __dynamic_array(type, item)
+#define __dynamic_array(type, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ 0, is_signed_type(type), FILTER_OTHER);\
+ if (ret) \
+ return ret;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
@@ -194,10 +127,13 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
static int ftrace_raw_init_event(struct ftrace_event_call *call)
{
- INIT_LIST_HEAD(&call->fields);
+ INIT_LIST_HEAD(&call->class->fields);
return 0;
}
+#undef __entry
+#define __entry REC
+
#undef __field
#define __field(type, item)
@@ -213,18 +149,25 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
#undef __dynamic_array
#define __dynamic_array(type, item)
+#undef F_printk
+#define F_printk(fmt, args...) #fmt ", " __stringify(args)
+
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \
+ \
+struct ftrace_event_class event_class_ftrace_##call = { \
+ .system = __stringify(TRACE_SYSTEM), \
+ .define_fields = ftrace_define_fields_##call, \
+ .raw_init = ftrace_raw_init_event, \
+}; \
\
struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .id = type, \
- .system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_raw_init_event, \
- .show_format = ftrace_format_##call, \
- .define_fields = ftrace_define_fields_##call, \
+ .event.type = etype, \
+ .class = &event_class_ftrace_##call, \
+ .print_fmt = print, \
}; \
#include "trace_entries.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b1342c5d37c..79f4bac99a9 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,6 +9,7 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include "trace.h"
@@ -18,6 +19,7 @@ struct fgraph_cpu_data {
pid_t last_pid;
int depth;
int ignore;
+ unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH];
};
struct fgraph_data {
@@ -38,7 +40,7 @@ struct fgraph_data {
#define TRACE_GRAPH_PRINT_OVERHEAD 0x4
#define TRACE_GRAPH_PRINT_PROC 0x8
#define TRACE_GRAPH_PRINT_DURATION 0x10
-#define TRACE_GRAPH_PRINT_ABS_TIME 0X20
+#define TRACE_GRAPH_PRINT_ABS_TIME 0x20
static struct tracer_opt trace_opts[] = {
/* Display overruns? (for self-debug purpose) */
@@ -177,7 +179,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
return ret;
}
-static int __trace_graph_entry(struct trace_array *tr,
+int __trace_graph_entry(struct trace_array *tr,
struct ftrace_graph_ent *trace,
unsigned long flags,
int pc)
@@ -187,7 +189,7 @@ static int __trace_graph_entry(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ent_entry *entry;
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return 0;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -212,13 +214,11 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
int cpu;
int pc;
- if (unlikely(!tr))
- return 0;
-
if (!ftrace_trace_task(current))
return 0;
- if (!ftrace_graph_addr(trace->func))
+ /* trace it when it is-nested-in or is a function enabled. */
+ if (!(trace->depth || ftrace_graph_addr(trace->func)))
return 0;
local_irq_save(flags);
@@ -231,9 +231,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
} 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);
@@ -241,7 +238,15 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
return ret;
}
-static void __trace_graph_return(struct trace_array *tr,
+int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+{
+ if (tracing_thresh)
+ return 1;
+ else
+ return trace_graph_entry(trace);
+}
+
+void __trace_graph_return(struct trace_array *tr,
struct ftrace_graph_ret *trace,
unsigned long flags,
int pc)
@@ -251,7 +256,7 @@ static void __trace_graph_return(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ret_entry *entry;
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -281,19 +286,39 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
pc = preempt_count();
__trace_graph_return(tr, trace, flags, pc);
}
- if (!trace->depth)
- clear_tsk_trace_graph(current);
atomic_dec(&data->disabled);
local_irq_restore(flags);
}
+void set_graph_array(struct trace_array *tr)
+{
+ graph_array = tr;
+
+ /* Make graph_array visible before we start tracing */
+
+ smp_mb();
+}
+
+void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+{
+ if (tracing_thresh &&
+ (trace->rettime - trace->calltime < tracing_thresh))
+ return;
+ else
+ trace_graph_return(trace);
+}
+
static int graph_trace_init(struct trace_array *tr)
{
int ret;
- graph_array = tr;
- ret = register_ftrace_graph(&trace_graph_return,
- &trace_graph_entry);
+ set_graph_array(tr);
+ if (tracing_thresh)
+ ret = register_ftrace_graph(&trace_graph_thresh_return,
+ &trace_graph_thresh_entry);
+ else
+ ret = register_ftrace_graph(&trace_graph_return,
+ &trace_graph_entry);
if (ret)
return ret;
tracing_start_cmdline_record();
@@ -301,11 +326,6 @@ static int graph_trace_init(struct trace_array *tr)
return 0;
}
-void set_graph_array(struct trace_array *tr)
-{
- graph_array = tr;
-}
-
static void graph_trace_reset(struct trace_array *tr)
{
tracing_stop_cmdline_record();
@@ -470,9 +490,10 @@ get_return_for_leaf(struct trace_iterator *iter,
* We need to consume the current entry to see
* the next one.
*/
- ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+ ring_buffer_consume(iter->tr->buffer, iter->cpu,
+ NULL, NULL);
event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
- NULL);
+ NULL, NULL);
}
if (!event)
@@ -506,17 +527,18 @@ get_return_for_leaf(struct trace_iterator *iter,
/* Signal a overhead of time execution to the output */
static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+print_graph_overhead(unsigned long long duration, struct trace_seq *s,
+ u32 flags)
{
/* If duration disappear, we don't need anything */
- if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
+ if (!(flags & TRACE_GRAPH_PRINT_DURATION))
return 1;
/* Non nested entry or return */
if (duration == -1)
return trace_seq_printf(s, " ");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
/* Duration exceeded 100 msecs */
if (duration > 100000ULL)
return trace_seq_printf(s, "! ");
@@ -542,7 +564,7 @@ static int print_graph_abs_time(u64 t, struct trace_seq *s)
static enum print_line_t
print_graph_irq(struct trace_iterator *iter, unsigned long addr,
- enum trace_type type, int cpu, pid_t pid)
+ enum trace_type type, int cpu, pid_t pid, u32 flags)
{
int ret;
struct trace_seq *s = &iter->seq;
@@ -552,21 +574,21 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
return TRACE_TYPE_UNHANDLED;
/* Absolute time */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+ if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
ret = print_graph_abs_time(iter->ts, s);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Cpu */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ if (flags & TRACE_GRAPH_PRINT_CPU) {
ret = print_graph_cpu(s, cpu);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Proc */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ if (flags & TRACE_GRAPH_PRINT_PROC) {
ret = print_graph_proc(s, pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
@@ -576,7 +598,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
}
/* No overhead */
- ret = print_graph_overhead(-1, s);
+ ret = print_graph_overhead(-1, s, flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
@@ -589,7 +611,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
return TRACE_TYPE_PARTIAL_LINE;
/* Don't close the duration column if haven't one */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ if (flags & TRACE_GRAPH_PRINT_DURATION)
trace_seq_printf(s, " |");
ret = trace_seq_printf(s, "\n");
@@ -659,7 +681,8 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
static enum print_line_t
print_graph_entry_leaf(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *entry,
- struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
+ struct ftrace_graph_ret_entry *ret_entry,
+ struct trace_seq *s, u32 flags)
{
struct fgraph_data *data = iter->private;
struct ftrace_graph_ret *graph_ret;
@@ -673,24 +696,30 @@ print_graph_entry_leaf(struct trace_iterator *iter,
duration = graph_ret->rettime - graph_ret->calltime;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. Since
* this is a leaf function, keep the comments
* equal to this depth.
*/
- *depth = call->depth - 1;
+ cpu_data->depth = call->depth - 1;
+
+ /* No need to keep this function around for this depth */
+ if (call->depth < FTRACE_RETFUNC_DEPTH)
+ cpu_data->enter_funcs[call->depth] = 0;
}
/* Overhead */
- ret = print_graph_overhead(duration, s);
+ ret = print_graph_overhead(duration, s, flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Duration */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ if (flags & TRACE_GRAPH_PRINT_DURATION) {
ret = print_graph_duration(duration, s);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
@@ -713,7 +742,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
static enum print_line_t
print_graph_entry_nested(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *entry,
- struct trace_seq *s, int cpu)
+ struct trace_seq *s, int cpu, u32 flags)
{
struct ftrace_graph_ent *call = &entry->graph_ent;
struct fgraph_data *data = iter->private;
@@ -721,19 +750,24 @@ print_graph_entry_nested(struct trace_iterator *iter,
int i;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
- *depth = call->depth;
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
+ cpu_data->depth = call->depth;
+
+ /* Save this function pointer to see if the exit matches */
+ if (call->depth < FTRACE_RETFUNC_DEPTH)
+ cpu_data->enter_funcs[call->depth] = call->func;
}
/* No overhead */
- ret = print_graph_overhead(-1, s);
+ ret = print_graph_overhead(-1, s, flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* No time */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ if (flags & TRACE_GRAPH_PRINT_DURATION) {
ret = trace_seq_printf(s, " | ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
@@ -759,7 +793,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
static enum print_line_t
print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
- int type, unsigned long addr)
+ int type, unsigned long addr, u32 flags)
{
struct fgraph_data *data = iter->private;
struct trace_entry *ent = iter->ent;
@@ -772,27 +806,27 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
if (type) {
/* Interrupt */
- ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+ ret = print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Absolute time */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+ if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
ret = print_graph_abs_time(iter->ts, s);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Cpu */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ if (flags & TRACE_GRAPH_PRINT_CPU) {
ret = print_graph_cpu(s, cpu);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Proc */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ if (flags & TRACE_GRAPH_PRINT_PROC) {
ret = print_graph_proc(s, ent->pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
@@ -814,7 +848,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
static enum print_line_t
print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
- struct trace_iterator *iter)
+ struct trace_iterator *iter, u32 flags)
{
struct fgraph_data *data = iter->private;
struct ftrace_graph_ent *call = &field->graph_ent;
@@ -822,14 +856,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
static enum print_line_t ret;
int cpu = iter->cpu;
- if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+ if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
return TRACE_TYPE_PARTIAL_LINE;
leaf_ret = get_return_for_leaf(iter, field);
if (leaf_ret)
- ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
+ ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags);
else
- ret = print_graph_entry_nested(iter, field, s, cpu);
+ ret = print_graph_entry_nested(iter, field, s, cpu, flags);
if (data) {
/*
@@ -848,37 +882,47 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
static enum print_line_t
print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
- struct trace_entry *ent, struct trace_iterator *iter)
+ struct trace_entry *ent, struct trace_iterator *iter,
+ u32 flags)
{
unsigned long long duration = trace->rettime - trace->calltime;
struct fgraph_data *data = iter->private;
pid_t pid = ent->pid;
int cpu = iter->cpu;
+ int func_match = 1;
int ret;
int i;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. This is the
* return from a function, we now want the comments
* to display at the same level of the bracket.
*/
- *depth = trace->depth - 1;
+ cpu_data->depth = trace->depth - 1;
+
+ if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+ if (cpu_data->enter_funcs[trace->depth] != trace->func)
+ func_match = 0;
+ cpu_data->enter_funcs[trace->depth] = 0;
+ }
}
- if (print_graph_prologue(iter, s, 0, 0))
+ if (print_graph_prologue(iter, s, 0, 0, flags))
return TRACE_TYPE_PARTIAL_LINE;
/* Overhead */
- ret = print_graph_overhead(duration, s);
+ ret = print_graph_overhead(duration, s, flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Duration */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ if (flags & TRACE_GRAPH_PRINT_DURATION) {
ret = print_graph_duration(duration, s);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
@@ -891,19 +935,32 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
return TRACE_TYPE_PARTIAL_LINE;
}
- ret = trace_seq_printf(s, "}\n");
- if (!ret)
- return TRACE_TYPE_PARTIAL_LINE;
+ /*
+ * If the return function does not have a matching entry,
+ * then the entry was lost. Instead of just printing
+ * the '}' and letting the user guess what function this
+ * belongs to, write out the function name.
