Merge tag 'perf-tools-fixes-for-v6.0-2022-09-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fail the 'perf test record' entry on error, fixing a regression where
   just setup stuff like allocating memory and not the actual things
   being tested failed.

 - Fixup disabling of -Wdeprecated-declarations for the python scripting
   engine, the previous attempt had a brown paper bag thinko.

 - Fix branch stack sampling test to include sanity check for branch
   filter on PowerPC.

 - Update is_ignored_symbol function to match the kernel ignored list,
   fixing running the 'perf test' entry that compares resolving symbols
   from kallsyms to resolving from vmlinux.

 - Augment the data source type with ARM's neoverse_spe list, the
   previous code was limited in its search resolving the data source.

 - Fix some clang 5 variable set but unused cases.

 - Get a perf cgroup more portably in BPF as the
   __builtin_preserve_enum_value builtin is not available in older
   versions of clang. In those cases we can forgo BPF's CO-RE (Compile
   Once, Run Everywhere).

 - More Fixes for Intel's hybrid CPU model.

* tag 'perf-tools-fixes-for-v6.0-2022-09-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf build: Fixup disabling of -Wdeprecated-declarations for the python scripting engine
  perf tests mmap-basic: Remove unused variable to address clang 15 warning
  perf parse-events: Ignore clang 15 warning about variable set but unused in bison produced code
  perf tests record: Fail the test if the 'errs' counter is not zero
  perf test: Fix test case 87 ("perf record tests") for hybrid systems
  perf arm-spe: augment the data source type with neoverse_spe list
  perf tests vmlinux-kallsyms: Update is_ignored_symbol function to match the kernel ignored list
  perf tests powerpc: Fix branch stack sampling test to include sanity check for branch filter
  perf parse-events: Remove "not supported" hybrid cache events
  perf print-events: Fix "perf list" can not display the PMU prefix for some hybrid cache events
  perf tools: Get a perf cgroup more portably in BPF

14 files changed, 92 insertions, 58 deletions

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index dfb6173b2a827f..9e9a2b67de1998 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 
 	for (i = 0; i < nsyscalls; ++i)
 		for (j = 0; j < expected_nr_events[i]; ++j) {
-			int foo = syscalls[i]();
-			++foo;
+			syscalls[i]();
 		}
 
 	md = &evlist->mmap[0];
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6a001fcfed68e5..4952abe716f318 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -332,7 +332,7 @@ out_delete_evlist:
 out:
 	if (err == -EACCES)
 		return TEST_SKIP;
-	if (err < 0)
+	if (err < 0 || errs != 0)
 		return TEST_FAIL;
 	return TEST_OK;
 }
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 00c7285ce1ac64..301f95427159dd 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -61,7 +61,7 @@ test_register_capture() {
     echo "Register capture test [Skipped missing registers]"
     return
   fi
-  if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \
+  if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \
     -c 1000 --per-thread true 2> /dev/null \
     | perf script -F ip,sym,iregs -i - 2> /dev/null \
     | egrep -q "DI:"
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index c644f94a650021..ec801cffae6bcd 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then
 fi
 
 # skip the test if the hardware doesn't support branch stack sampling
-perf record -b -o- -B true > /dev/null 2>&1 || exit 2
+# and if the architecture doesn't support filter types: any,save_type,u
+perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2
 
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 4fd8d703ff19ee..8ab035b55875c7 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type)
 	/* Symbol names that begin with the following are ignored.*/
 	static const char * const ignored_prefixes[] = {
 		"$",			/* local symbols for ARM, MIPS, etc. */
-		".LASANPC",		/* s390 kasan local symbols */
+		".L",			/* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */
 		"__crc_",		/* modversions */
 		"__efistub_",		/* arm64 EFI stub namespace */
-		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
+		"__kvm_nvhe_$",		/* arm64 local symbols in non-VHE KVM namespace */
+		"__kvm_nvhe_.L",	/* arm64 local symbols in non-VHE KVM namespace */
 		"__AArch64ADRPThunk_",	/* arm64 lld */
 		"__ARMV5PILongThunk_",	/* arm lld */
 		"__ARMV7PILongThunk_",
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9dfae1bda9cc3e..485e1a3431652a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -269,7 +269,7 @@ CFLAGS_expr-flex.o          += $(flex_flags)
 bison_flags := -DYYENABLE_NLS=0
 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
 ifeq ($(BISON_GE_35),1)
-  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum
+  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option
 else
   bison_flags += -w
 endif
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 22dcfe07e886f9..906476a839e1f5 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -498,7 +498,7 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco
 static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
 {
 	union perf_mem_data_src	data_src = { 0 };
-	bool is_neoverse = is_midr_in_range(midr, neoverse_spe);
+	bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe);
 
 	if (record->op == ARM_SPE_LD)
 		data_src.mem_op = PERF_MEM_OP_LOAD;
diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
index c72f8ad96f7519..9aa8cdd93de4e3 100644
--- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
@@ -48,6 +48,7 @@ const volatile __u32 num_cpus = 1;
 
 int enabled = 0;
 int use_cgroup_v2 = 0;
+int perf_subsys_id = -1;
 
 static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 {
@@ -58,7 +59,15 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 	int level;
 	int cnt;
 
