Merge tag 'perf-urgent-2026-09-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events fixes from Ingo Molnar

 - Fix sched_cb_list corruption on PMU callbacks that
   invoke list_del() during perf_event_overflow()
   calls (Thomas Richter)

 - Fix PEBS pt_regs->flags snapshot data that
   regressed with the introduction of adaptive
   PEBS v4 support (Dapeng Mi)

 - Fix possible drain_pebs() re-entry bug when
   intel_pmu_drain_pebs_buffer() is called from
   process context (Dapeng Mi)

* tag 'perf-urgent-2026-09-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Prevent drain_pebs() reentry
  perf/x86/intel: Correct pt_regs->flags update for PEBS path
  perf/core: Allow list_del during perf_event_overflow()

4 files changed, 45 insertions, 13 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cc13164d948f..1ac2ca35db53 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(int 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 8940f0292229..b98029b44052 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1242,8 +1242,11 @@ unlock:
 
 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)
@@ -2432,7 +2438,7 @@ static inline void __setup_pebs_basic_group(struct perf_event *event,
 {
 	/* The ip in basic is EventingIP */
 	set_linear_ip(regs, ip);
-	regs->flags = PERF_EFLAGS_EXACT;
+	regs->flags |= PERF_EFLAGS_EXACT;
 	setup_pebs_time(event, data, tsc);
 
 	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT)
@@ -2444,9 +2450,17 @@ static inline void __setup_pebs_gpr_group(struct perf_event *event,
 					  struct pebs_gprs *gprs,
 					  u64 sample_type)
 {
+	/*
+	 * Update flags with PEBS data. PERF_EFLAGS_EXACT must be set
+	 * in previous basic group handling.
+	 */
+	regs->flags = gprs->flags | PERF_EFLAGS_EXACT;
+
 	if (event->attr.precise_ip < 2) {
 		set_linear_ip(regs, gprs->ip);
 		regs->flags &= ~PERF_EFLAGS_EXACT;
+	} else if (regs->flags & X86_VM_MASK) {
+		regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 71ed5b2acea2..4680cba91340 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1638,6 +1638,9 @@ 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(int pmu_enabled);
+
 int intel_pmu_save_and_restart(struct perf_event *event);
 
 struct event_constraint *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 33210aff3ee6..fe33fe15689d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3925,13 +3925,13 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 				bool sched_in)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
-	struct perf_cpu_pmu_context *cpc;
+	struct perf_cpu_pmu_context *cpc, *cpc2;
 
 	/* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */
 	if (prev == next || cpuctx->task_ctx)
 		return;
 
-	list_for_each_entry(cpc, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
+	list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
 		__perf_pmu_sched_task(cpc, sched_in ? next : prev, sched_in);
 }