[PATCH v3 1/1] perf/kprobe: maxactive for fd-based kprobe

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Song Liu <songliubraving@xxxxxx>

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.

Note that changes in rethook implementation may render maxactive
obsolete.

[1]: https://github.com/iovisor/bpftrace/issues/835
[2]: https://lore.kernel.org/all/20191007223111.1142454-1-songliubraving@xxxxxx/

Signed-off-by: Song Liu <songliubraving@xxxxxx>
Signed-off-by: Dmitrii Dolgov <9erthalion6@xxxxxxxxx>
---
Changes in v3:
    - Set correct author

Changes in v2:
    - Fix comment about number bits for the offset

 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(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index e6e95a9f07a5..7ca453a73252 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -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,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 23bb19716ad3..e8127f9b4df5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -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 32 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;
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a114549720d6..129000327809 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -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;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 47cebef78532..3ad30cfce9c3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -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)) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 92cc149af0fd..26fe21980793 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -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 *
-- 
2.32.0




[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux