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 11/17] perf/x86: Add eGPRs into sample_regs
Date: Thu, 25 Sep 2025 14:12:07 +0800 [thread overview]
Message-ID: <20250925061213.178796-12-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 eGPRs 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 eGPRs.
The eGPRs is retrieved by XSAVE. Only support the eGPRs for X86_64.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
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 | 41 ++++++++++++++++++---------
arch/x86/events/perf_event.h | 10 +++++++
arch/x86/include/asm/perf_event.h | 4 +++
arch/x86/include/uapi/asm/perf_regs.h | 26 ++++++++++++++++-
arch/x86/kernel/perf_regs.c | 31 ++++++++++----------
5 files changed, 83 insertions(+), 29 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index c942c6f808ca..a435610f4d4a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -432,6 +432,8 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
perf_regs->h16zmm = get_xsave_addr(xsave, XFEATURE_Hi16_ZMM);
if (valid_mask & XFEATURE_MASK_OPMASK)
perf_regs->opmask = get_xsave_addr(xsave, XFEATURE_OPMASK);
+ if (valid_mask & XFEATURE_MASK_APX)
+ perf_regs->egpr = get_xsave_addr(xsave, XFEATURE_APX);
}
static void release_ext_regs_buffers(void)
@@ -709,22 +711,21 @@ int x86_pmu_hw_config(struct perf_event *event)
}
if (event->attr.sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) {
- /*
- * Besides the general purpose registers, XMM registers may
- * be collected as well.
- */
- if (event_has_extended_regs(event)) {
- if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
- return -EINVAL;
- if (!event->attr.precise_ip)
- return -EINVAL;
- if (event->attr.sample_simd_regs_enabled)
- return -EINVAL;
- }
-
if (event_has_simd_regs(event)) {
+ u64 reserved = ~GENMASK_ULL(PERF_REG_X86_64_MAX - 1, 0);
+
if (!(event->pmu->capabilities & PERF_PMU_CAP_SIMD_REGS))
return -EINVAL;
+ /*
+ * The XMM space in the perf_event_x86_regs is reclaimed
+ * for eGPRs and other general registers.
+ */
+ if (event->attr.sample_regs_user & reserved ||
+ event->attr.sample_regs_intr & reserved)
+ return -EINVAL;
+ if (event_needs_egprs(event) &&
+ !(x86_pmu.ext_regs_mask & XFEATURE_MASK_APX))
+ 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 &&
@@ -746,6 +747,17 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event_needs_opmask(event) &&
!(x86_pmu.ext_regs_mask & XFEATURE_MASK_OPMASK))
return -EINVAL;
+ } else {
+ /*
+ * Besides the general purpose registers, XMM registers may
+ * be collected as well.
+ */
+ if (event_has_extended_regs(event)) {
+ if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
+ return -EINVAL;
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+ }
}
}
@@ -1908,6 +1920,9 @@ static void x86_pmu_setup_extended_regs_data(struct perf_event *event,
perf_regs->opmask_regs = NULL;
if (event_needs_opmask(event))
mask |= XFEATURE_MASK_OPMASK;
+ perf_regs->egpr_regs = NULL;
+ if (event_needs_egprs(event))
+ mask |= XFEATURE_MASK_APX;
mask &= ~ignore_mask;
if (mask)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 4584de1c79a3..3dd0e669ddd4 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -182,6 +182,16 @@ static inline bool event_needs_opmask(struct perf_event *event)
return false;
}
+static inline bool event_needs_egprs(struct perf_event *event)
+{
+ if (event->attr.sample_simd_regs_enabled &&
+ (event->attr.sample_regs_user & PERF_X86_EGPRS_MASK ||
+ event->attr.sample_regs_intr & PERF_X86_EGPRS_MASK))
+ 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 d8cac3f9f8df..73c2064c13f9 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -617,6 +617,10 @@ struct x86_perf_regs {
u64 *opmask_regs;
struct avx_512_opmask_state *opmask;
};
+ union {
+ u64 *egpr_regs;
+ struct apx_state *egpr;
+ };
};
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 6f29fd9495a2..38644de89815 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,9 +27,32 @@ enum perf_event_x86_regs {
PERF_REG_X86_R13,
PERF_REG_X86_R14,
PERF_REG_X86_R15,
+ /*
+ * The EGPRs 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.
+ *
+ * Extended GPRs (EGPRs)
+ */
+ PERF_REG_X86_R16,
+ PERF_REG_X86_R17,
+ PERF_REG_X86_R18,
+ PERF_REG_X86_R19,
+ PERF_REG_X86_R20,
+ PERF_REG_X86_R21,
+ PERF_REG_X86_R22,
+ PERF_REG_X86_R23,
+ PERF_REG_X86_R24,
+ PERF_REG_X86_R25,
+ PERF_REG_X86_R26,
+ PERF_REG_X86_R27,
+ PERF_REG_X86_R28,
+ PERF_REG_X86_R29,
+ PERF_REG_X86_R30,
+ PERF_REG_X86_R31,
/* 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_R31 + 1,
/* These all need two bits set because they are 128bit */
PERF_REG_X86_XMM0 = 32,
@@ -54,6 +77,7 @@ enum perf_event_x86_regs {
};
#define PERF_REG_EXTENDED_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1))
+#define PERF_X86_EGPRS_MASK GENMASK_ULL(PERF_REG_X86_R31, PERF_REG_X86_R16)
enum {
PERF_REG_X86_XMM,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index f6e9cde11ba1..b98b47a79d02 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -92,14 +92,22 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
{
struct x86_perf_regs *perf_regs;
- if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ if (idx > PERF_REG_X86_R15) {
perf_regs = container_of(regs, struct x86_perf_regs, regs);
- /* SIMD registers are moved to dedicated sample_simd_vec_reg */
- if (perf_regs->abi & PERF_SAMPLE_REGS_ABI_SIMD)
- return 0;
- if (!perf_regs->xmm_regs)
- return 0;
- return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+
+ if (perf_regs->abi & PERF_SAMPLE_REGS_ABI_SIMD) {
+ if (idx <= PERF_REG_X86_R31) {
+ if (!perf_regs->egpr_regs)
+ return 0;
+ return perf_regs->egpr_regs[idx - PERF_REG_X86_R16];
+ }
+ } else {
+ if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ if (!perf_regs->xmm_regs)
+ return 0;
+ return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+ }
+ }
}
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
@@ -183,14 +191,7 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
~((1ULL << PERF_REG_X86_MAX) - 1))
#ifdef CONFIG_X86_32
-#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
- (1ULL << PERF_REG_X86_R9) | \
- (1ULL << PERF_REG_X86_R10) | \
- (1ULL << PERF_REG_X86_R11) | \
- (1ULL << PERF_REG_X86_R12) | \
- (1ULL << PERF_REG_X86_R13) | \
- (1ULL << PERF_REG_X86_R14) | \
- (1ULL << PERF_REG_X86_R15))
+#define REG_NOSUPPORT GENMASK_ULL(PERF_REG_X86_R31, PERF_REG_X86_R8)
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 ` Dapeng Mi [this message]
2025-09-25 6:12 ` [Patch v4 12/17] perf/x86: Add SSP into sample_regs Dapeng Mi
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=20250925061213.178796-12-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).