Merge tag 'perf-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:

 - AMD IBS improvements

 - Intel PMU driver updates

 - Extend core perf facilities & the ARM PMU driver to better handle ARM big.LITTLE events

 - Micro-optimize software events and the ring-buffer code

 - Misc cleanups & fixes

* tag 'perf-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/uncore: Remove unnecessary ?: operator around pcibios_err_to_errno() call
  perf/x86/intel: Add Crestmont PMU
  x86/cpu: Update Hybrids
  x86/cpu: Fix Crestmont uarch
  x86/cpu: Fix Gracemont uarch
  perf: Remove unused extern declaration arch_perf_get_page_size()
  perf: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  arm_pmu: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  perf/x86: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS capability
  arm_pmu: Add PERF_PMU_CAP_EXTENDED_HW_TYPE capability
  perf/x86/ibs: Set mem_lvl_num, mem_remote and mem_hops for data_src
  perf/mem: Add PERF_MEM_LVLNUM_NA to PERF_MEM_NA
  perf/mem: Introduce PERF_MEM_LVLNUM_UNC
  perf/ring_buffer: Use local_try_cmpxchg in __perf_output_begin
  locking/arch: Avoid variable shadowing in local_try_cmpxchg()
  perf/core: Use local64_try_cmpxchg in perf_swevent_set_period
  perf/x86: Use local64_try_cmpxchg
  perf/amd: Prevent grouping of IBS events

29 files changed, 228 insertions, 170 deletions

diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h
index 83e995b30e47..c49675852bdc 100644
--- a/arch/loongarch/include/asm/local.h
+++ b/arch/loongarch/include/asm/local.h
@@ -63,8 +63,8 @@ static inline long local_cmpxchg(local_t *l, long old, long new)
 
 static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
 {
-	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
-	return try_cmpxchg_local(&l->a.counter, __old, new);
+	return try_cmpxchg_local(&l->a.counter,
+				 (typeof(l->a.counter) *) old, new);
 }
 
 #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h
index 5daf6fe8e3e9..e6ae3df0349d 100644
--- a/arch/mips/include/asm/local.h
+++ b/arch/mips/include/asm/local.h
@@ -101,8 +101,8 @@ static __inline__ long local_cmpxchg(local_t *l, long old, long new)
 
 static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new)
 {
-	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
-	return try_cmpxchg_local(&l->a.counter, __old, new);
+	return try_cmpxchg_local(&l->a.counter,
+				 (typeof(l->a.counter) *) old, new);
 }
 
 #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 371014802191..6911c5399d02 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -156,8 +156,8 @@ perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width)
 	 * count to the generic event atomically:
 	 */
 	prev_raw_count = local64_read(&hwc->prev_count);
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					new_raw_count) != prev_raw_count)
+	if (!local64_try_cmpxchg(&hwc->prev_count,
+				 &prev_raw_count, new_raw_count))
 		return 0;
 
 	/*
@@ -247,11 +247,33 @@ int forward_event_to_ibs(struct perf_event *event)
 	return -ENOENT;
 }
 
+/*
+ * Grouping of IBS events is not possible since IBS can have only
+ * one event active at any point in time.
+ */
+static int validate_group(struct perf_event *event)
+{
+	struct perf_event *sibling;
+
+	if (event->group_leader == event)
+		return 0;
+
+	if (event->group_leader->pmu == event->pmu)
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu == event->pmu)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_ibs *perf_ibs;
 	u64 max_cnt, config;
+	int ret;
 
 	perf_ibs = get_ibs_pmu(event->attr.type);
 	if (!perf_ibs)
@@ -265,6 +287,10 @@ static int perf_ibs_init(struct perf_event *event)
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
+	ret = validate_group(event);
+	if (ret)
+		return ret;
+
 	if (hwc->sample_period) {
 		if (config & perf_ibs->cnt_mask)
 			/* raw max_cnt may not be set */
@@ -702,38 +728,63 @@ static u8 perf_ibs_data_src(union ibs_op_data2 *op_data2)
 	return op_data2->data_src_lo;
 }
 
