lkml.org 
[lkml]   [2019]   [Apr]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH v3 3/3] x86/perf/amd: Remove need to check "running" bit in NMI handler
Date
Spurious interrupt support was adding to perf in commit:
63e6be6d98e1 ("perf, x86: Catch spurious interrupts after disabling counters")

The two previous patches (resolving the race condition when disabling a
PMC and NMI latency mitigation) allow for the removal of this older
spurious interrupt support.

Currently in x86_pmu_stop(), the bit for the PMC in the active_mask bitmap
is cleared before disabling the PMC, which sets up a race condition. This
race condition was mitigated by introducing the running bitmap. That race
condition can be eliminated by first disabling the PMC, waiting for PMC
reset on overflow and then clearing the bit for the PMC in the active_mask
bitmap. The NMI handler will not re-enable a disabled counter.

If x86_pmu_stop() is called from the perf NMI handler, the NMI latency
mitigation support will guard against any unhandled NMI messages.

Cc: <stable@vger.kernel.org> # 4.14.x-
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
arch/x86/events/amd/core.c | 19 ++++++++++++++++++-
arch/x86/events/core.c | 13 +++----------
2 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 93ef53713359..a5e33db2f17a 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -490,6 +490,23 @@ static void amd_pmu_disable_all(void)
}
}

+static void amd_pmu_disable_event(struct perf_event *event)
+{
+ x86_pmu_disable_event(event);
+
+ /*
+ * This can be called from NMI context (via x86_pmu_stop). The counter
+ * may have overflowed, but either way, we'll never see it get reset
+ * by the NMI if we're already in the NMI. And the NMI latency support
+ * below will take care of any pending NMI that might have been
+ * generated by the overflow.
+ */
+ if (in_nmi())
+ return;
+
+ amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
/*
* Because of NMI latency, if multiple PMC counters are active or other sources
* of NMIs are received, the perf NMI handler can handle one or more overflowed
@@ -737,7 +754,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.disable_all = amd_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
+ .disable = amd_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_K7_EVNTSEL0,
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..81911e11a15d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;

- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+ if (test_bit(hwc->idx, cpuc->active_mask)) {
x86_pmu.disable(event);
+ __clear_bit(hwc->idx, cpuc->active_mask);
cpuc->events[hwc->idx] = NULL;
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
apic_write(APIC_LVTPC, APIC_DM_NMI);

for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- if (!test_bit(idx, cpuc->active_mask)) {
- /*
- * Though we deactivated the counter some cpus
- * might still deliver spurious interrupts still
- * in flight. Catch them:
- */
- if (__test_and_clear_bit(idx, cpuc->running))
- handled++;
+ if (!test_bit(idx, cpuc->active_mask))
continue;
- }

event = cpuc->events[idx];

\
 
 \ /
  Last update: 2019-04-01 23:47    [W:0.096 / U:3.980 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site