From 2793c4b66408b6378d762b38b3cbba578e59b167 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 1 Oct 2020 06:57:46 -0700
Subject: [PATCH 1/9] perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE

mainline inclusion
from mainline-v5.11-rc1
commit 8d97e71811aaafe4abf611dc24822fd6e73df1a1
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 8d97e71811aa perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE

-------------------------------------

Current perf can report both virtual addresses and physical addresses,
but not the MMU page size. Without the MMU page size information of the
utilized page, users cannot decide whether to promote/demote large pages
to optimize memory usage.

Add a new sample type for the data MMU page size.

Current perf already has a facility to collect data virtual addresses.
A page walker is required to walk the pages tables and calculate the
MMU page size from a given virtual address.

On some platforms, e.g., X86, the page walker is invoked in an NMI
handler. So the page walker must be NMI-safe and low overhead. Besides,
the page walker should work for both user and kernel virtual address.
The existing generic page walker, e.g., walk_page_range_novma(), is a
little bit complex and doesn't guarantee the NMI-safe. The follow_page()
is only for user-virtual address.

Add a new function perf_get_page_size() to walk the page tables and
calculate the MMU page size. In the function:
- Interrupts have to be disabled to prevent any teardown of the page
  tables.
- For user space threads, the current->mm is used for the page walker.
  For kernel threads and the like, the current->mm is NULL. The init_mm
  is used for the page walker. The active_mm is not used here, because
  it can be NULL.
  Quote from Peter Zijlstra,
  "context_switch() can set prev->active_mm to NULL when it transfers it
   to @next. It does this before @current is updated. So an NMI that
   comes in between this active_mm swizzling and updating @current will
   see !active_mm."
- The MMU page size is calculated from the page table level.

The method should work for all architectures, but it has only been
verified on X86. Should there be some architectures, which support perf,
where the method doesn't work, it can be fixed later separately.
Reporting the wrong page size would not be fatal for the architecture.

Some under discussion features may impact the method in the future.
Quote from Dave Hansen,
  "There are lots of weird things folks are trying to do with the page
   tables, like Address Space Isolation.  For instance, if you get a
   perf NMI when running userspace, current->mm->pgd is *different* than
   the PGD that was in use when userspace was running. It's close enough
   today, but it might not stay that way."
If the case happens later, lots of consecutive page walk errors will
happen. The worst case is that lots of page-size '0' are returned, which
would not be fatal.
In the perf tool, a check is implemented to detect this case. Once it
happens, a kernel patch could be implemented accordingly then.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-2-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/perf_event.h      |   1 +
 include/uapi/linux/perf_event.h |   4 +-
 kernel/events/core.c            | 103 ++++++++++++++++++++++++++++++++
 3 files changed, 107 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d4c912443ac6..7c692a4d4254 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1040,6 +1040,7 @@ struct perf_sample_data {
 
 	u64				phys_addr;
 	u64				cgroup;
+	u64				data_page_size;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b95d3c485d27..54695b2b20a3 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -143,8 +143,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
+	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
 
-	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 23,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -896,6 +897,7 @@ enum perf_event_type {
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
+	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4bd9dd6c3b72..af47b246e9cf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -51,6 +51,7 @@
 #include <linux/proc_ns.h>
 #include <linux/mount.h>
 #include <linux/min_heap.h>
+#include <linux/highmem.h>
 
 #include "internal.h"
 
@@ -1896,6 +1897,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		size += sizeof(data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		size += sizeof(data->data_page_size);
+
 	event->header_size = size;
 }
 
@@ -7007,6 +7011,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		perf_output_put(handle, data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		perf_output_put(handle, data->data_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7064,6 +7071,94 @@ static u64 perf_virt_to_phys(u64 virt)
 	return phys_addr;
 }
 
+#ifdef CONFIG_MMU
+
+/*
+ * Return the MMU page size of a given virtual address
+ */
+static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return 0;
+
+	if (p4d_leaf(*p4d))
+		return 1ULL << P4D_SHIFT;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return 0;
+
+	if (pud_leaf(*pud))
+		return 1ULL << PUD_SHIFT;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return 0;
+
+	if (pmd_leaf(*pmd))
+		return 1ULL << PMD_SHIFT;
+
+	pte = pte_offset_map(pmd, addr);
+	if (!pte_present(*pte)) {
+		pte_unmap(pte);
+		return 0;
+	}
+
+	pte_unmap(pte);
+	return PAGE_SIZE;
+}
+
+#else
+
+static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	return 0;
+}
+
+#endif
+
+static u64 perf_get_page_size(unsigned long addr)
+{
+	struct mm_struct *mm;
+	unsigned long flags;
+	u64 size;
+
+	if (!addr)
+		return 0;
+
+	/*
+	 * Software page-table walkers must disable IRQs,
+	 * which prevents any tear down of the page tables.
+	 */
+	local_irq_save(flags);
+
+	mm = current->mm;
+	if (!mm) {
+		/*
+		 * For kernel threads and the like, use init_mm so that
+		 * we can find kernel memory.
+		 */
+		mm = &init_mm;
+	}
+
+	size = __perf_get_page_size(mm, addr);
+
+	local_irq_restore(flags);
+
+	return size;
+}
+
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
 struct perf_callchain_entry *
@@ -7218,6 +7313,14 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 #endif
 
+	/*
+	 * PERF_DATA_PAGE_SIZE requires PERF_SAMPLE_ADDR. If the user doesn't
+	 * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr,
+	 * but the value will not dump to the userspace.
+	 */
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		data->data_page_size = perf_get_page_size(data->addr);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
-- 
Gitee


From eb1c70cddab584307ab00f86e604eb994e785129 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 1 Oct 2020 06:57:47 -0700
Subject: [PATCH 2/9] perf/x86/intel: Support PERF_SAMPLE_DATA_PAGE_SIZE

mainline inclusion
from mainline-v5.11-rc1
commit 76a5433f95f32d8a17c9f836be2084ed947c466b
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 76a5433f95f3 perf/x86/intel: Support PERF_SAMPLE_DATA_PAGE_SIZE

-------------------------------------

The new sample type, PERF_SAMPLE_DATA_PAGE_SIZE, requires the virtual
address. Update the data->addr if the sample type is set.

The large PEBS is disabled with the sample type, because perf doesn't
support munmap tracking yet. The PEBS buffer for large PEBS cannot be
flushed for each munmap. Wrong page size may be calculated. The large
PEBS can be enabled later separately when munmap tracking is supported.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-3-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/intel/ds.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 945d470f62d0..aa998de201c8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -961,7 +961,8 @@ static void adaptive_pebs_record_size_update(void)
 
 #define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
 				PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
-				PERF_SAMPLE_TRANSACTION)
+				PERF_SAMPLE_TRANSACTION |		     \
+				PERF_SAMPLE_DATA_PAGE_SIZE)
 
 static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 {
@@ -1337,6 +1338,10 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 	return val;
 }
 
+#define PERF_SAMPLE_ADDR_TYPE	(PERF_SAMPLE_ADDR |		\
+				 PERF_SAMPLE_PHYS_ADDR |	\
+				 PERF_SAMPLE_DATA_PAGE_SIZE)
+
 static void setup_pebs_fixed_sample_data(struct perf_event *event,
 				   struct pt_regs *iregs, void *__pebs,
 				   struct perf_sample_data *data,
@@ -1451,7 +1456,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	}
 
 
-	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
+	if ((sample_type & PERF_SAMPLE_ADDR_TYPE) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
 		data->addr = pebs->dla;
 
@@ -1579,7 +1584,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		if (sample_type & PERF_SAMPLE_DATA_SRC)
 			data->data_src.val = get_data_src(event, meminfo->aux);
 
-		if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+		if (sample_type & PERF_SAMPLE_ADDR_TYPE)
 			data->addr = meminfo->address;
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-- 
Gitee


From 6192c538508e4d2792efe4020cc0f8ff46ac2af4 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 1 Oct 2020 06:57:48 -0700
Subject: [PATCH 3/9] powerpc/perf: Support PERF_SAMPLE_DATA_PAGE_SIZE

mainline inclusion
from mainline-v5.11-rc1
commit 4cb6a42e4c4bc1902644eced67563e7405d4588e
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 4cb6a42e4c4b powerpc/perf: Support PERF_SAMPLE_DATA_PAGE_SIZE

-------------------------------------

The new sample type, PERF_SAMPLE_DATA_PAGE_SIZE, requires the virtual
address. Update the data->addr if the sample type is set.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-4-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/powerpc/perf/core-book3s.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index e49aa8fc6a49..0abd7e04b124 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2122,6 +2122,9 @@ static struct pmu power_pmu = {
 	.sched_task	= power_pmu_sched_task,
 };
 
+#define PERF_SAMPLE_ADDR_TYPE  (PERF_SAMPLE_ADDR |		\
+				PERF_SAMPLE_PHYS_ADDR |		\
+				PERF_SAMPLE_DATA_PAGE_SIZE)
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -2198,8 +2201,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
 
-		if (event->attr.sample_type &
-		    (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+		if (event->attr.sample_type & PERF_SAMPLE_ADDR_TYPE)
 			perf_get_data_addr(event, regs, &data.addr);
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
-- 
Gitee


From 8e033a79c9bf6155a5841fb2758d2712a482b08a Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 1 Oct 2020 06:57:49 -0700
Subject: [PATCH 4/9] perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

mainline inclusion
from mainline-v5.11-rc1
commit 995f088efebe1eba0282a6ffa12411b37f8990c2
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 995f088efebe perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

-------------------------------------

When studying code layout, it is useful to capture the page size of the
sampled code address.

Add a new sample type for code page size.
The new sample type requires collecting the ip. The code page size can
be calculated from the NMI-safe perf_get_page_size().

For large PEBS, it's very unlikely that the mapping is gone for the
earlier PEBS records. Enable the feature for the large PEBS. The worst
case is that page-size '0' is returned.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-5-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/perf_event.h    |  2 +-
 include/linux/perf_event.h      |  1 +
 include/uapi/linux/perf_event.h |  4 +++-
 kernel/events/core.c            | 11 ++++++++++-
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 0c3b8fa7e532..20a300db991f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -132,7 +132,7 @@ struct amd_nb {
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
-	PERF_SAMPLE_PERIOD)
+	PERF_SAMPLE_PERIOD | PERF_SAMPLE_CODE_PAGE_SIZE)
 
 #define PEBS_GP_REGS			\
 	((1ULL << PERF_REG_X86_AX)    | \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7c692a4d4254..2d48d62b8a98 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1041,6 +1041,7 @@ struct perf_sample_data {
 	u64				phys_addr;
 	u64				cgroup;
 	u64				data_page_size;
+	u64				code_page_size;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 54695b2b20a3..b15e3447cd9f 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -144,8 +144,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
 	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 23,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -898,6 +899,7 @@ enum perf_event_type {
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
 	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index af47b246e9cf..88751e38c07d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1900,6 +1900,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		size += sizeof(data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		size += sizeof(data->code_page_size);
+
 	event->header_size = size;
 }
 
@@ -7014,6 +7017,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		perf_output_put(handle, data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		perf_output_put(handle, data->code_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7194,7 +7200,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	__perf_event_header__init_id(header, data, event);
 
-	if (sample_type & PERF_SAMPLE_IP)
+	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
@@ -7321,6 +7327,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		data->data_page_size = perf_get_page_size(data->addr);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		data->code_page_size = perf_get_page_size(data->ip);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
-- 
Gitee


From 08f885e856796762b494fa1ef0af6438f0399d51 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 28 Jan 2021 14:40:07 -0800
Subject: [PATCH 5/9] perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT

mainline inclusion
from mainline-v5.12-rc1
commit 2a6c6b7d7ad346f0679d0963cb19b3f0ea7ef32c
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 2a6c6b7d7ad3 perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT

-------------------------------------

Current PERF_SAMPLE_WEIGHT sample type is very useful to expresses the
cost of an action represented by the sample. This allows the profiler
to scale the samples to be more informative to the programmer. It could
also help to locate a hotspot, e.g., when profiling by memory latencies,
the expensive load appear higher up in the histograms. But current
PERF_SAMPLE_WEIGHT sample type is solely determined by one factor. This
could be a problem, if users want two or more factors to contribute to
the weight. For example, Golden Cove core PMU can provide both the
instruction latency and the cache Latency information as factors for the
memory profiling.

For current X86 platforms, although meminfo::latency is defined as a
u64, only the lower 32 bits include the valid data in practice (No
memory access could last than 4G cycles). The higher 32 bits can be used
to store new factors.

Add a new sample type, PERF_SAMPLE_WEIGHT_STRUCT, to indicate the new
sample weight structure. It shares the same space as the
PERF_SAMPLE_WEIGHT sample type.

Users can apply either the PERF_SAMPLE_WEIGHT sample type or the
PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but
they cannot apply both sample types simultaneously.

Currently, only X86 and PowerPC use the PERF_SAMPLE_WEIGHT sample type.
- For PowerPC, there is nothing changed for the PERF_SAMPLE_WEIGHT
  sample type. There is no effect for the new PERF_SAMPLE_WEIGHT_STRUCT
  sample type. PowerPC can re-struct the weight field similarly later.
- For X86, the same value will be dumped for the PERF_SAMPLE_WEIGHT
  sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type for now.
  The following patches will apply the new factors for the
  PERF_SAMPLE_WEIGHT_STRUCT sample type.

