* [PATCH perf] perf: get_perf_callchain return NULL for crosstask
@ 2023-11-10 23:50 Jordan Rome
2023-11-11 0:10 ` Andrii Nakryiko
0 siblings, 1 reply; 5+ messages in thread
From: Jordan Rome @ 2023-11-10 23:50 UTC (permalink / raw)
To: linux-perf-users
Cc: bpf, linux-kernel, Andrii Nakryiko, Martin KaFai Lau,
Kernel Team, Peter Zijlstra, Ingo Molnar, Song Liu
Return NULL instead of returning 1 incorrect frame, which
currently happens when trying to walk the user stack for
any task that isn't current. Returning NULL is a better
indicator that this behavior is not supported.
This issue was found using bpf_get_task_stack inside a BPF
iterator ("iter/task"), which iterates over all tasks. The
single address/frame in the buffer when getting user stacks
for tasks that aren't current could not be symbolized (testing
multiple symbolizers).
Signed-off-by: Jordan Rome <linux@jordanrome.com>
---
kernel/events/callchain.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 1273be84392c..430fa544fa80 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -201,6 +201,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
}
if (user) {
+ if (crosstask)
+ return NULL;
+
if (!user_mode(regs)) {
if (current->mm)
regs = task_pt_regs(current);
@@ -209,9 +212,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
}
if (regs) {
- if (crosstask)
- goto exit_put;
-
if (add_mark)
perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
@@ -219,7 +219,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
}
}
-exit_put:
put_callchain_entry(rctx);
return entry;
--
2.39.3
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH perf] perf: get_perf_callchain return NULL for crosstask
2023-11-10 23:50 [PATCH perf] perf: get_perf_callchain return NULL for crosstask Jordan Rome
@ 2023-11-11 0:10 ` Andrii Nakryiko
2023-11-11 0:42 ` Jordan Rome
0 siblings, 1 reply; 5+ messages in thread
From: Andrii Nakryiko @ 2023-11-11 0:10 UTC (permalink / raw)
To: Jordan Rome
Cc: linux-perf-users, bpf, linux-kernel, Andrii Nakryiko,
Martin KaFai Lau, Kernel Team, Peter Zijlstra, Ingo Molnar,
Song Liu
On Fri, Nov 10, 2023 at 3:51 PM Jordan Rome <linux@jordanrome.com> wrote:
>
> Return NULL instead of returning 1 incorrect frame, which
> currently happens when trying to walk the user stack for
> any task that isn't current. Returning NULL is a better
> indicator that this behavior is not supported.
>
> This issue was found using bpf_get_task_stack inside a BPF
> iterator ("iter/task"), which iterates over all tasks. The
> single address/frame in the buffer when getting user stacks
> for tasks that aren't current could not be symbolized (testing
> multiple symbolizers).
>
> Signed-off-by: Jordan Rome <linux@jordanrome.com>
> ---
> kernel/events/callchain.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> index 1273be84392c..430fa544fa80 100644
> --- a/kernel/events/callchain.c
> +++ b/kernel/events/callchain.c
> @@ -201,6 +201,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> }
>
> if (user) {
> + if (crosstask)
> + return NULL;
I think you need that goto exit_put here.
> +
> if (!user_mode(regs)) {
> if (current->mm)
> regs = task_pt_regs(current);
> @@ -209,9 +212,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> }
>
> if (regs) {
> - if (crosstask)
> - goto exit_put;
> -
> if (add_mark)
> perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
>
> @@ -219,7 +219,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> }
> }
>
> -exit_put:
> put_callchain_entry(rctx);
>
> return entry;
> --
> 2.39.3
>
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH perf] perf: get_perf_callchain return NULL for crosstask
2023-11-11 0:10 ` Andrii Nakryiko
@ 2023-11-11 0:42 ` Jordan Rome
2023-11-11 4:32 ` Andrii Nakryiko
0 siblings, 1 reply; 5+ messages in thread
From: Jordan Rome @ 2023-11-11 0:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: linux-perf-users, bpf, linux-kernel, Andrii Nakryiko,
Martin KaFai Lau, Kernel Team, Peter Zijlstra, Ingo Molnar,
Song Liu
On Fri, Nov 10, 2023 at 7:10 PM Andrii Nakryiko
<andrii.nakryiko@gmail.com> wrote:
>
> On Fri, Nov 10, 2023 at 3:51 PM Jordan Rome <linux@jordanrome.com> wrote:
> >
> > Return NULL instead of returning 1 incorrect frame, which
> > currently happens when trying to walk the user stack for
> > any task that isn't current. Returning NULL is a better
> > indicator that this behavior is not supported.
