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, mark.rutland@arm.com, broonie@kernel.org,
	ravi.bangoria@amd.com, Kan Liang <kan.liang@linux.intel.com>
Subject: [RFC PATCH V2 09/13] perf/x86: Add ZMM into sample_simd_vec_regs
Date: Thu, 26 Jun 2025 12:56:06 -0700	[thread overview]
Message-ID: <20250626195610.405379-10-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20250626195610.405379-1-kan.liang@linux.intel.com>

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

The ZMM0-15 is composed of XMM, YMMH, and ZMMH. It requires 3 XSAVE
commands to get the complete value.
The ZMM16-31/YMM16-31/XMM16-31 are also supported, which only require
the XSAVE Hi16_ZMM.

Internally, the XMM, YMMH, ZMMH and Hi16_ZMM are stored in different
structures, which follow the XSAVE format. But the output dumps the ZMM
or Hi16 XMM/YMM/ZMM as a whole.

The qwords 8 imply ZMM.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/core.c                | 24 ++++++++++++++++++++++++
 arch/x86/events/perf_event.h          |  2 ++
 arch/x86/include/asm/perf_event.h     |  8 ++++++++
 arch/x86/include/uapi/asm/perf_regs.h |  8 ++++++--
 arch/x86/kernel/perf_regs.c           | 13 ++++++++++++-
 5 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 20c825e83a3f..3c05ca98ec3f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -423,6 +423,10 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
 
 	if (mask & XFEATURE_MASK_YMM)
 		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
+	if (mask & XFEATURE_MASK_ZMM_Hi256)
+		perf_regs->zmmh = get_xsave_addr(xsave, XFEATURE_ZMM_Hi256);
+	if (mask & XFEATURE_MASK_Hi16_ZMM)
+		perf_regs->h16zmm = get_xsave_addr(xsave, XFEATURE_Hi16_ZMM);
 }
 
 static void release_ext_regs_buffers(void)
@@ -451,6 +455,10 @@ static void reserve_ext_regs_buffers(void)
 		mask |= XFEATURE_MASK_SSE;
 	if (x86_pmu.ext_regs_mask & X86_EXT_REGS_YMM)
 		mask |= XFEATURE_MASK_YMM;
+	if (x86_pmu.ext_regs_mask & X86_EXT_REGS_ZMMH)
+		mask |= XFEATURE_MASK_ZMM_Hi256;
+	if (x86_pmu.ext_regs_mask & X86_EXT_REGS_H16ZMM)
+		mask |= XFEATURE_MASK_Hi16_ZMM;
 
 	size = xstate_calculate_size(mask, true);
 
@@ -734,6 +742,13 @@ int x86_pmu_hw_config(struct perf_event *event)
 			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS &&
 			    !(x86_pmu.ext_regs_mask & X86_EXT_REGS_YMM))
 				return -EINVAL;
+			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_ZMM_QWORDS &&
+			    !(x86_pmu.ext_regs_mask & X86_EXT_REGS_ZMMH))
+				return -EINVAL;
+			if ((fls64(event->attr.sample_simd_vec_reg_intr) > PERF_X86_H16ZMM_BASE ||
+			     fls64(event->attr.sample_simd_vec_reg_user) > PERF_X86_H16ZMM_BASE) &&
+			    !(x86_pmu.ext_regs_mask & X86_EXT_REGS_H16ZMM))
+				return -EINVAL;
 		}
 	}
 	return x86_setup_perfctr(event);
@@ -1851,6 +1866,15 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
 			perf_regs->ymmh_regs = NULL;
 			mask |= XFEATURE_MASK_YMM;
 		}
+		if (attr->sample_simd_vec_reg_qwords >= PERF_X86_ZMM_QWORDS) {
+			perf_regs->zmmh_regs = NULL;
+			mask |= XFEATURE_MASK_ZMM_Hi256;
+		}
+		if (fls64(attr->sample_simd_vec_reg_intr) > PERF_X86_H16ZMM_BASE ||
+		    fls64(attr->sample_simd_vec_reg_user) > PERF_X86_H16ZMM_BASE) {
+			perf_regs->h16zmm_regs = NULL;
+			mask |= XFEATURE_MASK_Hi16_ZMM;
+		}
 	}
 
 	mask &= ~ignore_mask;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7d332d0247ed..cc42e9d3e13d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -702,6 +702,8 @@ enum {
 enum {
 	X86_EXT_REGS_XMM	= BIT_ULL(0),
 	X86_EXT_REGS_YMM	= BIT_ULL(1),
+	X86_EXT_REGS_ZMMH	= BIT_ULL(2),
+	X86_EXT_REGS_H16ZMM	= BIT_ULL(3),
 };
 
