linux-kernel - [Patch v4 13/17] perf/x86/intel: Enable PERF_PMU_CAP_SIMD

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250925061213.178796-14-dapeng1.mi@linux.intel.com>
Date: Thu, 25 Sep 2025 14:12:09 +0800
From: Dapeng Mi <dapeng1.mi@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Namhyung Kim <namhyung@...nel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Dave Hansen <dave.hansen@...ux.intel.com>,
	Ian Rogers <irogers@...gle.com>,
	Adrian Hunter <adrian.hunter@...el.com>,
	Jiri Olsa <jolsa@...nel.org>,
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
	Kan Liang <kan.liang@...ux.intel.com>,
	Andi Kleen <ak@...ux.intel.com>,
	Eranian Stephane <eranian@...gle.com>
Cc: Mark Rutland <mark.rutland@....com>,
	broonie@...nel.org,
	Ravi Bangoria <ravi.bangoria@....com>,
	linux-kernel@...r.kernel.org,
	linux-perf-users@...r.kernel.org,
	Dapeng Mi <dapeng1.mi@...el.com>,
	Dapeng Mi <dapeng1.mi@...ux.intel.com>
Subject: [Patch v4 13/17] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS

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

Enable PERF_PMU_CAP_SIMD_REGS if there is XSAVES support for YMM, ZMM,
OPMASK, eGPRs, or SSP.

Disable large PEBS for these registers since PEBS HW doesn't support
them yet.

Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
---
 arch/x86/events/intel/core.c | 48 ++++++++++++++++++++++++++++++++++--
 1 file changed, 46 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2575ec0d2b77..dd46629c1ce6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4030,8 +4030,32 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 		flags &= ~PERF_SAMPLE_TIME;
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
-	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
-		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
+	if (event->attr.sample_simd_regs_enabled) {
+		u64 nolarge = PERF_X86_EGPRS_MASK | BIT_ULL(PERF_REG_X86_SSP);
+
+		/*
+		 * PEBS HW can only collect the XMM0-XMM15 for now.
+		 * Disable large PEBS for other vector registers, predicate
+		 * registers, eGPRs, and SSP.
+		 */
+		if (event->attr.sample_regs_user & nolarge ||
+		    fls64(event->attr.sample_simd_vec_reg_user) > PERF_X86_H16ZMM_BASE ||
+		    event->attr.sample_simd_pred_reg_user)
+			flags &= ~PERF_SAMPLE_REGS_USER;
+
+		if (event->attr.sample_regs_intr & nolarge ||
+		    fls64(event->attr.sample_simd_vec_reg_intr) > PERF_X86_H16ZMM_BASE ||
+		    event->attr.sample_simd_pred_reg_intr)
+			flags &= ~PERF_SAMPLE_REGS_INTR;
+
+		if (event->attr.sample_simd_vec_reg_qwords > PERF_X86_XMM_QWORDS)
+			flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
+	} else {
+		if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
+			flags &= ~PERF_SAMPLE_REGS_USER;
+		if (event->attr.sample_regs_intr & ~PEBS_GP_REGS)
+			flags &= ~PERF_SAMPLE_REGS_INTR;
+	}
 	return flags;
 }
 
@@ -5292,6 +5316,26 @@ static void intel_extended_regs_init(struct pmu *pmu)
 
 	x86_pmu.ext_regs_mask |= XFEATURE_MASK_SSE;
 	x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
+
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_YMM, NULL))
+		x86_pmu.ext_regs_mask |= XFEATURE_MASK_YMM;
+	if (boot_cpu_has(X86_FEATURE_APX) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_APX, NULL))
+		x86_pmu.ext_regs_mask |= XFEATURE_MASK_APX;
+	if (boot_cpu_has(X86_FEATURE_AVX512F)) {
+		if (cpu_has_xfeatures(XFEATURE_MASK_OPMASK, NULL))
+			x86_pmu.ext_regs_mask |= XFEATURE_MASK_OPMASK;
+		if (cpu_has_xfeatures(XFEATURE_MASK_ZMM_Hi256, NULL))
+			x86_pmu.ext_regs_mask |= XFEATURE_MASK_ZMM_Hi256;
+		if (cpu_has_xfeatures(XFEATURE_MASK_Hi16_ZMM, NULL))
+			x86_pmu.ext_regs_mask |= XFEATURE_MASK_Hi16_ZMM;
+	}
+	if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+		x86_pmu.ext_regs_mask |= XFEATURE_MASK_CET_USER;
+
+	if (x86_pmu.ext_regs_mask != XFEATURE_MASK_SSE)
+		x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_SIMD_REGS;
 }
 
 static void update_pmu_cap(struct pmu *pmu)
-- 
2.34.1