public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Dapeng Mi <dapeng1.mi@intel.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [Patch v3 15/22] perf/x86/intel: Support SSP register capturing for arch-PEBS
Date: Tue, 15 Apr 2025 11:44:21 +0000	[thread overview]
Message-ID: <20250415114428.341182-16-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20250415114428.341182-1-dapeng1.mi@linux.intel.com>

Arch-PEBS supports to capture shadow stack pointer (SSP) register in GPR
group. This patch supports to capture and output SSP register at
interrupt or user space, but capturing SSP at user space requires
'exclude_kernel' attribute must be set. That avoids kernel space SSP
register is captured unintentionally.

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/core.c                | 15 +++++++++++++++
 arch/x86/events/intel/core.c          |  3 ++-
 arch/x86/events/intel/ds.c            |  9 +++++++--
 arch/x86/events/perf_event.h          |  4 ++++
 arch/x86/include/asm/perf_event.h     |  1 +
 arch/x86/include/uapi/asm/perf_regs.h |  4 +++-
 arch/x86/kernel/perf_regs.c           |  7 +++++++
 7 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9c205a8a4fa6..0ccbe8385c7f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -650,6 +650,21 @@ int x86_pmu_hw_config(struct perf_event *event)
 			return -EINVAL;
 	}
 
+	if (unlikely(event->attr.sample_regs_user & BIT_ULL(PERF_REG_X86_SSP))) {
+		/* Only arch-PEBS supports to capture SSP register. */
+		if (!x86_pmu.arch_pebs || !event->attr.precise_ip)
+			return -EINVAL;
+		/* Only user space is allowed to capture. */
+		if (!event->attr.exclude_kernel)
+			return -EINVAL;
+	}
+
+	if (unlikely(event->attr.sample_regs_intr & BIT_ULL(PERF_REG_X86_SSP))) {
+		/* Only arch-PEBS supports to capture SSP register. */
+		if (!x86_pmu.arch_pebs || !event->attr.precise_ip)
+			return -EINVAL;
+	}
+
 	/* sample_regs_user never support XMM registers */
 	if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK))
 		return -EINVAL;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d543ed052743..b6416535f84d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4151,12 +4151,13 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
 static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
 	unsigned long flags = x86_pmu.large_pebs_flags;
+	u64 gprs_mask = x86_pmu.arch_pebs ? ARCH_PEBS_GP_REGS : PEBS_GP_REGS;
 
 	if (event->attr.use_clockid)
 		flags &= ~PERF_SAMPLE_TIME;
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
-	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
+	if (event->attr.sample_regs_user & ~gprs_mask)
 		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
 	return flags;
 }
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 19b51b4d0d94..91a093cba11f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1431,6 +1431,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	u64 sample_type = attr->sample_type;
 	u64 pebs_data_cfg = 0;
 	bool gprs, tsx_weight;
+	u64 gprs_mask;
 
 	if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
 	    attr->precise_ip > 1)
@@ -1445,10 +1446,11 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	 * + precise_ip < 2 for the non event IP
 	 * + For RTM TSX weight we need GPRs for the abort code.
 	 */
+	gprs_mask = x86_pmu.arch_pebs ? ARCH_PEBS_GP_REGS : PEBS_GP_REGS;
 	gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
-		(attr->sample_regs_intr & PEBS_GP_REGS)) ||
+		(attr->sample_regs_intr & gprs_mask)) ||
 	       ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		(attr->sample_regs_user & PEBS_GP_REGS));
+		(attr->sample_regs_user & gprs_mask));
 
 	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
 		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -2243,6 +2245,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 	perf_regs = container_of(regs, struct x86_perf_regs, regs);
 	perf_regs->xmm_regs = NULL;
+	perf_regs->ssp = 0;
 
 	format_group = basic->format_group;
 
