Linux Perf Users
 help / color / mirror / Atom feed
From: Matt Turner <mattst88@gmail.com>
To: Richard Henderson <richard.henderson@linaro.org>,
	 Magnus Lindholm <linmag7@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	 Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	 Namhyung Kim <namhyung@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	 Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
	 Adrian Hunter <adrian.hunter@intel.com>,
	 James Clark <james.clark@linaro.org>
Cc: linux-alpha@vger.kernel.org, linux-kernel@vger.kernel.org,
	 linux-perf-users@vger.kernel.org,
	Matt Turner <mattst88@gmail.com>
Subject: [PATCH v2 4/5] alpha/perf: attach ProfileMe status as PERF_SAMPLE_RAW data
Date: Fri, 30 Oct 2026 00:04:02 -0400	[thread overview]
Message-ID: <20261030-alpha-profileme-v2-4-c702f1c65272@gmail.com> (raw)
In-Reply-To: <20261030-alpha-profileme-v2-0-c702f1c65272@gmail.com>

A ProfileMe sample's PC alone does not say what happened to the profiled
instruction. I_STAT and PCTR_CTL do: whether it trapped and why, was
mispredicted, stalled, or was killed on a wrong path, and what PCTR1
counted during the window.

With PERF_SAMPLE_RAW, attach PMPC, I_STAT and PCTR_CTL to each ProfileMe
sample in a versioned struct alpha_profileme_sample. PMPC is included
because a PALmode PMPC is not the sample's IP. Killed instructions can be
told apart by PM_KILLED_BM and VAL. The 64-bit fields are packed after
the 32-bit version, since the payload follows the 32-bit raw size in the
sample record: they are then 8-byte aligned in the record, which needs
no padding.

Signed-off-by: Matt Turner <mattst88@gmail.com>
---
 arch/alpha/include/asm/perf_event.h      |  2 ++
 arch/alpha/include/uapi/asm/perf_event.h | 31 +++++++++++++++++++++++++++++++
 arch/alpha/kernel/perf_event.c           | 22 +++++++++++++++++++---
 3 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h
index 72536566014a..f498c1d47c07 100644
--- a/arch/alpha/include/asm/perf_event.h
+++ b/arch/alpha/include/asm/perf_event.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ALPHA_PERF_EVENT_H
 #define __ASM_ALPHA_PERF_EVENT_H
 
+#include <uapi/asm/perf_event.h>
+
 /*
  * Software events have no trap frame, so perf_fetch_caller_regs() fills
  * in a zeroed pt_regs. A zero ps already means kernel mode; only pc is
diff --git a/arch/alpha/include/uapi/asm/perf_event.h b/arch/alpha/include/uapi/asm/perf_event.h
new file mode 100644
index 000000000000..aa0eff5a917c
--- /dev/null
+++ b/arch/alpha/include/uapi/asm/perf_event.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_ALPHA_PERF_EVENT_H
+#define _UAPI_ASM_ALPHA_PERF_EVENT_H
+
+#include <linux/types.h>
+
+/*
+ * PERF_SAMPLE_RAW payload of a ProfileMe sample from the cpu PMU.
+ *
+ * pmpc, i_stat and pctr_ctl are the values of the PMPC, I_STAT and
+ * PCTR_CTL registers when the ProfileMe window closed. i_stat holds only
+ * bits 40:30 and pctr_ctl only bits 47:0. See the EV67/EV68 Hardware
+ * Reference Manuals for the field layout.
+ *
+ * In the sample record the payload follows the 32-bit PERF_SAMPLE_RAW
+ * size, so it starts 4 bytes past an 8-byte boundary. The 64-bit fields
+ * are packed after the 32-bit version so that they are 8-byte aligned in
+ * the record and no padding follows the payload.
+ *
+ * Fields may be added to the end in later versions.
+ */
+#define ALPHA_PROFILEME_SAMPLE_VERSION	1
+
+struct alpha_profileme_sample {
+	__u32 version;
+	__u64 pmpc __attribute__((packed));
+	__u64 i_stat __attribute__((packed));
+	__u64 pctr_ctl __attribute__((packed));
+};
+
+#endif /* _UAPI_ASM_ALPHA_PERF_EVENT_H */
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index c7f0ccf8ec80..c9d4b13817bc 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -944,10 +944,13 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 				       struct hw_perf_event *hwc,
 				       struct pt_regs *regs)
 {
+	struct alpha_profileme_sample pm;
+	struct perf_raw_record raw;
 	struct perf_sample_data data;
 	struct pt_regs *pm_regs;
-	unsigned long i_stat, pmpc, ovr, pc, saved_pc, saved_ps;
+	unsigned long pctr_ctl, i_stat, pmpc, ovr, pc, saved_pc, saved_ps;
 