The field in the union perf_sample_weight should be shared among
different architectures. A generic name is required, but it's hard to
abstract a name that applies to all architectures. For example, on X86,
the fields are to store all kinds of latency. While on PowerPC, it
stores MMCRA[TECX/TECM], which should not be latency. So a general name
prefix 'var$NUM' is used here.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jun Tian <jun.j.tian@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/powerpc/perf/core-book3s.c |  2 +-
 arch/x86/events/intel/ds.c      | 17 ++++++-------
 include/linux/perf_event.h      |  4 ++--
 include/uapi/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++--
 kernel/events/core.c            | 11 +++++----
 5 files changed, 59 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 0abd7e04b124..2710b0d7ae9f 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2217,7 +2217,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (event->attr.sample_type & PERF_SAMPLE_WEIGHT &&
 						ppmu->get_mem_weight)
-			ppmu->get_mem_weight(&data.weight);
+			ppmu->get_mem_weight(&data.weight.full);
 
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index aa998de201c8..b102e9aac2ff 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -960,7 +960,8 @@ static void adaptive_pebs_record_size_update(void)
 }
 
 #define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
-				PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+				PERF_SAMPLE_PHYS_ADDR |			     \
+				PERF_SAMPLE_WEIGHT_TYPE |		     \
 				PERF_SAMPLE_TRANSACTION |		     \
 				PERF_SAMPLE_DATA_PAGE_SIZE)
 
@@ -987,7 +988,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
 	       (attr->sample_regs_intr & PEBS_GP_REGS);
 
-	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
 		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
 		      x86_pmu.rtm_abort_event);
 
@@ -1369,8 +1370,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
-	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-		data->weight = pebs->lat;
+	if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE))
+		data->weight.full = pebs->lat;
 
 	/*
 	 * data.data_src encodes the data source
@@ -1462,8 +1463,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
-		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
+		if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll)
+			data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
 			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
@@ -1577,8 +1578,8 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	}
 
 	if (format_size & PEBS_DATACFG_MEMINFO) {
-		if (sample_type & PERF_SAMPLE_WEIGHT)
-			data->weight = meminfo->latency ?:
+		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+			data->weight.full = meminfo->latency ?:
 				intel_get_tsx_weight(meminfo->tsx_tuning);
 
 		if (sample_type & PERF_SAMPLE_DATA_SRC)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2d48d62b8a98..f0eafc958210 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1010,7 +1010,7 @@ struct perf_sample_data {
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
 	u64				period;
-	u64				weight;
+	union perf_sample_weight	weight;
 	u64				txn;
 	union  perf_mem_data_src	data_src;
 
@@ -1059,7 +1059,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->weight = 0;
+	data->weight.full = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b15e3447cd9f..b2cc246ec119 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -145,12 +145,14 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_CGROUP			= 1U << 21,
 	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
 	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
+	PERF_SAMPLE_WEIGHT_STRUCT		= 1U << 24,
 
-	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 25,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
+#define PERF_SAMPLE_WEIGHT_TYPE	(PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT)
 /*
  * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
  *
@@ -890,7 +892,24 @@ enum perf_event_type {
 	 * 	  char			data[size];
 	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
 	 *
-	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ union perf_sample_weight
+	 *	 {
+	 *		u64		full; && PERF_SAMPLE_WEIGHT
+	 *	#if defined(__LITTLE_ENDIAN_BITFIELD)
+	 *		struct {
+	 *			u32	var1_dw;
+	 *			u16	var2_w;
+	 *			u16	var3_w;
+	 *		} && PERF_SAMPLE_WEIGHT_STRUCT
+	 *	#elif defined(__BIG_ENDIAN_BITFIELD)
+	 *		struct {
+	 *			u16	var3_w;
+	 *			u16	var2_w;
+	 *			u32	var1_dw;
+	 *		} && PERF_SAMPLE_WEIGHT_STRUCT
+	 *	#endif
+	 *	 }
+	 *	}
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 *	{ u64			abi; # enum perf_sample_regs_abi
@@ -1248,4 +1267,23 @@ struct perf_branch_entry {
 		reserved:40;
 };
 
+union perf_sample_weight {
+	__u64		full;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	struct {
+		__u32	var1_dw;
+		__u16	var2_w;
+		__u16	var3_w;
+	};
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	struct {
+		__u16	var3_w;
+		__u16	var2_w;
+		__u32	var1_dw;
+	};
+#else
+#error "Unknown endianness"
+#endif
+};
+
 #endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 88751e38c07d..d60e3fb696a8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1879,8 +1879,8 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
-	if (sample_type & PERF_SAMPLE_WEIGHT)
-		size += sizeof(data->weight);
+	if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+		size += sizeof(data->weight.full);
 
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
@@ -6982,8 +6982,8 @@ void perf_output_sample(struct perf_output_handle *handle,
 					  data->regs_user.regs);
 	}
 
-	if (sample_type & PERF_SAMPLE_WEIGHT)
-		perf_output_put(handle, data->weight);
+	if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+		perf_output_put(handle, data->weight.full);
 
 	if (sample_type & PERF_SAMPLE_DATA_SRC)
 		perf_output_put(handle, data->data_src.val);
@@ -11643,6 +11643,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->sample_type & PERF_SAMPLE_CGROUP)
 		return -EINVAL;
 #endif
+	if ((attr->sample_type & PERF_SAMPLE_WEIGHT) &&
+	    (attr->sample_type & PERF_SAMPLE_WEIGHT_STRUCT))
+		return -EINVAL;
 
 out:
 	return ret;
-- 
Gitee


From c52507ad4ec4015f49b660f33726a9b8b67578a3 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 28 Jan 2021 14:40:08 -0800
Subject: [PATCH 6/9] perf/x86/intel: Factor out intel_update_topdown_event()

mainline inclusion
from mainline-v5.12-rc1
commit 628d923a3c464db98c1c98bb1e0cd50804caf681
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 628d923a3c46 perf/x86/intel: Factor out
intel_update_topdown_event()

-------------------------------------

Similar to Ice Lake, Intel Sapphire Rapids server also supports the
topdown performance metrics feature. The difference is that Intel
Sapphire Rapids server extends the PERF_METRICS MSR to feature TMA
method level two metrics, which will introduce 8 metrics events. Current
icl_update_topdown_event() only check 4 level one metrics events.

Factor out intel_update_topdown_event() to facilitate the code sharing
between Ice Lake and Sapphire Rapids.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-3-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jun Tian <jun.j.tian@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/intel/core.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5ba13b00e3a7..2acf6bfc467e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2325,8 +2325,8 @@ static void __icl_update_topdown_event(struct perf_event *event,
 	}
 }
 
-static void update_saved_topdown_regs(struct perf_event *event,
-				      u64 slots, u64 metrics)
+static void update_saved_topdown_regs(struct perf_event *event, u64 slots,
+				      u64 metrics, int metric_end)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
@@ -2335,7 +2335,7 @@ static void update_saved_topdown_regs(struct perf_event *event,
 	event->hw.saved_slots = slots;
 	event->hw.saved_metric = metrics;
 
-	for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+	for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) {
 		if (!is_topdown_idx(idx))
 			continue;
 		other = cpuc->events[idx];
@@ -2350,7 +2350,8 @@ static void update_saved_topdown_regs(struct perf_event *event,
  * The PERF_METRICS and Fixed counter 3 are read separately. The values may be
  * modify by a NMI. PMU has to be disabled before calling this function.
  */
-static u64 icl_update_topdown_event(struct perf_event *event)
+
+static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
@@ -2366,7 +2367,7 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 	/* read PERF_METRICS */
 	rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
 
-	for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+	for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) {
 		if (!is_topdown_idx(idx))
 			continue;
 		other = cpuc->events[idx];
@@ -2392,7 +2393,7 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 		 * Don't need to reset the PERF_METRICS and Fixed counter 3.
 		 * Because the values will be restored in next schedule in.
 		 */
-		update_saved_topdown_regs(event, slots, metrics);
+		update_saved_topdown_regs(event, slots, metrics, metric_end);
 		reset = false;
 	}
 
@@ -2401,12 +2402,17 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
 		wrmsrl(MSR_PERF_METRICS, 0);
 		if (event)
-			update_saved_topdown_regs(event, 0, 0);
+			update_saved_topdown_regs(event, 0, 0, metric_end);
 	}
 
 	return slots;
 }
 
+static u64 icl_update_topdown_event(struct perf_event *event)
+{
+	return intel_update_topdown_event(event, INTEL_PMC_IDX_TD_BE_BOUND);
+}
+
 static void intel_pmu_read_topdown_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-- 
Gitee


From 5f9be012dcc3e4143600e0db64d15f3e39cba0e5 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 28 Jan 2021 14:40:09 -0800
Subject: [PATCH 7/9] perf/x86/intel: Filter unsupported Topdown metrics event

mainline inclusion
from mainline-v5.12-rc1
commit 1ab5f235c176e93adc4f75000aae6c50fea9db00
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 1ab5f235c176 perf/x86/intel: Filter unsupported
Topdown metrics event

-------------------------------------

Intel Sapphire Rapids server will introduce 8 metrics events. Intel
Ice Lake only supports 4 metrics events. A perf tool user may mistakenly
use the unsupported events via RAW format on Ice Lake. The user can
still get a value from the unsupported Topdown metrics event once the
following Sapphire Rapids enabling patch is applied.

To enable the 8 metrics events on Intel Sapphire Rapids, the
INTEL_TD_METRIC_MAX has to be updated, which impacts the
is_metric_event(). The is_metric_event() is a generic function.
On Ice Lake, the newly added SPR metrics events will be mistakenly
accepted as metric events on creation. At runtime, the unsupported
Topdown metrics events will be updated.

Add a variable num_topdown_events in x86_pmu to indicate the available
number of the Topdown metrics event on the platform. Apply the number
into is_metric_event(). Only the supported Topdown metrics events
should be created as metrics events.

Apply the num_topdown_events in icl_update_topdown_event() as well. The
function can be reused by the following patch.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-4-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jun Tian <jun.j.tian@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/intel/core.c      | 15 +++++++++++++--
 arch/x86/events/perf_event.h      |  1 +
 arch/x86/include/asm/perf_event.h | 10 ++++++++--
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2acf6bfc467e..203b2446460f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2410,7 +2410,8 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 
 static u64 icl_update_topdown_event(struct perf_event *event)
 {
-	return intel_update_topdown_event(event, INTEL_PMC_IDX_TD_BE_BOUND);
+	return intel_update_topdown_event(event, INTEL_PMC_IDX_METRIC_BASE +
+						 x86_pmu.num_topdown_events - 1);
 }
 
 static void intel_pmu_read_topdown_event(struct perf_event *event)
@@ -3562,6 +3563,15 @@ static int core_pmu_hw_config(struct perf_event *event)
 	return intel_pmu_bts_config(event);
 }
 
+#define INTEL_TD_METRIC_AVAILABLE_MAX	(INTEL_TD_METRIC_RETIRING + \
+					 ((x86_pmu.num_topdown_events - 1) << 8))
+
+static bool is_available_metric_event(struct perf_event *event)
+{
+	return is_metric_event(event) &&
+		event->attr.config <= INTEL_TD_METRIC_AVAILABLE_MAX;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3641,7 +3651,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (event->attr.config & X86_ALL_EVENT_FLAGS)
 			return -EINVAL;
 
-		if (is_metric_event(event)) {
+		if (is_available_metric_event(event)) {
 			struct perf_event *leader = event->group_leader;
 
 			/* The metric events don't support sampling. */
@@ -5502,6 +5512,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
 		x86_pmu.lbr_pt_coexist = true;
 		intel_pmu_pebs_data_source_skl(pmem);
+		x86_pmu.num_topdown_events = 4;
 		x86_pmu.update_topdown_event = icl_update_topdown_event;
 		x86_pmu.set_topdown_event_period = icl_set_topdown_event_period;
 		pr_cont("Icelake events, ");
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 20a300db991f..7f4032b33131 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -778,6 +778,7 @@ struct x86_pmu {
 	/*
 	 * Intel perf metrics
 	 */
+	int		num_topdown_events;
 	u64		(*update_topdown_event)(struct perf_event *event);
 	int		(*set_topdown_event_period)(struct perf_event *event);
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index b9a7fd0a27e2..790129a1b441 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -280,8 +280,14 @@ struct x86_pmu_capability {
 #define INTEL_TD_METRIC_BAD_SPEC		0x8100	/* Bad speculation metric */
 #define INTEL_TD_METRIC_FE_BOUND		0x8200	/* FE bound metric */
 #define INTEL_TD_METRIC_BE_BOUND		0x8300	/* BE bound metric */
-#define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_BE_BOUND
-#define INTEL_TD_METRIC_NUM			4
+/* Level 2 metrics */
+#define INTEL_TD_METRIC_HEAVY_OPS		0x8400  /* Heavy Operations metric */
+#define INTEL_TD_METRIC_BR_MISPREDICT		0x8500  /* Branch Mispredict metric */
+#define INTEL_TD_METRIC_FETCH_LAT		0x8600  /* Fetch Latency metric */
+#define INTEL_TD_METRIC_MEM_BOUND		0x8700  /* Memory bound metric */
+
+#define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_MEM_BOUND
+#define INTEL_TD_METRIC_NUM			8
 
 static inline bool is_metric_idx(int idx)
 {
-- 
Gitee


From 67ab543ea12bf6d8a8690ab6b6d761c82211033f Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 28 Jan 2021 14:40:10 -0800
Subject: [PATCH 8/9] perf/x86/intel: Add perf core PMU support for Sapphire
 Rapids

mainline inclusion
from mainline-v5.12-rc1
commit 61b985e3e775a3a75fda04ce7ef1b1aefc4758bc
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 61b985e3e775 perf/x86/intel: Add perf core PMU support
for Sapphire Rapids

-------------------------------------

Add perf core PMU support for the Intel Sapphire Rapids server, which is
the successor of the Intel Ice Lake server. The enabling code is based
on Ice Lake, but there are several new features introduced.

The event encoding is changed and simplified, e.g., the event codes
which are below 0x90 are restricted to counters 0-3. The event codes
which above 0x90 are likely to have no restrictions. The event
constraints, extra_regs(), and hardware cache events table are changed
accordingly.

A new Precise Distribution (PDist) facility is introduced, which
further minimizes the skid when a precise event is programmed on the GP
counter 0. Enable the Precise Distribution (PDist) facility with :ppp
event. For this facility to work, the period must be initialized with a
value larger than 127. Add spr_limit_period() to apply the limit for
:ppp event.

Two new data source fields, data block & address block, are added in the
PEBS Memory Info Record for the load latency event. To enable the
feature,
- An auxiliary event has to be enabled together with the load latency
  event on Sapphire Rapids. A new flag PMU_FL_MEM_LOADS_AUX is
  introduced to indicate the case. A new event, mem-loads-aux, is
  exposed to sysfs for the user tool.
  Add a check in hw_config(). If the auxiliary event is not detected,
  return an unique error -ENODATA.
- The union perf_mem_data_src is extended to support the new fields.
- Ice Lake and earlier models do not support block information, but the
  fields may be set by HW on some machines. Add pebs_no_block to
  explicitly indicate the previous platforms which don't support the new
  block fields. Accessing the new block fields are ignored on those
  platforms.

A new store Latency facility is introduced, which leverages the PEBS
facility where it can provide additional information about sampled
stores. The additional information includes the data address, memory
auxiliary info (e.g. Data Source, STLB miss) and the latency of the
store access. To enable the facility, the new event (0x02cd) has to be
programed on the GP counter 0. A new flag PERF_X86_EVENT_PEBS_STLAT is
introduced to indicate the event. The store_latency_data() is introduced
to parse the memory auxiliary info.

The layout of access latency field of PEBS Memory Info Record has been
changed. Two latency, instruction latency (bit 15:0) and cache access
latency (bit 47:32) are recorded.
- The cache access latency is similar to previous memory access latency.
  For loads, the latency starts by the actual cache access until the
  data is returned by the memory subsystem.
  For stores, the latency starts when the demand write accesses the L1
  data cache and lasts until the cacheline write is completed in the
  memory subsystem.
  The cache access latency is stored in low 32bits of the sample type
  PERF_SAMPLE_WEIGHT_STRUCT.
- The instruction latency starts by the dispatch of the load operation
  for execution and lasts until completion of the instruction it belongs
  to.
  Add a new flag PMU_FL_INSTR_LATENCY to indicate the instruction
  latency support. The instruction latency is stored in the bit 47:32
  of the sample type PERF_SAMPLE_WEIGHT_STRUCT.

Extends the PERF_METRICS MSR to feature TMA method level 2 metrics. The
lower half of the register is the TMA level 1 metrics (legacy). The
upper half is also divided into four 8-bit fields for the new level 2
metrics. Expose all eight Topdown metrics events to user space.

The full description for the SPR features can be found at Intel
Architecture Instruction Set Extensions and Future Features
Programming Reference, 319433-041.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jun Tian <jun.j.tian@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/intel/core.c      | 307 +++++++++++++++++++++++++++++-
 arch/x86/events/intel/ds.c        | 118 +++++++++++-
 arch/x86/events/perf_event.h      |  12 +-
 arch/x86/include/asm/perf_event.h |   8 +-
 include/uapi/linux/perf_event.h   |  12 +-
 5 files changed, 443 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 203b2446460f..8609ebecd1e7 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -276,6 +276,55 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+	EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_spr_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x01c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
+
+	INTEL_EVENT_CONSTRAINT(0x2e, 0xff),
+	INTEL_EVENT_CONSTRAINT(0x3c, 0xff),
+	/*
+	 * Generally event codes < 0x90 are restricted to counters 0-3.
+	 * The 0x2E and 0x3C are exception, which has no restriction.
+	 */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x1),
+	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
+	/*
+	 * Generally event codes >= 0x90 are likely to have no restrictions.
+	 * The exception are defined as above.
+	 */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0xff),
+
+	EVENT_CONSTRAINT_END
+};
+
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -315,11 +364,15 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
 EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
 	"4", "2");
 
-EVENT_ATTR_STR(slots,			slots,		"event=0x00,umask=0x4");
-EVENT_ATTR_STR(topdown-retiring,	td_retiring,	"event=0x00,umask=0x80");
-EVENT_ATTR_STR(topdown-bad-spec,	td_bad_spec,	"event=0x00,umask=0x81");
-EVENT_ATTR_STR(topdown-fe-bound,	td_fe_bound,	"event=0x00,umask=0x82");
-EVENT_ATTR_STR(topdown-be-bound,	td_be_bound,	"event=0x00,umask=0x83");
+EVENT_ATTR_STR(slots,			slots,			"event=0x00,umask=0x4");
+EVENT_ATTR_STR(topdown-retiring,	td_retiring,		"event=0x00,umask=0x80");
+EVENT_ATTR_STR(topdown-bad-spec,	td_bad_spec,		"event=0x00,umask=0x81");
+EVENT_ATTR_STR(topdown-fe-bound,	td_fe_bound,		"event=0x00,umask=0x82");
+EVENT_ATTR_STR(topdown-be-bound,	td_be_bound,		"event=0x00,umask=0x83");
+EVENT_ATTR_STR(topdown-heavy-ops,	td_heavy_ops,		"event=0x00,umask=0x84");
+EVENT_ATTR_STR(topdown-br-mispredict,	td_br_mispredict,	"event=0x00,umask=0x85");
+EVENT_ATTR_STR(topdown-fetch-lat,	td_fetch_lat,		"event=0x00,umask=0x86");
+EVENT_ATTR_STR(topdown-mem-bound,	td_mem_bound,		"event=0x00,umask=0x87");
 
 static struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(td_slots_issued),
@@ -385,6 +438,108 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
+static __initconst const u64 spr_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,
+		[ C(RESULT_MISS)   ] = 0xe124,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_MISS)   ] = 0xe424,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x12a,
+		[ C(RESULT_MISS)   ] = 0x12a,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x12a,
+		[ C(RESULT_MISS)   ] = 0x12a,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,
+		[ C(RESULT_MISS)   ] = 0xe12,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,
+		[ C(RESULT_MISS)   ] = 0xe13,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = 0xe11,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4c4,
+		[ C(RESULT_MISS)   ] = 0x4c5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x12a,
+		[ C(RESULT_MISS)   ] = 0x12a,
+	},
+ },
+};
+
+static __initconst const u64 spr_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x10001,
+		[ C(RESULT_MISS)   ] = 0x3fbfc00001,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x3f3ffc0002,
+		[ C(RESULT_MISS)   ] = 0x3f3fc00002,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x10c000001,
+		[ C(RESULT_MISS)   ] = 0x3fb3000001,
+	},
+ },
+};
+
 /*
  * Notes on the events:
  * - data reads do not include code reads (comparable to earlier tables)
@@ -3572,6 +3727,17 @@ static bool is_available_metric_event(struct perf_event *event)
 		event->attr.config <= INTEL_TD_METRIC_AVAILABLE_MAX;
 }
 
+static inline bool is_mem_loads_event(struct perf_event *event)
+{
+	return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xcd, .umask=0x01);
+}
+
+static inline bool is_mem_loads_aux_event(struct perf_event *event)
+{
+	return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0x03, .umask=0x82);
+}
+
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3680,6 +3846,33 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * The load latency event X86_CONFIG(.event=0xcd, .umask=0x01) on SPR
+	 * doesn't function quite right. As a work-around it needs to always be
+	 * co-scheduled with a auxiliary event X86_CONFIG(.event=0x03, .umask=0x82).
+	 * The actual count of this second event is irrelevant it just needs
+	 * to be active to make the first event function correctly.
+	 *
+	 * In a group, the auxiliary event must be in front of the load latency
+	 * event. The rule is to simplify the implementation of the check.
+	 * That's because perf cannot have a complete group at the moment.
+	 */
+	if (x86_pmu.flags & PMU_FL_MEM_LOADS_AUX &&
+	    (event->attr.sample_type & PERF_SAMPLE_DATA_SRC) &&
+	    is_mem_loads_event(event)) {
+		struct perf_event *leader = event->group_leader;
+		struct perf_event *sibling = NULL;
+
+		if (!is_mem_loads_aux_event(leader)) {
+			for_each_sibling_event(sibling, leader) {
+				if (is_mem_loads_aux_event(sibling))
+					break;
+			}
+			if (list_entry_is_head(sibling, &leader->sibling_list, sibling_list))
+				return -ENODATA;
+		}
+	}
+
 	if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
 		return 0;
 
@@ -3879,6 +4072,29 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return hsw_get_event_constraints(cpuc, idx, event);
 }
 
+static struct event_constraint *
+spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	c = icl_get_event_constraints(cpuc, idx, event);
+
+	/*
+	 * The :ppp indicates the Precise Distribution (PDist) facility, which
+	 * is only supported on the GP counter 0. If a :ppp event which is not
+	 * available on the GP counter 0, error out.
+	 */
+	if (event->attr.precise_ip == 3) {
+		if (c->idxmsk64 & BIT_ULL(0))
+			return &counter0_constraint;
+
+		return &emptyconstraint;
+	}
+
+	return c;
+}
+
 static struct event_constraint *
 glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -3968,6 +4184,14 @@ static u64 nhm_limit_period(struct perf_event *event, u64 left)
 	return max(left, 32ULL);
 }
 
+static u64 spr_limit_period(struct perf_event *event, u64 left)
+{
+	if (event->attr.precise_ip == 3)
+		return max(left, 128ULL);
+
+	return left;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -4734,6 +4958,42 @@ static struct attribute *icl_tsx_events_attrs[] = {
 	NULL,
 };
 
+
+EVENT_ATTR_STR(mem-stores,	mem_st_spr,	"event=0xcd,umask=0x2");
+EVENT_ATTR_STR(mem-loads-aux,	mem_ld_aux,	"event=0x03,umask=0x82");
+
+static struct attribute *spr_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_spr),
+	EVENT_PTR(mem_ld_aux),
+	NULL,
+};
+
+static struct attribute *spr_td_events_attrs[] = {
+	EVENT_PTR(slots),
+	EVENT_PTR(td_retiring),
+	EVENT_PTR(td_bad_spec),
+	EVENT_PTR(td_fe_bound),
+	EVENT_PTR(td_be_bound),
+	EVENT_PTR(td_heavy_ops),
+	EVENT_PTR(td_br_mispredict),
+	EVENT_PTR(td_fetch_lat),
+	EVENT_PTR(td_mem_bound),
+	NULL,
+};
+
+static struct attribute *spr_tsx_events_attrs[] = {
+	EVENT_PTR(tx_start),
+	EVENT_PTR(tx_abort),
+	EVENT_PTR(tx_commit),
+	EVENT_PTR(tx_capacity_read),
+	EVENT_PTR(tx_capacity_write),
+	EVENT_PTR(tx_conflict),
+	EVENT_PTR(cycles_t),
+	EVENT_PTR(cycles_ct),
+	NULL,
+};
+
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -5519,6 +5779,43 @@ __init int intel_pmu_init(void)
 		name = "icelake";
 		break;
 
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+		pmem = true;
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		x86_pmu.event_constraints = intel_spr_event_constraints;
+		x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_spr_extra_regs;
+		x86_pmu.limit_period = spr_limit_period;
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = spr_get_event_constraints;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			hsw_format_attr : nhm_format_attr;
+		extra_skl_attr = skl_format_attr;
+		mem_attr = spr_events_attrs;
+		td_attr = spr_td_events_attrs;
+		tsx_attr = spr_tsx_events_attrs;
+		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
+		x86_pmu.lbr_pt_coexist = true;
+		intel_pmu_pebs_data_source_skl(pmem);
+		x86_pmu.num_topdown_events = 8;
+		x86_pmu.update_topdown_event = icl_update_topdown_event;
+		x86_pmu.set_topdown_event_period = icl_set_topdown_event_period;
+		pr_cont("Sapphire Rapids events, ");
+		name = "sapphire_rapids";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index b102e9aac2ff..dbb45ad2473f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -36,7 +36,9 @@ union intel_x86_pebs_dse {
 		unsigned int ld_dse:4;
 		unsigned int ld_stlb_miss:1;
 		unsigned int ld_locked:1;
-		unsigned int ld_reserved:26;
+		unsigned int ld_data_blk:1;
+		unsigned int ld_addr_blk:1;
+		unsigned int ld_reserved:24;
 	};
 	struct {
 		unsigned int st_l1d_hit:1;
@@ -45,6 +47,12 @@ union intel_x86_pebs_dse {
 		unsigned int st_locked:1;
 		unsigned int st_reserved2:26;
 	};
+	struct {
+		unsigned int st_lat_dse:4;
+		unsigned int st_lat_stlb_miss:1;
+		unsigned int st_lat_locked:1;
+		unsigned int ld_reserved3:26;
+	};
 };
 
 
@@ -198,6 +206,63 @@ static u64 load_latency_data(u64 status)
 	if (dse.ld_locked)
 		val |= P(LOCK, LOCKED);
 
+	/*
+	 * Ice Lake and earlier models do not support block infos.
+	 */
+	if (!x86_pmu.pebs_block) {
+		val |= P(BLK, NA);
+		return val;
+	}
+	/*
+	 * bit 6: load was blocked since its data could not be forwarded
+	 *        from a preceding store
+	 */
+	if (dse.ld_data_blk)
+		val |= P(BLK, DATA);
+
+	/*
+	 * bit 7: load was blocked due to potential address conflict with
+	 *        a preceding store
+	 */
+	if (dse.ld_addr_blk)
+		val |= P(BLK, ADDR);
+
+	if (!dse.ld_data_blk && !dse.ld_addr_blk)
+		val |= P(BLK, NA);
+
+	return val;
+}
+
+static u64 store_latency_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val;
+
+	dse.val = status;
+
+	/*
+	 * use the mapping table for bit 0-3
+	 */
+	val = pebs_data_source[dse.st_lat_dse];
+
+	/*
+	 * bit 4: TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (dse.st_lat_stlb_miss)
+		val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/*
+	 * bit 5: locked prefix
+	 */
+	if (dse.st_lat_locked)
+		val |= P(LOCK, LOCKED);
+
+	val |= P(BLK, NA);
+
 	return val;
 }
 
@@ -870,6 +935,28 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_spr_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),
+	INTEL_PLD_CONSTRAINT(0x1cd, 0xfe),
+	INTEL_PSD_CONSTRAINT(0x2cd, 0x1),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),
+
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),
+
+	/*
+	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
+	 * need the full constraints from the main table.
+	 */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -1332,6 +1419,8 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 
 	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
 		val = load_latency_data(aux);
+	else if (fl & PERF_X86_EVENT_PEBS_STLAT)
+		val = store_latency_data(aux);
 	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
 		val = precise_datala_hsw(event, aux);
 	else if (fst)
@@ -1508,6 +1597,9 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 #endif
 }
 
+#define PEBS_LATENCY_MASK			0xffff
+#define PEBS_CACHE_LATENCY_OFFSET		32
+
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
  */
@@ -1578,9 +1670,27 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	}
 
 	if (format_size & PEBS_DATACFG_MEMINFO) {
-		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
-			data->weight.full = meminfo->latency ?:
-				intel_get_tsx_weight(meminfo->tsx_tuning);
+		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
+			u64 weight = meminfo->latency;
+
+			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) {
+				data->weight.var2_w = weight & PEBS_LATENCY_MASK;
+				weight >>= PEBS_CACHE_LATENCY_OFFSET;
+			}
+
+			/*
+			 * Although meminfo::latency is defined as a u64,
+			 * only the lower 32 bits include the valid data
+			 * in practice on Ice Lake and earlier platforms.
+			 */
+			if (sample_type & PERF_SAMPLE_WEIGHT) {
+				data->weight.full = weight ?:
+					intel_get_tsx_weight(meminfo->tsx_tuning);
+			} else {
+				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
+					intel_get_tsx_weight(meminfo->tsx_tuning);
+			}
+		}
 
 		if (sample_type & PERF_SAMPLE_DATA_SRC)
 			data->data_src.val = get_data_src(event, meminfo->aux);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7f4032b33131..ea175468e31e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -80,6 +80,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
 #define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
 #define PERF_X86_EVENT_TOPDOWN		0x4000 /* Count Topdown slots/metrics events */
+#define PERF_X86_EVENT_PEBS_STLAT	0x8000 /* st+stlat data address sampling */
 
 static inline bool is_topdown_count(struct perf_event *event)
 {
@@ -445,6 +446,10 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
 
+#define INTEL_PSD_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_STLAT)
+
 #define INTEL_PST_CONSTRAINT(c, n)	\
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
@@ -726,7 +731,8 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1;
+			pebs_no_isolation	:1,
+			pebs_block		:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
@@ -874,6 +880,8 @@ do {									\
 #define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 #define PMU_FL_TFA		0x20 /* deal with TSX force abort */
 #define PMU_FL_PAIR		0x40 /* merge counters for large incr. events */
+#define PMU_FL_INSTR_LATENCY	0x80 /* Support Instruction Latency in PEBS Memory Info Record */
+#define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1163,6 +1171,8 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
 
 extern struct event_constraint intel_icl_pebs_event_constraints[];
 
+extern struct event_constraint intel_spr_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 790129a1b441..d3530eac30bc 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -261,8 +261,12 @@ struct x86_pmu_capability {
 #define INTEL_PMC_IDX_TD_BAD_SPEC		(INTEL_PMC_IDX_METRIC_BASE + 1)
 #define INTEL_PMC_IDX_TD_FE_BOUND		(INTEL_PMC_IDX_METRIC_BASE + 2)
 #define INTEL_PMC_IDX_TD_BE_BOUND		(INTEL_PMC_IDX_METRIC_BASE + 3)
-#define INTEL_PMC_IDX_METRIC_END		INTEL_PMC_IDX_TD_BE_BOUND
-#define INTEL_PMC_MSK_TOPDOWN			((0xfull << INTEL_PMC_IDX_METRIC_BASE) | \
+#define INTEL_PMC_IDX_TD_HEAVY_OPS		(INTEL_PMC_IDX_METRIC_BASE + 4)
+#define INTEL_PMC_IDX_TD_BR_MISPREDICT		(INTEL_PMC_IDX_METRIC_BASE + 5)
+#define INTEL_PMC_IDX_TD_FETCH_LAT		(INTEL_PMC_IDX_METRIC_BASE + 6)
+#define INTEL_PMC_IDX_TD_MEM_BOUND		(INTEL_PMC_IDX_METRIC_BASE + 7)
+#define INTEL_PMC_IDX_METRIC_END		INTEL_PMC_IDX_TD_MEM_BOUND
+#define INTEL_PMC_MSK_TOPDOWN			((0xffull << INTEL_PMC_IDX_METRIC_BASE) | \
 						INTEL_PMC_MSK_FIXED_SLOTS)
 
 /*
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b2cc246ec119..7d292de51410 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1146,14 +1146,16 @@ union perf_mem_data_src {
 			mem_lvl_num:4,	/* memory hierarchy level number */
 			mem_remote:1,   /* remote */
 			mem_snoopx:2,	/* snoop mode, ext */
-			mem_rsvd:24;
+			mem_blk:3,	/* access blocked */
+			mem_rsvd:21;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:24,
+		__u64	mem_rsvd:21,
+			mem_blk:3,	/* access blocked */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_remote:1,   /* remote */
 			mem_lvl_num:4,	/* memory hierarchy level number */
@@ -1236,6 +1238,12 @@ union perf_mem_data_src {
 #define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
 #define PERF_MEM_TLB_SHIFT	26
 
+/* Access blocked */
+#define PERF_MEM_BLK_NA		0x01 /* not available */
+#define PERF_MEM_BLK_DATA	0x02 /* data could not be forwarded */
+#define PERF_MEM_BLK_ADDR	0x04 /* address conflict */
+#define PERF_MEM_BLK_SHIFT	40
+
 #define PERF_MEM_S(a, s) \
 	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
 
-- 
Gitee


From 29807b8a2db770bca0163fdfe0fbf753017119cf Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 28 Jan 2021 14:40:11 -0800
Subject: [PATCH 9/9] perf/x86/intel: Support CPUID 10.ECX to disable fixed
 counters

mainline inclusion
from mainline-v5.12-rc1
commit 32451614da2a9cf4296f90d3606ac77814fb519d
category: feature
feature: SPR PMU core event enhancement
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I596BF

Intel-SIG: commit 32451614da2a perf/x86/intel: Support CPUID 10.ECX to
disable fixed counters

-------------------------------------

With Architectural Performance Monitoring Version 5, CPUID 10.ECX cpu
leaf indicates the fixed counter enumeration. This extends the previous
count to a bitmap which allows disabling even lower fixed counters.
It could be used by a Hypervisor.

The existing intel_ctrl variable is used to remember the bitmask of the
counters. All code that reads all counters is fixed to check this extra
bitmask.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1611873611-156687-6-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Jun Tian <jun.j.tian@intel.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/core.c       |  8 +++++++-
 arch/x86/events/intel/core.c | 34 ++++++++++++++++++++++++----------
 arch/x86/events/perf_event.h |  5 +++++
 3 files changed, 36 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index b79b9f21cbb3..e0f8b219046e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -255,6 +255,8 @@ static bool check_hw_exists(void)
 		if (ret)
 			goto msr_fail;
 		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+			if (fixed_counter_disabled(i))
+				continue;
 			if (val & (0x03 << i*4)) {
 				bios_fail = 1;
 				val_fail = val;
@@ -1534,6 +1536,8 @@ void perf_event_print_debug(void)
 			cpu, idx, prev_left);
 	}
 	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx))
+			continue;
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -2006,7 +2010,9 @@ static int __init init_hw_perf_events(void)
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
 	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... fixed-purpose events:   %lu\n",
+			hweight64((((1ULL << x86_pmu.num_counters_fixed) - 1)
+					<< INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl));
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
 	if (!x86_pmu.read)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8609ebecd1e7..46fb4cd60b3a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2723,8 +2723,11 @@ static void intel_pmu_reset(void)
 		wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
 		wrmsrl_safe(x86_pmu_event_addr(idx),  0ull);
 	}
-	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx))
+			continue;
 		wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+	}
 
 	if (ds)
 		ds->bts_index = ds->bts_buffer_base;
@@ -5217,7 +5220,7 @@ __init int intel_pmu_init(void)
 	union cpuid10_eax eax;
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
-	unsigned int unused;
+	unsigned int fixed_mask;
 	struct extra_reg *er;
 	bool pmem = false;
 	int version, i;
@@ -5239,7 +5242,7 @@ __init int intel_pmu_init(void)
 	 * Check whether the Architectural PerfMon supports
 	 * Branch Misses Retired hw_event or not.
 	 */
-	cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+	cpuid(10, &eax.full, &ebx.full, &fixed_mask, &edx.full);
 	if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
 		return -ENODEV;
 
@@ -5263,12 +5266,15 @@ __init int intel_pmu_init(void)
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
 	 * assume at least 3 events, when not running in a hypervisor:
 	 */
-	if (version > 1) {
+	if (version > 1 && version < 5) {
 		int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
 
 		x86_pmu.num_counters_fixed =
 			max((int)edx.split.num_counters_fixed, assume);
-	}
+
+		fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1;
+	} else if (version >= 5)
+		x86_pmu.num_counters_fixed = fls(fixed_mask);
 
 	if (version >= 4)
 		x86_pmu.counter_freezing = !disable_counter_freezing;
@@ -5858,8 +5864,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
 	}
 
-	x86_pmu.intel_ctrl |=
-		((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl |= (u64)fixed_mask << INTEL_PMC_IDX_FIXED;
 
 	/* AnyThread may be deprecated on arch perfmon v5 or later */
 	if (x86_pmu.intel_cap.anythread_deprecated)
@@ -5876,13 +5881,22 @@ __init int intel_pmu_init(void)
 			 * events to the generic counters.
 			 */
 			if (c->idxmsk64 & INTEL_PMC_MSK_TOPDOWN) {
+				/*
+				 * Disable topdown slots and metrics events,
+				 * if slots event is not in CPUID.
+				 */
+				if (!(INTEL_PMC_MSK_FIXED_SLOTS & x86_pmu.intel_ctrl))
+					c->idxmsk64 = 0;
 				c->weight = hweight64(c->idxmsk64);
 				continue;
 			}
 
-			if (c->cmask == FIXED_EVENT_FLAGS
-			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			if (c->cmask == FIXED_EVENT_FLAGS) {
+				/* Disabled fixed counters which are not in CPUID */
+				c->idxmsk64 &= x86_pmu.intel_ctrl;
+
+				if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES)
+					c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
 			c->idxmsk64 &=
 				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ea175468e31e..2c14ce97ae4b 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1072,6 +1072,11 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
 
+static inline bool fixed_counter_disabled(int i)
+{
+	return !(x86_pmu.intel_ctrl >> (i + INTEL_PMC_IDX_FIXED));
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
-- 
Gitee