-static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
-				 union ibs_op_data3 *op_data3,
-				 struct perf_sample_data *data)
+#define	L(x)		(PERF_MEM_S(LVL, x) | PERF_MEM_S(LVL, HIT))
+#define	LN(x)		PERF_MEM_S(LVLNUM, x)
+#define	REM		PERF_MEM_S(REMOTE, REMOTE)
+#define	HOPS(x)		PERF_MEM_S(HOPS, x)
+
+static u64 g_data_src[8] = {
+	[IBS_DATA_SRC_LOC_CACHE]	  = L(L3) | L(REM_CCE1) | LN(ANY_CACHE) | HOPS(0),
+	[IBS_DATA_SRC_DRAM]		  = L(LOC_RAM) | LN(RAM),
+	[IBS_DATA_SRC_REM_CACHE]	  = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1),
+	[IBS_DATA_SRC_IO]		  = L(IO) | LN(IO),
+};
+
+#define RMT_NODE_BITS			(1 << IBS_DATA_SRC_DRAM)
+#define RMT_NODE_APPLICABLE(x)		(RMT_NODE_BITS & (1 << x))
+
+static u64 g_zen4_data_src[32] = {
+	[IBS_DATA_SRC_EXT_LOC_CACHE]	  = L(L3) | LN(L3),
+	[IBS_DATA_SRC_EXT_NEAR_CCX_CACHE] = L(REM_CCE1) | LN(ANY_CACHE) | REM | HOPS(0),
+	[IBS_DATA_SRC_EXT_DRAM]		  = L(LOC_RAM) | LN(RAM),
+	[IBS_DATA_SRC_EXT_FAR_CCX_CACHE]  = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1),
+	[IBS_DATA_SRC_EXT_PMEM]		  = LN(PMEM),
+	[IBS_DATA_SRC_EXT_IO]		  = L(IO) | LN(IO),
+	[IBS_DATA_SRC_EXT_EXT_MEM]	  = LN(CXL),
+};
+
+#define ZEN4_RMT_NODE_BITS		((1 << IBS_DATA_SRC_EXT_DRAM) | \
+					 (1 << IBS_DATA_SRC_EXT_PMEM) | \
+					 (1 << IBS_DATA_SRC_EXT_EXT_MEM))
+#define ZEN4_RMT_NODE_APPLICABLE(x)	(ZEN4_RMT_NODE_BITS & (1 << x))
+
+static __u64 perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
+				  union ibs_op_data3 *op_data3,
+				  struct perf_sample_data *data)
 {
 	union perf_mem_data_src *data_src = &data->data_src;
 	u8 ibs_data_src = perf_ibs_data_src(op_data2);
 
 	data_src->mem_lvl = 0;
+	data_src->mem_lvl_num = 0;
 
 	/*
 	 * DcMiss, L2Miss, DataSrc, DcMissLat etc. are all invalid for Uncached
 	 * memory accesses. So, check DcUcMemAcc bit early.
 	 */
-	if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO) {
-		data_src->mem_lvl = PERF_MEM_LVL_UNC | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO)
+		return L(UNC) | LN(UNC);
 
 	/* L1 Hit */
-	if (op_data3->dc_miss == 0) {
-		data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_miss == 0)
+		return L(L1) | LN(L1);
 
 	/* L2 Hit */
 	if (op_data3->l2_miss == 0) {
 		/* Erratum #1293 */
 		if (boot_cpu_data.x86 != 0x19 || boot_cpu_data.x86_model > 0xF ||
-		    !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) {
-			data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
-			return;
-		}
+		    !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc))
+			return L(L2) | LN(L2);
 	}
 
 	/*
@@ -743,82 +794,36 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
 	if (data_src->mem_op != PERF_MEM_OP_LOAD)
 		goto check_mab;
 
-	/* L3 Hit */
 	if (ibs_caps & IBS_CAPS_ZEN4) {
-		if (ibs_data_src == IBS_DATA_SRC_EXT_LOC_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
-			return;
-		}
-	} else {
-		if (ibs_data_src == IBS_DATA_SRC_LOC_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_REM_CCE1 |
-					    PERF_MEM_LVL_HIT;
-			return;
-		}
-	}
+		u64 val = g_zen4_data_src[ibs_data_src];
 