+	pctr_ctl = wrperfmon(PERFMON_CMD_READ, 0);
 	i_stat = wrperfmon(PERFMON_CMD_I_STAT, 0);
 	pmpc = wrperfmon(PERFMON_CMD_PMPC, 0);
 
@@ -982,8 +985,8 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 	 * happens for ITB miss, Istream access violation and interrupt
 	 * redirects, and for instructions inside PALcode. Keep the
 	 * interrupted PC, which for redirects is the instruction that
-	 * trapped. Do the same for a user PMPC in a kernel thread, which has
-	 * no user frame.
+	 * trapped, and report the real PMPC in the raw data. Do the same
+	 * for a user PMPC in a kernel thread, which has no user frame.
 	 */
 	pm_regs = regs;
 	pc = pmpc & EV67_PMPC_PC_MASK;
@@ -1001,6 +1004,19 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 
 	perf_sample_data_init(&data, 0, hwc->last_period);
 
+	pm.version = ALPHA_PROFILEME_SAMPLE_VERSION;
+	pm.pmpc = pmpc;
+	pm.i_stat = i_stat;
+	/* PALcode sign-extends bit 47 of PCTR_CTL. */
+	pm.pctr_ctl = pctr_ctl & GENMASK(47, 0);
+	raw = (struct perf_raw_record) {
+		.frag = {
+			.size = sizeof(pm),
+			.data = &pm,
+		},
+	};
+	perf_sample_save_raw_data(&data, event, &raw);
+
 	if (!alpha_perf_event_set_period(event, hwc, 0))
 		return;
 

-- 
2.55.0


  parent reply	other threads:[~2026-10-30  4:04 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-30  4:03 [PATCH v2 0/5] alpha/perf: add ProfileMe sampling Matt Turner
2026-10-30  4:03 ` [PATCH v2 1/5] alpha/perf: pass PERFMON_CMD_LOGGING_ALL to the logging options call Matt Turner
2026-10-30  4:07   ` sashiko-bot
2026-10-30  4:04 ` [PATCH v2 2/5] alpha/perf: add sysfs format and event attributes Matt Turner
2026-10-30  4:07   ` sashiko-bot
2026-10-30  4:04 ` [PATCH v2 3/5] alpha/perf: implement ProfileMe sampling Matt Turner
2026-10-30  4:04 ` Matt Turner [this message]
2026-10-30  4:10   ` [PATCH v2 4/5] alpha/perf: attach ProfileMe status as PERF_SAMPLE_RAW data sashiko-bot
2026-10-30  4:04 ` [PATCH v2 5/5] alpha/perf: optionally randomize the ProfileMe sampling interval Matt Turner
2026-10-30  4:11   ` sashiko-bot

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=20261030-alpha-profileme-v2-4-c702f1c65272@gmail.com \
    --to=mattst88@gmail.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=irogers@google.com \
    --cc=james.clark@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linmag7@gmail.com \
    --cc=linux-alpha@vger.kernel.org \
    --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=richard.henderson@linaro.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