+ */
+ if (func_match) {
+ ret = trace_seq_printf(s, "}\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ } else {
+ ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
/* Overrun */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+ if (flags & TRACE_GRAPH_PRINT_OVERRUN) {
ret = trace_seq_printf(s, " (Overruns: %lu)\n",
trace->overrun);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
- ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
+ ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
+ cpu, pid, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
@@ -911,8 +968,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
}
static enum print_line_t
-print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
- struct trace_iterator *iter)
+print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
+ struct trace_iterator *iter, u32 flags)
{
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
struct fgraph_data *data = iter->private;
@@ -924,16 +981,16 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
if (data)
depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
- if (print_graph_prologue(iter, s, 0, 0))
+ if (print_graph_prologue(iter, s, 0, 0, flags))
return TRACE_TYPE_PARTIAL_LINE;
/* No overhead */
- ret = print_graph_overhead(-1, s);
+ ret = print_graph_overhead(-1, s, flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* No time */
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ if (flags & TRACE_GRAPH_PRINT_DURATION) {
ret = trace_seq_printf(s, " | ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
@@ -968,7 +1025,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
if (!event)
return TRACE_TYPE_UNHANDLED;
- ret = event->trace(iter, sym_flags);
+ ret = event->funcs->trace(iter, sym_flags, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
@@ -988,7 +1045,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
{
struct ftrace_graph_ent_entry *field;
struct fgraph_data *data = iter->private;
@@ -1009,7 +1066,7 @@ print_graph_function(struct trace_iterator *iter)
if (data && data->failed) {
field = &data->ent;
iter->cpu = data->cpu;
- ret = print_graph_entry(field, s, iter);
+ ret = print_graph_entry(field, s, iter, flags);
if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
ret = TRACE_TYPE_NO_CONSUME;
@@ -1029,32 +1086,50 @@ print_graph_function(struct trace_iterator *iter)
struct ftrace_graph_ent_entry saved;
trace_assign_type(field, entry);
saved = *field;
- return print_graph_entry(&saved, s, iter);
+ return print_graph_entry(&saved, s, iter, flags);
}
case TRACE_GRAPH_RET: {
struct ftrace_graph_ret_entry *field;
trace_assign_type(field, entry);
- return print_graph_return(&field->ret, s, entry, iter);
+ return print_graph_return(&field->ret, s, entry, iter, flags);
}
+ case TRACE_STACK:
+ case TRACE_FN:
+ /* dont trace stack and functions as comments */
+ return TRACE_TYPE_UNHANDLED;
+
default:
- return print_graph_comment(s, entry, iter);
+ return print_graph_comment(s, entry, iter, flags);
}
return TRACE_TYPE_HANDLED;
}
-static void print_lat_header(struct seq_file *s)
+static enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+ return print_graph_function_flags(iter, tracer_flags.val);
+}
+
+static enum print_line_t
+print_graph_function_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ return print_graph_function(iter);
+}
+
+static void print_lat_header(struct seq_file *s, u32 flags)
{
static const char spaces[] = " " /* 16 spaces */
" " /* 4 spaces */
" "; /* 17 spaces */
int size = 0;
- if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
size += 16;
- if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ if (flags & TRACE_GRAPH_PRINT_CPU)
size += 4;
- if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ if (flags & TRACE_GRAPH_PRINT_PROC)
size += 17;
seq_printf(s, "#%.*s _-----=> irqs-off \n", size, spaces);
@@ -1065,43 +1140,48 @@ static void print_lat_header(struct seq_file *s)
seq_printf(s, "#%.*s|||| / \n", size, spaces);
}
-static void print_graph_headers(struct seq_file *s)
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
{
int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
if (lat)
- print_lat_header(s);
+ print_lat_header(s, flags);
/* 1st line */
seq_printf(s, "#");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_printf(s, " TIME ");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ if (flags & TRACE_GRAPH_PRINT_CPU)
seq_printf(s, " CPU");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ if (flags & TRACE_GRAPH_PRINT_PROC)
seq_printf(s, " TASK/PID ");
if (lat)
seq_printf(s, "|||||");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_printf(s, " DURATION ");
seq_printf(s, " FUNCTION CALLS\n");
/* 2nd line */
seq_printf(s, "#");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_printf(s, " | ");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ if (flags & TRACE_GRAPH_PRINT_CPU)
seq_printf(s, " | ");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ if (flags & TRACE_GRAPH_PRINT_PROC)
seq_printf(s, " | | ");
if (lat)
seq_printf(s, "|||||");
- if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_printf(s, " | | ");
seq_printf(s, " | | | |\n");
}
-static void graph_trace_open(struct trace_iterator *iter)
+void print_graph_headers(struct seq_file *s)
+{
+ print_graph_headers_flags(s, tracer_flags.val);
+}
+
+void graph_trace_open(struct trace_iterator *iter)
{
/* pid and depth on the last trace processed */
struct fgraph_data *data;
@@ -1136,7 +1216,7 @@ static void graph_trace_open(struct trace_iterator *iter)
pr_warning("function graph tracer: not enough memory\n");
}
-static void graph_trace_close(struct trace_iterator *iter)
+void graph_trace_close(struct trace_iterator *iter)
{
struct fgraph_data *data = iter->private;
@@ -1146,6 +1226,20 @@ static void graph_trace_close(struct trace_iterator *iter)
}
}
+static struct trace_event_functions graph_functions = {
+ .trace = print_graph_function_event,
+};
+
+static struct trace_event graph_trace_entry_event = {
+ .type = TRACE_GRAPH_ENT,
+ .funcs = &graph_functions,
+};
+
+static struct trace_event graph_trace_ret_event = {
+ .type = TRACE_GRAPH_RET,
+ .funcs = &graph_functions
+};
+
static struct tracer graph_trace __read_mostly = {
.name = "function_graph",
.open = graph_trace_open,
@@ -1167,6 +1261,16 @@ static __init int init_graph_trace(void)
{
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
+ if (!register_ftrace_event(&graph_trace_entry_event)) {
+ pr_warning("Warning: could not register graph trace events\n");
+ return 1;
+ }
+
+ if (!register_ftrace_event(&graph_trace_ret_event)) {
+ pr_warning("Warning: could not register graph trace events\n");
+ return 1;
+ }
+
return register_tracer(&graph_trace);
}
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
deleted file mode 100644
index 7b97000745f..00000000000
--- a/kernel/trace/trace_hw_branches.c
+++ /dev/null
@@ -1,312 +0,0 @@
-/*
- * h/w branch tracer for x86 based on BTS
- *
- * Copyright (C) 2008-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-
-#include <asm/ds.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-
-#define BTS_BUFFER_SIZE (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
-
-#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
-
-static int trace_hw_branches_enabled __read_mostly;
-static int trace_hw_branches_suspended __read_mostly;
-static struct trace_array *hw_branch_trace __read_mostly;
-
-
-static void bts_trace_init_cpu(int cpu)
-{
- per_cpu(hwb_tracer, cpu) =
- ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
- BTS_BUFFER_SIZE, NULL, (size_t)-1,
- BTS_KERNEL);
-
- if (IS_ERR(per_cpu(hwb_tracer, cpu)))
- per_cpu(hwb_tracer, cpu) = NULL;
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
- int cpu;
-
- hw_branch_trace = tr;
- trace_hw_branches_enabled = 0;
-
- get_online_cpus();
- for_each_online_cpu(cpu) {
- bts_trace_init_cpu(cpu);
-
- if (likely(per_cpu(hwb_tracer, cpu)))
- trace_hw_branches_enabled = 1;
- }
- trace_hw_branches_suspended = 0;
- put_online_cpus();
-
- /* If we could not enable tracing on a single cpu, we fail. */
- return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
- int cpu;
-
- get_online_cpus();
- for_each_online_cpu(cpu) {
- if (likely(per_cpu(hwb_tracer, cpu))) {
- ds_release_bts(per_cpu(hwb_tracer, cpu));
- per_cpu(hwb_tracer, cpu) = NULL;
- }
- }
- trace_hw_branches_enabled = 0;
- trace_hw_branches_suspended = 0;
- put_online_cpus();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
- int cpu;
-
- get_online_cpus();
- for_each_online_cpu(cpu)
- if (likely(per_cpu(hwb_tracer, cpu)))
- ds_resume_bts(per_cpu(hwb_tracer, cpu));
- trace_hw_branches_suspended = 0;
- put_online_cpus();
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
- int cpu;
-
- get_online_cpus();
- for_each_online_cpu(cpu)
- if (likely(per_cpu(hwb_tracer, cpu)))
- ds_suspend_bts(per_cpu(hwb_tracer, cpu));
- trace_hw_branches_suspended = 1;
- put_online_cpus();
-}
-
-static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
-{
- int cpu = (long)hcpu;
-
- switch (action) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- /* The notification is sent with interrupts enabled. */
- if (trace_hw_branches_enabled) {
- bts_trace_init_cpu(cpu);
-
- if (trace_hw_branches_suspended &&
- likely(per_cpu(hwb_tracer, cpu)))
- ds_suspend_bts(per_cpu(hwb_tracer, cpu));
- }
- break;
-
- case CPU_DOWN_PREPARE:
- /* The notification is sent with interrupts enabled. */
- if (likely(per_cpu(hwb_tracer, cpu))) {
- ds_release_bts(per_cpu(hwb_tracer, cpu));
- per_cpu(hwb_tracer, cpu) = NULL;
- }
- }
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
- .notifier_call = bts_hotcpu_handler
-};
-
-static void bts_trace_print_header(struct seq_file *m)
-{
- seq_puts(m, "# CPU# TO <- FROM\n");
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
- unsigned long symflags = TRACE_ITER_SYM_OFFSET;
- struct trace_entry *entry = iter->ent;
- struct trace_seq *seq = &iter->seq;
- struct hw_branch_entry *it;
-
- trace_assign_type(it, entry);
-
- if (entry->type == TRACE_HW_BRANCHES) {
- if (trace_seq_printf(seq, "%4d ", iter->cpu) &&
- seq_print_ip_sym(seq, it->to, symflags) &&
- trace_seq_printf(seq, "\t <- ") &&
- seq_print_ip_sym(seq, it->from, symflags) &&
- trace_seq_printf(seq, "\n"))
- return TRACE_TYPE_HANDLED;
- return TRACE_TYPE_PARTIAL_LINE;
- }
- return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_hw_branch(u64 from, u64 to)
-{
- struct ftrace_event_call *call = &event_hw_branch;
- struct trace_array *tr = hw_branch_trace;
- struct ring_buffer_event *event;
- struct ring_buffer *buf;
- struct hw_branch_entry *entry;
- unsigned long irq1;
- int cpu;
-
- if (unlikely(!tr))
- return;
-
- if (unlikely(!trace_hw_branches_enabled))
- return;
-
- local_irq_save(irq1);
- cpu = raw_smp_processor_id();
- if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
- goto out;
-
- buf = tr->buffer;
- event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
- sizeof(*entry), 0, 0);
- if (!event)
- goto out;
- entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, 0, from);
- entry->ent.type = TRACE_HW_BRANCHES;
- entry->from = from;
- entry->to = to;
- if (!filter_check_discard(call, entry, buf, event))
- trace_buffer_unlock_commit(buf, event, 0, 0);
-
- out:
- atomic_dec(&tr->data[cpu]->disabled);
- local_irq_restore(irq1);
-}
-
-static void trace_bts_at(const struct bts_trace *trace, void *at)
-{
- struct bts_struct bts;
- int err = 0;
-
- WARN_ON_ONCE(!trace->read);
- if (!trace->read)
- return;
-
- err = trace->read(this_tracer, at, &bts);
- if (err < 0)
- return;
-
- switch (bts.qualifier) {
- case BTS_BRANCH:
- trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
- break;
- }
-}
-
-/*
- * Collect the trace on the current cpu and write it into the ftrace buffer.
- *
- * pre: tracing must be suspended on the current cpu
- */
-static void trace_bts_cpu(void *arg)
-{
- struct trace_array *tr = (struct trace_array *)arg;
- const struct bts_trace *trace;
- unsigned char *at;
-
- if (unlikely(!tr))
- return;
-
- if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
- return;
-
- if (unlikely(!this_tracer))
- return;
-
- trace = ds_read_bts(this_tracer);
- if (!trace)
- return;
-
- for (at = trace->ds.top; (void *)at < trace->ds.end;
- at += trace->ds.size)
- trace_bts_at(trace, at);
-
- for (at = trace->ds.begin; (void *)at < trace->ds.top;
- at += trace->ds.size)
- trace_bts_at(trace, at);
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
- int cpu;
-
- get_online_cpus();
- for_each_online_cpu(cpu)
- if (likely(per_cpu(hwb_tracer, cpu)))
- ds_suspend_bts(per_cpu(hwb_tracer, cpu));
- /*
- * We need to collect the trace on the respective cpu since ftrace
- * implicitly adds the record for the current cpu.
- * Once that is more flexible, we could collect the data from any cpu.
