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>,
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,
Zide Chen <zide.chen@intel.com>,
Falcon Thomas <thomas.falcon@intel.com>,
Dapeng Mi <dapeng1.mi@intel.com>,
Xudong Hao <xudong.hao@intel.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>,
Kan Liang <kan.liang@linux.intel.com>
Subject: [Patch v7 12/24] perf/x86: Enable XMM register sampling for REGS_USER case
Date: Tue, 24 Mar 2026 08:41:06 +0800 [thread overview]
Message-ID: <20260324004118.3772171-13-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20260324004118.3772171-1-dapeng1.mi@linux.intel.com>
This patch adds support for XMM register sampling in the REGS_USER case.
To handle simultaneous sampling of XMM registers for both REGS_INTR and
REGS_USER cases, a per-CPU `x86_user_regs` is introduced to store
REGS_USER-specific XMM registers. This prevents REGS_USER-specific XMM
register data from being overwritten by REGS_INTR-specific data if they
share the same `x86_perf_regs` structure.
To sample user-space XMM registers, the `x86_pmu_update_user_ext_regs()`
helper function is added. It checks if the `TIF_NEED_FPU_LOAD` flag is
set. If so, the user-space XMM register data can be directly retrieved
from the cached task FPU state, as the corresponding hardware registers
have been cleared or switched to kernel-space data. Otherwise, the data
must be read from the hardware registers using the `xsaves` instruction.
For PEBS events, `x86_pmu_update_user_ext_regs()` checks if the
PEBS-sampled XMM register data belongs to user-space. If so, no further
action is needed. Otherwise, the user-space XMM register data needs to be
re-sampled using the same method as for non-PEBS events.
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
arch/x86/events/core.c | 95 ++++++++++++++++++++++++++++++++++++------
1 file changed, 82 insertions(+), 13 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 22965a8a22b3..a5643c875190 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -696,7 +696,7 @@ int x86_pmu_hw_config(struct perf_event *event)
return -EINVAL;
}
- if (event->attr.sample_type & PERF_SAMPLE_REGS_INTR) {
+ 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.
@@ -707,15 +707,6 @@ int x86_pmu_hw_config(struct perf_event *event)
}
}
- if (event->attr.sample_type & PERF_SAMPLE_REGS_USER) {
- /*
- * Currently XMM registers sampling for REGS_USER is not
- * supported yet.
- */
- if (event_has_extended_regs(event))
- return -EINVAL;
- }
-
return x86_setup_perfctr(event);
}
@@ -1745,6 +1736,28 @@ static void x86_pmu_del(struct perf_event *event, int flags)
static_call_cond(x86_pmu_del)(event);
}
+/*
+ * When both PERF_SAMPLE_REGS_INTR and PERF_SAMPLE_REGS_USER are set,
+ * an additional x86_perf_regs is required to save user-space registers.
+ * Without this, user-space register data may be overwritten by kernel-space
+ * registers.
+ */
+static DEFINE_PER_CPU(struct x86_perf_regs, x86_user_regs);
+static void x86_pmu_perf_get_regs_user(struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct x86_perf_regs *x86_regs_user = this_cpu_ptr(&x86_user_regs);
+ struct perf_regs regs_user;
+
+ perf_get_regs_user(®s_user, regs);
+ data->regs_user.abi = regs_user.abi;
+ if (regs_user.regs) {
+ x86_regs_user->regs = *regs_user.regs;
+ data->regs_user.regs = &x86_regs_user->regs;
+ } else
+ data->regs_user.regs = NULL;
+}
+
static void x86_pmu_setup_gpregs_data(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
@@ -1757,7 +1770,14 @@ static void x86_pmu_setup_gpregs_data(struct perf_event *event,
data->regs_user.abi = perf_reg_abi(current);
data->regs_user.regs = regs;
} else if (!(current->flags & PF_KTHREAD)) {
- perf_get_regs_user(&data->regs_user, regs);
+ /*
+ * It cannot guarantee that the kernel will never
+ * touch the registers outside of the pt_regs,
+ * especially when more and more registers
+ * (e.g., SIMD, eGPR) are added. The live data
+ * cannot be used.
+ */
+ x86_pmu_perf_get_regs_user(data, regs);
} else {
data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
data->regs_user.regs = NULL;
@@ -1800,6 +1820,43 @@ static inline void x86_pmu_update_xregs(struct x86_perf_regs *perf_regs,
perf_regs->xmm_space = xsave->i387.xmm_space;
}
+/*
+ * This function retrieves cached user-space fpu registers (XMM/YMM/ZMM).
+ * If TIF_NEED_FPU_LOAD is set, it indicates that the user-space FPU state
+ * is cached. Otherwise, the data should be read directly from the hardware
+ * registers.
+ */
+static inline u64 x86_pmu_update_user_xregs(struct perf_sample_data *data,
+ u64 mask, u64 ignore_mask)
+{
+ struct x86_perf_regs *perf_regs;
+ struct xregs_state *xsave;
+ struct fpu *fpu;
+ struct fpstate *fps;
+
+ if (data->regs_user.abi == PERF_SAMPLE_REGS_ABI_NONE)
+ return 0;
+
+ if (test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ perf_regs = container_of(data->regs_user.regs,
+ struct x86_perf_regs, regs);
+ fpu = x86_task_fpu(current);
+ /*
+ * If __task_fpstate is set, it holds the right pointer,
+ * otherwise fpstate will.
+ */
+ fps = READ_ONCE(fpu->__task_fpstate);
+ if (!fps)
+ fps = fpu->fpstate;
+ xsave = &fps->regs.xsave;
+
+ x86_pmu_update_xregs(perf_regs, xsave, mask);
+ return 0;
+ }
+
+ return mask & ~ignore_mask;
+}
+
static void x86_pmu_sample_xregs(struct perf_event *event,
struct perf_sample_data *data,
u64 ignore_mask)
@@ -1807,6 +1864,7 @@ static void x86_pmu_sample_xregs(struct perf_event *event,
struct xregs_state *xsave = per_cpu(ext_regs_buf, smp_processor_id());
u64 sample_type = event->attr.sample_type;
struct x86_perf_regs *perf_regs;
+ u64 user_mask = 0;
u64 intr_mask = 0;
u64 mask = 0;
@@ -1817,15 +1875,26 @@ static void x86_pmu_sample_xregs(struct perf_event *event,
mask |= XFEATURE_MASK_SSE;
mask &= x86_pmu.ext_regs_mask;
+ if ((sample_type & PERF_SAMPLE_REGS_USER) && data->regs_user.abi)
+ user_mask = x86_pmu_update_user_xregs(data, mask, ignore_mask);
if ((sample_type & PERF_SAMPLE_REGS_INTR) && data->regs_intr.abi)
intr_mask = mask & ~ignore_mask;
+ if (user_mask | intr_mask) {
+ xsave->header.xfeatures = 0;
+ xsaves_nmi(xsave, user_mask | intr_mask);
+ }
+
+ if (user_mask) {
+ perf_regs = container_of(data->regs_user.regs,
+ struct x86_perf_regs, regs);
+ x86_pmu_update_xregs(perf_regs, xsave, user_mask);
+ }
+
if (intr_mask) {
perf_regs = container_of(data->regs_intr.regs,
struct x86_perf_regs, regs);
- xsave->header.xfeatures = 0;
- xsaves_nmi(xsave, mask);
x86_pmu_update_xregs(perf_regs, xsave, intr_mask);
}
}
--
2.34.1
next prev parent reply other threads:[~2026-03-24 0:46 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-24 0:40 [Patch v7 00/24] Support SIMD/eGPRs/SSP registers sampling for perf Dapeng Mi
2026-03-24 0:40 ` [Patch v7 01/24] perf/x86: Move hybrid PMU initialization before x86_pmu_starting_cpu() Dapeng Mi