@@ -2359,6 +2362,7 @@ static void setup_arch_pebs_sample_data(struct perf_event *event,
 
 	perf_regs = container_of(regs, struct x86_perf_regs, regs);
 	perf_regs->xmm_regs = NULL;
+	perf_regs->ssp = 0;
 
 	__setup_perf_sample_data(event, iregs, data);
 
@@ -2395,6 +2399,7 @@ static void setup_arch_pebs_sample_data(struct perf_event *event,
 
 		__setup_pebs_gpr_group(event, regs, (struct pebs_gprs *)gprs,
 				       sample_type);
+		perf_regs->ssp = gprs->ssp;
 	}
 
 	if (header->aux) {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c6c2ab34e711..6a8804a75de9 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -175,6 +175,10 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
+#define ARCH_PEBS_GP_REGS		\
+	(PEBS_GP_REGS |			\
+	 (1ULL << PERF_REG_X86_SSP))
+
 /*
  * Per register state.
  */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4e5adbc7baea..ba382361b13f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -704,6 +704,7 @@ extern void perf_events_lapic_init(void);
 struct pt_regs;
 struct x86_perf_regs {
 	struct pt_regs	regs;
+	u64		ssp;
 	u64		*xmm_regs;
 };
 
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index 7c9d2bb3833b..f9c5b16b1882 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,9 +27,11 @@ enum perf_event_x86_regs {
 	PERF_REG_X86_R13,
 	PERF_REG_X86_R14,
 	PERF_REG_X86_R15,
+	/* arch-PEBS supports to capture shadow stack pointer (SSP) */
+	PERF_REG_X86_SSP,
 	/* These are the limits for the GPRs. */
 	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
-	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+	PERF_REG_X86_64_MAX = PERF_REG_X86_SSP + 1,
 
 	/* These all need two bits set because they are 128bit */
 	PERF_REG_X86_XMM0  = 32,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 624703af80a1..985bd616200e 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -54,6 +54,8 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
 	PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
 	PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+	/* The pt_regs struct does not store Shadow stack pointer. */
+	(unsigned int) -1,
 #endif
 };
 
@@ -68,6 +70,11 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
 	}
 
+	if (idx == PERF_REG_X86_SSP) {
+		perf_regs = container_of(regs, struct x86_perf_regs, regs);
+		return perf_regs->ssp;
+	}
+
 	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
 		return 0;
 