> >
> > This issue was found using bpf_get_task_stack inside a BPF
> > iterator ("iter/task"), which iterates over all tasks. The
> > single address/frame in the buffer when getting user stacks
> > for tasks that aren't current could not be symbolized (testing
> > multiple symbolizers).
> >
> > Signed-off-by: Jordan Rome <linux@jordanrome.com>
> > ---
> > kernel/events/callchain.c | 7 +++----
> > 1 file changed, 3 insertions(+), 4 deletions(-)
> >
> > diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> > index 1273be84392c..430fa544fa80 100644
> > --- a/kernel/events/callchain.c
> > +++ b/kernel/events/callchain.c
> > @@ -201,6 +201,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > }
> >
> > if (user) {
> > + if (crosstask)
> > + return NULL;
>
> I think you need that goto exit_put here.
>
Why is that? Wouldn't that be the same behavior that already exists?
That being said we can probably move this check above get_callchain_entry
and exit earlier.
> > +
> > if (!user_mode(regs)) {
> > if (current->mm)
> > regs = task_pt_regs(current);
> > @@ -209,9 +212,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > }
> >
> > if (regs) {
> > - if (crosstask)
> > - goto exit_put;
> > -
> > if (add_mark)
> > perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
> >
> > @@ -219,7 +219,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > }
> > }
> >
> > -exit_put:
> > put_callchain_entry(rctx);
> >
> > return entry;
> > --
> > 2.39.3
> >
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH perf] perf: get_perf_callchain return NULL for crosstask
2023-11-11 0:42 ` Jordan Rome
@ 2023-11-11 4:32 ` Andrii Nakryiko
2023-11-11 11:31 ` Jordan Rome
0 siblings, 1 reply; 5+ messages in thread
From: Andrii Nakryiko @ 2023-11-11 4:32 UTC (permalink / raw)
To: Jordan Rome
Cc: linux-perf-users, bpf, linux-kernel, Andrii Nakryiko,
Martin KaFai Lau, Kernel Team, Peter Zijlstra, Ingo Molnar,
Song Liu
On Fri, Nov 10, 2023 at 4:43 PM Jordan Rome <linux@jordanrome.com> wrote:
>
> On Fri, Nov 10, 2023 at 7:10 PM Andrii Nakryiko
> <andrii.nakryiko@gmail.com> wrote:
> >
> > On Fri, Nov 10, 2023 at 3:51 PM Jordan Rome <linux@jordanrome.com> wrote:
> > >
> > > Return NULL instead of returning 1 incorrect frame, which
> > > currently happens when trying to walk the user stack for
> > > any task that isn't current. Returning NULL is a better
> > > indicator that this behavior is not supported.
> > >
> > > This issue was found using bpf_get_task_stack inside a BPF
> > > iterator ("iter/task"), which iterates over all tasks. The
> > > single address/frame in the buffer when getting user stacks
> > > for tasks that aren't current could not be symbolized (testing
> > > multiple symbolizers).
> > >
> > > Signed-off-by: Jordan Rome <linux@jordanrome.com>
> > > ---
> > > kernel/events/callchain.c | 7 +++----
> > > 1 file changed, 3 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> > > index 1273be84392c..430fa544fa80 100644
> > > --- a/kernel/events/callchain.c
> > > +++ b/kernel/events/callchain.c
> > > @@ -201,6 +201,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > }
> > >
> > > if (user) {
> > > + if (crosstask)
> > > + return NULL;
> >
> > I think you need that goto exit_put here.
> >
>
> Why is that? Wouldn't that be the same behavior that already exists?
> That being said we can probably move this check above get_callchain_entry
> and exit earlier.
If I read the code right, get_callchain_entry() does expect
put_callchain_entry(), which you are breaking with this return NULL.
But indeed, checking it early and bailing out might be the best solution here.
>
> > > +
> > > if (!user_mode(regs)) {
> > > if (current->mm)
> > > regs = task_pt_regs(current);
> > > @@ -209,9 +212,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > }
> > >
> > > if (regs) {
> > > - if (crosstask)
> > > - goto exit_put;
> > > -
> > > if (add_mark)
> > > perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
> > >
> > > @@ -219,7 +219,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > }
> > > }
> > >
> > > -exit_put:
> > > put_callchain_entry(rctx);
> > >
> > > return entry;
> > > --
> > > 2.39.3
> > >
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH perf] perf: get_perf_callchain return NULL for crosstask
2023-11-11 4:32 ` Andrii Nakryiko
@ 2023-11-11 11:31 ` Jordan Rome
0 siblings, 0 replies; 5+ messages in thread
From: Jordan Rome @ 2023-11-11 11:31 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: linux-perf-users, bpf, linux-kernel, Andrii Nakryiko,
Martin KaFai Lau, Kernel Team, Peter Zijlstra, Ingo Molnar,
Song Liu
On Fri, Nov 10, 2023 at 11:32 PM Andrii Nakryiko
<andrii.nakryiko@gmail.com> wrote:
>
> On Fri, Nov 10, 2023 at 4:43 PM Jordan Rome <linux@jordanrome.com> wrote:
> >
> > On Fri, Nov 10, 2023 at 7:10 PM Andrii Nakryiko
> > <andrii.nakryiko@gmail.com> wrote:
> > >
> > > On Fri, Nov 10, 2023 at 3:51 PM Jordan Rome <linux@jordanrome.com> wrote:
> > > >
> > > > Return NULL instead of returning 1 incorrect frame, which
> > > > currently happens when trying to walk the user stack for
> > > > any task that isn't current. Returning NULL is a better
> > > > indicator that this behavior is not supported.
> > > >
> > > > This issue was found using bpf_get_task_stack inside a BPF
> > > > iterator ("iter/task"), which iterates over all tasks. The
> > > > single address/frame in the buffer when getting user stacks
> > > > for tasks that aren't current could not be symbolized (testing
> > > > multiple symbolizers).
> > > >
> > > > Signed-off-by: Jordan Rome <linux@jordanrome.com>
> > > > ---
> > > > kernel/events/callchain.c | 7 +++----
> > > > 1 file changed, 3 insertions(+), 4 deletions(-)
> > > >
> > > > diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> > > > index 1273be84392c..430fa544fa80 100644
> > > > --- a/kernel/events/callchain.c
> > > > +++ b/kernel/events/callchain.c
> > > > @@ -201,6 +201,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > > }
> > > >
> > > > if (user) {
> > > > + if (crosstask)
> > > > + return NULL;
> > >
> > > I think you need that goto exit_put here.
> > >
> >
> > Why is that? Wouldn't that be the same behavior that already exists?
> > That being said we can probably move this check above get_callchain_entry
> > and exit earlier.
>
> If I read the code right, get_callchain_entry() does expect
> put_callchain_entry(), which you are breaking with this return NULL.
>
> But indeed, checking it early and bailing out might be the best solution here.
>
Sounds good. I'll move this check before `get_callchain_entry`.
> >
> > > > +
> > > > if (!user_mode(regs)) {
> > > > if (current->mm)
> > > > regs = task_pt_regs(current);
> > > > @@ -209,9 +212,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > > }
> > > >
> > > > if (regs) {
> > > > - if (crosstask)
> > > > - goto exit_put;
> > > > -
> > > > if (add_mark)
> > > > perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
> > > >
> > > > @@ -219,7 +219,6 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
> > > > }
> > > > }
> > > >
> > > > -exit_put:
> > > > put_callchain_entry(rctx);
> > > >
> > > > return entry;
> > > > --
> > > > 2.39.3
> > > >
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2023-11-11 11:32 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-11-10 23:50 [PATCH perf] perf: get_perf_callchain return NULL for crosstask Jordan Rome
2023-11-11 0:10 ` Andrii Nakryiko
2023-11-11 0:42 ` Jordan Rome
2023-11-11 4:32 ` Andrii Nakryiko
2023-11-11 11:31 ` Jordan Rome
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®