-	cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup);
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
+	cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup);
 	level = BPF_CORE_READ(cgrp, level);
 
 	for (cnt = 0; i < MAX_LEVELS; i++) {
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c4ba2bcf179f44..38e3b287dbb225 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -94,6 +94,8 @@ const volatile bool has_prev_state = false;
 const volatile bool needs_cgroup = false;
 const volatile bool uses_cgroup_v1 = false;
 
+int perf_subsys_id = -1;
+
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
  * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
@@ -119,11 +121,19 @@ static inline __u64 get_cgroup_id(struct task_struct *t)
 {
 	struct cgroup *cgrp;
 
-	if (uses_cgroup_v1)
-		cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup);
-	else
-		cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp);
+	if (!uses_cgroup_v1)
+		return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id);
+
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
 
+	cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup);
 	return BPF_CORE_READ(cgrp, kn, id);
 }
 
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 284f8eabd3b9ab..7c9f9150bad502 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr,
 	 * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
 	 */
 	attr->type = type;
-	attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
+	attr->config = (attr->config & PERF_HW_EVENT_MASK) |
+			((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
 }
 
 static int create_event_hybrid(__u32 config_type, int *idx,
@@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx,
 	__u64 config = attr->config;
 
 	config_hybrid_attr(attr, config_type, pmu->type);
+
+	/*
+	 * Some hybrid hardware cache events are only available on one CPU
+	 * PMU. For example, the 'L1-dcache-load-misses' is only available
+	 * on cpu_core, while the 'L1-icache-loads' is only available on
+	 * cpu_atom. We need to remove "not supported" hybrid cache events.
+	 */
+	if (attr->type == PERF_TYPE_HW_CACHE
+	    && !is_event_supported(attr->type, attr->config))
+		return 0;
+
 	evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id,
 					       pmu, config_terms);
-	if (evsel)
+	if (evsel) {
 		evsel->pmu_name = strdup(pmu->name);
-	else
+		if (!evsel->pmu_name)
+			return -ENOMEM;
+	} else
 		return -ENOMEM;
-
 	attr->type = type;
 	attr->config = config;
 	return 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f05e15acd33fe8..f3b2c2a87456bd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -28,6 +28,7 @@
 #include "util/parse-events-hybrid.h"
 #include "util/pmu-hybrid.h"
 #include "tracepoint.h"
+#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
+bool is_event_supported(u8 type, u64 config)
+{
+	bool ret = true;
+	int open_return;
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
+
+	evsel = evsel__new(&attr);
+	if (evsel) {
+		open_return = evsel__open(evsel, NULL, tmap);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+		evsel__delete(evsel);
+	}
+
+	perf_thread_map__put(tmap);
+	return ret;
+}
+
 const char *event_type(int type)
 {
 	switch (type) {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e6a601d9cd01b..07df7bb7b04200 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -19,6 +19,7 @@ struct option;
 struct perf_pmu;
 
 bool have_tracepoints(struct list_head *evlist);
+bool is_event_supported(u8 type, u64 config);
 
 const char *event_type(int type);
 
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index ba1ab51346854d..c4d5d87fae2f6b 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -22,7 +22,6 @@
 #include "probe-file.h"
 #include "string2.h"
 #include "strlist.h"
-#include "thread_map.h"
 #include "tracepoint.h"
 #include "pfm.h"
 #include "pmu-hybrid.h"
@@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
 	strlist__delete(sdtlist);
 }
 
-static bool is_event_supported(u8 type, unsigned int config)
-{
-	bool ret = true;
-	int open_return;
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = type,
-		.config = config,
-		.disabled = 1,
-	};
-	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
-	if (tmap == NULL)
-		return false;
-
-	evsel = evsel__new(&attr);
-	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
-
-		if (open_return == -EACCES) {
-			/*
-			 * This happens if the paranoid value
-			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
-			 */
-			evsel->core.attr.exclude_kernel = 1;
-			ret = evsel__open(evsel, NULL, tmap) >= 0;
-		}
-		evsel__delete(evsel);
-	}
-
-	perf_thread_map__put(tmap);
-	return ret;
-}
-
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
 	unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index c92326c2233a45..0f5ba28339cf9a 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -3,4 +3,4 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
 CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
 
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations