From: Delyan Kratunov <delyank@fb.com>
To: "peterz@infradead.org" <peterz@infradead.org>
Cc: "dietmar.eggemann@arm.com" <dietmar.eggemann@arm.com>,
"bigeasy@linutronix.de" <bigeasy@linutronix.de>,
"keescook@chromium.org" <keescook@chromium.org>,
"qais.yousef@arm.com" <qais.yousef@arm.com>,
Delyan Kratunov <delyank@fb.com>,
"andrii@kernel.org" <andrii@kernel.org>,
"x86@kernel.org" <x86@kernel.org>,
"vincent.guittot@linaro.org" <vincent.guittot@linaro.org>,
"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
"adharmap@quicinc.com" <adharmap@quicinc.com>,
"alexei.starovoitov@gmail.com" <alexei.starovoitov@gmail.com>,
"andrii.nakryiko@gmail.com" <andrii.nakryiko@gmail.com>,
"ast@kernel.org" <ast@kernel.org>,
"Kenta.Tada@sony.com" <Kenta.Tada@sony.com>,
"rdunlap@infradead.org" <rdunlap@infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"bristot@redhat.com" <bristot@redhat.com>,
"ebiederm@xmission.com" <ebiederm@xmission.com>,
"mingo@kernel.org" <mingo@kernel.org>,
"rostedt@goodmis.org" <rostedt@goodmis.org>,
"ed.tsai@mediatek.com" <ed.tsai@mediatek.com>,
"legion@kernel.org" <legion@kernel.org>,
"acme@kernel.org" <acme@kernel.org>,
"u.kleine-koenig@pengutronix.de" <u.kleine-koenig@pengutronix.de>,
"valentin.schneider@arm.com" <valentin.schneider@arm.com>,
"juri.lelli@redhat.com" <juri.lelli@redhat.com>,
"namhyung@kernel.org" <namhyung@kernel.org>
Subject: [PATCH v2] sched/tracing: append prev_state to tp args instead
Date: Wed, 11 May 2022 18:28:36 +0000 [thread overview]
Message-ID: <c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com> (raw)
In-Reply-To: <20220510082940.GA100765@worktop.programming.kicks-ass.net>
Commit fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting
sched_switch event, 2022-01-20) added a new prev_state argument to the
sched_switch tracepoint, before the prev task_struct pointer.
This reordering of arguments broke BPF programs that use the raw
tracepoint (e.g. tp_btf programs). The type of the second argument has
changed and existing programs that assume a task_struct* argument
(e.g. for bpf_task_storage access) will now fail to verify.
If we instead append the new argument to the end, all existing programs
would continue to work and can conditionally extract the prev_state
argument on supported kernel versions.
Fixes: fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20)
Signed-off-by: Delyan Kratunov <delyank@fb.com>
---
v1 -> v2:
Convert trace_events sample as well.
Sorry about that Peter and thanks for taking it in, it's much appreciated!
include/trace/events/sched.h | 6 +++---
kernel/sched/core.c | 2 +-
kernel/trace/fgraph.c | 4 ++--
kernel/trace/ftrace.c | 4 ++--
kernel/trace/trace_events.c | 8 ++++----
kernel/trace/trace_osnoise.c | 4 ++--
kernel/trace/trace_sched_switch.c | 4 ++--
kernel/trace/trace_sched_wakeup.c | 4 ++--
samples/trace_events/trace_custom_sched.h | 6 +++---
9 files changed, 21 insertions(+), 21 deletions(-)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 65e786756321..fbb99a61f714 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt,
TRACE_EVENT(sched_switch,
TP_PROTO(bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next),
+ struct task_struct *next,
+ unsigned int prev_state),
- TP_ARGS(preempt, prev_state, prev, next),
+ TP_ARGS(preempt, prev, next, prev_state),
TP_STRUCT__entry(
__array( char, prev_comm, TASK_COMM_LEN )
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51efaabac3e4..d58c0389eb23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6382,7 +6382,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
migrate_disable_switch(rq, prev);
psi_sched_switch(prev, next, !task_on_rq_queued(prev));
- trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf);
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 8f4fb328133a..a7e84c8543cb 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -404,9 +404,9 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
static void
ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next)
+ struct task_struct *next,
+ unsigned int prev_state)
{
unsigned long long timestamp;
int index;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f1d2f5e7263..af899b058c8d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7420,9 +7420,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
static void
ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next)
+ struct task_struct *next,
+ unsigned int prev_state)
{
struct trace_array *tr = data;
struct trace_pid_list *pid_list;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e11e167b7809..f97de82d1342 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -773,9 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
static void
event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next)
+ struct task_struct *next,
+ unsigned int prev_state)
{
struct trace_array *tr = data;
struct trace_pid_list *no_pid_list;
@@ -799,9 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
static void
event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next)
+ struct task_struct *next,
+ unsigned int prev_state)
{
struct trace_array *tr = data;
struct trace_pid_list *no_pid_list;
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index e9ae1f33a7f0..afb92e2f0aea 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1168,9 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
*/
static void
trace_sched_switch_callback(void *data, bool preempt,
- unsigned int prev_state,
struct task_struct *p,
- struct task_struct *n)
+ struct task_struct *n,
+ unsigned int prev_state)
{
struct osnoise_variables *osn_var = this_cpu_osn_var();
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 45796d8bd4b2..c9ffdcfe622e 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -22,8 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex);
static void
probe_sched_switch(void *ignore, bool preempt,
- unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
+ struct task_struct *prev, struct task_struct *next,
+ unsigned int prev_state)
{
int flags;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 46429f9a96fa..330aee1c1a49 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -426,8 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
static void notrace
probe_wakeup_sched_switch(void *ignore, bool preempt,
- unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
+ struct task_struct *prev, struct task_struct *next,
+ unsigned int prev_state)
{
struct trace_array_cpu *data;
u64 T0, T1, delta;
diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h
index 9fdd8e7c2a45..951388334a3f 100644
--- a/samples/trace_events/trace_custom_sched.h
+++ b/samples/trace_events/trace_custom_sched.h
@@ -25,11 +25,11 @@ TRACE_CUSTOM_EVENT(sched_switch,
* that the custom event is using.