-- 
2.40.1


  parent reply	other threads:[~2025-04-15  8:24 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-15 11:44 [Patch v3 00/22] Arch-PEBS and PMU supports for Clearwater Forest and Panther Lake Dapeng Mi
2025-04-15 11:44 ` [Patch v3 01/22] perf/x86/intel: Add Panther Lake support Dapeng Mi
2025-04-17 13:01   ` [tip: perf/core] " tip-bot2 for Kan Liang
2025-04-15 11:44 ` [Patch v3 02/22] perf/x86/intel: Add PMU support for Clearwater Forest Dapeng Mi
2025-04-17 13:01   ` [tip: perf/core] " tip-bot2 for Dapeng Mi
2025-04-15 11:44 ` [Patch v3 03/22] perf/x86/intel: Parse CPUID archPerfmonExt leaves for non-hybrid CPUs Dapeng Mi
2025-04-17 13:01   ` [tip: perf/core] " tip-bot2 for Dapeng Mi
2025-04-15 11:44 ` [Patch v3 04/22] perf/x86/intel: Decouple BTS initialization from PEBS initialization Dapeng Mi
2025-04-17 13:01   ` [tip: perf/core] " tip-bot2 for Dapeng Mi
2025-04-15 11:44 ` [Patch v3 05/22] perf/x86/intel: Rename x86_pmu.pebs to x86_pmu.ds_pebs Dapeng Mi
2025-04-17 13:01   ` [tip: perf/core] " tip-bot2 for Dapeng Mi
2025-04-15 11:44 ` [Patch v3 06/22] perf/x86/intel: Introduce pairs of PEBS static calls Dapeng Mi
2025-04-17 13:00   ` [tip: perf/core] " tip-bot2 for Dapeng Mi
2025-04-15 11:44 ` [Patch v3 07/22] perf/x86/intel: Initialize architectural PEBS Dapeng Mi
2025-04-15 11:44 ` [Patch v3 08/22] perf/x86/intel/ds: Factor out PEBS record processing code to functions Dapeng Mi
2025-04-15 11:44 ` [Patch v3 09/22] perf/x86/intel/ds: Factor out PEBS group " Dapeng Mi
2025-04-15 11:44 ` [Patch v3 10/22] perf/x86/intel: Process arch-PEBS records or record fragments Dapeng Mi
2025-04-15 13:57   ` Peter Zijlstra
2025-04-15 16:09     ` Liang, Kan
2025-04-15 11:44 ` [Patch v3 11/22] perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR Dapeng Mi
2025-04-15 13:45   ` Peter Zijlstra
2025-04-16  0:59     ` Mi, Dapeng
2025-04-15 13:48   ` Peter Zijlstra
2025-04-16  1:03     ` Mi, Dapeng
2025-04-15 11:44 ` [Patch v3 12/22] perf/x86/intel: Update dyn_constranit base on PEBS event precise level Dapeng Mi
2025-04-15 13:53   ` Peter Zijlstra
2025-04-15 16:31     ` Liang, Kan
2025-04-16  1:46       ` Mi, Dapeng
2025-04-16 13:59         ` Liang, Kan
2025-04-17  1:15           ` Mi, Dapeng
2025-04-16 15:32       ` Peter Zijlstra
2025-04-16 19:45         ` Liang, Kan
2025-04-16 19:56           ` Peter Zijlstra
2025-04-22 22:50             ` Liang, Kan
2025-04-15 11:44 ` [Patch v3 13/22] perf/x86/intel: Setup PEBS data configuration and enable legacy groups Dapeng Mi
2025-04-15 11:44 ` [Patch v3 14/22] perf/x86/intel: Add counter group support for arch-PEBS Dapeng Mi
2025-04-15 11:44 ` Dapeng Mi [this message]
2025-04-15 14:07   ` [Patch v3 15/22] perf/x86/intel: Support SSP register capturing " Peter Zijlstra
2025-04-16  5:49     ` Mi, Dapeng
2025-04-15 11:44 ` [Patch v3 16/22] perf/core: Support to capture higher width vector registers Dapeng Mi
2025-04-15 14:36   ` Peter Zijlstra
2025-04-16  6:42     ` Mi, Dapeng
2025-04-16 15:53       ` Peter Zijlstra
2025-04-17  2:00         ` Mi, Dapeng
2025-04-22  3:05         ` Mi, Dapeng
2025-04-15 11:44 ` [Patch v3 17/22] perf/x86/intel: Support arch-PEBS vector registers group capturing Dapeng Mi
2025-04-15 11:44 ` [Patch v3 18/22] perf tools: Support to show SSP register Dapeng Mi
2025-04-15 11:44 ` [Patch v3 19/22] perf tools: Enhance arch__intr/user_reg_mask() helpers Dapeng Mi
2025-04-15 11:44 ` [Patch v3 20/22] perf tools: Enhance sample_regs_user/intr to capture more registers Dapeng Mi
2025-04-15 11:44 ` [Patch v3 21/22] perf tools: Support to capture more vector registers (x86/Intel) Dapeng Mi
2025-04-15 11:44 ` [Patch v3 22/22] perf tools/tests: Add vector registers PEBS sampling test Dapeng Mi
2025-04-15 15:21 ` [Patch v3 00/22] Arch-PEBS and PMU supports for Clearwater Forest and Panther Lake Liang, Kan
2025-04-16  7:42   ` Peter Zijlstra

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=20250415114428.341182-16-dapeng1.mi@linux.intel.com \
    --to=dapeng1.mi@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@intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    /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