- */
- on_each_cpu(trace_bts_cpu, iter->tr, 1);
-
- for_each_online_cpu(cpu)
- if (likely(per_cpu(hwb_tracer, cpu)))
- ds_resume_bts(per_cpu(hwb_tracer, cpu));
- put_online_cpus();
-}
-
-static void trace_bts_close(struct trace_iterator *iter)
-{
- tracing_reset_online_cpus(iter->tr);
-}
-
-void trace_hw_branch_oops(void)
-{
- if (this_tracer) {
- ds_suspend_bts_noirq(this_tracer);
- trace_bts_cpu(hw_branch_trace);
- ds_resume_bts_noirq(this_tracer);
- }
-}
-
-struct tracer bts_tracer __read_mostly =
-{
- .name = "hw-branch-tracer",
- .init = bts_trace_init,
- .reset = bts_trace_reset,
- .print_header = bts_trace_print_header,
- .print_line = bts_trace_print_line,
- .start = bts_trace_start,
- .stop = bts_trace_stop,
- .open = trace_bts_prepare,
- .close = trace_bts_close,
-#ifdef CONFIG_FTRACE_SELFTEST
- .selftest = trace_selftest_startup_hw_branches,
-#endif /* CONFIG_FTRACE_SELFTEST */
-};
-
-__init static int init_bts_trace(void)
-{
- register_hotcpu_notifier(&bts_hotcpu_notifier);
- return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2974bc7538c..6fd486e0cef 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -34,6 +34,9 @@ static int trace_type __read_mostly;
static int save_lat_flag;
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
+static int start_irqsoff_tracer(struct trace_array *tr, int graph);
+
#ifdef CONFIG_PREEMPT_TRACER
static inline int
preempt_trace(void)
@@ -55,6 +58,23 @@ irq_trace(void)
# define irq_trace() (0)
#endif
+#define TRACE_DISPLAY_GRAPH 1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /* display latency trace as call graph */
+ { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+ { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+ .val = 0,
+ .opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
/*
* Sequence count - we record it when starting a measurement and
* skip the latency if the sequence has changed - some other section
@@ -108,6 +128,202 @@ static struct ftrace_ops trace_ops __read_mostly =
};
#endif /* CONFIG_FUNCTION_TRACER */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+ int cpu;
+
+ if (!(bit & TRACE_DISPLAY_GRAPH))
+ return -EINVAL;
+
+ if (!(is_graph() ^ set))
+ return 0;
+
+ stop_irqsoff_tracer(irqsoff_trace, !set);
+
+ for_each_possible_cpu(cpu)
+ per_cpu(tracing_cpu, cpu) = 0;
+
+ tracing_max_latency = 0;
+ tracing_reset_online_cpus(irqsoff_trace);
+
+ return start_irqsoff_tracer(irqsoff_trace, set);
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+ struct trace_array *tr = irqsoff_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int ret;
+ int cpu;
+ int pc;
+
+ cpu = raw_smp_processor_id();
+ if (likely(!per_cpu(tracing_cpu, cpu)))
+ return 0;
+
+ local_save_flags(flags);
+ /* slight chance to get a false positive on tracing_cpu */
+ if (!irqs_disabled_flags(flags))
+ return 0;
+
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ ret = __trace_graph_entry(tr, trace, flags, pc);
+ } else
+ ret = 0;
+
+ atomic_dec(&data->disabled);
+ return ret;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct trace_array *tr = irqsoff_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ cpu = raw_smp_processor_id();
+ if (likely(!per_cpu(tracing_cpu, cpu)))
+ return;
+
+ local_save_flags(flags);
+ /* slight chance to get a false positive on tracing_cpu */
+ if (!irqs_disabled_flags(flags))
+ return;
+
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ __trace_graph_return(tr, trace, flags, pc);
+ }
+
+ atomic_dec(&data->disabled);
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter)
+{
+ if (is_graph())
+ graph_trace_open(iter);
+
+}
+
+static void irqsoff_trace_close(struct trace_iterator *iter)
+{
+ if (iter->private)
+ graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
+ TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+ u32 flags = GRAPH_TRACER_FLAGS;
+
+ if (trace_flags & TRACE_ITER_LATENCY_FMT)
+ flags |= TRACE_GRAPH_PRINT_DURATION;
+ else
+ flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+ /*
+ * In graph mode call the graph tracer output function,
+ * otherwise go with the TRACE_FN event handler
+ */
+ if (is_graph())
+ return print_graph_function_flags(iter, flags);
+
+ return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_print_header(struct seq_file *s)
+{
+ if (is_graph()) {
+ struct trace_iterator *iter = s->private;
+ u32 flags = GRAPH_TRACER_FLAGS;
+
+ if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+ /* print nothing if the buffers are empty */
+ if (trace_empty(iter))
+ return;
+
+ print_trace_header(s, iter);
+ flags |= TRACE_GRAPH_PRINT_DURATION;
+ } else
+ flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+ print_graph_headers_flags(s, flags);
+ } else
+ trace_default_header(s);
+}
+
+static void
+trace_graph_function(struct trace_array *tr,
+ unsigned long ip, unsigned long flags, int pc)
+{
+ u64 time = trace_clock_local();
+ struct ftrace_graph_ent ent = {
+ .func = ip,
+ .depth = 0,
+ };
+ struct ftrace_graph_ret ret = {
+ .func = ip,
+ .depth = 0,
+ .calltime = time,
+ .rettime = time,
+ };
+
+ __trace_graph_entry(tr, &ent, flags, pc);
+ __trace_graph_return(tr, &ret, flags, pc);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+ unsigned long ip, unsigned long parent_ip,
+ unsigned long flags, int pc)
+{
+ if (!is_graph())
+ trace_function(tr, ip, parent_ip, flags, pc);
+ else {
+ trace_graph_function(tr, parent_ip, flags, pc);
+ trace_graph_function(tr, ip, flags, pc);
+ }
+}
+
+#else
+#define __trace_function trace_function
+
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+ return -EINVAL;
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+ return -1;
+}
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+ return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
+static void irqsoff_print_header(struct seq_file *s) { }
+static void irqsoff_trace_open(struct trace_iterator *iter) { }
+static void irqsoff_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
/*
* Should this new latency be reported/recorded?
*/
@@ -150,7 +366,7 @@ check_critical_timing(struct trace_array *tr,
if (!report_latency(delta))
goto out_unlock;
- trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+ __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
/* Skip 5 functions to get to the irq/preempt enable function */
__trace_stack(tr, flags, 5, pc);
@@ -172,7 +388,7 @@ out_unlock:
out:
data->critical_sequence = max_sequence;
data->preempt_timestamp = ftrace_now(cpu);
- trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+ __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
}
static inline void
@@ -204,7 +420,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
local_save_flags(flags);
- trace_function(tr, ip, parent_ip, flags, preempt_count());
+ __trace_function(tr, ip, parent_ip, flags, preempt_count());
per_cpu(tracing_cpu, cpu) = 1;
@@ -238,7 +454,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
atomic_inc(&data->disabled);
local_save_flags(flags);
- trace_function(tr, ip, parent_ip, flags, preempt_count());
+ __trace_function(tr, ip, parent_ip, flags, preempt_count());
check_critical_timing(tr, data, parent_ip ? : ip, cpu);
data->critical_start = 0;
atomic_dec(&data->disabled);
@@ -347,19 +563,32 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
}
#endif /* CONFIG_PREEMPT_TRACER */
-static void start_irqsoff_tracer(struct trace_array *tr)
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
{
- register_ftrace_function(&trace_ops);
- if (tracing_is_enabled())
+ int ret = 0;
+
+ if (!graph)
+ ret = register_ftrace_function(&trace_ops);
+ else
+ ret = register_ftrace_graph(&irqsoff_graph_return,
+ &irqsoff_graph_entry);
+
+ if (!ret && tracing_is_enabled())
tracer_enabled = 1;
else
tracer_enabled = 0;
+
+ return ret;
}
-static void stop_irqsoff_tracer(struct trace_array *tr)
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
{
tracer_enabled = 0;
- unregister_ftrace_function(&trace_ops);
+
+ if (!graph)
+ unregister_ftrace_function(&trace_ops);
+ else
+ unregister_ftrace_graph();
}
static void __irqsoff_tracer_init(struct trace_array *tr)
@@ -372,12 +601,14 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
/* make sure that the tracer is visible */
smp_wmb();
tracing_reset_online_cpus(tr);
- start_irqsoff_tracer(tr);
+
+ if (start_irqsoff_tracer(tr, is_graph()))
+ printk(KERN_ERR "failed to start irqsoff tracer\n");
}
static void irqsoff_tracer_reset(struct trace_array *tr)
{
- stop_irqsoff_tracer(tr);
+ stop_irqsoff_tracer(tr, is_graph());
if (!save_lat_flag)
trace_flags &= ~TRACE_ITER_LATENCY_FMT;
@@ -409,9 +640,15 @@ static struct tracer irqsoff_tracer __read_mostly =
.start = irqsoff_tracer_start,
.stop = irqsoff_tracer_stop,
.print_max = 1,
+ .print_header = irqsoff_print_header,
+ .print_line = irqsoff_print_line,
+ .flags = &tracer_flags,
+ .set_flag = irqsoff_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_irqsoff,
#endif
+ .open = irqsoff_trace_open,
+ .close = irqsoff_trace_close,
};
# define register_irqsoff(trace) register_tracer(&trace)
#else
@@ -435,9 +672,15 @@ static struct tracer preemptoff_tracer __read_mostly =
.start = irqsoff_tracer_start,
.stop = irqsoff_tracer_stop,
.print_max = 1,
+ .print_header = irqsoff_print_header,
+ .print_line = irqsoff_print_line,
+ .flags = &tracer_flags,
+ .set_flag = irqsoff_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptoff,
#endif
+ .open = irqsoff_trace_open,
+ .close = irqsoff_trace_close,
};
# define register_preemptoff(trace) register_tracer(&trace)
#else
@@ -463,9 +706,15 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
.start = irqsoff_tracer_start,
.stop = irqsoff_tracer_stop,
.print_max = 1,
+ .print_header = irqsoff_print_header,
+ .print_line = irqsoff_print_line,
+ .flags = &tracer_flags,
+ .set_flag = irqsoff_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptirqsoff,
#endif
+ .open = irqsoff_trace_open,
+ .close = irqsoff_trace_close,
};
# define register_preemptirqsoff(trace) register_tracer(&trace)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6ea90c0e2c9..faf7cefd15d 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -29,6 +29,8 @@
#include <linux/ctype.h>
#include <linux/ptrace.h>
#include <linux/perf_event.h>
+#include <linux/stringify.h>
+#include <asm/bitsperlong.h>
#include "trace.h"
#include "trace_output.h"
@@ -40,7 +42,6 @@
/* Reserved field names */
#define FIELD_STRING_IP "__probe_ip"
-#define FIELD_STRING_NARGS "__probe_nargs"
#define FIELD_STRING_RETIP "__probe_ret_ip"
#define FIELD_STRING_FUNC "__probe_func"
@@ -52,61 +53,102 @@ const char *reserved_field_names[] = {
"common_tgid",
"common_lock_depth",
FIELD_STRING_IP,
- FIELD_STRING_NARGS,
FIELD_STRING_RETIP,
FIELD_STRING_FUNC,
};
-struct fetch_func {
- unsigned long (*func)(struct pt_regs *, void *);
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *);
+#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
+#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
+
+/* Printing in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \
+static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+ const char *name, void *data)\
+{ \
+ return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+} \
+static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
+
+/* Data fetch function type */
+typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
+
+struct fetch_param {
+ fetch_func_t fn;
void *data;
};
-static __kprobes unsigned long call_fetch(struct fetch_func *f,
- struct pt_regs *regs)
-{
- return f->func(regs, f->data);
-}
-
-/* fetch handlers */
-static __kprobes unsigned long fetch_register(struct pt_regs *regs,
- void *offset)
-{
- return regs_get_register(regs, (unsigned int)((unsigned long)offset));
-}
-
-static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
- void *num)
+static __kprobes void call_fetch(struct fetch_param *fprm,
+ struct pt_regs *regs, void *dest)
{
- return regs_get_kernel_stack_nth(regs,
- (unsigned int)((unsigned long)num));
+ return fprm->fn(regs, fprm->data, dest);
}
-static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
-{
- unsigned long retval;
-
- if (probe_kernel_address(addr, retval))
- return 0;
- return retval;
+#define FETCH_FUNC_NAME(kind, type) fetch_##kind##_##type
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(kind) \
+DEFINE_FETCH_##kind(u8) \
+DEFINE_FETCH_##kind(u16) \
+DEFINE_FETCH_##kind(u32) \
+DEFINE_FETCH_##kind(u64)
+
+#define CHECK_BASIC_FETCH_FUNCS(kind, fn) \
+ ((FETCH_FUNC_NAME(kind, u8) == fn) || \
+ (FETCH_FUNC_NAME(kind, u16) == fn) || \
+ (FETCH_FUNC_NAME(kind, u32) == fn) || \
+ (FETCH_FUNC_NAME(kind, u64) == fn))
+
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type) \
+static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_register(regs, \
+ (unsigned int)((unsigned long)offset)); \
}
-
-static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
-{
- return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
+DEFINE_BASIC_FETCH_FUNCS(reg)
+
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
+ (unsigned int)((unsigned long)offset)); \
}
+DEFINE_BASIC_FETCH_FUNCS(stack)
-static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
- void *dummy)
-{
- return regs_return_value(regs);
+#define DEFINE_FETCH_retval(type) \
+static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+ void *dummy, void *dest) \
+{ \
+ *(type *)dest = (type)regs_return_value(regs); \
}
-
-static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
- void *dummy)
-{
- return kernel_stack_pointer(regs);
+DEFINE_BASIC_FETCH_FUNCS(retval)
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ if (probe_kernel_address(addr, retval)) \
+ *(type *)dest = 0; \
+ else \
+ *(type *)dest = retval; \
}
+DEFINE_BASIC_FETCH_FUNCS(memory)
/* Memory fetching by symbol */
struct symbol_cache {
@@ -150,51 +192,126 @@ static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
return sc;
}
-static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
-{
- struct symbol_cache *sc = data;
-
- if (sc->addr)
- return fetch_memory(regs, (void *)sc->addr);
- else
- return 0;
+#define DEFINE_FETCH_symbol(type) \
+static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct symbol_cache *sc = data; \
+ if (sc->addr) \
+ fetch_memory_##type(regs, (void *)sc->addr, dest); \
+ else \
+ *(type *)dest = 0; \
}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
-/* Special indirect memory access interface */
-struct indirect_fetch_data {
- struct fetch_func orig;
+/* Dereference memory access function */
+struct deref_fetch_param {
+ struct fetch_param orig;
long offset;
};
-static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
-{
- struct indirect_fetch_data *ind = data;
- unsigned long addr;
-
- addr = call_fetch(&ind->orig, regs);
- if (addr) {
- addr += ind->offset;
- return fetch_memory(regs, (void *)addr);
- } else
- return 0;
+#define DEFINE_FETCH_deref(type) \
+static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct deref_fetch_param *dprm = data; \
+ unsigned long addr; \
+ call_fetch(&dprm->orig, regs, &addr); \
+ if (addr) { \
+ addr += dprm->offset; \
+ fetch_memory_##type(regs, (void *)addr, dest); \
+ } else \
+ *(type *)dest = 0; \
}
+DEFINE_BASIC_FETCH_FUNCS(deref)
-static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
{
- if (data->orig.func == fetch_indirect)
- free_indirect_fetch_data(data->orig.data);
- else if (data->orig.func == fetch_symbol)
+ if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn))
+ free_deref_fetch_param(data->orig.data);
+ else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn))
free_symbol_cache(data->orig.data);
kfree(data);
}
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(kind, type) \
+ .kind = FETCH_FUNC_NAME(kind, type)
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
+ {.name = #ptype, \
+ .size = sizeof(ftype), \
+ .is_signed = sign, \
+ .print = PRINT_TYPE_FUNC_NAME(ptype), \
+ .fmt = PRINT_TYPE_FMT_NAME(ptype), \
+ASSIGN_FETCH_FUNC(reg, ftype), \
+ASSIGN_FETCH_FUNC(stack, ftype), \
+ASSIGN_FETCH_FUNC(retval, ftype), \
+ASSIGN_FETCH_FUNC(memory, ftype), \
+ASSIGN_FETCH_FUNC(symbol, ftype), \
+ASSIGN_FETCH_FUNC(deref, ftype), \
+ }
+
+/* Fetch type information table */
+static const struct fetch_type {
+ const char *name; /* Name of type */
+ size_t size; /* Byte size of type */
+ int is_signed; /* Signed flag */
+ print_type_func_t print; /* Print functions */
+ const char *fmt; /* Fromat string */
+ /* Fetch functions */
+ fetch_func_t reg;
+ fetch_func_t stack;
+ fetch_func_t retval;
+ fetch_func_t memory;
+ fetch_func_t symbol;
+ fetch_func_t deref;
+} fetch_type_table[] = {
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+};
+
+static const struct fetch_type *find_fetch_type(const char *type)
+{
+ int i;
+
+ if (!type)
+ type = DEFAULT_FETCH_TYPE_STR;
+
+ for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
+ if (strcmp(type, fetch_type_table[i].name) == 0)
+ return &fetch_type_table[i];
+ return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static __kprobes void fetch_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
+{
+ *(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+
/**
* Kprobe event core functions
*/
struct probe_arg {
- struct fetch_func fetch;
- const char *name;
+ struct fetch_param fetch;
+ unsigned int offset; /* Offset from argument entry */
+ const char *name; /* Name of this argument */
+ const char *comm; /* Command of this argument */
+ const struct fetch_type *type; /* Type of this argument */
};
/* Flags for trace_probe */
@@ -207,8 +324,9 @@ struct trace_probe {
unsigned long nhit;
unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
+ struct ftrace_event_class class;
struct ftrace_event_call call;
- struct trace_event event;
+ ssize_t size; /* trace entry size */
unsigned int nr_args;
struct probe_arg args[];
};
@@ -217,6 +335,7 @@ struct trace_probe {
(offsetof(struct trace_probe, args) + \
(sizeof(struct probe_arg) * (n)))
+
static __kprobes int probe_is_return(struct trace_probe *tp)
{
return tp->rp.handler != NULL;
@@ -227,51 +346,6 @@ static __kprobes const char *probe_symbol(struct trace_probe *tp)
return tp->symbol ? tp->symbol : "unknown";
}
-static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
-{
- int ret = -EINVAL;
-
- if (ff->func == fetch_argument)
- ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
- else if (ff->func == fetch_register) {
- const char *name;
- name = regs_query_register_name((unsigned int)((long)ff->data));
- ret = snprintf(buf, n, "%%%s", name);
- } else if (ff->func == fetch_stack)
- ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
- else if (ff->func == fetch_memory)
- ret = snprintf(buf, n, "@0x%p", ff->data);
- else if (ff->func == fetch_symbol) {
- struct symbol_cache *sc = ff->data;
- if (sc->offset)
- ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
- sc->offset);
- else
- ret = snprintf(buf, n, "@%s", sc->symbol);
- } else if (ff->func == fetch_retvalue)
- ret = snprintf(buf, n, "$retval");
- else if (ff->func == fetch_stack_address)
- ret = snprintf(buf, n, "$stack");
- else if (ff->func == fetch_indirect) {
- struct indirect_fetch_data *id = ff->data;
- size_t l = 0;
- ret = snprintf(buf, n, "%+ld(", id->offset);
- if (ret >= n)
- goto end;
- l += ret;
- ret = probe_arg_string(buf + l, n - l, &id->orig);
- if (ret < 0)
- goto end;
- l += ret;
- ret = snprintf(buf + l, n - l, ")");
- ret += l;
- }
-end:
- if (ret >= n)
- return -ENOSPC;
- return ret;
-}
-
static int register_probe_event(struct trace_probe *tp);
static void unregister_probe_event(struct trace_probe *tp);
@@ -330,6 +404,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
+ tp->call.class = &tp->class;
tp->call.name = kstrdup(event, GFP_KERNEL);
if (!tp->call.name)
goto error;
@@ -339,8 +414,8 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
- tp->call.system = kstrdup(group, GFP_KERNEL);
- if (!tp->call.system)
+ tp->class.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->class.system)
goto error;
INIT_LIST_HEAD(&tp->list);
@@ -354,11 +429,12 @@ error:
static void free_probe_arg(struct probe_arg *arg)
{
- if (arg->fetch.func == fetch_symbol)
+ if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn))
+ free_deref_fetch_param(arg->fetch.data);
+ else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn))
free_symbol_cache(arg->fetch.data);
- else if (arg->fetch.func == fetch_indirect)
- free_indirect_fetch_data(arg->fetch.data);
kfree(arg->name);
+ kfree(arg->comm);
}
static void free_trace_probe(struct trace_probe *tp)
@@ -368,7 +444,7 @@ static void free_trace_probe(struct trace_probe *tp)
for (i = 0; i < tp->nr_args; i++)
free_probe_arg(&tp->args[i]);
- kfree(tp->call.system);
+ kfree(tp->call.class->system);
kfree(tp->call.name);
kfree(tp->symbol);
kfree(tp);
@@ -381,7 +457,7 @@ static struct trace_probe *find_probe_event(const char *event,
list_for_each_entry(tp, &probe_list, list)
if (strcmp(tp->call.name, event) == 0 &&
- strcmp(tp->call.system, group) == 0)
+ strcmp(tp->call.class->system, group) == 0)
return tp;
return NULL;
}
@@ -406,7 +482,7 @@ static int register_trace_probe(struct trace_probe *tp)
mutex_lock(&probe_lock);
/* register as an event */
- old_tp = find_probe_event(tp->call.name, tp->call.system);
+ old_tp = find_probe_event(tp->call.name, tp->call.class->system);
if (old_tp) {
/* delete old event */
unregister_trace_probe(old_tp);
@@ -464,46 +540,41 @@ static int split_symbol_offset(char *symbol, unsigned long *offset)
#define PARAM_MAX_ARGS 16
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
-static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+ struct fetch_param *f, int is_return)
{
int ret = 0;
unsigned long param;
if (strcmp(arg, "retval") == 0) {
- if (is_return) {
- ff->func = fetch_retvalue;
- ff->data = NULL;
- } else
+ if (is_return)
+ f->fn = t->retval;
+ else
ret = -EINVAL;
} else if (strncmp(arg, "stack", 5) == 0) {
if (arg[5] == '\0') {
- ff->func = fetch_stack_address;
- ff->data = NULL;
+ if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
+ f->fn = fetch_stack_address;
+ else
+ ret = -EINVAL;
} else if (isdigit(arg[5])) {
ret = strict_strtoul(arg + 5, 10, &param);
if (ret || param > PARAM_MAX_STACK)
ret = -EINVAL;
else {
- ff->func = fetch_stack;
- ff->data = (void *)param;
+ f->fn = t->stack;
+ f->data = (void *)param;
}
} else
ret = -EINVAL;
- } else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
- ret = strict_strtoul(arg + 3, 10, &param);
- if (ret || param > PARAM_MAX_ARGS)
- ret = -EINVAL;
- else {
- ff->func = fetch_argument;
- ff->data = (void *)param;
- }
} else
ret = -EINVAL;
return ret;
}
/* Recursive argument parser */
-static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int __parse_probe_arg(char *arg, const struct fetch_type *t,
+ struct fetch_param *f, int is_return)
{
int ret = 0;
unsigned long param;
@@ -512,13 +583,13 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, ff, is_return);
+ ret = parse_probe_vars(arg + 1, t, f, is_return);
break;
case '%': /* named register */
ret = regs_query_register_offset(arg + 1);
if (ret >= 0) {
- ff->func = fetch_register;
- ff->data = (void *)(unsigned long)ret;
+ f->fn = t->reg;
+ f->data = (void *)(unsigned long)ret;
ret = 0;
}
break;
@@ -527,26 +598,22 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
ret = strict_strtoul(arg + 1, 0, &param);
if (ret)
break;
- ff->func = fetch_memory;
- ff->data = (void *)param;
+ f->fn = t->memory;
+ f->data = (void *)param;
} else {
ret = split_symbol_offset(arg + 1, &offset);
if (ret)
break;
- ff->data = alloc_symbol_cache(arg + 1, offset);
- if (ff->data)
- ff->func = fetch_symbol;
- else
- ret = -EINVAL;
+ f->data = alloc_symbol_cache(arg + 1, offset);
+ if (f->data)
+ f->fn = t->symbol;
}
break;
- case '+': /* indirect memory */
+ case '+': /* deref memory */
case '-':
tmp = strchr(arg, '(');
- if (!tmp) {
- ret = -EINVAL;
+ if (!tmp)
break;
- }
*tmp = '\0';
ret = strict_strtol(arg + 1, 0, &offset);
if (ret)
@@ -556,38 +623,58 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
arg = tmp + 1;
tmp = strrchr(arg, ')');
if (tmp) {
- struct indirect_fetch_data *id;
+ struct deref_fetch_param *dprm;
+ const struct fetch_type *t2 = find_fetch_type(NULL);
*tmp = '\0';
- id = kzalloc(sizeof(struct indirect_fetch_data),
- GFP_KERNEL);
- if (!id)
+ dprm = kzalloc(sizeof(struct deref_fetch_param),
+ GFP_KERNEL);
+ if (!dprm)
return -ENOMEM;
- id->offset = offset;
- ret = __parse_probe_arg(arg, &id->orig, is_return);
+ dprm->offset = offset;
+ ret = __parse_probe_arg(arg, t2, &dprm->orig,
+ is_return);
if (ret)
- kfree(id);
+ kfree(dprm);
else {
- ff->func = fetch_indirect;
- ff->data = (void *)id;
+ f->fn = t->deref;
+ f->data = (void *)dprm;
}
- } else
- ret = -EINVAL;
+ }
break;
- default:
- /* TODO: support custom handler */
- ret = -EINVAL;
}
+ if (!ret && !f->fn)
+ ret = -EINVAL;
return ret;
}
/* String length checking wrapper */
-static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_arg(char *arg, struct trace_probe *tp,
+ struct probe_arg *parg, int is_return)
{
+ const char *t;
+
if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
return -ENOSPC;
}
- return __parse_probe_arg(arg, ff, is_return);
+ parg->comm = kstrdup(arg, GFP_KERNEL);
+ if (!parg->comm) {
+ pr_info("Failed to allocate memory for command '%s'.\n", arg);
+ return -ENOMEM;
+ }
+ t = strchr(parg->comm, ':');
+ if (t) {
+ arg[t - parg->comm] = '\0';
+ t++;
+ }
+ parg->type = find_fetch_type(t);
+ if (!parg->type) {
+ pr_info("Unsupported type: %s\n", t);
+ return -EINVAL;
+ }
+ parg->offset = tp->size;
+ tp->size += parg->type->size;
+ return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
}
/* Return 1 if name is reserved or already used by another argument */
@@ -611,22 +698,24 @@ static int create_trace_probe(int argc, char **argv)
* - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
* - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
* Fetch args:
- * $argN : fetch Nth of function argument. (N:0-)
* $retval : fetch return value
* $stack : fetch stack address
* $stackN : fetch Nth of stack (N:0-)
* @ADDR : fetch memory at ADDR (ADDR should be in kernel)
* @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
* %REG : fetch register REG
- * Indirect memory fetch:
+ * Dereferencing memory fetch:
* +|-offs(ARG) : fetch memory at ARG +|- offs address.
