Miscellaneous perf events fixes:

- Fix deadlock in the perf_mmap() failure path (Peter Zijlstra)
 
  - Intel ACR (Auto Counter Reload) fixes (Dapeng Mi):
 
    - Fix validation and configuration of ACR masks
    - Fix ACR rescheduling bug causing stale masks
    - Disable the PMI on ACR-enabled hardware
    - Enable ACR on Panther Cover uarch too
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmn+kB0RHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1ib2RAAkh19iPRq7tHCXvDYJEHztpAuioyaKznw
 57pNlzG+/K/gg/yZ7uoCtXvogEHgDtart9ZtH7CVtZQgky6YfdiBq0g0pNSdOoY5
 O4IB0ZIXIu/FOh1+Q1k3Md5MeuxUz1Jp21Wq+JNK6VkWwfq+oCZ3XJK06+2C45wI
 uUePaEMFZn7VX9WOToZJQZME/+5yQvrgOq+D6gBs+y3UJO5u6kpdoley6fPXRtYV
 hyfBYiutJlcV1dJC9g7Dc6CHrBkaolFTKsRi2RjD658fHmUUMCubsn6lSG9UJqiZ
 CWtNMHJ/k1WBLuPLUaZBa3W0s+mUZ+0E6W3nLRHC2ORRQhAnQKeoDb2IWlVhYTdB
 NmyABPqjwvGfgidMh39aMt8GS4lFZBXGozVNWTZprN56U/jYH/Ol4cJNLJ9Ez5yk
 fzIkljCc5L/ZmxmqjJNBvmJtTpAt/FhN0qKT/k9jksISFE24bzZ0oRg3t051OyXs
 Mndldyl/2EFHA2PBIN2phISTVWh5lewYNBaK0SBbx77DX6NzMdevhdGAvw2cRVT/
 BJvqj+OeBfiaGBNb/lAIsoZCnuMClQi2t4jlKGkmN3n9hbgPyPAsz/WJRDLr9GZ+
 cqQgh7fL80HoqZTfV7tWxKTkDK3AciXXZE+8ntBpGC6CgMmgsJqLmxc60Jzfh2OO
 qGXcodOISag=
 =WNs1
 -----END PGP SIGNATURE-----

Merge tag 'perf-urgent-2026-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events fixes from Ingo Molnar:

 - Fix deadlock in the perf_mmap() failure path (Peter Zijlstra)

 - Intel ACR (Auto Counter Reload) fixes (Dapeng Mi):
     - Fix validation and configuration of ACR masks
     - Fix ACR rescheduling bug causing stale masks
     - Disable the PMI on ACR-enabled hardware
     - Enable ACR on Panther Cover uarch too

* tag 'perf-urgent-2026-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Enable auto counter reload for DMR
  perf/x86/intel: Disable PMI for self-reloaded ACR events
  perf/x86/intel: Always reprogram ACR events to prevent stale masks
  perf/x86/intel: Improve validation and configuration of ACR masks
  perf/core: Fix deadlock in perf_mmap() failure path

arch/x86/events/core.c

@@ -1294,13 +1294,16 @@ int x86_perf_rdpmc_index(struct perf_event *event)
 	return event->hw.event_base_rdpmc;
 }
 
-static inline int match_prev_assignment(struct hw_perf_event *hwc,
+static inline int match_prev_assignment(struct perf_event *event,
 					struct cpu_hw_events *cpuc,
 					int i)
 {
+	struct hw_perf_event *hwc = &event->hw;
+
 	return hwc->idx == cpuc->assign[i] &&
-		hwc->last_cpu == smp_processor_id() &&
-		hwc->last_tag == cpuc->tags[i];
+	       hwc->last_cpu == smp_processor_id() &&
+	       hwc->last_tag == cpuc->tags[i] &&
+	       !is_acr_event_group(event);
 }
 
 static void x86_pmu_start(struct perf_event *event, int flags);
@@ -1346,7 +1349,7 @@ static void x86_pmu_enable(struct pmu *pmu)
 			 * - no other event has used the counter since
 			 */
 			if (hwc->idx == -1 ||
-			    match_prev_assignment(hwc, cpuc, i))
+			    match_prev_assignment(event, cpuc, i))
 				continue;
 
 			/*
@@ -1367,7 +1370,7 @@ static void x86_pmu_enable(struct pmu *pmu)
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
-			if (!match_prev_assignment(hwc, cpuc, i))
+			if (!match_prev_assignment(event, cpuc, i))
 				x86_assign_hw_event(event, cpuc, i);
 			else if (i < n_running)
 				continue;

arch/x86/events/intel/core.c

@@ -3118,11 +3118,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	intel_set_masks(event, idx);
 
 	/*
-	 * Enable IRQ generation (0x8), if not PEBS,
-	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
-	 * if requested:
+	 * Enable IRQ generation (0x8), if not PEBS or self-reloaded
+	 * ACR event, and enable ring-3 counting (0x2) and ring-0
+	 * counting (0x1) if requested:
 	 */
-	if (!event->attr.precise_ip)
+	if (!event->attr.precise_ip && !is_acr_self_reload_event(event))
 		bits |= INTEL_FIXED_0_ENABLE_PMI;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= INTEL_FIXED_0_USER;
@@ -3306,6 +3306,15 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		intel_set_masks(event, idx);
 		static_call_cond(intel_pmu_enable_acr_event)(event);
 		static_call_cond(intel_pmu_enable_event_ext)(event);
+		/*
+		 * For self-reloaded ACR event, don't enable PMI since
+		 * HW won't set overflow bit in GLOBAL_STATUS. Otherwise,
+		 * the PMI would be recognized as a suspicious NMI.
+		 */
+		if (is_acr_self_reload_event(event))
+			hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+		else if (!event->attr.precise_ip)
+			hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
 		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
@@ -3332,23 +3341,41 @@ static void intel_pmu_enable_event(struct perf_event *event)
 static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
 {
 	struct perf_event *event, *leader;
-	int i, j, idx;
+	int i, j, k, bit, idx;
 
+	/*
+	 * FIXME: ACR mask parsing relies on cpuc->event_list[] (active events only).
+	 * Disabling an ACR event causes bit-shifting errors in the acr_mask of
+	 * remaining group members. As ACR sampling requires all events to be active,
+	 * this limitation is acceptable for now. Revisit if independent event toggling
+	 * is required.
+	 */
 	for (i = 0; i < cpuc->n_events; i++) {
 		leader = cpuc->event_list[i];
 		if (!is_acr_event_group(leader))
 			continue;
 
-		/* The ACR events must be contiguous. */
+		/* Find the last event of the ACR group. */
 		for (j = i; j < cpuc->n_events; j++) {
 			event = cpuc->event_list[j];
 			if (event->group_leader != leader->group_leader)
 				break;
-			for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
-				if (i + idx >= cpuc->n_events ||
-				    !is_acr_event_group(cpuc->event_list[i + idx]))
-					return;
-				__set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
+		}
+
+		/*
+		 * Translate the user-space ACR mask (attr.config2) into the physical
+		 * counter bitmask (hw.config1) for each ACR event in the group.
+		 * NOTE: ACR event contiguity is guaranteed by intel_pmu_hw_config().
+		 */
+		for (k = i; k < j; k++) {
+			event = cpuc->event_list[k];
+			event->hw.config1 = 0;
+			for_each_set_bit(bit, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
+				idx = i + bit;
+				/* Event index of ACR group must locate in [i, j). */
+				if (idx >= j || !is_acr_event_group(cpuc->event_list[idx]))
+					continue;
+				__set_bit(cpuc->assign[idx], (unsigned long *)&event->hw.config1);
 			}
 		}
 		i = j - 1;
@@ -7504,6 +7531,7 @@ static __always_inline void intel_pmu_init_pnc(struct pmu *pmu)
 	hybrid(pmu, event_constraints) = intel_pnc_event_constraints;
 	hybrid(pmu, pebs_constraints) = intel_pnc_pebs_event_constraints;
 	hybrid(pmu, extra_regs) = intel_pnc_extra_regs;
+	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 }
 
 static __always_inline void intel_pmu_init_skt(struct pmu *pmu)

arch/x86/events/perf_event.h

@@ -137,6 +137,16 @@ static inline bool is_acr_event_group(struct perf_event *event)
 	return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
 }
 
+static inline bool is_acr_self_reload_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < 0)
+		return false;
+
+	return test_bit(hwc->idx, (unsigned long *)&hwc->config1);
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */

kernel/events/core.c

@@ -7006,6 +7006,7 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 }
 
 static void perf_pmu_output_stop(struct perf_event *event);
+static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb);
 