-	/* A peer cache in a near CCX */
-	if (ibs_caps & IBS_CAPS_ZEN4 &&
-	    ibs_data_src == IBS_DATA_SRC_EXT_NEAR_CCX_CACHE) {
-		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+		if (!val)
+			goto check_mab;
 
-	/* A peer cache in a far CCX */
-	if (ibs_caps & IBS_CAPS_ZEN4) {
-		if (ibs_data_src == IBS_DATA_SRC_EXT_FAR_CCX_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT;
-			return;
+		/* HOPS_1 because IBS doesn't provide remote socket detail */
+		if (op_data2->rmt_node && ZEN4_RMT_NODE_APPLICABLE(ibs_data_src)) {
+			if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM)
+				val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1);
+			else
+				val |= REM | HOPS(1);
 		}
-	} else {
-		if (ibs_data_src == IBS_DATA_SRC_REM_CACHE) {
-			data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT;
-			return;
-		}
-	}
 
-	/* DRAM */
-	if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM) {
-		if (op_data2->rmt_node == 0)
-			data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
-		else
-			data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT;
-		return;
-	}
+		return val;
+	} else {
+		u64 val = g_data_src[ibs_data_src];
 
-	/* PMEM */
-	if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_PMEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_PMEM;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
-		}
-		return;
-	}
+		if (!val)
+			goto check_mab;
 
-	/* Extension Memory */
-	if (ibs_caps & IBS_CAPS_ZEN4 &&
-	    ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
+		/* HOPS_1 because IBS doesn't provide remote socket detail */
+		if (op_data2->rmt_node && RMT_NODE_APPLICABLE(ibs_data_src)) {
+			if (ibs_data_src == IBS_DATA_SRC_DRAM)
+				val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1);
+			else
+				val |= REM | HOPS(1);
 		}
-		return;
-	}
 
-	/* IO */
-	if (ibs_data_src == IBS_DATA_SRC_EXT_IO) {
-		data_src->mem_lvl = PERF_MEM_LVL_IO;
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO;
-		if (op_data2->rmt_node) {
-			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
-			/* IBS doesn't provide Remote socket detail */
-			data_src->mem_hops = PERF_MEM_HOPS_1;
-		}
-		return;
+		return val;
 	}
 
 check_mab:
@@ -829,12 +834,11 @@ check_mab:
 	 * DataSrc simultaneously. Prioritize DataSrc over MAB, i.e. set
 	 * MAB only when IBS fails to provide DataSrc.
 	 */
-	if (op_data3->dc_miss_no_mab_alloc) {
-		data_src->mem_lvl = PERF_MEM_LVL_LFB | PERF_MEM_LVL_HIT;
-		return;
-	}
+	if (op_data3->dc_miss_no_mab_alloc)
+		return L(LFB) | LN(LFB);
 
-	data_src->mem_lvl = PERF_MEM_LVL_NA;
+	/* Don't set HIT with NA */
+	return PERF_MEM_S(LVL, NA) | LN(NA);
 }
 
 static bool perf_ibs_cache_hit_st_valid(void)
@@ -924,7 +928,9 @@ static void perf_ibs_get_data_src(struct perf_ibs_data *ibs_data,
 				  union ibs_op_data2 *op_data2,
 				  union ibs_op_data3 *op_data3)
 {
-	perf_ibs_get_mem_lvl(op_data2, op_data3, data);
+	union perf_mem_data_src *data_src = &data->data_src;
+
+	data_src->val |= perf_ibs_get_mem_lvl(op_data2, op_data3, data);
 	perf_ibs_get_mem_snoop(op_data2, data);
 	perf_ibs_get_tlb_lvl(op_data3, data);
 	perf_ibs_get_mem_lock(op_data3, data);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9d248703cbdd..185f902e5f28 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -129,13 +129,11 @@ u64 x86_perf_event_update(struct perf_event *event)
 	 * exchange a new raw count - then add that new-prev delta
 	 * count to the generic event atomically:
 	 */
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	rdpmcl(hwc->event_base_rdpmc, new_raw_count);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					new_raw_count) != prev_raw_count)
-		goto again;
+	do {
+		rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	/*
 	 * Now we have the new raw value and have updated the prev
@@ -2168,7 +2166,6 @@ static int __init init_hw_perf_events(void)
 			hybrid_pmu->pmu = pmu;
 			hybrid_pmu->pmu.type = -1;
 			hybrid_pmu->pmu.attr_update = x86_pmu.attr_update;
-			hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS;
 			hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE;
 
