[v3] perf: Avoid undefined behavior from stopping/starting inactive events

[PATCH v3] perf: Avoid undefined behavior from stopping/starting inactive events

Posted by Yunseong Kim 1 month, 3 weeks ago

Calling pmu->start()/stop() on perf events in PERF_EVENT_STATE_OFF can
leave event->hw.idx at -1. When PMU drivers later attempt to use this
negative index as a shift exponent in bitwise operations, it leads to UBSAN
shift-out-of-bounds reports.

The issue is a logical flaw in how event groups handle throttling when some
members are intentionally disabled. Based on the analysis and the
reproducer provided by Mark Rutland (this issue on both arm64 and x86-64).

The scenario unfolds as follows:

 1. A group leader event is configured with a very aggressive sampling
    period (e.g., sample_period = 1). This causes frequent interrupts and
    triggers the throttling mechanism.
 2. A child event in the same group is created in a disabled state
    (.disabled = 1). This event remains in PERF_EVENT_STATE_OFF.
    Since it hasn't been scheduled onto the PMU, its event->hw.idx remains
    initialized at -1.
 3. When throttling occurs, perf_event_throttle_group() and later
    perf_event_unthrottle_group() iterate through all siblings, including
    the disabled child event.
 4. perf_event_throttle()/unthrottle() are called on this inactive child
    event, which then call event->pmu->start()/stop().
 5. The PMU driver receives the event with hw.idx == -1 and attempts to
    use it as a shift exponent. e.g., in macros like PMCNTENSET(idx),
    leading to the UBSAN report.

The throttling mechanism attempts to start/stop events that are not
actively scheduled on the hardware.

Move the state check into perf_event_throttle()/perf_event_unthrottle() so
that inactive events are skipped entirely. This ensures only active events
with a valid hw.idx are processed, preventing undefined behavior and
silencing UBSAN warnings. The corrected check ensures true before
proceeding with PMU operations.

The problem can be reproduced with the syzkaller reproducer:
Link: https://lore.kernel.org/lkml/714b7ba2-693e-42e4-bce4-feef2a5e7613@kzalloc.com/

Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yunseong Kim <ysk@kzalloc.com>
---
 kernel/events/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8060c2857bb2..872122e074e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event);
 
 static void perf_event_unthrottle(struct perf_event *event, bool start)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = 0;
 	if (start)
 		event->pmu->start(event, 0);
@@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = MAX_INTERRUPTS;
 	event->pmu->stop(event, 0);
 	if (event == event->group_leader)
-- 
2.50.0

Re: [PATCH v3] perf: Avoid undefined behavior from stopping/starting inactive events

Posted by Liang, Kan 1 month, 3 weeks ago


On 2025-08-12 11:10 a.m., Yunseong Kim wrote:
> Calling pmu->start()/stop() on perf events in PERF_EVENT_STATE_OFF can
> leave event->hw.idx at -1. When PMU drivers later attempt to use this
> negative index as a shift exponent in bitwise operations, it leads to UBSAN
> shift-out-of-bounds reports.
> 
> The issue is a logical flaw in how event groups handle throttling when some
> members are intentionally disabled. Based on the analysis and the
> reproducer provided by Mark Rutland (this issue on both arm64 and x86-64).
> 
> The scenario unfolds as follows:
> 
>  1. A group leader event is configured with a very aggressive sampling
>     period (e.g., sample_period = 1). This causes frequent interrupts and
>     triggers the throttling mechanism.
>  2. A child event in the same group is created in a disabled state
>     (.disabled = 1). This event remains in PERF_EVENT_STATE_OFF.
>     Since it hasn't been scheduled onto the PMU, its event->hw.idx remains
>     initialized at -1.
>  3. When throttling occurs, perf_event_throttle_group() and later
>     perf_event_unthrottle_group() iterate through all siblings, including
>     the disabled child event.
>  4. perf_event_throttle()/unthrottle() are called on this inactive child
>     event, which then call event->pmu->start()/stop().
>  5. The PMU driver receives the event with hw.idx == -1 and attempts to
>     use it as a shift exponent. e.g., in macros like PMCNTENSET(idx),
>     leading to the UBSAN report.
> 
> The throttling mechanism attempts to start/stop events that are not
> actively scheduled on the hardware.
> 
> Move the state check into perf_event_throttle()/perf_event_unthrottle() so
> that inactive events are skipped entirely. This ensures only active events
> with a valid hw.idx are processed, preventing undefined behavior and
> silencing UBSAN warnings. The corrected check ensures true before
> proceeding with PMU operations.
> 
> The problem can be reproduced with the syzkaller reproducer:
> Link: https://lore.kernel.org/lkml/714b7ba2-693e-42e4-bce4-feef2a5e7613@kzalloc.com/
> 
> Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
> Cc: Mark Rutland <mark.rutland@arm.com>
> Signed-off-by: Yunseong Kim <ysk@kzalloc.com>

Thanks for the fix.

