From 7c2128235eff99b448af8f4b5b2933495bf1a440 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Tue, 20 Jun 2023 14:46:03 +0530
Subject: [PATCH 01/18] perf/amd: Prevent grouping of IBS events

IBS PMUs can have only one event active at any point in time. Restrict
grouping of multiple IBS events.

Reported-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230620091603.269-1-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 371014802191..74e664266753 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -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 */

From 4c1c9dea2089374cb58505a0df6136969ff3c8b9 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Thu, 6 Jul 2023 16:16:48 +0200
Subject: [PATCH 02/18] perf/x86: Use local64_try_cmpxchg

Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old.
x86 CMPXCHG instruction returns success in ZF flag, so this change saves a
compare after cmpxchg (and related move instruction in front of cmpxchg).

Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails. There is no need to re-read the value in the loop.

No functional change intended.

Cc. "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230706141720.2672-1-ubizjak@gmail.com
---
 arch/x86/events/amd/ibs.c      |  4 ++--
 arch/x86/events/core.c         | 10 ++++------
 arch/x86/events/intel/cstate.c | 10 ++++------
 arch/x86/events/msr.c          |  8 +++-----
 4 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 74e664266753..7d29be0a279b 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;
 
 	/*
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9d248703cbdd..23c96420dea1 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
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 835862c548cc..97035db68df2 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);
 }
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 0feaaa571303..61c59e0627d4 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -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)) {

From 28fd85a10a2a73658c6e26056d9e093de06b5a22 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sat, 8 Jul 2023 10:10:57 +0200
Subject: [PATCH 03/18] perf/core: Use local64_try_cmpxchg in
 perf_swevent_set_period

Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
in perf_swevent_set_period.  x86 CMPXCHG instruction returns success in ZF
flag, so this change saves a compare after cmpxchg (and related move
instruction in front of cmpxchg).

Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails. There is no need to re-read the value in the loop.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230708081129.45915-1-ubizjak@gmail.com
---
 kernel/events/core.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78ae7b6f90fd..f84e2640ea2f 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;
 }

From d6b45484c130f4095313ae3edeb4aae662c12fb1 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sat, 8 Jul 2023 11:00:36 +0200
Subject: [PATCH 04/18] locking/arch: Avoid variable shadowing in
 local_try_cmpxchg()

Several architectures define arch_try_local_cmpxchg macro using
internal temporary variables named ___old, __old or _old. Remove
temporary varible in local_try_cmpxchg to avoid variable shadowing.

No functional change intended.

Fixes: d994f2c8e241 ("locking/arch: Wire up local_try_cmpxchg()")
Closes: https://lore.kernel.org/lkml/CAFGhKbyxtuk=LoW-E3yLXgcmR93m+Dfo5-u9oQA_YC5Fcy_t9g@mail.gmail.com/
Reported-by: Charlemagne Lasse <charlemagnelasse@gmail.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230708090048.63046-1-ubizjak@gmail.com
---
 arch/loongarch/include/asm/local.h | 4 ++--
 arch/mips/include/asm/local.h      | 4 ++--
 arch/x86/include/asm/local.h       | 4 ++--
 3 files changed, 6 insertions(+), 6 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/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 */

From 1af61adb3a23192023fec1733bd4c8500f53e546 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sat, 8 Jul 2023 11:00:37 +0200
Subject: [PATCH 05/18] perf/ring_buffer: Use local_try_cmpxchg in
 __perf_output_begin

Use local_try_cmpxchg instead of local_cmpxchg (*ptr, old, new) == old
in __perf_output_begin.  x86 CMPXCHG instruction returns success in ZF
flag, so this change saves a compare after cmpxchg (and related move
instruction in front of cmpxchg).

Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails. There is no need to re-read the value in the loop.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230708090048.63046-2-ubizjak@gmail.com
---
 kernel/events/ring_buffer.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

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;

From 526fffabc5fb63e80eb890c74b6570df2570c87f Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Tue, 25 Jul 2023 20:32:04 +0530
Subject: [PATCH 06/18] perf/mem: Introduce PERF_MEM_LVLNUM_UNC

Older API PERF_MEM_LVL_UNC can be replaced by PERF_MEM_LVLNUM_UNC.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230725150206.184-2-ravi.bangoria@amd.com
---
 include/uapi/linux/perf_event.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

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 */

From 5c6e623f1b8ebca39eeefba4b18d574eb5acf0bd Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Tue, 25 Jul 2023 20:32:05 +0530
Subject: [PATCH 07/18] perf/mem: Add PERF_MEM_LVLNUM_NA to PERF_MEM_NA

Add PERF_MEM_LVLNUM_NA wherever PERF_MEM_NA is used to set default values.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230725150206.184-3-ravi.bangoria@amd.com
---
 include/linux/perf_event.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2166a69e3bf2..dd92b4f5d370 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1194,7 +1194,8 @@ 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)

From 8bfc20baa9355d2ce6b031ff8bdb62c9456923f7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 25 Jul 2023 20:32:06 +0530
Subject: [PATCH 08/18] perf/x86/ibs: Set mem_lvl_num, mem_remote and mem_hops
 for data_src

Kernel IBS driver wasn't using new PERF_MEM_* APIs due to some of its
limitations. Mainly:

1. mem_lvl_num doesn't allow setting multiple sources whereas old API
   allows it. Setting multiple data sources is useful because IBS on
   pre-zen4 uarch doesn't provide fine granular DataSrc details (there
   is only one such DataSrc(2h) though).
2. perf mem sorting logic (sort__lvl_cmp()) ignores mem_lvl_num. perf
   c2c (c2c_decode_stats()) does not use mem_lvl_num at all.

1st one can be handled using ANY_CACHE with HOPS_0. 2nd is purely perf
tool specific issue and should be fixed separately.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230725150206.184-4-ravi.bangoria@amd.com
---
 arch/x86/events/amd/ibs.c | 160 +++++++++++++++++---------------------
 1 file changed, 70 insertions(+), 90 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 7d29be0a279b..6911c5399d02 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -728,38 +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);
 	}
 
 	/*
@@ -769,82 +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;
+		u64 val = g_zen4_data_src[ibs_data_src];
+
+		if (!val)
+			goto check_mab;
+
+		/* 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);
 		}
+
+		return val;
 	} 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_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 && 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);
 		}
-	} 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;
-	}
-
-	/* 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;
-	}
-
-	/* 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;
-		}
-		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:
@@ -855,12 +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)
@@ -950,7 +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);

From 5c816728651ae425954542fed64d21d40cb75a9f Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 24 Jul 2023 14:44:56 +0100
Subject: [PATCH 09/18] arm_pmu: Add PERF_PMU_CAP_EXTENDED_HW_TYPE capability

This capability gives us the ability to open PERF_TYPE_HARDWARE and
PERF_TYPE_HW_CACHE events on a specific PMU for free. All the
implementation is contained in the Perf core and tool code so no change
to the Arm PMU driver is needed.

The following basic use case now results in Perf opening the event on
all PMUs rather than picking only one in an unpredictable way:

  $ perf stat -e cycles -- taskset --cpu-list 0,1 stress -c 2

   Performance counter stats for 'taskset --cpu-list 0,1 stress -c 2':

         963279620      armv8_cortex_a57/cycles/                (99.19%)
         752745657      armv8_cortex_a53/cycles/                (94.80%)

Fixes: 55bcf6ef314a ("perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE")
Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230724134500.970496-2-james.clark@arm.com
---
 drivers/perf/arm_pmu.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f6ccb2cd4dfc..2e79201daa4a 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -880,8 +880,13 @@ struct arm_pmu *armpmu_alloc(void)
 		 * 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).
+		 *
+		 * 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_HETEROGENEOUS_CPUS | PERF_PMU_CAP_EXTENDED_REGS |
+				  PERF_PMU_CAP_EXTENDED_HW_TYPE,
 	};
 
 	pmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =

From 4b36873b4a3455590f686903c354c4716e149c74 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 24 Jul 2023 14:44:57 +0100
Subject: [PATCH 10/18] perf/x86: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS
 capability

Since commit bd2756811766 ("perf: Rewrite core context handling") the
relationship between perf_event_context and PMUs has changed so that
the error scenario that PERF_PMU_CAP_HETEROGENEOUS_CPUS originally
silenced no longer exists.

