perf/kprobe: maxactive for fd-based kprobe (pmu perf_kprobe)
Subsystems (2)
PATCH 1/1 perf/kprobe: maxactive for fd-based kprobe (pmu perf_kprobe)
Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace. [1] discussed the need of this in bpftrace. Use highest highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.
[1] https://github.com/iovisor/bpftrace/issues/835
--- 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
@@ -581,7 +581,8 @@ 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
@@ -8772,24 +8772,34 @@ 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 , };
@@ -8820,6 +8830,7 @@ 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 ;
@@ -8834,7 +8845,8 @@ 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
@@ -240,7 +240,8 @@ 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 ;
@@ -266,7 +267,7 @@ 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
@@ -1556,7 +1556,7 @@ 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) {struct trace_kprobe *tk;int ret;
@@ -1570,7 +1570,7 @@ 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
@@ -373,7 +373,7 @@ extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);#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
2.17.1
Hi,
Quoted 6 lines · On Mon, 7 Oct 2019 15:31:11 -0700 Song Liu <[email protected]> wrote:
Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace. [1] discussed the need of this in bpftrace. Use highest highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.
From the view point of trace_kprobe, this looks good to me.
Thank you,
Quoted 148 lines
Signed-off-by Song Liu <[email protected]>Cc Steven Rostedt (VMware) <[email protected]>Cc Masami Hiramatsu <[email protected]>Cc Peter Zijlstra (Intel) <[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@@ -581,7 +581,8 @@ 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@@ -8772,24 +8772,34 @@ 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 , };@@ -8820,6 +8830,7 @@ 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 ;@@ -8834,7 +8845,8 @@ 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@@ -240,7 +240,8 @@ 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 ;@@ -266,7 +267,7 @@ 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@@ -1556,7 +1556,7 @@ 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) {struct trace_kprobe *tk;int ret;@@ -1570,7 +1570,7 @@ 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@@ -373,7 +373,7 @@ extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);#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
2.17.1
Signature · 1 line
Masami Hiramatsu <[email protected]>
Quoted 14 lines · Masami Hiramatsu
Hi,
Quoted 5 lines · On Mon, 7 Oct 2019 15:31:11 -0700 Song Liu <[email protected]> wrote:
Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace. [1] discussed the need of this in bpftrace. Use highest highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.
Quoted 5 lines
Quoted 1 line
From the view point of
trace_kprobe, this looks good to me.Acked-by Masami Hiramatsu <[email protected]>
Thanks Masami!
Hi Peter and Steven,
Could you please share your comments on this?
Thanks,
Song
[ Added Ingo ]
Quoted 11 lines · On Mon, 7 Oct 2019 15:31:11 -0700 Song Liu <[email protected]> wrote:
Enable specifying maxactive for fd based kretprobe. This will be useful for tracing tools like bcc and bpftrace. [1] discussed the need of this in bpftrace. Use highest highest 12 bit (bit 52-63) to allow maximal maxactive of 4095.
[1] https://github.com/iovisor/bpftrace/issues/835
Signed-off-by Song Liu <[email protected]>Cc Steven Rostedt (VMware) <[email protected]>Cc Masami Hiramatsu <[email protected]>Cc Peter Zijlstra (Intel) <[email protected]>
-- Steve
Quoted 140 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@@ -581,7 +581,8 @@ 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@@ -8772,24 +8772,34 @@ 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 , };@@ -8820,6 +8830,7 @@ 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 ;@@ -8834,7 +8845,8 @@ 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@@ -240,7 +240,8 @@ 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 ;@@ -266,7 +267,7 @@ 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@@ -1556,7 +1556,7 @@ 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) {struct trace_kprobe *tk;int ret;@@ -1570,7 +1570,7 @@ 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@@ -373,7 +373,7 @@ extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);#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 *