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>,
Thomas Gleixner <tglx@linutronix.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Jiri Olsa <jolsa@kernel.org>,
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: Mark Rutland <mark.rutland@arm.com>,
broonie@kernel.org, Ravi Bangoria <ravi.bangoria@amd.com>,
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 v4 12/17] perf/x86: Add SSP into sample_regs
Date: Thu, 25 Sep 2025 14:12:08 +0800 [thread overview]
Message-ID: <20250925061213.178796-13-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20250925061213.178796-1-dapeng1.mi@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
The SSP is only supported when the new SIMD registers configuration
method is used, which moves the XMM to sample_simd_vec_regs. So the
space can be reclaimed for the SSP.
The SSP is retrieved by XSAVE. Only support the SSP for X86_64.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Co-developed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
arch/x86/events/core.c | 11 ++++++++++-
arch/x86/events/perf_event.h | 10 ++++++++++
arch/x86/include/asm/perf_event.h | 4 ++++
arch/x86/include/uapi/asm/perf_regs.h | 7 +++++--
arch/x86/kernel/perf_regs.c | 8 +++++++-
5 files changed, 36 insertions(+), 4 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a435610f4d4a..7c29c9029379 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -434,6 +434,8 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
perf_regs->opmask = get_xsave_addr(xsave, XFEATURE_OPMASK);
if (valid_mask & XFEATURE_MASK_APX)
perf_regs->egpr = get_xsave_addr(xsave, XFEATURE_APX);
+ if (valid_mask & XFEATURE_MASK_CET_USER)
+ perf_regs->cet = get_xsave_addr(xsave, XFEATURE_CET_USER);
}
static void release_ext_regs_buffers(void)
@@ -712,7 +714,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) {
if (event_has_simd_regs(event)) {
- u64 reserved = ~GENMASK_ULL(PERF_REG_X86_64_MAX - 1, 0);
+ u64 reserved = ~GENMASK_ULL(PERF_REG_MISC_MAX - 1, 0);
if (!(event->pmu->capabilities & PERF_PMU_CAP_SIMD_REGS))
return -EINVAL;
@@ -726,6 +728,10 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event_needs_egprs(event) &&
!(x86_pmu.ext_regs_mask & XFEATURE_MASK_APX))
return -EINVAL;
+ if (event_needs_ssp(event) &&
+ !(x86_pmu.ext_regs_mask & XFEATURE_MASK_CET_USER))
+ return -EINVAL;
+
/* Not require any vector registers but set width */
if (event->attr.sample_simd_vec_reg_qwords &&
!event->attr.sample_simd_vec_reg_intr &&
@@ -1923,6 +1929,9 @@ static void x86_pmu_setup_extended_regs_data(struct perf_event *event,
perf_regs->egpr_regs = NULL;
if (event_needs_egprs(event))
mask |= XFEATURE_MASK_APX;
+ perf_regs->cet_regs = NULL;
+ if (event_needs_ssp(event))
+ mask |= XFEATURE_MASK_CET_USER;
mask &= ~ignore_mask;
if (mask)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 3dd0e669ddd4..6ff4aa23833f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -192,6 +192,16 @@ static inline bool event_needs_egprs(struct perf_event *event)
return false;
}
+static inline bool event_needs_ssp(struct perf_event *event)
+{
+ if (event->attr.sample_simd_regs_enabled &&
+ (event->attr.sample_regs_user & BIT_ULL(PERF_REG_X86_SSP) ||
+ event->attr.sample_regs_intr & BIT_ULL(PERF_REG_X86_SSP)))
+ return true;
+
+ return false;
+}
+
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 73c2064c13f9..9d10299355c5 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -621,6 +621,10 @@ struct x86_perf_regs {
u64 *egpr_regs;
struct apx_state *egpr;
};
+ union {
+ u64 *cet_regs;
+ struct cet_user_state *cet;
+ };
};
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 38644de89815..0cf0490c47b2 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -28,9 +28,9 @@ enum perf_event_x86_regs {
PERF_REG_X86_R14,
PERF_REG_X86_R15,
/*
- * The EGPRs and XMM have overlaps. Only one can be used
+ * The EGPRs/SSP and XMM have overlaps. Only one can be used
* at a time. For the ABI type PERF_SAMPLE_REGS_ABI_SIMD,
- * utilize EGPRs. For the other ABI type, XMM is used.
+ * utilize EGPRs/SSP. For the other ABI type, XMM is used.
*
* Extended GPRs (EGPRs)
*/
@@ -54,6 +54,9 @@ enum perf_event_x86_regs {
PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
PERF_REG_X86_64_MAX = PERF_REG_X86_R31 + 1,
+ PERF_REG_X86_SSP,
+ PERF_REG_MISC_MAX = PERF_REG_X86_SSP + 1,
+
/* These all need two bits set because they are 128bit */
PERF_REG_X86_XMM0 = 32,
PERF_REG_X86_XMM1 = 34,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index b98b47a79d02..4d519867a3ef 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -101,6 +101,11 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
return 0;
return perf_regs->egpr_regs[idx - PERF_REG_X86_R16];
}
+ if (idx == PERF_REG_X86_SSP) {
+ if (!perf_regs->cet_regs)
+ return 0;
+ return perf_regs->cet_regs[1];
+ }
} else {
if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
if (!perf_regs->xmm_regs)
@@ -191,7 +196,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
~((1ULL << PERF_REG_X86_MAX) - 1))
#ifdef CONFIG_X86_32
-#define REG_NOSUPPORT GENMASK_ULL(PERF_REG_X86_R31, PERF_REG_X86_R8)
+#define REG_NOSUPPORT (GENMASK_ULL(PERF_REG_X86_R31, PERF_REG_X86_R8) | \
+ BIT_ULL(PERF_REG_X86_SSP))
int perf_reg_validate(u64 mask)
{
--
2.34.1
next prev parent reply other threads:[~2025-09-25 6:15 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-25 6:11 [Patch v4 00/17] Support vector and more extended registers in perf Dapeng Mi
2025-09-25 6:11 ` [Patch v4 01/17] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2025-09-25 6:11 ` [Patch v4 02/17] perf/x86: Setup the regs data Dapeng Mi
2025-09-25 6:11 ` [Patch v4 03/17] x86/fpu/xstate: Add xsaves_nmi Dapeng Mi
2025-09-25 15:07 ` Dave Hansen
2025-09-28 5:31 ` Mi, Dapeng
2025-09-29 19:01 ` Dave Hansen
2025-09-30 2:44 ` Mi, Dapeng
2025-09-25 6:12 ` [Patch v4 04/17] perf: Move has_extended_regs() to header file Dapeng Mi
2025-09-25 6:12 ` [Patch v4 05/17] perf/x86: Support XMM register for non-PEBS and REGS_USER Dapeng Mi
2025-09-25 6:12 ` [Patch v4 06/17] perf: Support SIMD registers Dapeng Mi
2025-09-25 6:12 ` [Patch v4 07/17] perf/x86: Move XMM to sample_simd_vec_regs Dapeng Mi
2025-09-25 6:12 ` [Patch v4 08/17] perf/x86: Add YMM into sample_simd_vec_regs Dapeng Mi
2025-09-25 6:12 ` [Patch v4 09/17] perf/x86: Add ZMM " Dapeng Mi
2025-09-25 6:12 ` [Patch v4 10/17] perf/x86: Add OPMASK into sample_simd_pred_reg Dapeng Mi
2025-09-25 6:12 ` [Patch v4 11/17] perf/x86: Add eGPRs into sample_regs Dapeng Mi
2025-09-25 6:12 ` Dapeng Mi [this message]
2025-09-25 6:12 ` [Patch v4 13/17] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS Dapeng Mi
2025-09-25 6:12 ` [Patch v4 14/17] perf tools: Only support legacy regs for the PT and PERF_REGS_MASK Dapeng Mi
2025-09-25 6:12 ` [Patch v4 15/17] perf tools: headers: Sync with the kernel sources Dapeng Mi
2025-09-25 6:12 ` [Patch v4 16/17] perf tools: parse-regs: Support the new SIMD format Dapeng Mi
2025-09-25 6:12 ` [Patch v4 17/17] perf tools: regs: Support to dump regs for PERF_SAMPLE_REGS_ABI_SIMD Dapeng Mi
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=20250925061213.178796-13-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=broonie@kernel.org \
--cc=dapeng1.mi@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@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 \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.