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>

Thanks,
Kan

> ---
>  kernel/events/core.c | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 8060c2857bb2..872122e074e5 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event);
>  
>  static void perf_event_unthrottle(struct perf_event *event, bool start)
>  {
> +	if (event->state != PERF_EVENT_STATE_ACTIVE)
> +		return;
> +
>  	event->hw.interrupts = 0;
>  	if (start)
>  		event->pmu->start(event, 0);
> @@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
>  
>  static void perf_event_throttle(struct perf_event *event)
>  {
> +	if (event->state != PERF_EVENT_STATE_ACTIVE)
> +		return;
> +
>  	event->hw.interrupts = MAX_INTERRUPTS;
>  	event->pmu->stop(event, 0);
>  	if (event == event->group_leader)

Re: [PATCH v3] perf: Avoid undefined behavior from stopping/starting inactive events

Posted by Peter Zijlstra 1 month, 2 weeks ago

On Tue, Aug 12, 2025 at 04:51:28PM -0700, Liang, Kan wrote:
> 
> 
> On 2025-08-12 11:10 a.m., Yunseong Kim wrote:
> > Calling pmu->start()/stop() on perf events in PERF_EVENT_STATE_OFF can
> > leave event->hw.idx at -1. When PMU drivers later attempt to use this
> > negative index as a shift exponent in bitwise operations, it leads to UBSAN
> > shift-out-of-bounds reports.
> > 
> > The issue is a logical flaw in how event groups handle throttling when some
> > members are intentionally disabled. Based on the analysis and the
> > reproducer provided by Mark Rutland (this issue on both arm64 and x86-64).
> > 
> > The scenario unfolds as follows:
> > 
> >  1. A group leader event is configured with a very aggressive sampling
> >     period (e.g., sample_period = 1). This causes frequent interrupts and
> >     triggers the throttling mechanism.
> >  2. A child event in the same group is created in a disabled state
> >     (.disabled = 1). This event remains in PERF_EVENT_STATE_OFF.
> >     Since it hasn't been scheduled onto the PMU, its event->hw.idx remains
> >     initialized at -1.
> >  3. When throttling occurs, perf_event_throttle_group() and later
> >     perf_event_unthrottle_group() iterate through all siblings, including
> >     the disabled child event.
> >  4. perf_event_throttle()/unthrottle() are called on this inactive child
> >     event, which then call event->pmu->start()/stop().
> >  5. The PMU driver receives the event with hw.idx == -1 and attempts to
> >     use it as a shift exponent. e.g., in macros like PMCNTENSET(idx),
> >     leading to the UBSAN report.
> > 
> > The throttling mechanism attempts to start/stop events that are not
> > actively scheduled on the hardware.
> > 
> > Move the state check into perf_event_throttle()/perf_event_unthrottle() so
> > that inactive events are skipped entirely. This ensures only active events
> > with a valid hw.idx are processed, preventing undefined behavior and
> > silencing UBSAN warnings. The corrected check ensures true before
> > proceeding with PMU operations.
> > 
> > The problem can be reproduced with the syzkaller reproducer:
> > Link: https://lore.kernel.org/lkml/714b7ba2-693e-42e4-bce4-feef2a5e7613@kzalloc.com/
> > 
> > Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
> > Cc: Mark Rutland <mark.rutland@arm.com>
> > Signed-off-by: Yunseong Kim <ysk@kzalloc.com>
> 
> Thanks for the fix.
> 
> Reviewed-by: Kan Liang <kan.liang@linux.intel.com>

Thanks both!

[tip: perf/urgent] perf: Avoid undefined behavior from stopping/starting inactive events

Posted by tip-bot2 for Yunseong Kim 1 month, 2 weeks ago

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     b64fdd422a85025b5e91ead794db9d3ef970e369
Gitweb:        https://git.kernel.org/tip/b64fdd422a85025b5e91ead794db9d3ef970e369
Author:        Yunseong Kim <ysk@kzalloc.com>
AuthorDate:    Tue, 12 Aug 2025 18:10:47 
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Fri, 15 Aug 2025 13:12:56 +02:00

perf: Avoid undefined behavior from stopping/starting inactive events

Calling pmu->start()/stop() on perf events in PERF_EVENT_STATE_OFF can
leave event->hw.idx at -1. When PMU drivers later attempt to use this
negative index as a shift exponent in bitwise operations, it leads to UBSAN
shift-out-of-bounds reports.

The issue is a logical flaw in how event groups handle throttling when some
members are intentionally disabled. Based on the analysis and the
reproducer provided by Mark Rutland (this issue on both arm64 and x86-64).

The scenario unfolds as follows:

 1. A group leader event is configured with a very aggressive sampling
    period (e.g., sample_period = 1). This causes frequent interrupts and
    triggers the throttling mechanism.
 2. A child event in the same group is created in a disabled state
    (.disabled = 1). This event remains in PERF_EVENT_STATE_OFF.
    Since it hasn't been scheduled onto the PMU, its event->hw.idx remains
    initialized at -1.
 3. When throttling occurs, perf_event_throttle_group() and later
    perf_event_unthrottle_group() iterate through all siblings, including
    the disabled child event.
 4. perf_event_throttle()/unthrottle() are called on this inactive child
    event, which then call event->pmu->start()/stop().
 5. The PMU driver receives the event with hw.idx == -1 and attempts to
    use it as a shift exponent. e.g., in macros like PMCNTENSET(idx),
    leading to the UBSAN report.

The throttling mechanism attempts to start/stop events that are not
actively scheduled on the hardware.

Move the state check into perf_event_throttle()/perf_event_unthrottle() so
that inactive events are skipped entirely. This ensures only active events
with a valid hw.idx are processed, preventing undefined behavior and
silencing UBSAN warnings. The corrected check ensures true before
proceeding with PMU operations.

The problem can be reproduced with the syzkaller reproducer:

Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
Signed-off-by: Yunseong Kim <ysk@kzalloc.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250812181046.292382-2-ysk@kzalloc.com
---
 kernel/events/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8060c28..872122e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event);
 
 static void perf_event_unthrottle(struct perf_event *event, bool start)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = 0;
 	if (start)
 		event->pmu->start(event, 0);
@@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = MAX_INTERRUPTS;
 	event->pmu->stop(event, 0);
 	if (event == event->group_leader)