2026-03-24 0:40 ` [Patch v7 02/24] perf/x86/intel: Avoid PEBS event on fixed counters without extended PEBS Dapeng Mi
2026-03-24 0:40 ` [Patch v7 03/24] perf/x86/intel: Enable large PEBS sampling for XMMs Dapeng Mi
2026-03-24 0:40 ` [Patch v7 04/24] perf/x86/intel: Convert x86_perf_regs to per-cpu variables Dapeng Mi
2026-03-24 0:40 ` [Patch v7 05/24] perf: Eliminate duplicate arch-specific functions definations Dapeng Mi
2026-03-24 0:41 ` [Patch v7 06/24] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2026-03-24 0:41 ` [Patch v7 07/24] perf/x86: Introduce x86-specific x86_pmu_setup_regs_data() Dapeng Mi
2026-03-25 5:18 ` Mi, Dapeng
2026-03-24 0:41 ` [Patch v7 08/24] x86/fpu/xstate: Add xsaves_nmi() helper Dapeng Mi
2026-03-24 0:41 ` [Patch v7 09/24] x86/fpu: Ensure TIF_NEED_FPU_LOAD is set after saving FPU state Dapeng Mi
2026-03-24 0:41 ` [Patch v7 10/24] perf: Move and rename has_extended_regs() for ARCH-specific use Dapeng Mi
2026-03-24 0:41 ` [Patch v7 11/24] perf/x86: Enable XMM Register Sampling for Non-PEBS Events Dapeng Mi
2026-03-25 7:30 ` Mi, Dapeng
2026-03-24 0:41 ` Dapeng Mi [this message]
2026-03-25 7:58 ` [Patch v7 12/24] perf/x86: Enable XMM register sampling for REGS_USER case Mi, Dapeng
2026-03-24 0:41 ` [Patch v7 13/24] perf: Add sampling support for SIMD registers Dapeng Mi
2026-03-25 8:44 ` Mi, Dapeng
2026-03-24 0:41 ` [Patch v7 14/24] perf/x86: Enable XMM sampling using sample_simd_vec_reg_* fields Dapeng Mi
2026-03-25 9:01 ` Mi, Dapeng
2026-03-24 0:41 ` [Patch v7 15/24] perf/x86: Enable YMM " Dapeng Mi
2026-03-24 0:41 ` [Patch v7 16/24] perf/x86: Enable ZMM " Dapeng Mi
2026-03-24 0:41 ` [Patch v7 17/24] perf/x86: Enable OPMASK sampling using sample_simd_pred_reg_* fields Dapeng Mi
2026-03-24 0:41 ` [Patch v7 18/24] perf: Enhance perf_reg_validate() with simd_enabled argument Dapeng Mi
2026-03-24 0:41 ` [Patch v7 19/24] perf/x86: Enable eGPRs sampling using sample_regs_* fields Dapeng Mi
2026-03-24 0:41 ` [Patch v7 20/24] perf/x86: Enable SSP " Dapeng Mi
2026-03-25 9:25 ` Mi, Dapeng
2026-03-24 0:41 ` [Patch v7 21/24] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS capability Dapeng Mi
2026-03-24 0:41 ` [Patch v7 22/24] perf/x86/intel: Enable arch-PEBS based SIMD/eGPRs/SSP sampling Dapeng Mi
2026-03-24 0:41 ` [Patch v7 23/24] perf/x86: Activate back-to-back NMI detection for arch-PEBS induced NMIs Dapeng Mi
2026-03-24 0:41 ` [Patch v7 24/24] perf/x86/intel: Add sanity check for PEBS fragment size Dapeng Mi
2026-03-24 1:08 ` [Patch v7 00/24] Support SIMD/eGPRs/SSP registers sampling for perf Mi, Dapeng
2026-03-25 9:41 ` Mi, Dapeng
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=20260324004118.3772171-13-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 \
--cc=thomas.falcon@intel.com \
--cc=xudong.hao@intel.com \
--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