Linux Perf Users
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Dapeng Mi <dapeng1.mi@intel.com>, Zide Chen <zide.chen@intel.com>,
	Falcon Thomas <thomas.falcon@intel.com>,
	Xudong Hao <xudong.hao@intel.com>
Subject: Re: [Patch v3 8/8] perf/x86/intel: Prevent drain_pebs() reentry
Date: Wed, 12 Aug 2026 17:18:27 +0200	[thread overview]
Message-ID: <20260812151827.GO776954@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <8a1b03a0-c45e-4a86-af20-bcd15ccb7f8e@linux.intel.com>

On Tue, Aug 11, 2026 at 06:00:43PM +0800, Mi, Dapeng wrote:

> > So what specific callchain is going sideways?

> But for the helper __intel_pmu_pebs_disable(), it seems the whole PMU is
> not disabled, only the target counter has been stopped. Here is one call-chain.
> 
> __perf_addr_filters_adjust()
>   perf_event_stop()
>     __perf_event_stop()
>       x86_pmu_stop() (event->pmu->stop)
>         intel_pmu_disable_event()
>           intel_pmu_pebs_disable()
>             __intel_pmu_pebs_disable()
>               intel_pmu_drain_large_pebs()
>                 intel_pmu_drain_pebs_buffer()
> 

Right, so that needs to be included in the changelog. Also, lets target
that more specifically.

How about something like so?

---
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index db92ded774dd..e092ef6e37f4 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3125,6 +3125,27 @@ static void intel_pmu_del_event(struct perf_event *event)
 		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
+int __intel_pmu_quiesce(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int pmu_enabled = cpuc->enabled;
+
+	cpuc->enabled = 0;
+	if (pmu_enabled)
+		intel_pmu_disable_all();
+
+	return pmu_enabled;
+}
+
+void __intel_pmu_resume(bool pmu_enabled)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	cpuc->enabled = pmu_enabled;
+	if (pmu_enabled)
+		intel_pmu_enable_all(0);
+}
+
 static int icl_set_topdown_event_period(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -3316,16 +3337,13 @@ static void intel_pmu_read_event(struct perf_event *event)
 	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) ||
 	    is_pebs_counter_event_group(event)) {
 		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-		bool pmu_enabled = cpuc->enabled;
+		int pmu_enabled;
 
 		/* Only need to call update_topdown_event() once for group read. */
 		if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ))
 			return;
 
-		cpuc->enabled = 0;
-		if (pmu_enabled)
-			intel_pmu_disable_all();
-
+		pmu_enabled = __intel_pmu_quiesce();
 		/*
 		 * If the PEBS counters snapshotting is enabled,
 		 * the topdown event is available in PEBS records.
@@ -3334,10 +3352,7 @@ static void intel_pmu_read_event(struct perf_event *event)
 			static_call(intel_pmu_update_topdown_event)(event, NULL);
 		else
 			intel_pmu_drain_pebs_buffer();
-
-		cpuc->enabled = pmu_enabled;
-		if (pmu_enabled)
-			intel_pmu_enable_all(0);
+		__intel_pmu_resume(pmu_enabled);
 
 		return;
 	}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index e86e4ba91e1b..54890dda0589 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1242,8 +1242,11 @@ int intel_pmu_drain_bts_buffer(void)
 
 void intel_pmu_drain_pebs_buffer(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_sample_data data;
 
+	WARN_ON_ONCE(cpuc->enabled);
+
 	static_call(x86_pmu_drain_pebs)(NULL, &data);
 }
 
@@ -1864,8 +1867,11 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
 {
 	if (cpuc->n_pebs == cpuc->n_large_pebs &&
-	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
+	    cpuc->n_pebs != cpuc->n_pebs_via_pt) {
+		int enabled = __intel_pmu_quiesce();
 		intel_pmu_drain_pebs_buffer();
+		__intel_pmu_resume(enabled);
+	}
 }
 
 static void __intel_pmu_pebs_enable(struct perf_event *event)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8c0b32ffab35..c7848c4cabae 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1644,6 +1644,9 @@ static __always_inline void __intel_pmu_lbr_disable(void)
 	wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
+extern int __intel_pmu_quiesce(void);
+extern void __intel_pmu_resume(bool pmu_enabled);
+
 int intel_pmu_save_and_restart(struct perf_event *event);
 
 struct event_constraint *

  reply	other threads:[~2026-08-12 15:18 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-17  8:03 [Patch v3 0/8] perf/x86: Miscellaneous PMU bug fixes and optimizations Dapeng Mi
2026-07-17  8:03 ` [Patch v3 1/8] perf/x86: Unregister PMI handler on PMU init failure Dapeng Mi
2026-07-17  8:33   ` sashiko-bot
2026-07-20  1:17     ` Mi, Dapeng
2026-07-17  8:03 ` [Patch v3 2/8] perf/x86: Free hybrid state " Dapeng Mi
2026-07-17  8:03 ` [Patch v3 3/8] perf/x86: Guard intel_pmu_cpu_dead() against invalid hybrid PMU casts Dapeng Mi
2026-07-17  9:31   ` sashiko-bot
2026-07-20  1:30     ` Mi, Dapeng
2026-07-17  8:03 ` [Patch v3 4/8] perf/x86/intel: Unwind cpuc state if PEBS buffer setup fails Dapeng Mi
2026-07-17  8:03 ` [Patch v3 5/8] perf/x86: Remove stale fixed counter helper and fix hybrid PMU access Dapeng Mi
2026-07-17  8:03 ` [Patch v3 6/8] perf/x86/intel: Fix intel_cap handling on hybrid PMUs Dapeng Mi
2026-08-10 12:18   ` Peter Zijlstra
2026-08-10 12:25     ` Mi, Dapeng
2026-07-17  8:03 ` [Patch v3 7/8] perf/x86: Optimize ACR handling in match_prev_assignment() Dapeng Mi
2026-07-17  8:03 ` [Patch v3 8/8] perf/x86/intel: Prevent drain_pebs() reentry Dapeng Mi
2026-07-17 10:38   ` sashiko-bot
2026-07-20  1:36     ` Mi, Dapeng
2026-08-10 13:01   ` Peter Zijlstra
2026-08-11  1:39     ` Mi, Dapeng
2026-08-11  8:22       ` Peter Zijlstra
2026-08-11 10:00         ` Mi, Dapeng
2026-08-12 15:18           ` Peter Zijlstra [this message]
2026-07-21 14:58 ` [Patch v3 0/8] perf/x86: Miscellaneous PMU bug fixes and optimizations Chen, Zide
2026-08-10  9:06 ` Mi, Dapeng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260812151827.GO776954@noisy.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=dapeng1.mi@intel.com \
    --cc=dapeng1.mi@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=thomas.falcon@intel.com \
    --cc=xudong.hao@intel.com \
    --cc=zide.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox