diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c601939a74b1..c20d8cd47c48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads,	mem_ld_grt,	"event=0xd0,umask=0x5,ldlat=3");
+EVENT_ATTR_STR(mem-stores,	mem_st_grt,	"event=0xd0,umask=0x6");
+
+static struct attribute *grt_mem_attrs[] = {
+	EVENT_PTR(mem_ld_grt),
+	EVENT_PTR(mem_st_grt),
+	NULL
+};
+
 static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
@@ -5975,6 +5984,36 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
+	case INTEL_FAM6_ALDERLAKE_N:
+		x86_pmu.mid_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_grt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_grt();
+		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = tnt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = nhm_format_attr;
+		pr_cont("Gracemont events, ");
+		name = "gracemont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -6317,7 +6356,6 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 		/*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index de1f55d51784..ac973c6f82ad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem)
 	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
 {
 	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
 	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 }
 
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+	__intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
 void __init intel_pmu_pebs_data_source_adl(void)
 {
 	u64 *data_source;
@@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 
 	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
 	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
-	intel_pmu_pebs_data_source_grt(data_source);
+	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba3d24a6a4ec..266143abcbd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem);
 
 void intel_pmu_pebs_data_source_adl(void);
 
+void intel_pmu_pebs_data_source_grt(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2621fd24ad26..ff4bffc502c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6893,9 +6893,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
+	unsigned long flags;
 	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -6931,6 +6938,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\