[PATCH 7/7] perf mem record: Use the IBS swfilt filter when available

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

IBS events with exclude_{user,kernel} bits, as used for per-thread
recording when kernel samples are not allowed, are rejected by the
kernel on hardware without the privilege filter, so per-thread 'perf mem
record' fails on AMD:

  $ perf mem record -o /dev/null -- true
  Error:
  Failure to open event 'ibs_op/ldlat=0/u' on PMU 'ibs_op' which will be removed.
  Invalid event (ibs_op/ldlat=0/u) in per-thread mode, enable system wide with '-a'.

Kernel v6.14 added swfilt, a software privilege filter exposed as the
'swfilt' format term, making those events usable per-thread:

  $ perf record -e ibs_op/ldlat=0,swfilt=1/ -- true

Give the ibs_op memory events extra tables with the swfilt term in the
event names, selected in perf_pmu__arch_init() when the PMU exposes the
term, keeping the names that need system wide mode otherwise, with the
knowledge that IBS needs this staying in the arch code: the generic
mem-events table and name builder don't know about it.  The variant is
used even for records that end up without exclude bits: 'perf record'
adds those bits itself when the first open fails, after the name was
built, and that retry needs the term.  With the term in the event name,
the per-thread 'perf mem record' done by the 'data type profiling' shell
test works on AMD kernels with swfilt, so the skip 29f320d2 added to it
no longer triggers there, and the 'Test data symbol' shell test adjusts
its event regex for the added term.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/mem-events.c      | 24 ++++++++++++++++++++++
 tools/perf/arch/x86/util/mem-events.h      |  2 ++
 tools/perf/arch/x86/util/pmu.c             | 10 +++++++--
 tools/perf/tests/shell/test_data_symbol.sh |  6 ++++--
 tools/perf/util/mem-events.c               | 11 ++++++----
 5 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index b38f519020ff8c6f..2052750cd707c7e5 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -21,14 +21,38 @@ struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,			NULL,				NULL,		false,	0),
 };
 
+/*
+ * IBS events with exclude_{user,kernel} bits set, as used by perf to
+ * record per-thread when kernel samples are not allowed, are rejected
+ * by the kernel on hardware without the privilege filter unless the
+ * swfilt software filter is used, so there are extra sets of tables
+ * with the swfilt term in the event names, selected in
+ * perf_pmu__arch_init() when the PMU exposes the term.  The term is not
+ * conditional on the event already having exclude bits: perf record
+ * adds those bits itself when the first open fails with EACCES on an
+ * unprivileged setup, after the name was built, and that retry only
+ * succeeds with the term in it.
+ */
 struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,		NULL,		NULL,	false,	0),
 	E(NULL,		NULL,		NULL,	false,	0),
 	E("mem-ldst",	"%s//",		NULL,	false,	0),
 };
 
+struct perf_mem_event perf_mem_events_amd_swfilt[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/swfilt=1/",	NULL,	false,	0),
+};
+
 struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,		NULL,		NULL,	false,	0),
 	E(NULL,		NULL,		NULL,	false,	0),
 	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
 };
+
+struct perf_mem_event perf_mem_events_amd_ldlat_swfilt[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,			NULL,	false,	0),
+	E(NULL,		NULL,			NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u,swfilt=1/",	NULL,	true,	0),
+};
diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h
index 11e09a256f5bb084..f707de38037017c1 100644
--- a/tools/perf/arch/x86/util/mem-events.h
+++ b/tools/perf/arch/x86/util/mem-events.h
@@ -6,6 +6,8 @@ extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
 extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
 
 extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_swfilt[PERF_MEM_EVENTS__MAX];
 extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat_swfilt[PERF_MEM_EVENTS__MAX];
 
 #endif /* _X86_MEM_EVENTS_H */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 2c24ef3140da5e9b..fd4491fda117e51a 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -333,6 +333,7 @@ static void uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha
 void perf_pmu__arch_init(struct perf_pmu *pmu)
 {
 	struct perf_pmu_caps *ldlat_cap;
+	bool swfilt_format;
 
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
 		pmu->auxtrace = true;
@@ -348,7 +349,10 @@ void perf_pmu__arch_init(struct perf_pmu *pmu)
 		if (strcmp(pmu->name, "ibs_op"))
 			return;
 
-		pmu->mem_events = perf_mem_events_amd;
+		swfilt_format = perf_pmu__has_format(pmu, "swfilt");
+		pmu->mem_events = swfilt_format ?
+				  perf_mem_events_amd_swfilt :
+				  perf_mem_events_amd;
 
 		if (!perf_pmu__caps_parse(pmu))
 			return;
@@ -358,7 +362,9 @@ void perf_pmu__arch_init(struct perf_pmu *pmu)
 			return;
 
 		perf_mem_events__loads_ldlat = 0;
-		pmu->mem_events = perf_mem_events_amd_ldlat;
+		pmu->mem_events = swfilt_format ?
+				  perf_mem_events_amd_ldlat_swfilt :
+				  perf_mem_events_amd_ldlat;
 	} else {
 		if (pmu->is_core) {
 			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index d61b5659a46d9a77..52c837fddb639595 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -65,15 +65,17 @@ if (($is_amd >= 1)); then
 	# --ldlat on AMD:
 	# o Zen4 and earlier uarch does not support ldlat
 	# o Even on supported platforms, it's disabled (--ldlat=0) by default.
+	# o Kernels with the swfilt term add it even when ldlat is not
+	#   supported, so only check ldlat when the term is present.
 	ldlat=${BASH_REMATCH[1]}
-	if [[ -n $ldlat ]]; then
+	if [[ $ldlat == *ldlat=* ]]; then
 		if ! [[ "$ldlat" =~ ldlat=0 ]]; then
 			echo "ERROR: ldlat not initialized to 0?"
 			exit 1
 		fi
 
 		mem_events="$(perf mem record -v --ldlat=150 -e list 2>&1)"
-		if ! [[ "$mem_events" =~ ^mem-ldst.*ibs_op/ldlat=150/.*available ]]; then
+		if ! [[ "$mem_events" =~ ^mem-ldst.*ibs_op/ldlat=150[,/].*available ]]; then
 			echo "ERROR: --ldlat not honored?"
 			exit 1
 		fi
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 0b49fce251fcc184..0b07011939d7d7c3 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -82,6 +82,7 @@ static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i,
 					     char *buf, size_t buf_size)
 {
 	struct perf_mem_event *e;
+	const char *name;
 
 	if (i >= PERF_MEM_EVENTS__MAX || !pmu)
 		return NULL;
@@ -90,24 +91,26 @@ static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i,
 	if (!e || !e->name)
 		return NULL;
 
+	name = e->name;
+
 	if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) {
 		if (e->ldlat) {
 			if (!e->aux_event) {
 				/* ARM and Most of Intel */
 				scnprintf(buf, buf_size,
-					  e->name, pmu->name,
+					  name, pmu->name,
 					  perf_mem_events__loads_ldlat);
 			} else {
 				/* Intel with mem-loads-aux event */
 				scnprintf(buf, buf_size,
-					  e->name, pmu->name, pmu->name,
+					  name, pmu->name, pmu->name,
 					  perf_mem_events__loads_ldlat);
 			}
 		} else {
 			if (!e->aux_event) {
 				/* AMD and POWER */
 				scnprintf(buf, buf_size,
-					  e->name, pmu->name);
+					  name, pmu->name);
 			} else {
 				return NULL;
 			}
@@ -117,7 +120,7 @@ static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i,
 
 	if (i == PERF_MEM_EVENTS__STORE) {
 		scnprintf(buf, buf_size,
-			  e->name, pmu->name);
+			  name, pmu->name);
 		return buf;
 	}
 
-- 
2.53.0