* Alias name of args:
* NAME=FETCHARG : set NAME as alias of FETCHARG.
+ * Type of args:
+ * FETCHARG:TYPE : use TYPE instead of unsigned long.
*/
struct trace_probe *tp;
int i, ret = 0;
int is_return = 0, is_delete = 0;
- char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+ char *symbol = NULL, *event = NULL, *group = NULL;
+ char *arg, *tmp;
unsigned long offset = 0;
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
@@ -651,12 +740,12 @@ static int create_trace_probe(int argc, char **argv)
event = strchr(group, '/') + 1;
event[-1] = '\0';
if (strlen(group) == 0) {
- pr_info("Group name is not specifiled\n");
+ pr_info("Group name is not specified\n");
return -EINVAL;
}
}
if (strlen(event) == 0) {
- pr_info("Event name is not specifiled\n");
+ pr_info("Event name is not specified\n");
return -EINVAL;
}
}
@@ -689,7 +778,7 @@ static int create_trace_probe(int argc, char **argv)
return -EINVAL;
}
/* an address specified */
- ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+ ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
if (ret) {
pr_info("Failed to parse address.\n");
return ret;
@@ -739,13 +828,6 @@ static int create_trace_probe(int argc, char **argv)
else
arg = argv[i];
- if (conflict_field_name(argv[i], tp->args, i)) {
- pr_info("Argument%d name '%s' conflicts with "
- "another field.\n", i, argv[i]);
- ret = -EINVAL;
- goto error;
- }
-
tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
if (!tp->args[i].name) {
pr_info("Failed to allocate argument%d name '%s'.\n",
@@ -753,9 +835,19 @@ static int create_trace_probe(int argc, char **argv)
ret = -ENOMEM;
goto error;
}
+ tmp = strchr(tp->args[i].name, ':');
+ if (tmp)
+ *tmp = '_'; /* convert : to _ */
+
+ if (conflict_field_name(tp->args[i].name, tp->args, i)) {
+ pr_info("Argument%d name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
+ goto error;
+ }
/* Parse fetch argument */
- ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+ ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
if (ret) {
pr_info("Parse error at argument%d. (%d)\n", i, ret);
kfree(tp->args[i].name);
@@ -810,11 +902,10 @@ static void probes_seq_stop(struct seq_file *m, void *v)
static int probes_seq_show(struct seq_file *m, void *v)
{
struct trace_probe *tp = v;
- int i, ret;
- char buf[MAX_ARGSTR_LEN + 1];
+ int i;
seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+ seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
if (!tp->symbol)
seq_printf(m, " 0x%p", tp->rp.kp.addr);
@@ -823,15 +914,10 @@ static int probes_seq_show(struct seq_file *m, void *v)
else
seq_printf(m, " %s", probe_symbol(tp));
- for (i = 0; i < tp->nr_args; i++) {
- ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
- if (ret < 0) {
- pr_warning("Argument%d decoding error(%d).\n", i, ret);
- return ret;
- }
- seq_printf(m, " %s=%s", tp->args[i].name, buf);
- }
+ for (i = 0; i < tp->nr_args; i++)
+ seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
seq_printf(m, "\n");
+
return 0;
}
@@ -958,12 +1044,13 @@ static const struct file_operations kprobe_profile_ops = {
};
/* Kprobe handler */
-static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
{
struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
- struct kprobe_trace_entry *entry;
+ struct kprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
+ u8 *data;
int size, i, pc;
unsigned long irq_flags;
struct ftrace_event_call *call = &tp->call;
@@ -973,32 +1060,32 @@ static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
local_save_flags(irq_flags);
pc = preempt_count();
- size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+ size = sizeof(*entry) + tp->size;
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
- return 0;
+ return;
entry = ring_buffer_event_data(event);
- entry->nargs = tp->nr_args;
entry->ip = (unsigned long)kp->addr;
+ data = (u8 *)&entry[1];
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
if (!filter_current_check_discard(buffer, call, entry, event))
trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
- return 0;
}
/* Kretprobe handler */
-static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
- struct kretprobe_trace_entry *entry;
+ struct kretprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
+ u8 *data;
int size, i, pc;
unsigned long irq_flags;
struct ftrace_event_call *call = &tp->call;
@@ -1006,39 +1093,37 @@ static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
local_save_flags(irq_flags);
pc = preempt_count();
- size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+ size = sizeof(*entry) + tp->size;
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
- return 0;
+ return;
entry = ring_buffer_event_data(event);
- entry->nargs = tp->nr_args;
entry->func = (unsigned long)tp->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
+ data = (u8 *)&entry[1];
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
if (!filter_current_check_discard(buffer, call, entry, event))
trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
-
- return 0;
}
/* Event entry printers */
enum print_line_t
-print_kprobe_event(struct trace_iterator *iter, int flags)
+print_kprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
- struct kprobe_trace_entry *field;
+ struct kprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
+ u8 *data;
int i;
- field = (struct kprobe_trace_entry *)iter->ent;
- event = ftrace_find_event(field->ent.type);
- tp = container_of(event, struct trace_probe, event);
+ field = (struct kprobe_trace_entry_head *)iter->ent;
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
@@ -1049,9 +1134,10 @@ print_kprobe_event(struct trace_iterator *iter, int flags)
if (!trace_seq_puts(s, ")"))
goto partial;
- for (i = 0; i < field->nargs; i++)
- if (!trace_seq_printf(s, " %s=%lx",
- tp->args[i].name, field->args[i]))
+ data = (u8 *)&field[1];
+ for (i = 0; i < tp->nr_args; i++)
+ if (!tp->args[i].type->print(s, tp->args[i].name,
+ data + tp->args[i].offset))
goto partial;
if (!trace_seq_puts(s, "\n"))
@@ -1063,17 +1149,17 @@ partial:
}
enum print_line_t
-print_kretprobe_event(struct trace_iterator *iter, int flags)
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
- struct kretprobe_trace_entry *field;
+ struct kretprobe_trace_entry_head *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
+ u8 *data;
int i;
- field = (struct kretprobe_trace_entry *)iter->ent;
- event = ftrace_find_event(field->ent.type);
- tp = container_of(event, struct trace_probe, event);
+ field = (struct kretprobe_trace_entry_head *)iter->ent;
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
@@ -1090,9 +1176,10 @@ print_kretprobe_event(struct trace_iterator *iter, int flags)
if (!trace_seq_puts(s, ")"))
goto partial;
- for (i = 0; i < field->nargs; i++)
- if (!trace_seq_printf(s, " %s=%lx",
- tp->args[i].name, field->args[i]))
+ data = (u8 *)&field[1];
+ for (i = 0; i < tp->nr_args; i++)
+ if (!tp->args[i].type->print(s, tp->args[i].name,
+ data + tp->args[i].offset))
goto partial;
if (!trace_seq_puts(s, "\n"))
@@ -1129,8 +1216,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
static int probe_event_raw_init(struct ftrace_event_call *event_call)
{
- INIT_LIST_HEAD(&event_call->fields);
-
return 0;
}
@@ -1148,242 +1233,170 @@ static int probe_event_raw_init(struct ftrace_event_call *event_call)
static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
- struct kprobe_trace_entry field;
+ struct kprobe_trace_entry_head field;
struct trace_probe *tp = (struct trace_probe *)event_call->data;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
- DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++)
- DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ for (i = 0; i < tp->nr_args; i++) {
+ ret = trace_define_field(event_call, tp->args[i].type->name,
+ tp->args[i].name,
+ sizeof(field) + tp->args[i].offset,
+ tp->args[i].type->size,
+ tp->args[i].type->is_signed,
+ FILTER_OTHER);
+ if (ret)
+ return ret;
+ }
return 0;
}
static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
- struct kretprobe_trace_entry field;
+ struct kretprobe_trace_entry_head field;
struct trace_probe *tp = (struct trace_probe *)event_call->data;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
- DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++)
- DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ for (i = 0; i < tp->nr_args; i++) {
+ ret = trace_define_field(event_call, tp->args[i].type->name,
+ tp->args[i].name,
+ sizeof(field) + tp->args[i].offset,
+ tp->args[i].type->size,
+ tp->args[i].type->is_signed,
+ FILTER_OTHER);
+ if (ret)
+ return ret;
+ }
return 0;
}
-static int __probe_event_show_format(struct trace_seq *s,
- struct trace_probe *tp, const char *fmt,
- const char *arg)
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
{
int i;
+ int pos = 0;
- /* Show format */
- if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
- return 0;
+ const char *fmt, *arg;
- for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
- return 0;
+ if (!probe_is_return(tp)) {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ } else {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ }
- if (!trace_seq_printf(s, "\", %s", arg))
- return 0;
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
- for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
- return 0;
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
- return trace_seq_puts(s, "\n");
-}
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+ tp->args[i].name, tp->args[i].type->fmt);
+ }
-#undef SHOW_FIELD
-#define SHOW_FIELD(type, item, name) \
- do { \
- ret = trace_seq_printf(s, "\tfield:" #type " %s;\t" \
- "offset:%u;\tsize:%u;\tsigned:%d;\n", name,\
- (unsigned int)offsetof(typeof(field), item),\
- (unsigned int)sizeof(type), \
- is_signed_type(type)); \
- if (!ret) \
- return 0; \
- } while (0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-static int kprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
-{
- struct kprobe_trace_entry field __attribute__((unused));
- int ret, i;
- struct trace_probe *tp = (struct trace_probe *)call->data;
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tp->args[i].name);
+ }
- SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
- SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+#undef LEN_OR_ZERO
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++)
- SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
- trace_seq_puts(s, "\n");
-
- return __probe_event_show_format(s, tp, "(%lx)",
- "REC->" FIELD_STRING_IP);
+ /* return the length of print_fmt */
+ return pos;
}
-static int kretprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
+static int set_print_fmt(struct trace_probe *tp)
{
- struct kretprobe_trace_entry field __attribute__((unused));
- int ret, i;
- struct trace_probe *tp = (struct trace_probe *)call->data;
+ int len;
+ char *print_fmt;
- SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
- SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
- SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tp, NULL, 0);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++)
- SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
- trace_seq_puts(s, "\n");
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tp, print_fmt, len + 1);