*/
TP_PROTO(bool preempt,
- unsigned int prev_state,
struct task_struct *prev,
- struct task_struct *next),
+ struct task_struct *next,
+ unsigned int prev_state),
- TP_ARGS(preempt, prev_state, prev, next),
+ TP_ARGS(preempt, prev, next, prev_state),
/*
* The next fields are where the customization happens.
--
2.35.3
next prev parent reply other threads:[~2022-05-11 18:28 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-20 16:25 [PATCH v3 0/2] sched/tracing: sched_switch prev_state reported as TASK_RUNNING when it's not Valentin Schneider
2022-01-20 16:25 ` [PATCH v3 1/2] sched/tracing: Don't re-read p->state when emitting sched_switch event Valentin Schneider
2022-03-01 15:24 ` [tip: sched/core] " tip-bot2 for Valentin Schneider
2022-03-04 16:13 ` Valentin Schneider
2022-03-08 18:02 ` Qais Yousef
2022-03-08 18:10 ` Greg KH
2022-03-08 18:51 ` Qais Yousef
2022-04-09 23:38 ` Qais Yousef
2022-04-10 22:06 ` Qais Yousef
2022-04-10 23:22 ` Holger Hoffstätte
2022-04-11 7:18 ` Holger Hoffstätte
2022-04-11 7:28 ` Greg KH
2022-04-11 8:05 ` Holger Hoffstätte
2022-04-11 13:23 ` Greg KH
2022-04-11 13:22 ` Greg KH
2022-04-11 21:06 ` Qais Yousef
2022-01-20 16:25 ` [PATCH v3 2/2] sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE Valentin Schneider
2022-03-01 15:24 ` [tip: sched/core] " tip-bot2 for Valentin Schneider
2022-04-09 23:42 ` [PATCH v3 2/2] " Qais Yousef
2022-04-10 6:14 ` Greg KH
2022-04-10 22:13 ` Qais Yousef
2022-04-11 13:20 ` Greg KH
2022-04-11 20:18 ` Qais Yousef
2022-01-21 17:15 ` [PATCH v3 0/2] sched/tracing: sched_switch prev_state reported as TASK_RUNNING when it's not Steven Rostedt
2022-02-27 15:33 ` Peter Zijlstra
2022-04-21 22:12 ` [PATCH] sched/tracing: append prev_state to tp args instead Delyan Kratunov
2022-04-22 10:13 ` Valentin Schneider
2022-04-22 11:09 ` Peter Zijlstra
2022-04-22 15:55 ` Steven Rostedt
2022-04-22 16:54 ` Andrii Nakryiko
2022-04-22 16:37 ` Andrii Nakryiko
2022-04-22 17:22 ` Delyan Kratunov
2022-04-22 18:30 ` Alexei Starovoitov
2022-04-26 12:28 ` Peter Zijlstra
2022-04-26 14:09 ` Qais Yousef
2022-04-26 15:54 ` Andrii Nakryiko
2022-04-27 10:34 ` Qais Yousef
2022-04-27 18:17 ` Andrii Nakryiko
2022-04-27 20:32 ` Alexei Starovoitov
2022-04-28 10:02 ` Qais Yousef
2022-05-09 19:32 ` Andrii Nakryiko
2022-05-10 7:01 ` Peter Zijlstra
2022-05-10 8:29 ` Peter Zijlstra
2022-05-10 14:31 ` Steven Rostedt
2022-05-11 18:28 ` Delyan Kratunov [this message]
2022-05-11 19:10 ` [PATCH v2] " Steven Rostedt
2022-05-11 22:45 ` [tip: sched/urgent] sched/tracing: Append " tip-bot2 for Delyan Kratunov
2022-05-11 23:40 ` [PATCH v2] sched/tracing: append " Thomas Gleixner
2022-04-26 15:51 ` [PATCH] " Andrii Nakryiko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com \
--to=delyank@fb.com \
--cc=Kenta.Tada@sony.com \
--cc=acme@kernel.org \
--cc=adharmap@quicinc.com \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=andrii.nakryiko@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=bristot@redhat.com \
--cc=dietmar.eggemann@arm.com \
--cc=ebiederm@xmission.com \
--cc=ed.tsai@mediatek.com \
--cc=juri.lelli@redhat.com \
--cc=keescook@chromium.org \
--cc=legion@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=qais.yousef@arm.com \
--cc=rdunlap@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=u.kleine-koenig@pengutronix.de \
--cc=valentin.schneider@arm.com \
--cc=vincent.guittot@linaro.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome