Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1692975 > unrolled thread
| Started by | Jiri Olsa <jolsa@kernel.org> |
|---|---|
| First post | 2017-07-20 16:20 +0200 |
| Last post | 2017-07-21 11:50 +0200 |
| Articles | 3 — 3 participants |
Back to article view | Back to linux.kernel
[PATCH] perf: Fix locking for children siblings group read Jiri Olsa <jolsa@kernel.org> - 2017-07-20 16:20 +0200
Re: [PATCH] perf: Fix locking for children siblings group read Peter Zijlstra <peterz@infradead.org> - 2017-07-20 16:50 +0200
[tip:perf/urgent] perf/core: Fix locking for children siblings group read tip-bot for Jiri Olsa <tipbot@zytor.com> - 2017-07-21 11:50 +0200
| From | Jiri Olsa <jolsa@kernel.org> |
|---|---|
| Date | 2017-07-20 16:20 +0200 |
| Subject | [PATCH] perf: Fix locking for children siblings group read |
| Message-ID | <u5kt4-bb-17@gated-at.bofh.it> |
We're missing ctx lock when iterating children siblings
within the perf_read path for group reading. Following
race and crash can happen:
User space doing read syscall on event group leader:
T1:
perf_read
lock event->ctx->mutex
perf_read_group
lock leader->child_mutex
__perf_read_group_add(child)
list_for_each_entry(sub, &leader->sibling_list, group_entry)
----> sub might be invalid at this point, because it could
get removed via perf_event_exit_task_context in T2
Child exiting and cleaning up its events:
T2:
perf_event_exit_task_context
lock ctx->mutex
list_for_each_entry_safe(child_event, next, &child_ctx->event_list,...
perf_event_exit_event(child)
lock ctx->lock
perf_group_detach(child)
unlock ctx->lock
----> child is removed from sibling_list without any sync
with T1 path above
...
free_event(child)
Before the child is removed from the leader's child_list,
(and thus is omitted from perf_read_group processing), we
need to ensure that perf_read_group touches child's
siblings under its ctx->lock.
Tested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/events/core.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9747e422ab20..585955b41489 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4365,7 +4365,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
static int __perf_read_group_add(struct perf_event *leader,
u64 read_format, u64 *values)
{
+ struct perf_event_context *ctx = leader->ctx;
struct perf_event *sub;
+ unsigned long flags;
int n = 1; /* skip @nr */
int ret;
@@ -4395,12 +4397,15 @@ static int __perf_read_group_add(struct perf_event *leader,
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
+ raw_spin_lock_irqsave(&ctx->lock, flags);
+
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
values[n++] += perf_event_count(sub);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
}
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
return 0;
}
--
2.9.4
[toc] | [next] | [standalone]
| From | Peter Zijlstra <peterz@infradead.org> |
|---|---|
| Date | 2017-07-20 16:50 +0200 |
| Message-ID | <u5kW7-lk-27@gated-at.bofh.it> |
| In reply to | #1692975 |
On Thu, Jul 20, 2017 at 04:14:55PM +0200, Jiri Olsa wrote:
> We're missing ctx lock when iterating children siblings
> within the perf_read path for group reading. Following
> race and crash can happen:
>
> User space doing read syscall on event group leader:
>
> T1:
> perf_read
> lock event->ctx->mutex
> perf_read_group
> lock leader->child_mutex
> __perf_read_group_add(child)
> list_for_each_entry(sub, &leader->sibling_list, group_entry)
>
> ----> sub might be invalid at this point, because it could
> get removed via perf_event_exit_task_context in T2
>
> Child exiting and cleaning up its events:
>
> T2:
> perf_event_exit_task_context
> lock ctx->mutex
> list_for_each_entry_safe(child_event, next, &child_ctx->event_list,...
> perf_event_exit_event(child)
> lock ctx->lock
> perf_group_detach(child)
> unlock ctx->lock
>
> ----> child is removed from sibling_list without any sync
> with T1 path above
>
> ...
> free_event(child)
>
> Before the child is removed from the leader's child_list,
> (and thus is omitted from perf_read_group processing), we
> need to ensure that perf_read_group touches child's
> siblings under its ctx->lock.