+ tp->call.print_fmt = print_fmt;
- return __probe_event_show_format(s, tp, "(%lx <- %lx)",
- "REC->" FIELD_STRING_FUNC
- ", REC->" FIELD_STRING_RETIP);
+ return 0;
}
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
/* Kprobe profile handler */
-static __kprobes int kprobe_profile_func(struct kprobe *kp,
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
struct ftrace_event_call *call = &tp->call;
- struct kprobe_trace_entry *entry;
- struct trace_entry *ent;
- int size, __size, i, pc, __cpu;
- unsigned long irq_flags;
- char *trace_buf;
- char *raw_data;
+ struct kprobe_trace_entry_head *entry;
+ struct hlist_head *head;
+ u8 *data;
+ int size, __size, i;
int rctx;
- pc = preempt_count();
- __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+ __size = sizeof(*entry) + tp->size;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"profile buffer not large enough"))
- return 0;
-
- /*
- * Protect the non nmi buffer
- * This also protects the rcu read side
- */
- local_irq_save(irq_flags);
-
- rctx = perf_swevent_get_recursion_context();
- if (rctx < 0)
- goto end_recursion;
+ return;
- __cpu = smp_processor_id();
-
- if (in_nmi())
- trace_buf = rcu_dereference(perf_trace_buf_nmi);
- else
- trace_buf = rcu_dereference(perf_trace_buf);
-
- if (!trace_buf)
- goto end;
-
- raw_data = per_cpu_ptr(trace_buf, __cpu);
-
- /* Zero dead bytes from alignment to avoid buffer leak to userspace */
- *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
- entry = (struct kprobe_trace_entry *)raw_data;
- ent = &entry->ent;
+ entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+ if (!entry)
+ return;
- tracing_generic_entry_update(ent, irq_flags, pc);
- ent->type = call->id;
- entry->nargs = tp->nr_args;
entry->ip = (unsigned long)kp->addr;
+ data = (u8 *)&entry[1];
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- perf_tp_event(call->id, entry->ip, 1, entry, size);
-
-end:
- perf_swevent_put_recursion_context(rctx);
-end_recursion:
- local_irq_restore(irq_flags);
+ call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
- return 0;
+ head = per_cpu_ptr(call->perf_events, smp_processor_id());
+ perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
}
/* Kretprobe profile handler */
-static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
struct ftrace_event_call *call = &tp->call;
- struct kretprobe_trace_entry *entry;
- struct trace_entry *ent;
- int size, __size, i, pc, __cpu;
- unsigned long irq_flags;
- char *trace_buf;
- char *raw_data;
+ struct kretprobe_trace_entry_head *entry;
+ struct hlist_head *head;
+ u8 *data;
+ int size, __size, i;
int rctx;
- pc = preempt_count();
- __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+ __size = sizeof(*entry) + tp->size;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"profile buffer not large enough"))
- return 0;
-
- /*
- * Protect the non nmi buffer
- * This also protects the rcu read side
- */
- local_irq_save(irq_flags);
+ return;
- rctx = perf_swevent_get_recursion_context();
- if (rctx < 0)
- goto end_recursion;
-
- __cpu = smp_processor_id();
-
- if (in_nmi())
- trace_buf = rcu_dereference(perf_trace_buf_nmi);
- else
- trace_buf = rcu_dereference(perf_trace_buf);
-
- if (!trace_buf)
- goto end;
-
- raw_data = per_cpu_ptr(trace_buf, __cpu);
-
- /* Zero dead bytes from alignment to avoid buffer leak to userspace */
- *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
- entry = (struct kretprobe_trace_entry *)raw_data;
- ent = &entry->ent;
+ entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+ if (!entry)
+ return;
- tracing_generic_entry_update(ent, irq_flags, pc);
- ent->type = call->id;
- entry->nargs = tp->nr_args;
entry->func = (unsigned long)tp->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
+ data = (u8 *)&entry[1];
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
-
-end:
- perf_swevent_put_recursion_context(rctx);
-end_recursion:
- local_irq_restore(irq_flags);
+ call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
- return 0;
+ head = per_cpu_ptr(call->perf_events, smp_processor_id());
+ perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
}
-static int probe_profile_enable(struct ftrace_event_call *call)
+static int probe_perf_enable(struct ftrace_event_call *call)
{
struct trace_probe *tp = (struct trace_probe *)call->data;
@@ -1395,7 +1408,7 @@ static int probe_profile_enable(struct ftrace_event_call *call)
return enable_kprobe(&tp->rp.kp);
}
-static void probe_profile_disable(struct ftrace_event_call *call)
+static void probe_perf_disable(struct ftrace_event_call *call)
{
struct trace_probe *tp = (struct trace_probe *)call->data;
@@ -1408,8 +1421,28 @@ static void probe_profile_disable(struct ftrace_event_call *call)
disable_kprobe(&tp->rp.kp);
}
}
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return probe_event_enable(event);
+ case TRACE_REG_UNREGISTER:
+ probe_event_disable(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return probe_perf_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ probe_perf_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
@@ -1418,10 +1451,10 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
if (tp->flags & TP_FLAG_TRACE)
kprobe_trace_func(kp, regs);
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
if (tp->flags & TP_FLAG_PROFILE)
- kprobe_profile_func(kp, regs);
-#endif /* CONFIG_EVENT_PROFILE */
+ kprobe_perf_func(kp, regs);
+#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1432,13 +1465,21 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
if (tp->flags & TP_FLAG_TRACE)
kretprobe_trace_func(ri, regs);
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
if (tp->flags & TP_FLAG_PROFILE)
- kretprobe_profile_func(ri, regs);
-#endif /* CONFIG_EVENT_PROFILE */
+ kretprobe_perf_func(ri, regs);
+#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
+static struct trace_event_functions kretprobe_funcs = {
+ .trace = print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+ .trace = print_kprobe_event
+};
+
static int register_probe_event(struct trace_probe *tp)
{
struct ftrace_event_call *call = &tp->call;
@@ -1446,33 +1487,31 @@ static int register_probe_event(struct trace_probe *tp)
/* Initialize ftrace_event_call */
if (probe_is_return(tp)) {
- tp->event.trace = print_kretprobe_event;
- call->raw_init = probe_event_raw_init;
- call->show_format = kretprobe_event_show_format;
- call->define_fields = kretprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &kretprobe_funcs;
+ call->class->raw_init = probe_event_raw_init;
+ call->class->define_fields = kretprobe_event_define_fields;
} else {
- tp->event.trace = print_kprobe_event;
- call->raw_init = probe_event_raw_init;
- call->show_format = kprobe_event_show_format;
- call->define_fields = kprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &kprobe_funcs;
+ call->class->raw_init = probe_event_raw_init;
+ call->class->define_fields = kprobe_event_define_fields;
}
- call->event = &tp->event;
- call->id = register_ftrace_event(&tp->event);
- if (!call->id)
+ if (set_print_fmt(tp) < 0)
+ return -ENOMEM;
+ ret = register_ftrace_event(&call->event);
+ if (!ret) {
+ kfree(call->print_fmt);
return -ENODEV;
- call->enabled = 0;
- call->regfunc = probe_event_enable;
- call->unregfunc = probe_event_disable;
-
-#ifdef CONFIG_EVENT_PROFILE
- call->profile_enable = probe_profile_enable;
- call->profile_disable = probe_profile_disable;
-#endif
+ }
+ call->flags = 0;
+ call->class->reg = kprobe_register;
call->data = tp;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
- unregister_ftrace_event(&tp->event);
+ kfree(call->print_fmt);
+ unregister_ftrace_event(&call->event);
}
return ret;
}
@@ -1481,6 +1520,7 @@ static void unregister_probe_event(struct trace_probe *tp)
{
/* tp->event is unregistered in trace_remove_event_call() */
trace_remove_event_call(&tp->call);
+ kfree(tp->call.print_fmt);
}
/* Make a debugfs interface for controling probe points */
@@ -1523,28 +1563,67 @@ static int kprobe_trace_selftest_target(int a1, int a2, int a3,
static __init int kprobe_trace_self_tests_init(void)
{
- int ret;
+ int ret, warn = 0;
int (*target)(int, int, int, int, int, int);
+ struct trace_probe *tp;
target = kprobe_trace_selftest_target;
pr_info("Testing kprobe tracing: ");
ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
- "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
- if (WARN_ON_ONCE(ret))
- pr_warning("error enabling function entry\n");
+ "$stack $stack0 +0($stack)");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on probing function entry.\n");
+ warn++;
+ } else {
+ /* Enable trace point */
+ tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tp == NULL)) {
+ pr_warning("error on getting new probe.\n");
+ warn++;
+ } else
+ probe_event_enable(&tp->call);
+ }
ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
"$retval");
- if (WARN_ON_ONCE(ret))
- pr_warning("error enabling function return\n");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on probing function return.\n");
+ warn++;
+ } else {
+ /* Enable trace point */
+ tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tp == NULL)) {
+ pr_warning("error on getting new probe.\n");
+ warn++;
+ } else
+ probe_event_enable(&tp->call);
+ }
+
+ if (warn)
+ goto end;
ret = target(1, 2, 3, 4, 5, 6);
- cleanup_all_probes();
+ ret = command_trace_probe("-:testprobe");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on deleting a probe.\n");
+ warn++;
+ }
+
+ ret = command_trace_probe("-:testprobe2");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on deleting a probe.\n");
+ warn++;
+ }
- pr_cont("OK\n");
+end:
+ cleanup_all_probes();
+ if (warn)
+ pr_cont("NG: Some tests are failed. Please check them.\n");
+ else
+ pr_cont("OK\n");
return 0;
}
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index 94103cdcf9d..8eaf00749b6 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -23,6 +23,7 @@
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include "trace_output.h"
@@ -33,12 +34,6 @@
#include <asm/atomic.h>
-/*
- * For now, let us restrict the no. of symbols traced simultaneously to number
- * of available hardware breakpoint registers.
- */
-#define KSYM_TRACER_MAX HBP_NUM
-
#define KSYM_TRACER_OP_LEN 3 /* rw- */
struct trace_ksym {
@@ -52,7 +47,6 @@ struct trace_ksym {
static struct trace_array *ksym_trace_array;
-static unsigned int ksym_filter_entry_count;
static unsigned int ksym_tracing_enabled;
static HLIST_HEAD(ksym_filter_head);
@@ -180,13 +174,6 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
struct trace_ksym *entry;
int ret = -ENOMEM;
- if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
- printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
- " new requests for tracing can be accepted now.\n",
- KSYM_TRACER_MAX);
- return -ENOSPC;
- }
-
entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
if (!entry)
return -ENOMEM;
@@ -202,13 +189,17 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
if (IS_ERR(entry->ksym_hbp)) {
ret = PTR_ERR(entry->ksym_hbp);
- printk(KERN_INFO "ksym_tracer request failed. Try again"
- " later!!\n");
+ if (ret == -ENOSPC) {
+ printk(KERN_ERR "ksym_tracer: Maximum limit reached."
