[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251205110706.GT2528459@noisy.programming.kicks-ass.net>
Date: Fri, 5 Dec 2025 12:07:06 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Dapeng Mi <dapeng1.mi@...ux.intel.com>
Cc: 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>,
Andi Kleen <ak@...ux.intel.com>,
Eranian Stephane <eranian@...gle.com>,
Mark Rutland <mark.rutland@....com>, broonie@...nel.org,
Ravi Bangoria <ravi.bangoria@....com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org, Zide Chen <zide.chen@...el.com>,
Falcon Thomas <thomas.falcon@...el.com>,
Dapeng Mi <dapeng1.mi@...el.com>, Xudong Hao <xudong.hao@...el.com>,
Kan Liang <kan.liang@...ux.intel.com>
Subject: Re: [Patch v5 07/19] perf: Add sampling support for SIMD registers
On Wed, Dec 03, 2025 at 02:54:48PM +0800, Dapeng Mi wrote:
> @@ -545,6 +547,25 @@ struct perf_event_attr {
> __u64 sig_data;
>
> __u64 config3; /* extension of config2 */
> +
> +
> + /*
> + * Defines set of SIMD registers to dump on samples.
> + * The sample_simd_regs_enabled !=0 implies the
> + * set of SIMD registers is used to config all SIMD registers.
> + * If !sample_simd_regs_enabled, sample_regs_XXX may be used to
> + * config some SIMD registers on X86.
> + */
> + union {
> + __u16 sample_simd_regs_enabled;
> + __u16 sample_simd_pred_reg_qwords;
> + };
> + __u32 sample_simd_pred_reg_intr;
> + __u32 sample_simd_pred_reg_user;
> + __u16 sample_simd_vec_reg_qwords;
> + __u64 sample_simd_vec_reg_intr;
> + __u64 sample_simd_vec_reg_user;
> + __u32 __reserved_4;
> };
This is poorly aligned and causes holes.
This:
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d292f96bc06f..2deb8dd0ca37 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -545,6 +545,14 @@ struct perf_event_attr {
__u64 sig_data;
__u64 config3; /* extension of config2 */
+
+ __u16 sample_simd_pred_reg_qwords;
+ __u32 sample_simd_pred_reg_intr;
+ __u32 sample_simd_pred_reg_user;
+ __u16 sample_simd_vec_reg_qwords;
+ __u64 sample_simd_vec_reg_intr;
+ __u64 sample_simd_vec_reg_user;
+ __u32 __reserved_4;
};
/*
results in:
__u64 config3; /* 128 8 */
__u16 sample_simd_pred_reg_qwords; /* 136 2 */
/* XXX 2 bytes hole, try to pack */
__u32 sample_simd_pred_reg_intr; /* 140 4 */
__u32 sample_simd_pred_reg_user; /* 144 4 */
__u16 sample_simd_vec_reg_qwords; /* 148 2 */
/* XXX 2 bytes hole, try to pack */
__u64 sample_simd_vec_reg_intr; /* 152 8 */
__u64 sample_simd_vec_reg_user; /* 160 8 */
__u32 __reserved_4; /* 168 4 */
A better layout might be:
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d292f96bc06f..f72707e9df68 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -545,6 +545,15 @@ struct perf_event_attr {
__u64 sig_data;
__u64 config3; /* extension of config2 */
+
+ __u16 sample_simd_pred_reg_qwords;
+ __u16 sample_simd_vec_reg_qwords;
+ __u32 __reserved_4;
+
+ __u32 sample_simd_pred_reg_intr;
+ __u32 sample_simd_pred_reg_user;
+ __u64 sample_simd_vec_reg_intr;
+ __u64 sample_simd_vec_reg_user;
};
/*
such that:
__u64 config3; /* 128 8 */
__u16 sample_simd_pred_reg_qwords; /* 136 2 */
__u16 sample_simd_vec_reg_qwords; /* 138 2 */
__u32 __reserved_4; /* 140 4 */
__u32 sample_simd_pred_reg_intr; /* 144 4 */
__u32 sample_simd_pred_reg_user; /* 148 4 */
__u64 sample_simd_vec_reg_intr; /* 152 8 */
__u64 sample_simd_vec_reg_user; /* 160 8 */
Powered by blists - more mailing lists