 			err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2a284ba951b7..fa355d3658a6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2129,6 +2129,17 @@ static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(topdown-retiring,       td_retiring_cmt,        "event=0x72,umask=0x0");
+EVENT_ATTR_STR(topdown-bad-spec,       td_bad_spec_cmt,        "event=0x73,umask=0x0");
+
+static struct attribute *cmt_events_attrs[] = {
+	EVENT_PTR(td_fe_bound_tnt),
+	EVENT_PTR(td_retiring_cmt),
+	EVENT_PTR(td_bad_spec_cmt),
+	EVENT_PTR(td_be_bound_tnt),
+	NULL
+};
+
 static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff3ffffffffffull, RSP_0),
@@ -4847,6 +4858,8 @@ PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
 PMU_FORMAT_ATTR(frontend, "config1:0-23");
 
+PMU_FORMAT_ATTR(snoop_rsp, "config1:0-63");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -4877,6 +4890,13 @@ static struct attribute *slm_format_attr[] = {
 	NULL
 };
 
+static struct attribute *cmt_format_attr[] = {
+	&format_attr_offcore_rsp.attr,
+	&format_attr_ldlat.attr,
+	&format_attr_snoop_rsp.attr,
+	NULL
+};
+
 static struct attribute *skl_format_attr[] = {
 	&format_attr_frontend.attr,
 	NULL,
@@ -5656,7 +5676,6 @@ static struct attribute *adl_hybrid_extra_attr[] = {
 	NULL
 };
 
-PMU_FORMAT_ATTR_SHOW(snoop_rsp, "config1:0-63");
 FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small);
 
 static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
@@ -6174,7 +6193,7 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
-	case INTEL_FAM6_ALDERLAKE_N:
+	case INTEL_FAM6_ATOM_GRACEMONT:
 		x86_pmu.mid_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -6204,6 +6223,37 @@ __init int intel_pmu_init(void)
 		name = "gracemont";
 		break;
 
+	case INTEL_FAM6_ATOM_CRESTMONT:
+	case INTEL_FAM6_ATOM_CRESTMONT_X:
+		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_cmt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_cmt();
+		x86_pmu.pebs_latency_data = mtl_latency_data_small;
+		x86_pmu.get_event_constraints = cmt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = cmt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = cmt_format_attr;
+		pr_cont("Crestmont events, ");
+		name = "crestmont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 835862c548cc..96fffb2d521d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -365,13 +365,11 @@ static void cstate_pmu_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	u64 prev_raw_count, new_raw_count;
 
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	new_raw_count = cstate_pmu_read_counter(event);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-			    new_raw_count) != prev_raw_count)
-		goto again;
+	do {
+		new_raw_count = cstate_pmu_read_counter(event);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	local64_add(new_raw_count - prev_raw_count, &event->count);
 }
@@ -671,6 +669,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
@@ -686,7 +685,6 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_cstates),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index df88576d6b2a..eb8dd8b8a1e8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -144,7 +144,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_cmt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_cmt(u64 *data_source)
 {
 	data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
@@ -164,7 +164,12 @@ void __init intel_pmu_pebs_data_source_mtl(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_cmt(data_source);
+	__intel_pmu_pebs_data_source_cmt(data_source);
+}
+
+void __init intel_pmu_pebs_data_source_cmt(void)
+{
+	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
 }
 
 static u64 precise_store_data(u64 status)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index bc226603ef3e..69043e02e8a7 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1858,7 +1858,6 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rkl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
@@ -1867,6 +1866,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_uncore_init),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index d49e90dc04a4..4d349986f76a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1502,7 +1502,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 
 	pci_dev_put(ubox_dev);
 