 /*
  * A buffer can be mmap()ed multiple times; either directly through the same
@@ -7021,8 +7022,6 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	mapped_f unmapped = get_mapped(event, event_unmapped);
 	struct perf_buffer *rb = ring_buffer_get(event);
 	struct user_struct *mmap_user = rb->mmap_user;
-	int mmap_locked = rb->mmap_locked;
-	unsigned long size = perf_data_size(rb);
 	bool detach_rest = false;
 
 	/* FIXIES vs perf_pmu_unregister() */
@@ -7117,11 +7116,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	 * Aside from that, this buffer is 'fully' detached and unmapped,
 	 * undo the VM accounting.
 	 */
-
-	atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
-			&mmap_user->locked_vm);
-	atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
-	free_uid(mmap_user);
+	perf_mmap_unaccount(vma, rb);
 
 out_put:
 	ring_buffer_put(rb); /* could be last */
@@ -7261,6 +7256,15 @@ static void perf_mmap_account(struct vm_area_struct *vma, long user_extra, long
 	atomic64_add(extra, &vma->vm_mm->pinned_vm);
 }
 
+static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb)
+{
+	struct user_struct *user = rb->mmap_user;
+
+	atomic_long_sub((perf_data_size(rb) >> PAGE_SHIFT) + 1 - rb->mmap_locked,
+			&user->locked_vm);
+	atomic64_sub(rb->mmap_locked, &vma->vm_mm->pinned_vm);
+}
+
 static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event,
 			unsigned long nr_pages)
 {
@@ -7323,8 +7327,6 @@ static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event,
 	if (!rb)
 		return -ENOMEM;
 
-	refcount_set(&rb->mmap_count, 1);
-	rb->mmap_user = get_current_user();
 	rb->mmap_locked = extra;
 
 	ring_buffer_attach(event, rb);
@@ -7474,16 +7476,54 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			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().
+		 * Try to map it into the page table. On fail 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);
+		if (likely(!ret))
+			return 0;
+
+		/* Error path */
+
+		/*
+		 * If this is the first mmap(), then event->mmap_count should
+		 * be stable at 1. It is only modified by:
+		 * perf_mmap_{open,close}() and perf_mmap().
+		 *
+		 * The former are not possible because this mmap() hasn't been
+		 * successful yet, and the latter is serialized by
+		 * event->mmap_mutex which we still hold (note that mmap_lock
+		 * is not strictly sufficient here, because the event fd can
+		 * be passed to another process through trivial means like
+		 * fork(), leading to concurrent mmap() from different mm).
+		 *
+		 * Make sure to remove event->rb before releasing
+		 * event->mmap_mutex, such that any concurrent mmap() will not
+		 * attempt use this failed buffer.
+		 */
+		if (refcount_read(&event->mmap_count) == 1) {
+			/*
+			 * Minimal perf_mmap_close(); there can't be AUX or
+			 * other events on account of this being the first.
+			 */
+			mapped = get_mapped(event, event_unmapped);
+			if (mapped)
+				mapped(event, vma->vm_mm);
+			perf_mmap_unaccount(vma, event->rb);
+			ring_buffer_attach(event, NULL);	/* drops last rb->refcount */
+			refcount_set(&event->mmap_count, 0);
+			return ret;
+		}
+
+		/*
+		 * Otherwise this is an already existing buffer, and there is
+		 * no race vs first exposure, so fall-through and call
+		 * perf_mmap_close().
+		 */
 	}
 
+	perf_mmap_close(vma);
 	return ret;
 }
 

kernel/events/internal.h

@@ -67,6 +67,7 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head)
 	struct perf_buffer *rb;
 
 	rb = container_of(rcu_head, struct perf_buffer, rcu_head);
+	free_uid(rb->mmap_user);
 	rb_free(rb);
 }
 

kernel/events/ring_buffer.c

@@ -340,6 +340,8 @@ ring_buffer_init(struct perf_buffer *rb, long watermark, int flags)
 		rb->paused = 1;
 
 	mutex_init(&rb->aux_mutex);
+	rb->mmap_user = get_current_user();
+	refcount_set(&rb->mmap_count, 1);
 }
 
 void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)