diff options
Diffstat (limited to 'tools/perf')
-rw-r--r-- | tools/perf/Makefile.config | 1 | ||||
-rw-r--r-- | tools/perf/Makefile.perf | 3 | ||||
-rw-r--r-- | tools/perf/arch/arm/util/pmu.c | 2 | ||||
-rw-r--r-- | tools/perf/arch/x86/include/arch-tests.h | 1 | ||||
-rw-r--r-- | tools/perf/arch/x86/tests/Build | 1 | ||||
-rw-r--r-- | tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c | 71 | ||||
-rw-r--r-- | tools/perf/arch/x86/tests/arch-tests.c | 2 | ||||
-rw-r--r-- | tools/perf/builtin-ftrace.c | 2 | ||||
-rw-r--r-- | tools/perf/trace/beauty/include/linux/socket.h | 1 | ||||
-rw-r--r-- | tools/perf/trace/beauty/msg_flags.c | 6 | ||||
-rw-r--r-- | tools/perf/util/Build | 2 | ||||
-rw-r--r-- | tools/perf/util/arm-spe-decoder/arm-spe-decoder.c | 2 | ||||
-rw-r--r-- | tools/perf/util/bpf_skel/sample_filter.bpf.c | 4 | ||||
-rw-r--r-- | tools/perf/util/cs-etm.h | 13 | ||||
-rw-r--r-- | tools/perf/util/evsel.c | 1 | ||||
-rw-r--r-- | tools/perf/util/evsel.h | 6 | ||||
-rw-r--r-- | tools/perf/util/symbol-elf.c | 27 |
17 files changed, 129 insertions, 16 deletions
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 70268442f7ee..a794d9eca93d 100644 --- a/tools/perf/Makefile.config +++ b/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)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1593c5dcaa9e..f48794816d82 100644 --- a/tools/perf/Makefile.perf +++ b/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 $< > $@ diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5..a9623b128ece 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 902e9ea9b99e..93d3b8877baa 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -11,6 +11,7 @@ int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest); int test__bp_modify(struct test_suite *test, int subtest); int test__x86_sample_parsing(struct test_suite *test, int subtest); +int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest); extern struct test_suite *arch_tests[]; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 6f4e8636c3bf..fd02d8181718 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ perf-y += arch-tests.o perf-y += sample-parsing.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-test.o perf-$(CONFIG_X86_64) += bp-modify.o +perf-y += amd-ibs-via-core-pmu.o diff --git a/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c new file mode 100644 index 000000000000..2902798ca5c1 --- /dev/null +++ b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arch-tests.h" +#include "linux/perf_event.h" +#include "tests/tests.h" +#include "pmu.h" +#include "pmus.h" +#include "../perf-sys.h" +#include "debug.h" + +#define NR_SUB_TESTS 5 + +static struct sub_tests { + int type; + unsigned long config; + bool valid; +} sub_tests[NR_SUB_TESTS] = { + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, true }, + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, false }, + { PERF_TYPE_RAW, 0x076, true }, + { PERF_TYPE_RAW, 0x0C1, true }, + { PERF_TYPE_RAW, 0x012, false }, +}; + +static int event_open(int type, unsigned long config) +{ + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(struct perf_event_attr)); + attr.type = type; + attr.size = sizeof(struct perf_event_attr); + attr.config = config; + attr.disabled = 1; + attr.precise_ip = 1; + attr.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr.sample_period = 100000; + + return sys_perf_event_open(&attr, -1, 0, -1, 0); +} + +int test__amd_ibs_via_core_pmu(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_pmu *ibs_pmu; + int ret = TEST_OK; + int fd, i; + + if (list_empty(&pmus)) + perf_pmu__scan(NULL); + + ibs_pmu = perf_pmu__find("ibs_op"); + if (!ibs_pmu) + return TEST_SKIP; + + for (i = 0; i < NR_SUB_TESTS; i++) { + fd = event_open(sub_tests[i].type, sub_tests[i].config); + pr_debug("type: 0x%x, config: 0x%lx, fd: %d - ", sub_tests[i].type, + sub_tests[i].config, fd); + if ((sub_tests[i].valid && fd == -1) || + (!sub_tests[i].valid && fd > 0)) { + pr_debug("Fail\n"); + ret = TEST_FAIL; + } else { + pr_debug("Pass\n"); + } + + if (fd > 0) + close(fd); + } + + return ret; +} diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index aae6ea0fe52b..b5c85ab8d92e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -22,6 +22,7 @@ struct test_suite suite__intel_pt = { DEFINE_SUITE("x86 bp modify", bp_modify); #endif DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); +DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu); struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -35,5 +36,6 @@ struct test_suite *arch_tests[] = { &suite__bp_modify, #endif &suite__x86_sample_parsing, + &suite__amd_ibs_via_core_pmu, NULL, }; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6..f9906f52e4fa 100644 --- a/tools/perf/builtin-ftrace.c +++ b/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), }; diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 13c3a237b9c9..3bef212a24d7 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -318,7 +318,6 @@ struct ucred { #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */ -#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */ diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c index ea68db08b8e7..aa9934020232 100644 --- a/tools/perf/trace/beauty/msg_flags.c +++ b/tools/perf/trace/beauty/msg_flags.c @@ -8,8 +8,8 @@ #ifndef MSG_WAITFORONE #define MSG_WAITFORONE 0x10000 #endif -#ifndef MSG_SENDPAGE_NOTLAST -#define MSG_SENDPAGE_NOTLAST 0x20000 +#ifndef MSG_SPLICE_PAGES +#define MSG_SPLICE_PAGES 0x8000000 #endif #ifndef MSG_FASTOPEN #define MSG_FASTOPEN 0x20000000 @@ -50,7 +50,7 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, P_MSG_FLAG(NOSIGNAL); P_MSG_FLAG(MORE); P_MSG_FLAG(WAITFORONE); - P_MSG_FLAG(SENDPAGE_NOTLAST); + P_MSG_FLAG(SPLICE_PAGES); P_MSG_FLAG(FASTOPEN); P_MSG_FLAG(CMSG_CLOEXEC); #undef P_MSG_FLAG diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f2719..f9df1df1eec0 100644 --- a/tools/perf/util/Build +++ b/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 diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index f3918f290df5..ba807071d3c1 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -51,7 +51,7 @@ static u64 arm_spe_calc_ip(int index, u64 payload) * (bits [63:56]) is assigned as top-byte tag; so we only can * retrieve address value from bits [55:0]. * - * According to Documentation/arm64/memory.rst, if detects the + * According to Documentation/arch/arm64/memory.rst, if detects the * specific pattern in bits [55:52] of payload which falls in * the kernel space, should fixup the top byte and this allows * perf tool to parse DSO symbol for data address correctly. diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed..fb94f5280626 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/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; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b34..ecca40787ac9 100644 --- a/tools/perf/util/cs-etm.h +++ b/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); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 2f5910b31fa9..c2dbb5647e75 100644 --- a/tools/perf/util/evsel.c +++ b/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); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index df8928745fc6..0f54f28a69c2 100644 --- a/tools/perf/util/evsel.h +++ b/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_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc52265..63882a4db5c7 100644 --- a/tools/perf/util/symbol-elf.c +++ b/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; |