-	return err ? pcibios_err_to_errno(err) : 0;
+	return pcibios_err_to_errno(err);
 }
 
 int snbep_uncore_pci_init(void)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 0feaaa571303..9e237b30f017 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -106,7 +106,7 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_ROCKETLAKE:
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
+	case INTEL_FAM6_ATOM_GRACEMONT:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
@@ -244,12 +244,10 @@ static void msr_event_update(struct perf_event *event)
 	s64 delta;
 
 	/* Careful, an NMI might modify the previous event value: */
-again:
 	prev = local64_read(&event->hw.prev_count);
-	now = msr_read_counter(event);
-
-	if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev)
-		goto again;
+	do {
+		now = msr_read_counter(event);
+	} while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, now));
 
 	delta = now - prev;
 	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index d6de4487348c..c8ba2be7585d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1606,6 +1606,8 @@ void intel_pmu_pebs_data_source_grt(void);
 
 void intel_pmu_pebs_data_source_mtl(void);
 
+void intel_pmu_pebs_data_source_cmt(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 52e6e7ed4f78..1579429846cc 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -804,7 +804,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&model_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&model_skl),
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index b3af2d45bbbb..5fcd85fd64fd 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -98,8 +98,6 @@
 #define INTEL_FAM6_ICELAKE_L		0x7E	/* Sunny Cove */
 #define INTEL_FAM6_ICELAKE_NNPI		0x9D	/* Sunny Cove */
 
-#define INTEL_FAM6_LAKEFIELD		0x8A	/* Sunny Cove / Tremont */
-
 #define INTEL_FAM6_ROCKETLAKE		0xA7	/* Cypress Cove */
 
 #define INTEL_FAM6_TIGERLAKE_L		0x8C	/* Willow Cove */
@@ -112,21 +110,24 @@
 #define INTEL_FAM6_GRANITERAPIDS_X	0xAD
 #define INTEL_FAM6_GRANITERAPIDS_D	0xAE
 
+/* "Hybrid" Processors (P-Core/E-Core) */
+
+#define INTEL_FAM6_LAKEFIELD		0x8A	/* Sunny Cove / Tremont */
+
 #define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
 #define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
-#define INTEL_FAM6_ALDERLAKE_N		0xBE
 
-#define INTEL_FAM6_RAPTORLAKE		0xB7
+#define INTEL_FAM6_RAPTORLAKE		0xB7	/* Raptor Cove / Enhanced Gracemont */
 #define INTEL_FAM6_RAPTORLAKE_P		0xBA
 #define INTEL_FAM6_RAPTORLAKE_S		0xBF
 
 #define INTEL_FAM6_METEORLAKE		0xAC
 #define INTEL_FAM6_METEORLAKE_L		0xAA
 
-#define INTEL_FAM6_LUNARLAKE_M		0xBD
-
 #define INTEL_FAM6_ARROWLAKE		0xC6
 
+#define INTEL_FAM6_LUNARLAKE_M		0xBD
+
 /* "Small Core" Processors (Atom/E-Core) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
@@ -154,9 +155,10 @@
 #define INTEL_FAM6_ATOM_TREMONT		0x96 /* Elkhart Lake */
 #define INTEL_FAM6_ATOM_TREMONT_L	0x9C /* Jasper Lake */
 
-#define INTEL_FAM6_SIERRAFOREST_X	0xAF
+#define INTEL_FAM6_ATOM_GRACEMONT	0xBE /* Alderlake N */
 
-#define INTEL_FAM6_GRANDRIDGE		0xB6
+#define INTEL_FAM6_ATOM_CRESTMONT_X	0xAF /* Sierra Forest */
+#define INTEL_FAM6_ATOM_CRESTMONT	0xB6 /* Grand Ridge */
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 56d4ef604b91..635132a12778 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -127,8 +127,8 @@ static inline long local_cmpxchg(local_t *l, long old, long new)
 
 static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
 {
-	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
-	return try_cmpxchg_local(&l->a.counter, __old, new);
+	return try_cmpxchg_local(&l->a.counter,
+				 (typeof(l->a.counter) *) old, new);
 }
 
