[PATCH 4/5] alpha/perf: attach ProfileMe status as PERF_SAMPLE_RAW data

[Matt Turner]

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.

Signed-off-by: Matt Turner <mattst88@xxxxxxxxx>
---
 arch/alpha/include/asm/perf_event.h      |  2 ++
 arch/alpha/include/uapi/asm/perf_event.h | 27 +++++++++++++++++++++++++++
 arch/alpha/kernel/perf_event.c           | 21 +++++++++++++++++++--
 3 files changed, 48 insertions(+), 2 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..0cb7d6f3cb15
--- /dev/null
+++ b/arch/alpha/include/uapi/asm/perf_event.h
@@ -0,0 +1,27 @@
+/* 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.
+ *
+ * Fields may be added to the end in later versions.
+ */
+#define ALPHA_PROFILEME_SAMPLE_VERSION	1
+
+struct alpha_profileme_sample {
+	__u32 version;
+	__u32 reserved;
+	__u64 pmpc;
+	__u64 i_stat;
+	__u64 pctr_ctl;
+};
+
+#endif /* _UAPI_ASM_ALPHA_PERF_EVENT_H */
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 24c96feda942..06c9afeb7c05 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -915,10 +915,13 @@ 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;
+	unsigned long pctr_ctl, i_stat, pmpc, ovr;
 
+	pctr_ctl = wrperfmon(PERFMON_CMD_READ, 0);
 	i_stat = wrperfmon(PERFMON_CMD_I_STAT, 0);
 	pmpc = wrperfmon(PERFMON_CMD_PMPC, 0);
 
@@ -941,7 +944,7 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 	 * perf cannot resolve. That 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.
+	 * instruction that trapped, and report the real PMPC in the raw data.
 	 */
 	pm_regs = *regs;
 	if (!(pmpc & EV67_PMPC_PAL)) {
@@ -955,6 +958,20 @@ 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.reserved = 0;
+	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))
 		perf_event_overflow(event, &data, &pm_regs);
 }

-- 
2.55.0