perf tools fixes for v6.4: 2nd batch

- Fix BPF CO-RE naming convention for checking the availability of fields on
   'union perf_mem_data_src' on the running kernel.
 
 - Remove the use of llvm-strip on BPF skel object files, not needed, fixes a
   build breakage when the llvm package, that contains it in most distros, isn't
   installed.
 
 - Fix tools that use both evsel->{bpf_counter_list,bpf_filters}, removing them from a
   union.
 
 - Remove extra "--" from the 'perf ftrace latency' --use-nsec option,
   previously it was working only when using the '-n' alternative.
 
 - Don't stop building when both binutils-devel and a C++ compiler isn't
   available to compile the alternative C++ demangle support code, disable that
   feature instead.
 
 - Sync the linux/in.h and coresight-pmu.h header copies with the kernel sources.
 
 - Fix relative include path to cs-etm.h.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCZHY9egAKCRCyPKLppCJ+
 JzbBAQCv+i0j/+garWKCTSe33yztzQGS6jxu/YzQrbQO427DMwEA9fJgp/r2OQC5
 wMM5gng2fPaHe6Hs4cnPL/SzMxLC2gQ=
 =fHRR
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-fixes-for-v6.4-2-2023-05-30' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix BPF CO-RE naming convention for checking the availability of
   fields on 'union perf_mem_data_src' on the running kernel

 - Remove the use of llvm-strip on BPF skel object files, not needed,
   fixes a build breakage when the llvm package, that contains it in
   most distros, isn't installed

 - Fix tools that use both evsel->{bpf_counter_list,bpf_filters},
   removing them from a union

 - Remove extra "--" from the 'perf ftrace latency' --use-nsec option,
   previously it was working only when using the '-n' alternative

 - Don't stop building when both binutils-devel and a C++ compiler isn't
   available to compile the alternative C++ demangle support code,
   disable that feature instead

 - Sync the linux/in.h and coresight-pmu.h header copies with the kernel
   sources

 - Fix relative include path to cs-etm.h

* tag 'perf-tools-fixes-for-v6.4-2-2023-05-30' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf evsel: Separate bpf_counter_list and bpf_filters, can be used at the same time
  tools headers UAPI: Sync the linux/in.h with the kernel sources
  perf cs-etm: Copy kernel coresight-pmu.h header
  perf bpf: Do not use llvm-strip on BPF binary
  perf build: Don't compile demangle-cxx.cpp if not necessary
  perf arm: Fix include path to cs-etm.h
  perf bpf filter: Fix a broken perf sample data naming for BPF CO-RE
  perf ftrace latency: Remove unnecessary "--" from --use-nsec option

tools/include/linux/coresight-pmu.h

@@ -21,19 +21,6 @@
  */
 #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu)  (0x10 + (cpu * 2))
 
-/* CoreSight trace ID is currently the bottom 7 bits of the value */
-#define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
-
-/*
- * perf record will set the legacy meta data values as unused initially.
- * This allows perf report to manage the decoders created when dynamic
- * allocation in operation.
- */
-#define CORESIGHT_TRACE_ID_UNUSED_FLAG	BIT(31)
-
-/* Value to set for unused trace ID values */
-#define CORESIGHT_TRACE_ID_UNUSED_VAL	0x7F
-
 /*
  * Below are the definition of bit offsets for perf option, and works as
  * arbitrary values for all ETM versions.

tools/include/uapi/linux/in.h

@@ -163,6 +163,7 @@ struct in_addr {
 #define IP_MULTICAST_ALL		49
 #define IP_UNICAST_IF			50
 #define IP_LOCAL_PORT_RANGE		51
+#define IP_PROTOCOL			52
 
 #define MCAST_EXCLUDE	0
 #define MCAST_INCLUDE	1

tools/perf/Makefile.config

@@ -927,6 +927,7 @@ ifndef NO_DEMANGLE
     EXTLIBS += -lstdc++
     CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT
     CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT
+    $(call detected,CONFIG_CXX_DEMANGLE)
   endif
   ifdef BUILD_NONDISTRO
     ifeq ($(filter -liberty,$(EXTLIBS)),)

tools/perf/Makefile.perf

@@ -181,7 +181,6 @@ HOSTCC  ?= gcc
 HOSTLD  ?= ld
 HOSTAR  ?= ar
 CLANG   ?= clang
-LLVM_STRIP ?= llvm-strip
 
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
@@ -1083,7 +1082,7 @@ $(BPFTOOL): | $(SKEL_TMP_OUT)
 
 $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
 	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
-	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@
+	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
 
 $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)
 	$(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@

tools/perf/arch/arm/util/pmu.c

@@ -12,7 +12,7 @@
 #include "arm-spe.h"
 #include "hisi-ptt.h"
 #include "../../../util/pmu.h"
-#include "../cs-etm.h"
+#include "../../../util/cs-etm.h"
 
 struct perf_event_attr
 *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)

tools/perf/builtin-ftrace.c

@@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv)
 	OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf,
 		    "Use BPF to measure function latency"),
 #endif
-	OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec,
+	OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec,
 		    "Use nano-second histogram"),
 	OPT_PARENT(common_options),
 	};

tools/perf/util/Build

@@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o
 
 perf-$(CONFIG_LIBCAP) += cap.o
 
-perf-y += demangle-cxx.o
+perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o
 perf-y += demangle-ocaml.o
 perf-y += demangle-java.o
 perf-y += demangle-rust.o

tools/perf/util/bpf_skel/sample_filter.bpf.c

@@ -25,7 +25,7 @@ struct perf_sample_data___new {
 } __attribute__((preserve_access_index));
 
 /* new kernel perf_mem_data_src definition */
-union perf_mem_data_src__new {
+union perf_mem_data_src___new {
 	__u64 val;
 	struct {
 		__u64   mem_op:5,	/* type of opcode */
@@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
 		if (entry->part == 7)
 			return kctx->data->data_src.mem_blk;
 		if (entry->part == 8) {
-			union perf_mem_data_src__new *data = (void *)&kctx->data->data_src;
+			union perf_mem_data_src___new *data = (void *)&kctx->data->data_src;
 
 			if (bpf_core_field_exists(data->mem_hops))
 				return data->mem_hops;

tools/perf/util/cs-etm.h

@@ -227,6 +227,19 @@ struct cs_etm_packet_queue {
 #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \
 			  sizeof(((struct perf_record_auxtrace_info *)0)->reserved__))
 
+/* CoreSight trace ID is currently the bottom 7 bits of the value */
+#define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
+
+/*
+ * perf record will set the legacy meta data values as unused initially.
+ * This allows perf report to manage the decoders created when dynamic
+ * allocation in operation.
+ */
+#define CORESIGHT_TRACE_ID_UNUSED_FLAG	BIT(31)
+
+/* Value to set for unused trace ID values */
+#define CORESIGHT_TRACE_ID_UNUSED_VAL	0x7F
+
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
 struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu);

tools/perf/util/evsel.c

@@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel,
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->config_terms);
 	INIT_LIST_HEAD(&evsel->bpf_counter_list);
+	INIT_LIST_HEAD(&evsel->bpf_filters);
 	perf_evsel__object.init(evsel);
 	evsel->sample_size = __evsel__sample_size(attr->sample_type);
 	evsel__calc_id_pos(evsel);

tools/perf/util/evsel.h

@@ -151,10 +151,8 @@ struct evsel {
 	 */
 	struct bpf_counter_ops	*bpf_counter_ops;
 
-	union {
+	struct list_head	bpf_counter_list; /* for perf-stat -b */
-		struct list_head	bpf_counter_list; /* for perf-stat -b */
+	struct list_head	bpf_filters; /* for perf-record --filter */
-		struct list_head	bpf_filters; /* for perf-record --filter */
-	};
 
 	/* for perf-stat --use-bpf */
 	int			bperf_leader_prog_fd;

tools/perf/util/symbol-elf.c

@@ -31,6 +31,13 @@
 #include <bfd.h>
 #endif
 
+#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT)
+#ifndef DMGL_PARAMS
+#define DMGL_PARAMS     (1 << 0)  /* Include function args */
+#define DMGL_ANSI       (1 << 1)  /* Include const, volatile, etc */
+#endif
+#endif
+
 #ifndef EM_AARCH64
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
@@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym)
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
 }
 
+/*
+ * Demangle C++ function signature, typically replaced by demangle-cxx.cpp
+ * version.
+ */
+__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused,
+			      bool modifiers __maybe_unused)
+{
+#ifdef HAVE_LIBBFD_SUPPORT
+	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
+
+	return bfd_demangle(NULL, str, flags);
+#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT)
+	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
+
+	return cplus_demangle(str, flags);
+#else
+	return NULL;
+#endif
+}
+
 static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
 	char *demangled = NULL;