 #define PERF_PEBS_DATA_SOURCE_MAX	0x100
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 81e3143fd91a..2d78bd9649bd 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -601,6 +601,14 @@ struct x86_perf_regs {
 		u64	*ymmh_regs;
 		struct ymmh_struct *ymmh;
 	};
+	union {
+		u64	*zmmh_regs;
+		struct avx_512_zmm_uppers_state *zmmh;
+	};
+	union {
+		u64	*h16zmm_regs;
+		struct avx_512_hi16_state *h16zmm;
+	};
 };
 
 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 feb3e8f80761..f74e3ba65be2 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -55,12 +55,16 @@ enum perf_event_x86_regs {
 
 #define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 
-#define PERF_X86_SIMD_VEC_REGS_MAX	16
+#define PERF_X86_SIMD_VEC_REGS_MAX	32
 #define PERF_X86_SIMD_VEC_MASK		GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
 
+#define PERF_X86_H16ZMM_BASE		16
+
 #define PERF_X86_XMM_QWORDS		2
 #define PERF_X86_YMM_QWORDS		4
 #define PERF_X86_YMMH_QWORDS		(PERF_X86_YMM_QWORDS / 2)
-#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_YMM_QWORDS
+#define PERF_X86_ZMM_QWORDS		8
+#define PERF_X86_ZMMH_QWORDS		(PERF_X86_ZMM_QWORDS / 2)
+#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_ZMM_QWORDS
 
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 37cf0a282915..74e05e2e5c90 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -89,6 +89,12 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			 qwords_idx >= PERF_X86_SIMD_QWORDS_MAX))
 		return 0;
 
+	if (idx >= PERF_X86_H16ZMM_BASE) {
+		if (!perf_regs->h16zmm_regs)
+			return 0;
+		return perf_regs->h16zmm_regs[idx * PERF_X86_ZMM_QWORDS + qwords_idx];
+	}
+
 	if (qwords_idx < PERF_X86_XMM_QWORDS) {
 		if (!perf_regs->xmm_regs)
 			return 0;
@@ -97,6 +103,10 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 		if (!perf_regs->ymmh_regs)
 			return 0;
 		return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS + qwords_idx - PERF_X86_XMM_QWORDS];
+	} else if (qwords_idx < PERF_X86_ZMM_QWORDS) {
+		if (!perf_regs->zmmh_regs)
+			return 0;
+		return perf_regs->zmmh_regs[idx * PERF_X86_ZMMH_QWORDS + qwords_idx - PERF_X86_YMM_QWORDS];
 	}
 
 	return 0;
@@ -114,7 +124,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
 			return -EINVAL;
 	} else {
 		if (vec_qwords != PERF_X86_XMM_QWORDS &&
-		    vec_qwords != PERF_X86_YMM_QWORDS)
+		    vec_qwords != PERF_X86_YMM_QWORDS &&
+		    vec_qwords != PERF_X86_ZMM_QWORDS)
 			return -EINVAL;
 		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
 			return -EINVAL;
-- 
2.38.1


  parent reply	other threads:[~2025-06-26 19:57 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-26 19:55 [RFC PATCH V2 00/13] Support vector and more extended registers in perf kan.liang
2025-06-26 19:55 ` [RFC PATCH V2 01/13] perf/x86: Use x86_perf_regs in the x86 nmi handler kan.liang
2025-06-26 19:55 ` [RFC PATCH V2 02/13] perf/x86: Setup the regs data kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 03/13] x86/fpu/xstate: Add xsaves_nmi kan.liang
2025-07-02  0:18   ` Chang S. Bae
2025-07-07 18:12     ` Liang, Kan
2025-07-07 18:17       ` Dave Hansen
2025-06-26 19:56 ` [RFC PATCH V2 04/13] perf: Move has_extended_regs() to header file kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 05/13] perf/x86: Support XMM register for non-PEBS and REGS_USER kan.liang
2025-06-27 14:35   ` Dave Hansen
2025-06-27 21:23     ` Liang, Kan
2025-06-26 19:56 ` [RFC PATCH V2 06/13] perf: Support SIMD registers kan.liang
2025-07-02 11:16   ` Mark Brown
2025-07-07 18:12     ` Liang, Kan
2025-06-26 19:56 ` [RFC PATCH V2 07/13] perf/x86: Move XMM to sample_simd_vec_regs kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 08/13] perf/x86: Add YMM into sample_simd_vec_regs kan.liang
2025-06-26 19:56 ` kan.liang [this message]
2025-06-26 19:56 ` [RFC PATCH V2 10/13] perf/x86: Add OPMASK into sample_simd_pred_reg kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 11/13] perf/x86: Add eGPRs into sample_regs kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 12/13] perf/x86: Add SSP " kan.liang
2025-06-26 19:56 ` [RFC PATCH V2 13/13] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS kan.liang

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=20250626195610.405379-10-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=broonie@kernel.org \
    --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=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --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®