Remove the capability to avoid confusion that it actually influences
any perf core behavior. This change should be a no-op.

Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230724134500.970496-3-james.clark@arm.com
---
 arch/x86/events/core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 23c96420dea1..185f902e5f28 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2166,7 +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,

From 80391d8c387d406e2ec79776ec834666ab9611b0 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 24 Jul 2023 14:44:58 +0100
Subject: [PATCH 11/18] arm_pmu: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS
 capability

Since commit bd2756811766 ("perf: Rewrite core context handling") the
relationship between perf_event_context and PMUs has changed so that
the error scenario that PERF_PMU_CAP_HETEROGENEOUS_CPUS originally
silenced no longer exists.

Remove the capability and associated comment to avoid confusion that it
actually influences any perf core behavior. This change should be a
no-op.

Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230724134500.970496-4-james.clark@arm.com
---
 drivers/perf/arm_pmu.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 2e79201daa4a..d712a19e47ac 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -877,15 +877,12 @@ 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,
 	};
 

From 0cb52ad7bbb27bc6700412b055c743d5ae501b29 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 24 Jul 2023 14:44:59 +0100
Subject: [PATCH 12/18] perf: Remove unused PERF_PMU_CAP_HETEROGENEOUS_CPUS
 capability

Since commit bd2756811766 ("perf: Rewrite core context handling") the
relationship between perf_event_context and PMUs has changed so that
the error scenario that PERF_PMU_CAP_HETEROGENEOUS_CPUS originally
silenced no longer exists.

Remove the capability to avoid confusion that it actually influences
any perf core behavior and shift down the following capability bits to
fill in the unused space. This change should be a no-op.

Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230724134500.970496-5-james.clark@arm.com
---
 include/linux/perf_event.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dd92b4f5d370..9b1cf3c19c5f 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;
 

From 62af03223785c11a0916df6a854ef4785d2350a5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 25 Jul 2023 21:50:38 +0800
Subject: [PATCH 13/18] perf: Remove unused extern declaration
 arch_perf_get_page_size()

commit 8af26be06272 ("perf/core: Fix arch_perf_get_page_size()")
left behind this.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230725135038.25060-1-yuehaibing@huawei.com
---
 include/linux/perf_event.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9b1cf3c19c5f..e83f13ce4a9f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -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.
  *

From 882cdb06b668488a42ef717a260c05ba7dc43a49 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Aug 2023 14:38:07 +0200
Subject: [PATCH 14/18] x86/cpu: Fix Gracemont uarch

Alderlake N is an E-core only product using Gracemont
micro-architecture. It fits the pre-existing naming scheme perfectly
fine, adhere to it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230807150405.686834933@infradead.org
---
 arch/x86/events/intel/core.c              |  2 +-
 arch/x86/events/intel/cstate.c            |  2 +-
 arch/x86/events/intel/uncore.c            |  2 +-
 arch/x86/events/msr.c                     |  2 +-
 arch/x86/events/rapl.c                    |  2 +-
 arch/x86/include/asm/intel-family.h       |  3 ++-
 arch/x86/kernel/cpu/intel_epb.c           |  2 +-
 arch/x86/mm/init.c                        |  2 +-
 drivers/idle/intel_idle.c                 | 10 +++++-----
 drivers/platform/x86/intel/pmc/core.c     |  2 +-
 drivers/powercap/intel_rapl_common.c      |  2 +-
 drivers/powercap/intel_rapl_msr.c         |  2 +-
 drivers/thermal/intel/intel_tcc_cooling.c |  2 +-
 tools/power/x86/turbostat/turbostat.c     |  2 +-
 14 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a149fafad813..c7e7ed6814ef 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6167,7 +6167,7 @@ __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));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 97035db68df2..96fffb2d521d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -669,6 +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),
@@ -684,7 +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/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/msr.c b/arch/x86/events/msr.c
index 61c59e0627d4..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:
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..40413262b4cc 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -114,7 +114,6 @@
 
 #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_P		0xBA
@@ -154,6 +153,8 @@
 #define INTEL_FAM6_ATOM_TREMONT		0x96 /* Elkhart Lake */
 #define INTEL_FAM6_ATOM_TREMONT_L	0x9C /* Jasper Lake */
 
+#define INTEL_FAM6_ATOM_GRACEMONT	0xBE /* Alderlake N */
+
 #define INTEL_FAM6_SIERRAFOREST_X	0xAF
 
 #define INTEL_FAM6_GRANDRIDGE		0xB6
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 8192452d1d2d..ad207f3cf4d1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -273,7 +273,7 @@ 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/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b930036edbbe..46c6de321c50 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -960,7 +960,7 @@ 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",
@@ -1405,8 +1405,8 @@ 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 = {
@@ -1479,7 +1479,7 @@ 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),
@@ -1979,7 +1979,7 @@ 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/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/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 4e646e5e48f6..a942a2527a9a 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 569e25eab1e1..1e775b0db211 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -141,7 +141,7 @@ 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/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:

From 0cfd8fbadd6833d243c9a9d8649ba4a9f4361c93 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Aug 2023 14:38:08 +0200
Subject: [PATCH 15/18] x86/cpu: Fix Crestmont uarch

Sierra Forest and Grand Ridge are both E-core only using Crestmont
micro-architecture, They fit the pre-existing naming scheme prefectly
fine, adhere to it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230807150405.757666627@infradead.org
---
 arch/x86/include/asm/intel-family.h                         | 5 ++---
 drivers/edac/i10nm_base.c                                   | 2 +-
 drivers/platform/x86/intel/speed_select_if/isst_if_common.c | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 40413262b4cc..49d40eebe36a 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -155,9 +155,8 @@
 
 #define INTEL_FAM6_ATOM_GRACEMONT	0xBE /* Alderlake N */
 
-#define INTEL_FAM6_SIERRAFOREST_X	0xAF
-
-#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/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/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
index 1f59ac55c5f7..47e5a947b0b4 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),
 	{}
 };
 

From 535445621a66faa7050c21d9d668595116285648 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Aug 2023 14:38:09 +0200
Subject: [PATCH 16/18] x86/cpu: Update Hybrids

Give the hybrid thingies their own section, appropriately between Core
and Atom.

Add the Raptor Lake uarch names.

Put Lunar Lake after Arrow Lake per interweb guidance.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230807150405.828551866@infradead.org
---
 arch/x86/include/asm/intel-family.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 49d40eebe36a..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 */
@@ -112,20 +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_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 */

From a430021faad6b4fa86c820fc3e7f8dbfc2f14fb4 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 22 May 2023 04:30:35 -0700
Subject: [PATCH 17/18] perf/x86/intel: Add Crestmont PMU

The Grand Ridge and Sierra Forest are successors to Snow Ridge. They
both have Crestmont core. From the core PMU's perspective, they are
similar to the e-core of MTL. The only difference is the LBR event
logging feature, which will be implemented in the following patches.

Create a non-hybrid PMU setup for Grand Ridge and Sierra Forest.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lore.kernel.org/r/20230522113040.2329924-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 52 +++++++++++++++++++++++++++++++++++-
 arch/x86/events/intel/ds.c   |  9 +++++--
 arch/x86/events/perf_event.h |  2 ++
 3 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c7e7ed6814ef..64a3533997e1 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),
@@ -4840,6 +4851,8 @@ 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,
@@ -4870,6 +4883,13 @@ 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,
@@ -5649,7 +5669,6 @@ 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[] = {
@@ -6197,6 +6216,37 @@ __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/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/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);

From 2c65477f14a359db9f1edee5dd8e683d3dae69e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Thu, 24 Aug 2023 16:28:32 +0300
Subject: [PATCH 18/18] perf/x86/uncore: Remove unnecessary ?: operator around
 pcibios_err_to_errno() call
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If err == 0, pcibios_err_to_errno(err) returns 0 so the ?: construct
can be removed.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230824132832.78705-15-ilpo.jarvinen@linux.intel.com
---
 arch/x86/events/intel/uncore_snbep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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)