 /* Always has a lock prefix */
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 3b8476158236..e4c3ba91321c 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -206,7 +206,7 @@ static int intel_epb_offline(unsigned int cpu)
 static const struct x86_cpu_id intel_epb_normal[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f1697a522845..ffa25e962343 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -272,7 +272,7 @@ static void __init probe_page_size_mask(void)
 static const struct x86_cpu_id invlpg_miss_ids[] = {
 	INTEL_MATCH(INTEL_FAM6_ALDERLAKE   ),
 	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
-	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
+	INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ),
 	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE  ),
 	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
 	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index a897b6aff368..5abf997ca7c1 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -906,7 +906,7 @@ static const struct x86_cpu_id i10nm_cpuids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SAPPHIRERAPIDS_X,	X86_STEPPINGS(0x0, 0xf), &spr_cfg),
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(EMERALDRAPIDS_X,	X86_STEPPINGS(0x0, 0xf), &spr_cfg),
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(GRANITERAPIDS_X,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
-	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SIERRAFOREST_X,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT_X,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 256c2d42e350..ea5a6a14c553 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -923,7 +923,7 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-static struct cpuidle_state adl_n_cstates[] __initdata = {
+static struct cpuidle_state gmt_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
@@ -1349,8 +1349,8 @@ static const struct idle_cpu idle_cpu_adl_l __initconst = {
 	.state_table = adl_l_cstates,
 };
 
-static const struct idle_cpu idle_cpu_adl_n __initconst = {
-	.state_table = adl_n_cstates,
+static const struct idle_cpu idle_cpu_gmt __initconst = {
+	.state_table = gmt_cstates,
 };
 
 static const struct idle_cpu idle_cpu_spr __initconst = {
@@ -1423,7 +1423,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&idle_cpu_adl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&idle_cpu_adl_l),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&idle_cpu_adl_n),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&idle_cpu_gmt),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&idle_cpu_knl),
@@ -1898,7 +1898,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		break;
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
+	case INTEL_FAM6_ATOM_GRACEMONT:
 		adl_idle_state_table_update();
 		break;
 	}
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f6ccb2cd4dfc..d712a19e47ac 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -877,11 +877,13 @@ struct arm_pmu *armpmu_alloc(void)
 		.attr_groups	= pmu->attr_groups,
 		/*
 		 * This is a CPU PMU potentially in a heterogeneous
-		 * configuration (e.g. big.LITTLE). This is not an uncore PMU,
-		 * and we have taken ctx sharing into account (e.g. with our
-		 * pmu::filter callback and pmu::event_init group validation).
+		 * configuration (e.g. big.LITTLE) so
+		 * PERF_PMU_CAP_EXTENDED_HW_TYPE is required to open
+		 * PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE events on a
+		 * specific PMU.
 		 */
-		.capabilities	= PERF_PMU_CAP_HETEROGENEOUS_CPUS | PERF_PMU_CAP_EXTENDED_REGS,
+		.capabilities	= PERF_PMU_CAP_EXTENDED_REGS |
+				  PERF_PMU_CAP_EXTENDED_HW_TYPE,
 	};
 
 	pmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 5a36b3f77bc5..84c175b9721a 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -1123,7 +1123,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	icl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		tgl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		tgl_core_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		tgl_core_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	tgl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		adl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        tgl_core_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		adl_core_init),
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
index a95004e3d80b..08df9494603c 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
@@ -720,7 +720,7 @@ static struct miscdevice isst_if_char_driver = {
 
 static const struct x86_cpu_id hpm_cpu_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X,	NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(SIERRAFOREST_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	NULL),
 	{}
 };
 
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 8fac57b28f8a..72a8d336f980 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1250,7 +1250,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&rapl_defaults_core),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        &rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&rapl_defaults_core),
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index dd471021f237..250bd41a588c 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -142,7 +142,7 @@ static const struct x86_cpu_id pl4_support_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, NULL),
diff --git a/drivers/thermal/intel/intel_tcc_cooling.c b/drivers/thermal/intel/intel_tcc_cooling.c
index e95f799454fe..6c392147e6d1 100644
--- a/drivers/thermal/intel/intel_tcc_cooling.c
+++ b/drivers/thermal/intel/intel_tcc_cooling.c
@@ -60,7 +60,7 @@ static const struct x86_cpu_id tcc_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, NULL),
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2166a69e3bf2..e83f13ce4a9f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -288,10 +288,9 @@ struct perf_event_pmu_context;
 #define PERF_PMU_CAP_EXTENDED_REGS		0x0008
 #define PERF_PMU_CAP_EXCLUSIVE			0x0010
 #define PERF_PMU_CAP_ITRACE			0x0020
-#define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x0040
-#define PERF_PMU_CAP_NO_EXCLUDE			0x0080
-#define PERF_PMU_CAP_AUX_OUTPUT			0x0100
-#define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0200
+#define PERF_PMU_CAP_NO_EXCLUDE			0x0040
+#define PERF_PMU_CAP_AUX_OUTPUT			0x0080
+#define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0100
 
 struct perf_output_handle;
 
@@ -1194,7 +1193,8 @@ struct perf_sample_data {
 		    PERF_MEM_S(LVL, NA)   |\
 		    PERF_MEM_S(SNOOP, NA) |\
 		    PERF_MEM_S(LOCK, NA)  |\
-		    PERF_MEM_S(TLB, NA))
+		    PERF_MEM_S(TLB, NA)   |\
+		    PERF_MEM_S(LVLNUM, NA))
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
@@ -1860,10 +1860,6 @@ extern void arch_perf_update_userpage(struct perf_event *event,
 				      struct perf_event_mmap_page *userpg,
 				      u64 now);
 
-#ifdef CONFIG_MMU
-extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
-#endif
-
 /*
  * Snapshot branch stack on software events.
  *
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 37675437b768..39c6a250dd1b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1339,7 +1339,8 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x8 available */
+/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2554f5fc70dc..93015cb64d4e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9595,16 +9595,16 @@ u64 perf_swevent_set_period(struct perf_event *event)
 
 	hwc->last_period = hwc->sample_period;
 
-again:
-	old = val = local64_read(&hwc->period_left);
-	if (val < 0)
-		return 0;
+	old = local64_read(&hwc->period_left);
+	do {
+		val = old;
+		if (val < 0)
+			return 0;
 
-	nr = div64_u64(period + val, period);
-	offset = nr * period;
-	val -= offset;
-	if (local64_cmpxchg(&hwc->period_left, old, val) != old)
-		goto again;
+		nr = div64_u64(period + val, period);
+		offset = nr * period;
+		val -= offset;
+	} while (!local64_try_cmpxchg(&hwc->period_left, &old, val));
 
 	return nr;
 }
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a0433f37b024..fb1e180b5f0a 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -191,9 +191,10 @@ __perf_output_begin(struct perf_output_handle *handle,
 
 	perf_output_get_handle(handle);
 
+	offset = local_read(&rb->head);
 	do {
+		head = offset;
 		tail = READ_ONCE(rb->user_page->data_tail);
-		offset = head = local_read(&rb->head);
 		if (!rb->overwrite) {
 			if (unlikely(!ring_buffer_has_space(head, tail,
 							    perf_data_size(rb),
@@ -217,7 +218,7 @@ __perf_output_begin(struct perf_output_handle *handle,
 			head += size;
 		else
 			head -= size;
-	} while (local_cmpxchg(&rb->head, offset, head) != offset);
+	} while (!local_try_cmpxchg(&rb->head, &offset, head));
 
 	if (backward) {
 		offset = head;
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 8a36ba5df9f9..9a10512e3407 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -5447,7 +5447,7 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_LAKEFIELD:
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
+	case INTEL_FAM6_ATOM_GRACEMONT:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S: