mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org,
	namhyung@kernel.org, tglx@linutronix.de,
	dave.hansen@linux.intel.com, irogers@google.com,
	adrian.hunter@intel.com, jolsa@kernel.org,
	alexander.shishkin@linux.intel.com, linux-kernel@vger.kernel.org
Cc: dapeng1.mi@linux.intel.com, ak@linux.intel.com,
	zide.chen@intel.com, Kan Liang <kan.liang@linux.intel.com>
Subject: [RFC PATCH 10/12] perf/x86: Add ZMM in extended regs
Date: Fri, 13 Jun 2025 06:49:41 -0700	[thread overview]
Message-ID: <20250613134943.3186517-11-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20250613134943.3186517-1-kan.liang@linux.intel.com>

From: Kan Liang <kan.liang@linux.intel.com>

Support ZMM as the extended registers. It can be configured in the
sample_ext_regs_intr/user.

Only the PMU with PERF_PMU_CAP_EXTENDED_REGS2 supports the feature.
The value can be retrieved via the XSAVES.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/core.c                | 14 +++++++++
 arch/x86/events/perf_event.h          | 11 ++++++-
 arch/x86/include/asm/perf_event.h     |  2 ++
 arch/x86/include/uapi/asm/perf_regs.h | 43 +++++++++++++++++++++++++--
 arch/x86/kernel/perf_regs.c           | 10 +++++++
 5 files changed, 77 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 741e6dfd50a5..9bcef9a32dd2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -437,6 +437,10 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
 	__x86_pmu_get_regs(XFEATURE_MASK_YMM, perf_regs->ymmh_regs, XSAVE_YMM_SIZE);
 	__x86_pmu_get_regs(XFEATURE_MASK_APX, perf_regs->apx_regs, sizeof(struct apx_state));
 	__x86_pmu_get_regs(XFEATURE_MASK_OPMASK, perf_regs->opmask_regs, sizeof(struct avx_512_opmask_state));
+	__x86_pmu_get_regs(XFEATURE_MASK_ZMM_Hi256, perf_regs->zmmh_regs,
+			   sizeof(struct avx_512_zmm_uppers_state));
+	__x86_pmu_get_regs(XFEATURE_MASK_Hi16_ZMM, perf_regs->h16zmm_regs,
+			   sizeof(struct avx_512_hi16_state));
 }
 
 static void release_ext_regs_buffers(void)
@@ -468,6 +472,10 @@ static void reserve_ext_regs_buffers(void)
 		size += sizeof(struct apx_state);
 	if (x86_pmu.ext_regs_mask & BIT_ULL(X86_EXT_REGS_OPMASK))
 		size += sizeof(struct avx_512_opmask_state);
+	if (x86_pmu.ext_regs_mask & BIT_ULL(X86_EXT_REGS_ZMMH))
+		size += sizeof(struct avx_512_zmm_uppers_state);
+	if (x86_pmu.ext_regs_mask & BIT_ULL(X86_EXT_REGS_H16ZMM))
+		size += sizeof(struct avx_512_hi16_state);
 
 	/* XSAVE feature requires 64-byte alignment. */
 	size += 64;
@@ -747,6 +755,8 @@ int x86_pmu_hw_config(struct perf_event *event)
 			check_ext_regs(X86_EXT_REGS_YMM);
 			check_ext_regs(X86_EXT_REGS_APX);
 			check_ext_regs(X86_EXT_REGS_OPMASK);
+			check_ext_regs(X86_EXT_REGS_ZMMH);
+			check_ext_regs(X86_EXT_REGS_H16ZMM);
 		}
 	}
 	return x86_setup_perfctr(event);
@@ -1852,6 +1862,10 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
 			   XFEATURE_MASK_APX, PERF_X86_EXT_REG_APX_SIZE);
 	init_ext_regs_data(X86_EXT_REGS_OPMASK, perf_regs->opmask_regs,
 			   XFEATURE_MASK_OPMASK, PERF_X86_EXT_REG_OPMASK_SIZE);
+	init_ext_regs_data(X86_EXT_REGS_ZMMH, perf_regs->zmmh_regs,
+			   XFEATURE_MASK_ZMM_Hi256, PERF_X86_EXT_REG_ZMMH_SIZE);
+	init_ext_regs_data(X86_EXT_REGS_H16ZMM, perf_regs->h16zmm_regs,
+			   XFEATURE_MASK_Hi16_ZMM, PERF_X86_EXT_REG_H16ZMM_SIZE);
 
 	mask &= ~ignore_mask;
 	if (mask)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c2626dcea1a0..93a65c529afe 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -692,6 +692,8 @@ enum {
 	X86_EXT_REGS_YMM,
 	X86_EXT_REGS_APX,
 	X86_EXT_REGS_OPMASK,
+	X86_EXT_REGS_ZMMH,
+	X86_EXT_REGS_H16ZMM,
 };
 
 #define PERF_PEBS_DATA_SOURCE_MAX	0x100
@@ -1324,7 +1326,7 @@ static inline u64 x86_pmu_get_event_config(struct perf_event *event)
 
 static inline int get_num_ext_regs(u64 *ext_regs, unsigned int type)
 {
-	u64 mask;
+	u64 mask, mask2;
 
 	switch (type) {
 	case X86_EXT_REGS_YMM:
@@ -1336,6 +1338,13 @@ static inline int get_num_ext_regs(u64 *ext_regs, unsigned int type)
 	case X86_EXT_REGS_OPMASK:
 		mask = GENMASK_ULL(PERF_REG_X86_OPMASK7, PERF_REG_X86_OPMASK0);
 		return hweight64(ext_regs[0] & mask);
+	case X86_EXT_REGS_ZMMH:
+		mask = GENMASK_ULL(PERF_REG_X86_ZMMH15, PERF_REG_X86_ZMMH0);
+		return hweight64(ext_regs[0] & mask);
+	case X86_EXT_REGS_H16ZMM:
+		mask = GENMASK_ULL(PERF_REG_X86_EXT_REGS_64, PERF_REG_X86_ZMM16);
+		mask2 = GENMASK_ULL(PERF_REG_X86_ZMM31 - 64, 0);
+		return hweight64(ext_regs[0] & mask) + hweight64(ext_regs[1] & mask2);
 	default:
 		return 0;
 	}
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4e971f38ff94..eb35ba9afbb4 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -596,6 +596,8 @@ struct x86_perf_regs {
 	u64		*ymmh_regs;
 	u64		*apx_regs;
 	u64		*opmask_regs;
+	u64		*zmmh_regs;
+	u64		*h16zmm_regs;
 };
 
 extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index b9ec58b98c5e..c43a025b0c01 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -102,15 +102,54 @@ enum perf_event_x86_ext_regs {
 	PERF_REG_X86_OPMASK6,
 	PERF_REG_X86_OPMASK7,
 
-	PERF_REG_X86_EXT_REGS_MAX = PERF_REG_X86_OPMASK7,
+	/* ZMMH 0-15 Registers */
+	PERF_REG_X86_ZMMH0,
+	PERF_REG_X86_ZMMH1,
+	PERF_REG_X86_ZMMH2,
+	PERF_REG_X86_ZMMH3,
+	PERF_REG_X86_ZMMH4,
+	PERF_REG_X86_ZMMH5,
+	PERF_REG_X86_ZMMH6,
+	PERF_REG_X86_ZMMH7,
+	PERF_REG_X86_ZMMH8,
+	PERF_REG_X86_ZMMH9,
+	PERF_REG_X86_ZMMH10,
+	PERF_REG_X86_ZMMH11,
+	PERF_REG_X86_ZMMH12,
+	PERF_REG_X86_ZMMH13,
+	PERF_REG_X86_ZMMH14,
+	PERF_REG_X86_ZMMH15,
+
+	/* H16ZMM 16-31 Registers */
+	PERF_REG_X86_ZMM16,
+	PERF_REG_X86_ZMM17,
+	PERF_REG_X86_ZMM18,
+	PERF_REG_X86_ZMM19,
+	PERF_REG_X86_ZMM20,
+	PERF_REG_X86_ZMM21,
+	PERF_REG_X86_ZMM22,
+	PERF_REG_X86_ZMM23,
+	PERF_REG_X86_ZMM24,
+	PERF_REG_X86_ZMM25,
+	PERF_REG_X86_ZMM26,
+	PERF_REG_X86_ZMM27,
+	PERF_REG_X86_ZMM28,
+	PERF_REG_X86_ZMM29,
+	PERF_REG_X86_ZMM30,
+	PERF_REG_X86_ZMM31,
+
+	PERF_REG_X86_EXT_REGS_64 = PERF_REG_X86_ZMM23,
+	PERF_REG_X86_EXT_REGS_MAX = PERF_REG_X86_ZMM31,
 };
 
 enum perf_event_x86_ext_reg_size {
 	PERF_X86_EXT_REG_YMMH_SIZE	= 2,
 	PERF_X86_EXT_REG_APX_SIZE	= 1,
 	PERF_X86_EXT_REG_OPMASK_SIZE	= 1,
+	PERF_X86_EXT_REG_ZMMH_SIZE	= 4,
+	PERF_X86_EXT_REG_H16ZMM_SIZE	= 8,
 
 	/* max of PERF_REG_X86_XXX_SIZE */
-	PERF_X86_EXT_REG_SIZE_MAX	= PERF_X86_EXT_REG_YMMH_SIZE,
+	PERF_X86_EXT_REG_SIZE_MAX	= PERF_X86_EXT_REG_H16ZMM_SIZE,
 };
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 34b94b846f00..d5721ea85c5d 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -92,6 +92,16 @@ static u64 perf_ext_reg_value(struct pt_regs *regs, int idx,
 						    idx - PERF_REG_X86_OPMASK0,
 						    perf_regs->opmask_regs,
 						    PERF_X86_EXT_REG_OPMASK_SIZE);
+		case PERF_REG_X86_ZMMH0 ... PERF_REG_X86_ZMMH15:
+			return __perf_ext_reg_value(ext, ext_size,
+						    idx - PERF_REG_X86_ZMMH0,
+						    perf_regs->zmmh_regs,
+						    PERF_X86_EXT_REG_ZMMH_SIZE);
+		case PERF_REG_X86_ZMM16 ... PERF_REG_X86_ZMM31:
+			return __perf_ext_reg_value(ext, ext_size,
+						    idx - PERF_REG_X86_ZMM16,
+						    perf_regs->h16zmm_regs,
+						    PERF_X86_EXT_REG_H16ZMM_SIZE);
 		default:
 			WARN_ON_ONCE(1);
 			*ext_size = 0;
-- 
2.38.1


  parent reply	other threads:[~2025-06-13 13:50 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-13 13:49 [RFC PATCH 00/12] Support vector and more extended registers in perf kan.liang
2025-06-13 13:49 ` [RFC PATCH 01/12] perf/x86: Use x86_perf_regs in the x86 nmi handler kan.liang
2025-06-13 13:49 ` [RFC PATCH 02/12] perf/x86: Setup the regs data kan.liang
2025-06-13 13:49 ` [RFC PATCH 03/12] x86/fpu/xstate: Add xsaves_nmi kan.liang
2025-06-13 14:39   ` Dave Hansen
2025-06-13 14:54     ` Liang, Kan
2025-06-13 15:19       ` Dave Hansen
2025-06-13 13:49 ` [RFC PATCH 04/12] perf: Move has_extended_regs() to header file kan.liang
2025-06-13 13:49 ` [RFC PATCH 05/12] perf/x86: Support XMM register for non-PEBS and REGS_USER kan.liang
2025-06-13 15:15   ` Dave Hansen
2025-06-13 17:51     ` Liang, Kan
2025-06-13 15:34   ` Dave Hansen
2025-06-13 18:14     ` Liang, Kan
2025-06-13 13:49 ` [RFC PATCH 06/12] perf: Support extension of sample_regs kan.liang
2025-06-17  8:00   ` Mi, Dapeng
2025-06-17  8:14   ` Peter Zijlstra
2025-06-17  9:49     ` Mi, Dapeng
2025-06-17 10:28       ` Peter Zijlstra
2025-06-17 12:14         ` Mi, Dapeng
2025-06-17 13:33           ` Peter Zijlstra
2025-06-17 14:06             ` Peter Zijlstra
2025-06-17 14:24               ` Mark Rutland
2025-06-17 14:44                 ` Peter Zijlstra
2025-06-17 14:55                   ` Mark Rutland
2025-06-17 19:00                     ` Mark Brown
2025-06-17 20:32                     ` Liang, Kan
2025-06-18  9:35                       ` Peter Zijlstra
2025-06-18 10:10                         ` Liang, Kan
2025-06-18 13:30                           ` Peter Zijlstra
2025-06-18 13:52                             ` Liang, Kan
2025-06-18 14:30                               ` Dave Hansen
2025-06-18 14:47                                 ` Dave Hansen
2025-06-18 15:24                                   ` Liang, Kan
2025-06-18 14:45                               ` Peter Zijlstra
2025-06-18 15:22                                 ` Liang, Kan
2025-06-13 13:49 ` [RFC PATCH 07/12] perf/x86: Add YMMH in extended regs kan.liang
2025-06-13 15:48   ` Dave Hansen
2025-06-13 13:49 ` [RFC PATCH 08/12] perf/x86: Add APX " kan.liang
2025-06-13 16:02   ` Dave Hansen
2025-06-13 17:17     ` Liang, Kan
2025-06-17  8:19   ` Peter Zijlstra
2025-06-13 13:49 ` [RFC PATCH 09/12] perf/x86: Add OPMASK " kan.liang
2025-06-13 13:49 ` kan.liang [this message]
2025-06-13 13:49 ` [RFC PATCH 11/12] perf/x86: Add SSP " kan.liang
2025-06-13 13:49 ` [RFC PATCH 12/12] perf/x86/intel: Support extended registers kan.liang
2025-06-17  7:50 ` [RFC PATCH 00/12] Support vector and more extended registers in perf Mi, Dapeng
2025-06-17  8:24 ` Peter Zijlstra
2025-06-17 13:52   ` Liang, Kan
2025-06-17 14:29     ` Peter Zijlstra
2025-06-17 15:23       ` Liang, Kan
2025-06-17 17:34         ` Peter Zijlstra
2025-06-18  0:57         ` Mi, Dapeng
2025-06-18 10:47           ` Liang, Kan
2025-06-18 12:28             ` Mi, Dapeng
2025-06-18 13:15               ` Liang, Kan
2025-06-19  0:41                 ` Mi, Dapeng
2025-06-19 11:11                   ` Liang, Kan
2025-06-19 12:26                     ` Mi, Dapeng
2025-06-19 13:38                     ` Peter Zijlstra
2025-06-19 14:27                       ` Liang, Kan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250613134943.3186517-11-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=dapeng1.mi@linux.intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=zide.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®