One additional note; this bug got exposed by commit:
ba5213ae6b88 ("perf/core: Correct event creation with PERF_FORMAT_GROUP")
which made it possible to actually trigger this code-path.
So while it doesn't fix a bug in that commit per-se, we should maybe
have a Fixes: tag with that commit in because that commit exposed it and
this should be added to any kernel that commit goes into.
> Tested-by: Andi Kleen <ak@linux.intel.com>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Thanks Jiri!
> ---
> kernel/events/core.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 9747e422ab20..585955b41489 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -4365,7 +4365,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
> static int __perf_read_group_add(struct perf_event *leader,
> u64 read_format, u64 *values)
> {
> + struct perf_event_context *ctx = leader->ctx;
> struct perf_event *sub;
> + unsigned long flags;
> int n = 1; /* skip @nr */
> int ret;
>
> @@ -4395,12 +4397,15 @@ static int __perf_read_group_add(struct perf_event *leader,
> if (read_format & PERF_FORMAT_ID)
> values[n++] = primary_event_id(leader);
>
> + raw_spin_lock_irqsave(&ctx->lock, flags);
> +
> list_for_each_entry(sub, &leader->sibling_list, group_entry) {
> values[n++] += perf_event_count(sub);
> if (read_format & PERF_FORMAT_ID)
> values[n++] = primary_event_id(sub);
> }
>
> + raw_spin_unlock_irqrestore(&ctx->lock, flags);
> return 0;
> }
>
> --
> 2.9.4
>
[toc] | [prev] | [next] | [standalone]
| From | tip-bot for Jiri Olsa <tipbot@zytor.com> |
|---|---|
| Date | 2017-07-21 11:50 +0200 |
| Subject | [tip:perf/urgent] perf/core: Fix locking for children siblings group read |
| Message-ID | <u5CJj-37O-3@gated-at.bofh.it> |
| In reply to | #1692975 |
Commit-ID: 2aeb1883547626d82c597cce2c99f0b9c62e2425
Gitweb: http://git.kernel.org/tip/2aeb1883547626d82c597cce2c99f0b9c62e2425
Author: Jiri Olsa <jolsa@kernel.org>
AuthorDate: Thu, 20 Jul 2017 16:14:55 +0200
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 21 Jul 2017 09:54:23 +0200
perf/core: Fix locking for children siblings group read
We're missing ctx lock when iterating children siblings
within the perf_read path for group reading. Following
race and crash can happen:
User space doing read syscall on event group leader:
T1:
perf_read
lock event->ctx->mutex
perf_read_group
lock leader->child_mutex
__perf_read_group_add(child)
list_for_each_entry(sub, &leader->sibling_list, group_entry)
----> sub might be invalid at this point, because it could
get removed via perf_event_exit_task_context in T2
Child exiting and cleaning up its events:
T2:
perf_event_exit_task_context
lock ctx->mutex
list_for_each_entry_safe(child_event, next, &child_ctx->event_list,...
perf_event_exit_event(child)
lock ctx->lock
perf_group_detach(child)
unlock ctx->lock
----> child is removed from sibling_list without any sync
with T1 path above
...
free_event(child)
Before the child is removed from the leader's child_list,
(and thus is omitted from perf_read_group processing), we
need to ensure that perf_read_group touches child's
siblings under its ctx->lock.
Peter further notes:
| One additional note; this bug got exposed by commit:
|
| ba5213ae6b88 ("perf/core: Correct event creation with PERF_FORMAT_GROUP")
|
| which made it possible to actually trigger this code-path.
Tested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: ba5213ae6b88 ("perf/core: Correct event creation with PERF_FORMAT_GROUP")
Link: http://lkml.kernel.org/r/20170720141455.2106-1-jolsa@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/events/core.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c9cdbd3..c17c088 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4372,7 +4372,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
static int __perf_read_group_add(struct perf_event *leader,
u64 read_format, u64 *values)
{
+ struct perf_event_context *ctx = leader->ctx;
struct perf_event *sub;
+ unsigned long flags;
int n = 1; /* skip @nr */
int ret;
@@ -4402,12 +4404,15 @@ static int __perf_read_group_add(struct perf_event *leader,
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
+ raw_spin_lock_irqsave(&ctx->lock, flags);
+
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
values[n++] += perf_event_count(sub);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
}
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
return 0;
}
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web