perf/x86/intel: Fix bugs of auto counter reload sampling

index 4768236c054b..ca910e6bfc77 100644
@@ -3332,23 +3332,41 @@ 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;

index 03ce1bc7ef2e..e766621f9449 100644
@@ -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;

index ca910e6bfc77..9e77d836b878 100644
@@ -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:

index fad87d3c8b2c..524668dcf4cc 100644
@@ -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 */

index 9e77d836b878..4d5c35f0df5c 100644
@@ -7518,6 +7518,7 @@ 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)

index 4d5c35f0df5c..e05e1aad989e 100644
@@ -3169,10 +3169,10 @@ static void intel_pmu_config_acr(int idx, u64 mask, u32 reload)
 		wrmsrl(msr_b + msr_offset, mask);
 		cpuc->acr_cfg_b[idx] = mask;
 	}
-	/* Only need to update the reload value when there is a valid config value. */
-	if (mask && cpuc->acr_cfg_c[idx] != reload) {
+	/* Only update CFG_C reload when ACR is actively enabled (mask != 0) */
+	if (mask && ((cpuc->cfg_c_val[idx] & ARCH_PEBS_RELOAD) != reload)) {
 		wrmsrl(msr_c + msr_offset, reload);
-		cpuc->acr_cfg_c[idx] = reload;
+		cpuc->cfg_c_val[idx] = reload;
 	}
 }
 

@@ -3198,14 +3198,15 @@ static void intel_pmu_enable_event_ext(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	union arch_pebs_index old, new;
-	struct arch_pebs_cap cap;
 	u64 ext = 0;
 
-	cap = hybrid(cpuc->pmu, arch_pebs_cap);
+	if (is_acr_event_group(event))
+		ext |= (-hwc->sample_period) & ARCH_PEBS_RELOAD;
 
 	if (event->attr.precise_ip) {
 		u64 pebs_data_cfg = intel_get_arch_pebs_data_config(event);
+		struct arch_pebs_cap cap = hybrid(cpuc->pmu, arch_pebs_cap);
+		union arch_pebs_index old, new;
 
 		ext |= ARCH_PEBS_EN;
 		if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD)

index 524668dcf4cc..40d6fe0afc4a 100644
@@ -322,10 +322,8 @@ struct cpu_hw_events {
 	u64			fixed_ctrl_val;
 	u64			active_fixed_ctrl_val;
 
-	/* Intel ACR configuration */
+	/* Intel ACR/arch-PEBS configuration */
 	u64			acr_cfg_b[X86_PMC_IDX_MAX];
-	u64			acr_cfg_c[X86_PMC_IDX_MAX];
-	/* Cached CFG_C values */
 	u64			cfg_c_val[X86_PMC_IDX_MAX];
 
 	/*