perf/x86/intel: Fix race in intel_pmu_disable_event
Subsystems (2)
Jiri Olsa
reviewerPATCH 1/1 perf/x86/intel: Fix race in intel_pmu_disable_event
New race in x86_pmu_stop was introduced by replacing the atomic __test_and_clear_bit of cpuc->active_mask by separate test_bit and __clear_bit calls in following patch:
3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler")
The race causes panic for PEBS events with enabled callchains:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:perf_prepare_sample+0x8c/0x530 Call Trace: <NMI> perf_event_output_forward+0x2a/0x80 __perf_event_overflow+0x51/0xe0 handle_pmi_common+0x19e/0x240 intel_pmu_handle_irq+0xad/0x170 perf_event_nmi_handler+0x2e/0x50 nmi_handle+0x69/0x110 default_do_nmi+0x3e/0x100 do_nmi+0x11a/0x180 end_repeat_nmi+0x16/0x1a RIP: 0010:native_write_msr+0x6/0x20 ... </NMI> intel_pmu_disable_event+0x98/0xf0 x86_pmu_stop+0x6e/0xb0 x86_pmu_del+0x46/0x140 event_sched_out.isra.97+0x7e/0x160 ...
The event is configured to make samples from PEBS drain code, but when it's disabled, we'll go through NMI path instead, where data->callchain will not get allocated and we'll crash:
x86_pmu_stop
test_bit(hwc->idx, cpuc->active_mask)
intel_pmu_disable_event(event)
{
...
intel_pmu_pebs_disable(event);
...EVENT OVERFLOW -> <NMI>
intel_pmu_handle_irq
handle_pmi_common
TEST PASSES -> test_bit(bit, cpuc->active_mask))
perf_event_overflow
perf_prepare_sample
{
...
if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
data->callchain = perf_callchain(event, regs);
CRASH -> size += data->callchain->nr;
}
</NMI>
...
x86_pmu_disable_event(event)
}
__clear_bit(hwc->idx, cpuc->active_mask);Fixing this by disabling the event itself before setting off the PEBS bit.
--- arch/x86/events/intel/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
arch/x86/events/intel/core.c +7 -3
@@ -2159,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); -if (unlikely (event->attr.precise_ip)) -intel_pmu_pebs_disable (event); -if (unlikely (hwc->config_base ==MSR_ARCH_PERFMON_FIXED_CTR_CTRL )) {intel_pmu_disable_fixed (hwc);return ; }x86_pmu_disable_event (event); + +/* +* Needs to be called after x86_pmu_disable_event, +* so we don't trigger the event without PEBS bit set. +*/ +if (unlikely (event->attr.precise_ip)) +intel_pmu_pebs_disable (event); }static void intel_pmu_del_event (struct perf_event *event)
Signature · 1 line
2.20.1
tip-bot for Jiri Olsa
merge bot[tip:perf/urgent] perf/x86/intel: Fix race in intel_pmu_disable_event()
perf/x86/intel: Fix race in intel_pmu_disable_event()
Commit-ID: 6f55967ad9d9752813e36de6d5fdbd19741adfc7 Gitweb: https://git.kernel.org/tip/6f55967ad9d9752813e36de6d5fdbd19741adfc7 Author: Jiri Olsa <[email protected]> AuthorDate: Sat, 4 May 2019 17:15:56 +0200 Committer: Ingo Molnar <[email protected]> CommitDate: Sun, 5 May 2019 13:00:48 +0200
perf/x86/intel: Fix race in intel_pmu_disable_event()
New race in x86_pmu_stop() was introduced by replacing the atomic __test_and_clear_bit() of cpuc->active_mask by separate test_bit() and __clear_bit() calls in the following commit:
3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler")
The race causes panic for PEBS events with enabled callchains:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:perf_prepare_sample+0x8c/0x530 Call Trace: <NMI> perf_event_output_forward+0x2a/0x80 __perf_event_overflow+0x51/0xe0 handle_pmi_common+0x19e/0x240 intel_pmu_handle_irq+0xad/0x170 perf_event_nmi_handler+0x2e/0x50 nmi_handle+0x69/0x110 default_do_nmi+0x3e/0x100 do_nmi+0x11a/0x180 end_repeat_nmi+0x16/0x1a RIP: 0010:native_write_msr+0x6/0x20 ... </NMI> intel_pmu_disable_event+0x98/0xf0 x86_pmu_stop+0x6e/0xb0 x86_pmu_del+0x46/0x140 event_sched_out.isra.97+0x7e/0x160 ...
The event is configured to make samples from PEBS drain code, but when it's disabled, we'll go through NMI path instead, where data->callchain will not get allocated and we'll crash:
x86_pmu_stop
test_bit(hwc->idx, cpuc->active_mask)
intel_pmu_disable_event(event)
{
...
intel_pmu_pebs_disable(event);
...EVENT OVERFLOW -> <NMI>
intel_pmu_handle_irq
handle_pmi_common
TEST PASSES -> test_bit(bit, cpuc->active_mask))
perf_event_overflow
perf_prepare_sample
{
...
if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
data->callchain = perf_callchain(event, regs);
CRASH -> size += data->callchain->nr;
}
</NMI>
...
x86_pmu_disable_event(event)
}
__clear_bit(hwc->idx, cpuc->active_mask);Fixing this by disabling the event itself before setting off the PEBS bit.
--- arch/x86/events/intel/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
arch/x86/events/intel/core.c +7 -3
@@ -2091,15 +2091,19 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); -if (unlikely (event->attr.precise_ip)) -intel_pmu_pebs_disable (event); -if (unlikely (hwc->config_base ==MSR_ARCH_PERFMON_FIXED_CTR_CTRL )) {intel_pmu_disable_fixed (hwc);return ; }x86_pmu_disable_event (event); + +/* +* Needs to be called after x86_pmu_disable_event, +* so we don't trigger the event without PEBS bit set. +*/ +if (unlikely (event->attr.precise_ip)) +intel_pmu_pebs_disable (event); }static void intel_pmu_del_event (struct perf_event *event)