+ " No new requests for tracing can be accepted now.\n");
+ } else {
+ printk(KERN_INFO "ksym_tracer request failed. Try again"
+ " later!!\n");
+ }
goto err;
}
hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
- ksym_filter_entry_count++;
return 0;
@@ -264,7 +255,6 @@ static void __ksym_trace_reset(void)
hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
ksym_hlist) {
unregister_wide_hw_breakpoint(entry->ksym_hbp);
- ksym_filter_entry_count--;
hlist_del_rcu(&(entry->ksym_hlist));
synchronize_rcu();
kfree(entry);
@@ -337,7 +327,6 @@ static ssize_t ksym_trace_filter_write(struct file *file,
goto out_unlock;
}
/* Error or "symbol:---" case: drop it */
- ksym_filter_entry_count--;
hlist_del_rcu(&(entry->ksym_hlist));
synchronize_rcu();
kfree(entry);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 0acd834659e..017fa376505 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
+#include <linux/slab.h>
#include <linux/time.h>
#include <asm/atomic.h>
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8e46b3323cd..57c1b459647 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -209,6 +209,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
return 1;
}
+EXPORT_SYMBOL(trace_seq_putc);
int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
{
@@ -253,7 +254,7 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
void *ret;
if (s->full)
- return 0;
+ return NULL;
if (len > ((PAGE_SIZE - 1) - s->len)) {
s->full = 1;
@@ -355,6 +356,21 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
}
EXPORT_SYMBOL(ftrace_print_symbols_seq);
+const char *
+ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
+{
+ int i;
+ const char *ret = p->buffer + p->len;
+
+ for (i = 0; i < buf_len; i++)
+ trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]);
+
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(ftrace_print_hex_seq);
+
#ifdef CONFIG_KRETPROBES
static inline const char *kretprobed(const char *name)
{
@@ -726,6 +742,9 @@ int register_ftrace_event(struct trace_event *event)
if (WARN_ON(!event))
goto out;
+ if (WARN_ON(!event->funcs))
+ goto out;
+
INIT_LIST_HEAD(&event->list);
if (!event->type) {
@@ -758,14 +777,14 @@ int register_ftrace_event(struct trace_event *event)
goto out;
}
- if (event->trace == NULL)
- event->trace = trace_nop_print;
- if (event->raw == NULL)
- event->raw = trace_nop_print;
- if (event->hex == NULL)
- event->hex = trace_nop_print;
- if (event->binary == NULL)
- event->binary = trace_nop_print;
+ if (event->funcs->trace == NULL)
+ event->funcs->trace = trace_nop_print;
+ if (event->funcs->raw == NULL)
+ event->funcs->raw = trace_nop_print;
+ if (event->funcs->hex == NULL)
+ event->funcs->hex = trace_nop_print;
+ if (event->funcs->binary == NULL)
+ event->funcs->binary = trace_nop_print;
key = event->type & (EVENT_HASHSIZE - 1);
@@ -807,13 +826,15 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
* Standard events
*/
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags)
+enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return TRACE_TYPE_HANDLED;
}
/* TRACE_FN */
-static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -840,7 +861,8 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
-static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
@@ -854,7 +876,8 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -867,7 +890,8 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -880,14 +904,18 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_fn_event = {
- .type = TRACE_FN,
+static struct trace_event_functions trace_fn_funcs = {
.trace = trace_fn_trace,
.raw = trace_fn_raw,
.hex = trace_fn_hex,
.binary = trace_fn_bin,
};
+static struct trace_event trace_fn_event = {
+ .type = TRACE_FN,
+ .funcs = &trace_fn_funcs,
+};
+
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
@@ -916,13 +944,14 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_print(iter, "==>");
}
static enum print_line_t trace_wake_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
return trace_ctxwake_print(iter, " +");
}
@@ -950,12 +979,14 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_raw(iter, 0);
}
-static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_raw(iter, '+');
}
@@ -984,18 +1015,20 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_hex(iter, 0);
}
-static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_hex(iter, '+');
}
static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct ctx_switch_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1012,25 +1045,33 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_ctx_event = {
- .type = TRACE_CTX,
+static struct trace_event_functions trace_ctx_funcs = {
.trace = trace_ctx_print,
.raw = trace_ctx_raw,
.hex = trace_ctx_hex,
.binary = trace_ctxwake_bin,
};
-static struct trace_event trace_wake_event = {
- .type = TRACE_WAKE,
+static struct trace_event trace_ctx_event = {
+ .type = TRACE_CTX,
+ .funcs = &trace_ctx_funcs,
+};
+
+static struct trace_event_functions trace_wake_funcs = {
.trace = trace_wake_print,
.raw = trace_wake_raw,
.hex = trace_wake_hex,
.binary = trace_ctxwake_bin,
};
+static struct trace_event trace_wake_event = {
+ .type = TRACE_WAKE,
+ .funcs = &trace_wake_funcs,
+};
+
/* TRACE_SPECIAL */
static enum print_line_t trace_special_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
@@ -1046,7 +1087,7 @@ static enum print_line_t trace_special_print(struct trace_iterator *iter,
}
static enum print_line_t trace_special_hex(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1061,7 +1102,7 @@ static enum print_line_t trace_special_hex(struct trace_iterator *iter,
}
static enum print_line_t trace_special_bin(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1075,18 +1116,22 @@ static enum print_line_t trace_special_bin(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_special_event = {
- .type = TRACE_SPECIAL,
+static struct trace_event_functions trace_special_funcs = {
.trace = trace_special_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_special_event = {
+ .type = TRACE_SPECIAL,
+ .funcs = &trace_special_funcs,
+};
+
/* TRACE_STACK */
static enum print_line_t trace_stack_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct stack_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1114,17 +1159,21 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_stack_event = {
- .type = TRACE_STACK,
+static struct trace_event_functions trace_stack_funcs = {
.trace = trace_stack_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_stack_event = {
+ .type = TRACE_STACK,
+ .funcs = &trace_stack_funcs,
+};
+
/* TRACE_USER_STACK */
static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct userstack_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1143,17 +1192,22 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_user_stack_event = {
- .type = TRACE_USER_STACK,
+static struct trace_event_functions trace_user_stack_funcs = {
.trace = trace_user_stack_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_user_stack_event = {
+ .type = TRACE_USER_STACK,
+ .funcs = &trace_user_stack_funcs,
+};
+
/* TRACE_BPRINT */
static enum print_line_t
-trace_bprint_print(struct trace_iterator *iter, int flags)
+trace_bprint_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
@@ -1178,7 +1232,8 @@ trace_bprint_print(struct trace_iterator *iter, int flags)
static enum print_line_t
-trace_bprint_raw(struct trace_iterator *iter, int flags)
+trace_bprint_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct bprint_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1197,16 +1252,19 @@ trace_bprint_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
+static struct trace_event_functions trace_bprint_funcs = {
+ .trace = trace_bprint_print,
+ .raw = trace_bprint_raw,
+};
static struct trace_event trace_bprint_event = {
.type = TRACE_BPRINT,
- .trace = trace_bprint_print,
- .raw = trace_bprint_raw,
+ .funcs = &trace_bprint_funcs,
};
/* TRACE_PRINT */
static enum print_line_t trace_print_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1225,7 +1283,8 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct print_entry *field;
@@ -1240,12 +1299,16 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_print_event = {
- .type = TRACE_PRINT,
+static struct trace_event_functions trace_print_funcs = {
.trace = trace_print_print,
.raw = trace_print_raw,
};
+static struct trace_event trace_print_event = {
+ .type = TRACE_PRINT,
+ .funcs = &trace_print_funcs,
+};
+
static struct trace_event *events[] __initdata = {
&trace_fn_event,
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 9d91c72ba38..c038eba0492 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -25,7 +25,7 @@ extern void trace_event_read_unlock(void);
extern struct trace_event *ftrace_find_event(int type);
extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
- int flags);
+ int flags, struct trace_event *event);
extern int
trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 5fca0f51fde..8f758d070c4 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,8 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
}
static void
-probe_sched_switch(struct rq *__rq, struct task_struct *prev,
- struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
unsigned long flags;
@@ -109,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
}
static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
{
struct trace_array_cpu *data;
unsigned long flags;
@@ -139,21 +138,21 @@ static int tracing_sched_register(void)
{
int ret;
- ret = register_trace_sched_wakeup(probe_sched_wakeup);
+ ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return ret;
}
- ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+ ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
- ret = register_trace_sched_switch(probe_sched_switch);
+ ret = register_trace_sched_switch(probe_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
@@ -162,17 +161,17 @@ static int tracing_sched_register(void)
return ret;
fail_deprobe_wake_new:
- unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
fail_deprobe:
- unregister_trace_sched_wakeup(probe_sched_wakeup);
+ unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
return ret;
}
static void tracing_sched_unregister(void)
{
- unregister_trace_sched_switch(probe_sched_switch);
- unregister_trace_sched_wakeup_new(probe_sched_wakeup);
- unregister_trace_sched_wakeup(probe_sched_wakeup);
+ unregister_trace_sched_switch(probe_sched_switch, NULL);
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+ unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
static void tracing_start_sched_switch(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0271742abb8..0e73bc2ef8c 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -98,7 +98,8 @@ static int report_latency(cycle_t delta)
return 1;
}
-static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
{
if (task != wakeup_task)
return;
@@ -107,8 +108,8 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
}
static void notrace
-probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
- struct task_struct *next)
+probe_wakeup_sched_switch(void *ignore,
+ struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
cycle_t T0, T1, delta;
@@ -200,7 +201,7 @@ static void wakeup_reset(struct trace_array *tr)
}
static void
-probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p, int success)
{
struct trace_array_cpu *data;
int cpu = smp_processor_id();
@@ -264,28 +265,28 @@ static void start_wakeup_tracer(struct trace_array *tr)
{
int ret;
- ret = register_trace_sched_wakeup(probe_wakeup);
+ ret = register_trace_sched_wakeup(probe_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return;
}
- ret = register_trace_sched_wakeup_new(probe_wakeup);
+ ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
- ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+ ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
goto fail_deprobe_wake_new;
}
- ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+ ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_migrate_task\n");
@@ -312,19 +313,19 @@ static void start_wakeup_tracer(struct trace_array *tr)
return;
fail_deprobe_wake_new:
- unregister_trace_sched_wakeup_new(probe_wakeup);
+ unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
- unregister_trace_sched_wakeup(probe_wakeup);
+ unregister_trace_sched_wakeup(probe_wakeup, NULL);
}
static void stop_wakeup_tracer(struct trace_array *tr)
{
tracer_enabled = 0;
unregister_ftrace_function(&trace_ops);
- unregister_trace_sched_switch(probe_wakeup_sched_switch);
- unregister_trace_sched_wakeup_new(probe_wakeup);
- unregister_trace_sched_wakeup(probe_wakeup);
- unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
+ unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+ unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+ unregister_trace_sched_wakeup(probe_wakeup, NULL);
+ unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
}
static int __wakeup_tracer_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 280fea470d6..250e7f9bd2f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -3,6 +3,7 @@
#include <linux/stringify.h>
#include <linux/kthread.h>
#include <linux/delay.h>
+#include <linux/slab.h>
static inline int trace_valid_entry(struct trace_entry *entry)
{
@@ -16,7 +17,6 @@ static inline int trace_valid_entry(struct trace_entry *entry)
case TRACE_BRANCH:
case TRACE_GRAPH_ENT:
case TRACE_GRAPH_RET:
- case TRACE_HW_BRANCHES:
case TRACE_KSYM:
return 1;
}
@@ -29,7 +29,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
struct trace_entry *entry;
unsigned int loops = 0;
- while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+ while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
entry = ring_buffer_event_data(event);
/*
@@ -255,7 +255,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
/* Maximum number of functions to trace before diagnosing a hang */
#define GRAPH_MAX_FUNC_TEST 100000000
-static void __ftrace_dump(bool disable_tracing);
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
static unsigned int graph_hang_thresh;
/* Wrap the real function entry probe to avoid possible hanging */
@@ -266,7 +267,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
ftrace_graph_stop();
printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
if (ftrace_dump_on_oops)
- __ftrace_dump(false);
+ __ftrace_dump(false, DUMP_ALL);
return 0;
}
@@ -754,62 +755,6 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
}
#endif /* CONFIG_BRANCH_TRACER */
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
- struct trace_array *tr)
-{
- struct trace_iterator *iter;
- struct tracer tracer;
- unsigned long count;
- int ret;
-
- if (!trace->open) {
- printk(KERN_CONT "missing open function...");
- return -1;
- }
-
- ret = tracer_init(trace, tr);
- if (ret) {
- warn_failed_init_tracer(trace, ret);
- return ret;
- }
-
- /*
- * The hw-branch tracer needs to collect the trace from the various
- * cpu trace buffers - before tracing is stopped.
- */
- iter = kzalloc(sizeof(*iter), GFP_KERNEL);
- if (!iter)
- return -ENOMEM;
-
- memcpy(&tracer, trace, sizeof(tracer));
-
- iter->trace = &tracer;
- iter->tr = tr;
- iter->pos = -1;
- mutex_init(&iter->mutex);
-
- trace->open(iter);
-
- mutex_destroy(&iter->mutex);
- kfree(iter);
-
- tracing_stop();
-
- ret = trace_test_buffer(tr, &count);
- trace->reset(tr);
- tracing_start();
-
- if (!ret && !count) {
- printk(KERN_CONT "no entries found..");
- ret = -1;
- }
-
- return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
#ifdef CONFIG_KSYM_TRACER
static int ksym_selftest_dummy;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 678a5120ee3..f4bc9b27de5 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -157,6 +157,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
unsigned long val, flags;
char buf[64];
int ret;
+ int cpu;
if (count >= sizeof(buf))
return -EINVAL;
@@ -171,9 +172,20 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
return ret;
local_irq_save(flags);
+
+ /*
+ * In case we trace inside arch_spin_lock() or after (NMI),
+ * we will cause circular lock, so we also need to increase
+ * the percpu trace_active here.
+ */
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
arch_spin_lock(&max_stack_lock);
*ptr = val;
arch_spin_unlock(&max_stack_lock);
+
+ per_cpu(trace_active, cpu)--;
local_irq_restore(flags);
return count;
@@ -206,7 +218,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ int cpu;
+
local_irq_disable();
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
arch_spin_lock(&max_stack_lock);
if (*pos == 0)
@@ -217,7 +235,13 @@ static void *t_start(struct seq_file *m, loff_t *pos)
static void t_stop(struct seq_file *m, void *p)
{
+ int cpu;
+
arch_spin_unlock(&max_stack_lock);
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)--;
+
local_irq_enable();
}
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index a4bb239eb98..96cffb269e7 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -10,6 +10,7 @@
#include <linux/list.h>
+#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/debugfs.h>
#include "trace_stat.h"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 75289f372dd..d2c859cec9e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
#include <trace/syscall.h>
#include <trace/events/syscalls.h>
+#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
#include <linux/perf_event.h>
@@ -14,6 +15,54 @@ static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+
+static int syscall_enter_define_fields(struct ftrace_event_call *call);
+static int syscall_exit_define_fields(struct ftrace_event_call *call);
+
+static struct list_head *
+syscall_get_enter_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->enter_fields;
+}
+
+static struct list_head *
+syscall_get_exit_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->exit_fields;
+}
+
+struct trace_event_functions enter_syscall_print_funcs = {
+ .trace = print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+ .trace = print_syscall_exit,
+};
+
+struct ftrace_event_class event_class_syscall_enter = {
+ .system = "syscalls",
+ .reg = syscall_enter_register,
+ .define_fields = syscall_enter_define_fields,
+ .get_fields = syscall_get_enter_fields,
+ .raw_init = init_syscall_trace,
+};
+
+struct ftrace_event_class event_class_syscall_exit = {
+ .system = "syscalls",
+ .reg = syscall_exit_register,
+ .define_fields = syscall_exit_define_fields,
+ .get_fields = syscall_get_exit_fields,
+ .raw_init = init_syscall_trace,
+};
+
extern unsigned long __start_syscalls_metadata[];
extern unsigned long __stop_syscalls_metadata[];
@@ -52,7 +101,8 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
}
enum print_line_t
-print_syscall_enter(struct trace_iterator *iter, int flags)
+print_syscall_enter(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
@@ -67,7 +117,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
if (!entry)
goto end;
- if (entry->enter_event->id != ent->type) {
+ if (entry->enter_event->event.type != ent->type) {
WARN_ON_ONCE(1);
goto end;
}
@@ -104,7 +154,8 @@ end:
}
enum print_line_t
-print_syscall_exit(struct trace_iterator *iter, int flags)
+print_syscall_exit(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
@@ -122,7 +173,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
- if (entry->exit_event->id != ent->type) {
+ if (entry->exit_event->event.type != ent->type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
@@ -143,73 +194,68 @@ extern char *__bad_type_size(void);
#type, #name, offsetof(typeof(trace), name), \
sizeof(trace.name), is_signed_type(type)
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+static
+int __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
{
int i;
- int ret;
- struct syscall_metadata *entry = call->data;
- struct syscall_trace_enter trace;
- int offset = offsetof(struct syscall_trace_enter, args);
+ int pos = 0;
- ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n",
- SYSCALL_FIELD(int, nr));
- if (!ret)
- return 0;
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
- entry->args[i]);
- if (!ret)
- return 0;
- ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
- "\tsigned:%u;\n", offset,
- sizeof(unsigned long),
- is_signed_type(unsigned long));
- if (!ret)
- return 0;
- offset += sizeof(unsigned long);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+ entry->args[i], sizeof(unsigned long),
+ i == entry->nb_args - 1 ? "" : ", ");
}
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- trace_seq_puts(s, "\nprint fmt: \"");
for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
- sizeof(unsigned long),
- i == entry->nb_args - 1 ? "" : ", ");
- if (!ret)
- return 0;
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", ((unsigned long)(REC->%s))", entry->args[i]);
}
- trace_seq_putc(s, '"');
- for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
- entry->args[i]);
- if (!ret)
- return 0;
- }
+#undef LEN_OR_ZERO
- return trace_seq_putc(s, '\n');
+ /* return the length of print_fmt */
+ return pos;
}
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
{
- int ret;
- struct syscall_trace_exit trace;
+ char *print_fmt;
+ int len;
+ struct syscall_metadata *entry = call->data;
- ret = trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n",
- SYSCALL_FIELD(int, nr),
- SYSCALL_FIELD(long, ret));
- if (!ret)
+ if (entry->enter_event != call) {
+ call->print_fmt = "\"0x%lx\", REC->ret";
return 0;
+ }
+
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_enter_print_fmt(entry, NULL, 0);
+
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
- return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+ /* Second: actually write the @print_fmt */
+ __set_enter_print_fmt(entry, print_fmt, len + 1);
+ call->print_fmt = print_fmt;
+
+ return 0;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ if (entry->enter_event == call)
+ kfree(call->print_fmt);
}
-int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
struct syscall_metadata *meta = call->data;
@@ -232,7 +278,7 @@ int syscall_enter_define_fields(struct ftrace_event_call *call)
return ret;
}
-int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int syscall_exit_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_exit trace;
int ret;
@@ -247,7 +293,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
return ret;
}
-void ftrace_syscall_enter(struct pt_regs *regs, long id)
+void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
@@ -269,7 +315,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->enter_event->id, size, 0, 0);
+ sys_data->enter_event->event.type, size, 0, 0);
if (!event)
return;
@@ -282,7 +328,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-void ftrace_syscall_exit(struct pt_regs *regs, long ret)
+void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
@@ -301,7 +347,7 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
return;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->exit_event->id, sizeof(*entry), 0, 0);
+ sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
if (!event)
return;
@@ -324,7 +370,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
- ret = register_trace_sys_enter(ftrace_syscall_enter);
+ ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
if (!ret) {
set_bit(num, enabled_enter_syscalls);
sys_refcount_enter++;
@@ -344,7 +390,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
sys_refcount_enter--;
clear_bit(num, enabled_enter_syscalls);
if (!sys_refcount_enter)
- unregister_trace_sys_enter(ftrace_syscall_enter);
+ unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
@@ -358,7 +404,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
- ret = register_trace_sys_exit(ftrace_syscall_exit);
+ ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
if (!ret) {
set_bit(num, enabled_exit_syscalls);
sys_refcount_exit++;
@@ -378,7 +424,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
sys_refcount_exit--;
clear_bit(num, enabled_exit_syscalls);
if (!sys_refcount_exit)
- unregister_trace_sys_exit(ftrace_syscall_exit);
+ unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
@@ -386,12 +432,22 @@ int init_syscall_trace(struct ftrace_event_call *call)
{
int id;
- id = register_ftrace_event(call->event);
- if (!id)
- return -ENODEV;
- call->id = id;
- INIT_LIST_HEAD(&call->fields);
- return 0;
+ if (set_syscall_print_fmt(call) < 0)
+ return -ENOMEM;
+
+ id = trace_event_raw_init(call);
+
+ if (id < 0) {
+ free_syscall_print_fmt(call);
+ return id;
+ }
+
+ return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+ return (unsigned long)sys_call_table[nr];
}
int __init init_ftrace_syscalls(void)
@@ -421,27 +477,24 @@ int __init init_ftrace_syscalls(void)
}
core_initcall(init_ftrace_syscalls);
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
- unsigned long flags;
- char *trace_buf;
- char *raw_data;
+ struct hlist_head *head;
int syscall_nr;
int rctx;
int size;
- int cpu;
syscall_nr = syscall_get_nr(current, regs);
- if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+ if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -453,44 +506,24 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
size = ALIGN(size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
- "profile buffer not large enough"))
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "perf buffer not large enough"))
return;
- /* Protect the per cpu buffer, begin the rcu read side */
- local_irq_save(flags);
-
- rctx = perf_swevent_get_recursion_context();
- if (rctx < 0)
- goto end_recursion;
-
- cpu = smp_processor_id();
-
- trace_buf = rcu_dereference(perf_trace_buf);
-
- if (!trace_buf)
- goto end;
-
- raw_data = per_cpu_ptr(trace_buf, cpu);
-
- /* zero the dead bytes from align to not leak stack to user */
- *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
+ sys_data->enter_event->event.type, regs, &rctx);
+ if (!rec)
+ return;
- rec = (struct syscall_trace_enter *) raw_data;
- tracing_generic_entry_update(&rec->ent, 0, 0);
- rec->ent.type = sys_data->enter_event->id;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size);
-end:
- perf_swevent_put_recursion_context(rctx);
-end_recursion:
- local_irq_restore(flags);
+ head = per_cpu_ptr(sys_data->enter_event->perf_events, smp_processor_id());
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
}
-int prof_sysenter_enable(struct ftrace_event_call *call)
+int perf_sysenter_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
@@ -498,47 +531,44 @@ int prof_sysenter_enable(struct ftrace_event_call *call)
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- if (!sys_prof_refcount_enter)
- ret = register_trace_sys_enter(prof_syscall_enter);
+ if (!sys_perf_refcount_enter)
+ ret = register_trace_sys_enter(perf_syscall_enter, NULL);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
- set_bit(num, enabled_prof_enter_syscalls);
- sys_prof_refcount_enter++;
+ set_bit(num, enabled_perf_enter_syscalls);
+ sys_perf_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-void prof_sysenter_disable(struct ftrace_event_call *call)
+void perf_sysenter_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- sys_prof_refcount_enter--;
- clear_bit(num, enabled_prof_enter_syscalls);
- if (!sys_prof_refcount_enter)
- unregister_trace_sys_enter(prof_syscall_enter);
+ sys_perf_refcount_enter--;
+ clear_bit(num, enabled_perf_enter_syscalls);
+ if (!sys_perf_refcount_enter)
+ unregister_trace_sys_enter(perf_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
- unsigned long flags;
+ struct hlist_head *head;
int syscall_nr;
- char *trace_buf;
- char *raw_data;
int rctx;
int size;
- int cpu;
syscall_nr = syscall_get_nr(current, regs);
- if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+ if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -553,45 +583,23 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
* Impossible, but be paranoid with the future
* How to put this check outside runtime?
*/
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
- "exit event has grown above profile buffer size"))
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "exit event has grown above perf buffer size"))
return;
- /* Protect the per cpu buffer, begin the rcu read side */
- local_irq_save(flags);
-
- rctx = perf_swevent_get_recursion_context();
- if (rctx < 0)
- goto end_recursion;
-
- cpu = smp_processor_id();
-
- trace_buf = rcu_dereference(perf_trace_buf);
-
- if (!trace_buf)
- goto end;
-
- raw_data = per_cpu_ptr(trace_buf, cpu);
-
- /* zero the dead bytes from align to not leak stack to user */
- *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
-
- rec = (struct syscall_trace_exit *)raw_data;
+ rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
+ sys_data->exit_event->event.type, regs, &rctx);
+ if (!rec)
+ return;
- tracing_generic_entry_update(&rec->ent, 0, 0);
- rec->ent.type = sys_data->exit_event->id;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size);
-
-end:
- perf_swevent_put_recursion_context(rctx);
-end_recursion:
- local_irq_restore(flags);
+ head = per_cpu_ptr(sys_data->exit_event->perf_events, smp_processor_id());
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
}
-int prof_sysexit_enable(struct ftrace_event_call *call)
+int perf_sysexit_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
@@ -599,33 +607,73 @@ int prof_sysexit_enable(struct ftrace_event_call *call)
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- if (!sys_prof_refcount_exit)
- ret = register_trace_sys_exit(prof_syscall_exit);
+ if (!sys_perf_refcount_exit)
+ ret = register_trace_sys_exit(perf_syscall_exit, NULL);
if (ret) {
pr_info("event trace: Could not activate"
- "syscall entry trace point");
+ "syscall exit trace point");
} else {
- set_bit(num, enabled_prof_exit_syscalls);
- sys_prof_refcount_exit++;
+ set_bit(num, enabled_perf_exit_syscalls);
+ sys_perf_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-void prof_sysexit_disable(struct ftrace_event_call *call)
+void perf_sysexit_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- sys_prof_refcount_exit--;
- clear_bit(num, enabled_prof_exit_syscalls);
- if (!sys_prof_refcount_exit)
- unregister_trace_sys_exit(prof_syscall_exit);
+ sys_perf_refcount_exit--;
+ clear_bit(num, enabled_perf_exit_syscalls);
+ if (!sys_perf_refcount_exit)
+ unregister_trace_sys_exit(perf_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
+#endif /* CONFIG_PERF_EVENTS */
+
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_enter(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_enter(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysenter_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysenter_disable(event);
+ return 0;
#endif
+ }
+ return 0;
+}
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_exit(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_exit(event);
+ return 0;
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysexit_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysexit_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 40cafb07dff..a7cc3793baf 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
#include <trace/events/workqueue.h>
#include <linux/list.h>
#include <linux/percpu.h>
+#include <linux/slab.h>
#include <linux/kref.h>
#include "trace_stat.h"
#include "trace.h"
@@ -48,7 +49,8 @@ static void cpu_workqueue_stat_free(struct kref *kref)
/* Insertion of a work */
static void
-probe_workqueue_insertion(struct task_struct *wq_thread,
+probe_workqueue_insertion(void *ignore,
+ struct task_struct *wq_thread,
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -69,7 +71,8 @@ found:
/* Execution of a work */
static void
-probe_workqueue_execution(struct task_struct *wq_thread,
+probe_workqueue_execution(void *ignore,
+ struct task_struct *wq_thread,
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -89,7 +92,8 @@ found:
}
/* Creation of a cpu workqueue thread */
-static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+static void probe_workqueue_creation(void *ignore,
+ struct task_struct *wq_thread, int cpu)
{
struct cpu_workqueue_stats *cws;
unsigned long flags;
@@ -113,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
}
/* Destruction of a cpu workqueue thread */
-static void probe_workqueue_destruction(struct task_struct *wq_thread)
+static void
+probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
{
/* Workqueue only execute on one cpu */
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -258,19 +263,19 @@ int __init trace_workqueue_early_init(void)
{
int ret, cpu;
- ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+ ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
if (ret)
goto out;
- ret = register_trace_workqueue_execution(probe_workqueue_execution);
+ ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
if (ret)
goto no_insertion;
- ret = register_trace_workqueue_creation(probe_workqueue_creation);
+ ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
if (ret)
goto no_execution;
- ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+ ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
if (ret)
goto no_creation;
@@ -282,11 +287,11 @@ int __init trace_workqueue_early_init(void)
return 0;
no_creation:
- unregister_trace_workqueue_creation(probe_workqueue_creation);
+ unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
no_execution:
- unregister_trace_workqueue_execution(probe_workqueue_execution);
+ unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
no_insertion:
- unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+ unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
out:
pr_warning("trace_workqueue: unable to trace workqueues\n");