Merge tag 'perf-urgent-2026-03-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events fixes from Ingo Molnar:

 - Fix lock ordering bug found by lockdep in perf_event_wakeup()

 - Fix uncore counter enumeration on Granite Rapids and Sierra Forest

 - Fix perf_mmap() refcount bug found by Syzkaller

 - Fix __perf_event_overflow() vs perf_remove_from_context() race

* tag 'perf-urgent-2026-03-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Fix __perf_event_overflow() vs perf_remove_from_context() race
  perf/core: Fix refcount bug and potential UAF in perf_mmap
  perf/x86/intel/uncore: Add per-scheduler IMC CAS count events
  perf/core: Fix invalid wait context in ctx_sched_in()

1 files changed, 62 insertions, 21 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ac70d68217b6..1f5699b339ec 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4138,7 +4138,8 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			if (*perf_event_fasync(event))
 				event->pending_kill = POLL_ERR;
 
-			perf_event_wakeup(event);
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending_irq);
 		} else {
 			struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu);
 
@@ -7464,28 +7465,28 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = perf_mmap_aux(vma, event, nr_pages);
 		if (ret)
 			return ret;
-	}
 
-	/*
-	 * Since pinned accounting is per vm we cannot allow fork() to copy our
-	 * vma.
-	 */
-	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
-	vma->vm_ops = &perf_mmap_vmops;
+		/*
+		 * Since pinned accounting is per vm we cannot allow fork() to copy our
+		 * vma.
+		 */
+		vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
+		vma->vm_ops = &perf_mmap_vmops;
 
-	mapped = get_mapped(event, event_mapped);
-	if (mapped)
-		mapped(event, vma->vm_mm);
+		mapped = get_mapped(event, event_mapped);
+		if (mapped)
+			mapped(event, vma->vm_mm);
 
-	/*
-	 * Try to map it into the page table. On fail, invoke
-	 * perf_mmap_close() to undo the above, as the callsite expects
-	 * full cleanup in this case and therefore does not invoke
-	 * vmops::close().
-	 */
-	ret = map_range(event->rb, vma);
-	if (ret)
-		perf_mmap_close(vma);
+		/*
+		 * Try to map it into the page table. On fail, invoke
+		 * perf_mmap_close() to undo the above, as the callsite expects
+		 * full cleanup in this case and therefore does not invoke
+		 * vmops::close().
+		 */
+		ret = map_range(event->rb, vma);
+		if (ret)
+			perf_mmap_close(vma);
+	}
 
 	return ret;
 }
@@ -10776,6 +10777,13 @@ int perf_event_overflow(struct perf_event *event,
 			struct perf_sample_data *data,
 			struct pt_regs *regs)
 {
+	/*
+	 * Entry point from hardware PMI, interrupts should be disabled here.
+	 * This serializes us against perf_event_remove_from_context() in
+	 * things like perf_event_release_kernel().
+	 */
+	lockdep_assert_irqs_disabled();
+
 	return __perf_event_overflow(event, 1, data, regs);
 }
 
@@ -10852,6 +10860,19 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	/*
+	 * This is:
+	 *   - software		preempt
+	 *   - tracepoint	preempt
+	 *   -   tp_target_task	irq (ctx->lock)
+	 *   - uprobes		preempt/irq
+	 *   - kprobes		preempt/irq
+	 *   - hw_breakpoint	irq
+	 *
+	 * Any of these are sufficient to hold off RCU and thus ensure @event
+	 * exists.
+	 */
+	lockdep_assert_preemption_disabled();
 	local64_add(nr, &event->count);
 
 	if (!regs)
@@ -10860,6 +10881,16 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 	if (!is_sampling_event(event))
 		return;
 
+	/*
+	 * Serialize against event_function_call() IPIs like normal overflow
+	 * event handling. Specifically, must not allow
+	 * perf_event_release_kernel() -> perf_remove_from_context() to make
+	 * progress and 'release' the event from under us.
+	 */
+	guard(irqsave)();
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
 		data->period = nr;
 		return perf_swevent_overflow(event, 1, data, regs);
@@ -11358,6 +11389,11 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	struct perf_sample_data data;
 	struct perf_event *event;
 
+	/*
+	 * Per being a tracepoint, this runs with preemption disabled.
+	 */
+	lockdep_assert_preemption_disabled();
+
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = entry_size,
@@ -11690,6 +11726,11 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	struct perf_sample_data sample;
 	struct pt_regs *regs = data;
 
+	/*
+	 * Exception context, will have interrupts disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
 	perf_sample_data_init(&sample, bp->attr.bp_addr, 0);
 
 	if (!bp->hw.state && !perf_exclude_event(bp, regs))
@@ -12154,7 +12195,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && is_idle_task(current)))
-			if (__perf_event_overflow(event, 1, &data, regs))
+			if (perf_event_overflow(event, &data, regs))
 				ret = HRTIMER_NORESTART;
 	}