Skip to contentSkip to conversation

perf/kprobe: maxactive for fd-based kprobe

PATCH Superseded Dmitrii Dolgov 4 participants 8 messages Jun 9, 2022 – Jun 18, 2022

Subsystems (3)

v1 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 perf/kprobe: maxactive for fd-based kprobe

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

---
 include/linux/trace_events.h    |  3 ++-
 kernel/events/core.c            | 20 ++++++++++++++++----
 kernel/trace/trace_event_perf.c |  5 +++--
 kernel/trace/trace_kprobe.c     |  4 ++--
 kernel/trace/trace_probe.h      |  2 +-
 5 files changed, 24 insertions(+), 10 deletions(-)
include/linux/trace_events.h +2 -1
index e6e95a9f07a5..7ca453a73252 100644
@@ -850,7 +850,8 @@ extern void perf_trace_destroy(struct perf_event *event);
 extern int  perf_trace_add(struct perf_event *event, int flags);
 extern void perf_trace_del(struct perf_event *event, int flags);
 #ifdef CONFIG_KPROBE_EVENTS
-extern int  perf_kprobe_init(struct perf_event *event, bool is_retprobe);
+extern int  perf_kprobe_init(struct perf_event *event, bool is_retprobe,
+			     int max_active);
 extern void perf_kprobe_destroy(struct perf_event *event);
 extern int bpf_get_kprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **symbol,
kernel/events/core.c +16 -4
index 23bb19716ad3..f0e936b3dfc4 100644
@@ -9809,24 +9809,34 @@ static struct pmu perf_tracepoint = {
  * PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe
  *                               if not set, create kprobe/uprobe
  *
- * The following values specify a reference counter (or semaphore in the
- * terminology of tools like dtrace, systemtap, etc.) Userspace Statically
- * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset.
+ * PERF_UPROBE_REF_CTR_OFFSET_* specify a reference counter (or semaphore
+ * in the terminology of tools like dtrace, systemtap, etc.) Userspace
+ * Statically Defined Tracepoints (USDT). Currently, we use 40 bit for the
+ * offset.
  *
  * PERF_UPROBE_REF_CTR_OFFSET_BITS	# of bits in config as th offset
  * PERF_UPROBE_REF_CTR_OFFSET_SHIFT	# of bits to shift left
+ *
+ * PERF_KPROBE_MAX_ACTIVE_* defines max_active for kretprobe.
+ * KRETPROBE_MAXACTIVE_MAX is 4096. We allow 4095 here to save a bit.
  */
 enum perf_probe_config {
 	PERF_PROBE_CONFIG_IS_RETPROBE = 1U << 0,  /* [k,u]retprobe */
 	PERF_UPROBE_REF_CTR_OFFSET_BITS = 32,
 	PERF_UPROBE_REF_CTR_OFFSET_SHIFT = 64 - PERF_UPROBE_REF_CTR_OFFSET_BITS,
+	PERF_KPROBE_MAX_ACTIVE_BITS = 12,
+	PERF_KPROBE_MAX_ACTIVE_SHIFT = 64 - PERF_KPROBE_MAX_ACTIVE_BITS,
 };
 
 PMU_FORMAT_ATTR(retprobe, "config:0");
 #endif
 
 #ifdef CONFIG_KPROBE_EVENTS
+/* KRETPROBE_MAXACTIVE_MAX is 4096, only allow 4095 here to save a bit */
+PMU_FORMAT_ATTR(max_active, "config:52-63");
+
 static struct attribute *kprobe_attrs[] = {
+	&format_attr_max_active.attr,
 	&format_attr_retprobe.attr,
 	NULL,
 };
@@ -9857,6 +9867,7 @@ static int perf_kprobe_event_init(struct perf_event *event)
 {
 	int err;
 	bool is_retprobe;
+	int max_active;
 
 	if (event->attr.type != perf_kprobe.type)
 		return -ENOENT;
@@ -9871,7 +9882,8 @@ static int perf_kprobe_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 
 	is_retprobe = event->attr.config & PERF_PROBE_CONFIG_IS_RETPROBE;
-	err = perf_kprobe_init(event, is_retprobe);
+	max_active = event->attr.config >> PERF_KPROBE_MAX_ACTIVE_SHIFT;
+	err = perf_kprobe_init(event, is_retprobe, max_active);
 	if (err)
 		return err;
 
kernel/trace/trace_event_perf.c +3 -2
index a114549720d6..129000327809 100644
@@ -245,7 +245,8 @@ void perf_trace_destroy(struct perf_event *p_event)
 }
 
 #ifdef CONFIG_KPROBE_EVENTS
-int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
+int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe,
+					 int max_active)
 {
 	int ret;
 	char *func = NULL;
@@ -271,7 +272,7 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
 
 	tp_event = create_local_trace_kprobe(
 		func, (void *)(unsigned long)(p_event->attr.kprobe_addr),
-		p_event->attr.probe_offset, is_retprobe);
+		p_event->attr.probe_offset, is_retprobe, max_active);
 	if (IS_ERR(tp_event)) {
 		ret = PTR_ERR(tp_event);
 		goto out;
kernel/trace/trace_kprobe.c +2 -2
index 47cebef78532..3ad30cfce9c3 100644
@@ -1784,7 +1784,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk)
 /* create a trace_kprobe, but don't add it to global lists */
 struct trace_event_call *
 create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
-			  bool is_return)
+			  bool is_return, int max_active)
 {
 	enum probe_print_type ptype;
 	struct trace_kprobe *tk;
@@ -1799,7 +1799,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 	event = func ? func : "DUMMY_EVENT";
 
 	tk = alloc_trace_kprobe(KPROBE_EVENT_SYSTEM, event, (void *)addr, func,
-				offs, 0 /* maxactive */, 0 /* nargs */,
+				offs, max_active, 0 /* nargs */,
 				is_return);
 
 	if (IS_ERR(tk)) {
kernel/trace/trace_probe.h +1 -1
index 92cc149af0fd..26fe21980793 100644
@@ -376,7 +376,7 @@ extern int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_typ
 #ifdef CONFIG_PERF_EVENTS
 extern struct trace_event_call *
 create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
-			  bool is_return);
+			  bool is_return, int max_active);
 extern void destroy_local_trace_kprobe(struct trace_event_call *event_call);
 
 extern struct trace_event_call *
Signature · 1 line
2.32.0
#1 lore raw
Quoted 6 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

Quoted 6 lines

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

I've recently stumbled upon this seemingly lost topic, and wanted to raise it again. Please let me know if there is a more appropriate way to do so.

#2 lore raw
Quoted 11 lines · Dmitry Dolgov
Quoted 11 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

Quoted 5 lines
Quoted 2 lines

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

I've recently stumbled upon this seemingly lost topic, and wanted to raise it again. Please let me know if there is a more appropriate way to do so.

With kretprobe using rethook the maxactive limit is no longer used. So we probably don't need this patch.

Masami, wdyt?

#3 lore raw
Quoted 15 lines · On Sat, 11 Jun 2022 11:28:36 -0700 Alexei Starovoitov…
Quoted 14 lines · Dmitry Dolgov
Quoted 13 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

Quoted 7 lines
Quoted 2 lines

I've recently stumbled upon this seemingly lost topic, and wanted to raise it again. Please let me know if there is a more appropriate way to do so.

With kretprobe using rethook the maxactive limit is no longer used. So we probably don't need this patch.

Masami, wdyt?

No, rethook is just a library version of kretprobe return hook, so the maxactive is still alive. I would like to make the rethook to use(share with) function graph's per-task shadow stack. When that is done, the maxactive will be removed.

Thank you,

Signature · 1 line
Masami Hiramatsu (Google) <[email protected]>
#4 lore raw
Quoted 25 lines · Masami Hiramatsu
Quoted 21 lines · On Sat, 11 Jun 2022 11:28:36 -0700 Alexei Starovoitov…
Quoted 11 lines · Dmitry Dolgov
Quoted 11 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

Quoted 5 lines
Quoted 2 lines

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

I've recently stumbled upon this seemingly lost topic, and wanted to raise it again. Please let me know if there is a more appropriate way to do so.

With kretprobe using rethook the maxactive limit is no longer used. So we probably don't need this patch.

Quoted 6 lines
Quoted 1 line

Masami, wdyt?

No, rethook is just a library version of kretprobe return hook, so the maxactive is still alive. I would like to make the rethook to use(share with) function graph's per-task shadow stack. When that is done, the maxactive will be removed.

Thanks for clarification! Does it mean that the possibility of setting maxactive still makes sense, until the rethook changes you've mentioned will land?

On a side note, is it possible to somehow follow/review/test the work about rethook and function graph's shadow stack?

#5 lore raw
Quoted 27 lines · On Wed, 15 Jun 2022 22:00:29 +0200 Dmitry Dolgov <[email protected]> wrote:
Quoted 27 lines · Masami Hiramatsu
Quoted 22 lines · On Sat, 11 Jun 2022 11:28:36 -0700 Alexei Starovoitov…
Quoted 11 lines · Dmitry Dolgov
Quoted 11 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

Quoted 5 lines
Quoted 2 lines

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

I've recently stumbled upon this seemingly lost topic, and wanted to raise it again. Please let me know if there is a more appropriate way to do so.

With kretprobe using rethook the maxactive limit is no longer used. So we probably don't need this patch.

Masami, wdyt?

Quoted 8 lines
Quoted 4 lines

No, rethook is just a library version of kretprobe return hook, so the maxactive is still alive. I would like to make the rethook to use(share with) function graph's per-task shadow stack. When that is done, the maxactive will be removed.

Thanks for clarification! Does it mean that the possibility of setting maxactive still makes sense, until the rethook changes you've mentioned will land?

Yes, unfortunatelly, there is no magic. We need a shadow stack without runtime allocation for this purpose. Thus what we can do is to use a per-task pre-allocated shadow stack page or make a common pool of nodes for variable-length shadow-stack. Both has pros and cons (depends on the system configuration).

Quoted 3 lines

On a side note, is it possible to somehow follow/review/test the work about rethook and function graph's shadow stack?

Hmm, good question. It should work theoletically, but it is easy to be tested by ftrace tracefs interface on x86. Just enable function-graph tracer and add a kretprobe event on some fucntion. E.g.

echo function-graph > current_tracer
echo r:test vfs_read >> kprobe_events
echo 1 > events/kprobes/enable

Thank you,

Signature · 1 line
Masami Hiramatsu (Google) <[email protected]>
#6 lore raw
In reply to Dmitrii Dolgov
Quoted 8 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

Quoted 6 lines

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

Thanks for pulling this out of the cracks. :)

Since there isn't much change from [2], I think this should still show "From:" me, and with "Signed-off-by" both of us.

And a nit below:

Thanks,
Song

Quoted 29 lines

---

include/linux/trace_events.h    |  3 ++-
kernel/events/core.c            | 20 ++++++++++++++++----
kernel/trace/trace_event_perf.c |  5 +++--
kernel/trace/trace_kprobe.c     |  4 ++--
kernel/trace/trace_probe.h      |  2 +-
5 files changed, 24 insertions(+), 10 deletions(-)
include/linux/trace_events.h +2 -1
index e6e95a9f07a5..7ca453a73252 100644
@@ -850,7 +850,8 @@ extern void perf_trace_destroy(struct perf_event *event);
 extern int  perf_trace_add(struct perf_event *event, int flags);
 extern void perf_trace_del(struct perf_event *event, int flags);
 #ifdef CONFIG_KPROBE_EVENTS
-extern int  perf_kprobe_init(struct perf_event *event, bool is_retprobe);
+extern int  perf_kprobe_init(struct perf_event *event, bool is_retprobe,
+			     int max_active);
 extern void perf_kprobe_destroy(struct perf_event *event);
 extern int bpf_get_kprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **symbol,
kernel/events/core.c +0 -0
index 23bb19716ad3..f0e936b3dfc4 100644

kernel/events/core.c static struct pmu perf_tracepoint = { · line 9814

Quoted 9 lines
kernel/events/core.c +3 -3
@@ -9809,24 +9809,34 @@ static struct pmu perf_tracepoint = {
 * PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe
 *                               if not set, create kprobe/uprobe
 *
- * The following values specify a reference counter (or semaphore in the
- * terminology of tools like dtrace, systemtap, etc.) Userspace Statically
- * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset.
+ * PERF_UPROBE_REF_CTR_OFFSET_* specify a reference counter (or semaphore
+ * in the terminology of tools like dtrace, systemtap, etc.) Userspace
+ * Statically Defined Tracepoints (USDT). Currently, we use 40 bit for the

40 bit is not accurate anymore, let's fix it (32).

Otherwise, LGTM.

[...]

#7 lore raw
Quoted 13 lines · Song Liu
Quoted 12 lines · Dmitrii Dolgov

Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace (see for example discussion [1]). Use highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.

The original patch [2] seems to be fallen through the cracks and wasn't applied. I've merely rebased the work done by Song Liu and verififed it still works.

Quoted 7 lines
Quoted 2 lines

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/[email protected]/

Thanks for pulling this out of the cracks. :)

Since there isn't much change from [2], I think this should still show "From:" me, and with "Signed-off-by" both of us.

Yep, sorry for that -- the second version should have all mentioned correctly. Thanks!