[PATCH 6/6] perf mem record: Use the IBS swfilt filter when available

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>

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

  $ perf mem record -o /dev/null -- true
  Failure to open event 'ibs_op/ldlat=0/u' on PMU 'ibs_op' which will be removed.

Kernel v6.14 added swfilt, a software privilege filter exposed as the
'swfilt' format term, making those events usable per-thread.  Give the
ibs_op memory events extra tables with the term, selected in
perf_pmu__arch_init() when the PMU exposes it, keeping the names that
need system wide mode otherwise; the knowledge that IBS needs this
stays in the arch code.

Suggested-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Suggested-by: Ravi Bangoria <ravi.bangoria@xxxxxxx>
Reviewed-by: Ravi Bangoria <ravi.bangoria@xxxxxxx>
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/arch/x86/util/mem-events.c      | 17 +++++++++++++++++
 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 ++++--
 4 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index b38f519020ff8c6f..8b46c8a1ce4520d0 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -21,14 +21,31 @@ 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 are rejected on hardware
+ * without the privilege filter unless swfilt is used: the extra tables
+ * carry the term, selected when the PMU exposes 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
-- 
2.53.0