diff options
85 files changed, 3804 insertions, 1328 deletions
diff --git a/tools/build/Build b/tools/build/Build deleted file mode 100644 index 76d1a4960973..000000000000 --- a/tools/build/Build +++ /dev/null @@ -1,3 +0,0 @@ -hostprogs := fixdep - -fixdep-y := fixdep.o diff --git a/tools/build/Makefile b/tools/build/Makefile index 17cdf01e29a0..fea3cf647f5b 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -43,12 +43,5 @@ ifneq ($(wildcard $(TMP_O)),) $(Q)$(MAKE) -C feature OUTPUT=$(TMP_O) clean >/dev/null endif -$(OUTPUT)fixdep-in.o: FORCE - $(Q)$(MAKE) $(build)=fixdep - -$(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o - $(QUIET_LINK)$(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ $< - -FORCE: - -.PHONY: FORCE +$(OUTPUT)fixdep: $(srctree)/tools/build/fixdep.c + $(QUIET_CC)$(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ $< diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include index 8dadaa0fbb43..0e4de83400ac 100644 --- a/tools/build/Makefile.include +++ b/tools/build/Makefile.include @@ -1,8 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-only build := -f $(srctree)/tools/build/Makefile.build dir=. obj +# More than just $(Q), we sometimes want to suppress all command output from a +# recursive make -- even the 'up to date' printout. +ifeq ($(V),1) + Q ?= + SILENT_MAKE = +$(Q)$(MAKE) +else + Q ?= @ + SILENT_MAKE = +$(Q)$(MAKE) --silent +endif + fixdep: - $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep fixdep-clean: $(Q)$(MAKE) -C $(srctree)/tools/build clean diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index db5c99318c79..0acb1fc14e19 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -46,5 +46,7 @@ extern char * __must_check skip_spaces(const char *); extern char *strim(char *); +extern void remove_spaces(char *s); + extern void *memchr_inv(const void *start, int c, size_t bytes); #endif /* _TOOLS_LINUX_STRING_H_ */ diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 30745f35d0d2..834fd64c7130 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -69,7 +69,7 @@ char *get_tracing_file(const char *name) { char *file; - if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0) + if (asprintf(&file, "%s%s", tracing_path_mount(), name) < 0) return NULL; return file; diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 0da84cb9e66d..f02725b123b3 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -5,3 +5,4 @@ TAGS tags cscope.* /bpf_helper_defs.h +fixdep diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 2cf892774346..1b22f0f37288 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -108,6 +108,8 @@ MAKEOVERRIDES= all: +OUTPUT ?= ./ +OUTPUT := $(abspath $(OUTPUT))/ export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include @@ -141,7 +143,10 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_GENERATED) +$(SHARED_OBJDIR) $(STATIC_OBJDIR): + $(Q)mkdir -p $@ + +$(BPF_IN_SHARED): force $(BPF_GENERATED) | $(SHARED_OBJDIR) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -151,9 +156,11 @@ $(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(SHARED_OBJDIR) $(SHARED_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_GENERATED) +$(BPF_IN_STATIC): force $(BPF_GENERATED) | $(STATIC_OBJDIR) + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(STATIC_OBJDIR) $(STATIC_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -263,7 +270,7 @@ install_pkgconfig: $(PC_FILE) install: install_lib install_pkgconfig install_headers -clean: +clean: fixdep-clean $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ diff --git a/tools/lib/perf/.gitignore b/tools/lib/perf/.gitignore new file mode 100644 index 000000000000..0f5b4af63f62 --- /dev/null +++ b/tools/lib/perf/.gitignore @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +libperf.pc +libperf.so.* +tests-shared +tests-static diff --git a/tools/lib/string.c b/tools/lib/string.c index 8b6892f959ab..3126d2cff716 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -153,6 +153,19 @@ char *strim(char *s) return skip_spaces(s); } +/* + * remove_spaces - Removes whitespaces from @s + */ +void remove_spaces(char *s) +{ + char *d = s; + + do { + while (*d == ' ') + ++d; + } while ((*s++ = *d++)); +} + /** * strreplace - Replace all occurrences of character in string. * @s: The string to operate on. diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index b87213263a5e..59b09f280e49 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -76,7 +76,7 @@ include $(srctree)/tools/build/Makefile.include all: fixdep $(LIBFILE) -$(SUBCMD_IN): FORCE +$(SUBCMD_IN): fixdep FORCE @$(MAKE) $(build)=libsubcmd $(LIBFILE): $(SUBCMD_IN) diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index b95524bea021..156c5f37b051 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -165,6 +165,9 @@ include::itrace.txt[] --type-stat:: Show stats for the data type annotation. +--skip-empty:: + Do not display empty (or dummy) events. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index d780b93fcf87..eaec8253be68 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -9,7 +9,7 @@ perf-ftrace - simple wrapper for kernel's ftrace functionality SYNOPSIS -------- [verse] -'perf ftrace' {trace|latency} <command> +'perf ftrace' {trace|latency|profile} <command> DESCRIPTION ----------- @@ -23,6 +23,9 @@ kernel's ftrace infrastructure. 'perf ftrace latency' calculates execution latency of a given function (optionally with BPF) and display it as a histogram. + 'perf ftrace profile' show a execution profile for each function including + total, average, max time and the number of calls. + The following options apply to perf ftrace. COMMON OPTIONS @@ -125,6 +128,7 @@ OPTIONS for 'perf ftrace trace' - verbose - Show process names, PIDs, timestamps, etc. - thresh=<n> - Setup trace duration threshold in microseconds. - depth=<n> - Set max depth for function graph tracer to follow. + - tail - Print function name at the end. OPTIONS for 'perf ftrace latency' @@ -145,6 +149,48 @@ OPTIONS for 'perf ftrace latency' Use nano-second instead of micro-second as a base unit of the histogram. +OPTIONS for 'perf ftrace profile' +--------------------------------- + +-T:: +--trace-funcs=:: + Set function filter on the given function (or a glob pattern). + Multiple functions can be given by using this option more than once. + The function argument also can be a glob pattern. It will be passed + to 'set_ftrace_filter' in tracefs. + +-N:: +--notrace-funcs=:: + Do not trace functions given by the argument. Like -T option, this + can be used more than once to specify multiple functions (or glob + patterns). It will be passed to 'set_ftrace_notrace' in tracefs. + +-G:: +--graph-funcs=:: + Set graph filter on the given function (or a glob pattern). This is + useful to trace for functions executed from the given function. This + can be used more than once to specify multiple functions. It will be + passed to 'set_graph_function' in tracefs. + +-g:: +--nograph-funcs=:: + Set graph notrace filter on the given function (or a glob pattern). + Like -G option, this is useful for the function_graph tracer only and + disables tracing for function executed from the given function. This + can be used more than once to specify multiple functions. It will be + passed to 'set_graph_notrace' in tracefs. + +-m:: +--buffer-size:: + Set the size of per-cpu tracing buffer, <size> is expected to + be a number with appended unit character - B/K/M/G. + +-s:: +--sort=:: + Sort the result by the given field. Available values are: + total, avg, max, count, name. Default is 'total'. + + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-trace[1] diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 47456b212e99..8a1bd9ff0f86 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -28,15 +28,8 @@ and kernel support is required. See linkperf:perf-arm-spe[1] for a setup guide. Due to the statistical nature of SPE sampling, not every memory operation will be sampled. -OPTIONS -------- -<command>...:: - Any command you can specify in a shell. - --i:: ---input=<file>:: - Input file name. - +COMMON OPTIONS +-------------- -f:: --force:: Don't do ownership validation @@ -45,24 +38,9 @@ OPTIONS --type=<type>:: Select the memory operation type: load or store (default: load,store) --D:: ---dump-raw-samples:: - Dump the raw decoded samples on the screen in a format that is easy to parse with - one sample per line. - --x:: ---field-separator=<separator>:: - Specify the field separator used when dump raw samples (-D option). By default, - The separator is the space character. - --C:: ---cpu=<cpu>:: - Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a - comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default - is to monitor all CPUS. --U:: ---hide-unresolved:: - Only display entries resolved to a symbol. +-v:: +--verbose:: + Be more verbose (show counter open errors, etc) -p:: --phys-data:: @@ -73,6 +51,9 @@ OPTIONS RECORD OPTIONS -------------- +<command>...:: + Any command you can specify in a shell. + -e:: --event <event>:: Event selector. Use 'perf mem record -e list' to list available events. @@ -85,14 +66,65 @@ RECORD OPTIONS --all-user:: Configure all used events to run in user space. --v:: ---verbose:: - Be more verbose (show counter open errors, etc) - --ldlat <n>:: Specify desired latency for loads event. Supported on Intel and Arm64 processors only. Ignored on other archs. +REPORT OPTIONS +-------------- +-i:: +--input=<file>:: + Input file name. + +-C:: +--cpu=<cpu>:: + Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a + comma-separated list with no space: 0,1. Ranges of CPUs are specified with - + like 0-2. Default is to monitor all CPUS. + +-D:: +--dump-raw-samples:: + Dump the raw decoded samples on the screen in a format that is easy to parse with + one sample per line. + +-s:: +--sort=<key>:: + Group result by given key(s) - multiple keys can be specified + in CSV format. The keys are specific to memory samples are: + symbol_daddr, symbol_iaddr, dso_daddr, locked, tlb, mem, snoop, + dcacheline, phys_daddr, data_page_size, blocked. + + - symbol_daddr: name of data symbol being executed on at the time of sample + - symbol_iaddr: name of code symbol being executed on at the time of sample + - dso_daddr: name of library or module containing the data being executed + on at the time of the sample + - locked: whether the bus was locked at the time of the sample + - tlb: type of tlb access for the data at the time of the sample + - mem: type of memory access for the data at the time of the sample + - snoop: type of snoop (if any) for the data at the time of the sample + - dcacheline: the cacheline the data address is on at the time of the sample + - phys_daddr: physical address of data being executed on at the time of sample + - data_page_size: the data page size of data being executed on at the time of sample + - blocked: reason of blocked load access for the data at the time of the sample + + And the default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat. + +-T:: +--type-profile:: + Show data-type profile result instead of code symbols. This requires + the debug information and it will change the default sort keys to: + mem, snoop, tlb, type. + +-U:: +--hide-unresolved:: + Only display entries resolved to a symbol. + +-x:: +--field-separator=<separator>:: + Specify the field separator used when dump raw samples (-D option). By default, + The separator is the space character. + In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index d6532ed97c02..41e36b4dc765 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -828,6 +828,11 @@ filtered through the mask provided by -C option. only, as of now. So the applications built without the frame pointer might see bogus addresses. +--setup-filter=<action>:: + Prepare BPF filter to be used by regular users. The action should be + either "pin" or "unpin". The filter can be used after it's pinned. + + include::intel-hybrid.txt[] SEE ALSO diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 75f3f6e0a231..816d5d84816b 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -51,8 +51,14 @@ else override DEBUG = 0 endif +ifeq ($(JOBS),1) + BUILD_TYPE := sequential +else + BUILD_TYPE := parallel +endif + define print_msg - @printf ' BUILD: Doing '\''make \033[33m-j'$(JOBS)'\033[m'\'' parallel build\n' + @printf ' BUILD: Doing '\''make \033[33m-j'$(JOBS)'\033[m'\'' $(BUILD_TYPE) build\n' endef define make diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index f8148db5fc38..72534bb72d43 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1277,6 +1277,8 @@ clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $( $(OUTPUT)util/intel-pt-decoder/inat-tables.c \ $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ $(OUTPUT)pmu-events/pmu-events.c \ + $(OUTPUT)pmu-events/test-empty-pmu-events.c \ + $(OUTPUT)pmu-events/empty-pmu-events.log \ $(OUTPUT)pmu-events/metric_test.log \ $(OUTPUT)$(fadvise_advice_array) \ $(OUTPUT)$(fsconfig_arrays) \ diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 1c9541d01722..57dc94a6e38c 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -23,16 +23,19 @@ void perf_pmu__arch_init(struct perf_pmu *pmu) #ifdef HAVE_AUXTRACE_SUPPORT if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { /* add ETM default config here */ + pmu->auxtrace = true; pmu->selectable = true; pmu->perf_event_attr_init_default = cs_etm_get_default_config; #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { + pmu->auxtrace = true; pmu->selectable = true; pmu->is_uncore = false; pmu->perf_event_attr_init_default = arm_spe_pmu_default_config; if (strstarts(pmu->name, "arm_spe_")) pmu->mem_events = perf_mem_events_arm; } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { + pmu->auxtrace = true; pmu->selectable = true; #endif } diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 4af0c3a0f86e..f86d9f4798bd 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -11,7 +11,8 @@ struct arm64_annotate { static int arm64_mov__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, - struct map_symbol *ms __maybe_unused) + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *endptr; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 0b52e67edb3b..d59f6ca499f2 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/string.h> #include <linux/zalloc.h> #include <time.h> @@ -132,32 +133,66 @@ static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu) return sample_period; } +static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) +{ + u64 bit; + + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = arm_spe_pmu__sample_period(evsel->pmu); + evsel->needs_auxtrace_mmap = true; + + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace event + * must come first. + */ + evlist__to_front(evsel->evlist, evsel); + + /* + * In the case of per-cpu mmaps, sample CPU for AUX event; + * also enable the timestamp tracing for samples correlation. + */ + if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) { + evsel__set_sample_bit(evsel, CPU); + evsel__set_config_if_unset(evsel->pmu, evsel, "ts_enable", 1); + } + + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(evsel, DATA_SRC); + + /* + * The PHYS_ADDR flag does not affect the driver behaviour, it is used to + * inform that the resulting output's SPE samples contain physical addresses + * where applicable. + */ + bit = perf_pmu__format_bits(evsel->pmu, "pa_enable"); + if (evsel->core.attr.config & bit) + evsel__set_sample_bit(evsel, PHYS_ADDR); +} + static int arm_spe_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) { struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); - struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; - struct evsel *evsel, *arm_spe_evsel = NULL; + struct evsel *evsel, *tmp; struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; - u64 bit; sper->evlist = evlist; evlist__for_each_entry(evlist, evsel) { - if (evsel->core.attr.type == arm_spe_pmu->type) { - if (arm_spe_evsel) { - pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n"); + if (evsel__is_aux_event(evsel)) { + if (!strstarts(evsel->pmu_name, ARM_SPE_PMU_NAME)) { + pr_err("Found unexpected auxtrace event: %s\n", + evsel->pmu_name); return -EINVAL; } - evsel->core.attr.freq = 0; - evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu); - evsel->needs_auxtrace_mmap = true; - arm_spe_evsel = evsel; opts->full_auxtrace = true; } } @@ -222,37 +257,11 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, opts->auxtrace_snapshot_size); - /* - * To obtain the auxtrace buffer file descriptor, the auxtrace event - * must come first. - */ - evlist__to_front(evlist, arm_spe_evsel); - - /* - * In the case of per-cpu mmaps, sample CPU for AUX event; - * also enable the timestamp tracing for samples correlation. - */ - if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) { - evsel__set_sample_bit(arm_spe_evsel, CPU); - evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel, - "ts_enable", 1); + evlist__for_each_entry_safe(evlist, tmp, evsel) { + if (evsel__is_aux_event(evsel)) + arm_spe_setup_evsel(evsel, cpus); } - /* - * Set this only so that perf report knows that SPE generates memory info. It has no effect - * on the opening of the event or the SPE data produced. - */ - evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); - - /* - * The PHYS_ADDR flag does not affect the driver behaviour, it is used to - * inform that the resulting output's SPE samples contain physical addresses - * where applicable. - */ - bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable"); - if (arm_spe_evsel->core.attr.config & bit) - evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); - /* Add dummy event to keep tracking */ err = parse_event(evlist, "dummy:u"); if (err) @@ -301,12 +310,16 @@ static int arm_spe_snapshot_start(struct auxtrace_record *itr) struct arm_spe_recording *ptr = container_of(itr, struct arm_spe_recording, itr); struct evsel *evsel; + int ret = -EINVAL; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->arm_spe_pmu->type) - return evsel__disable(evsel); + if (evsel__is_aux_event(evsel)) { + ret = evsel__disable(evsel); + if (ret < 0) + return ret; + } } - return -EINVAL; + return ret; } static int arm_spe_snapshot_finish(struct auxtrace_record *itr) @@ -314,12 +327,16 @@ static int arm_spe_snapshot_finish(struct auxtrace_record *itr) struct arm_spe_recording *ptr = container_of(itr, struct arm_spe_recording, itr); struct evsel *evsel; + int ret = -EINVAL; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->arm_spe_pmu->type) - return evsel__enable(evsel); + if (evsel__is_aux_event(evsel)) { + ret = evsel__enable(evsel); + if (ret < 0) + return ret; + } } - return -EINVAL; + return ret; } static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx) diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c index 21cc7e4149f7..ab43b1ab51e3 100644 --- a/tools/perf/arch/loongarch/annotate/instructions.c +++ b/tools/perf/arch/loongarch/annotate/instructions.c @@ -5,7 +5,8 @@ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited */ -static int loongarch_call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) +static int loongarch_call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) { char *c, *endptr, *tok, *name; struct map *map = ms->map; @@ -51,7 +52,8 @@ static struct ins_ops loongarch_call_ops = { .scnprintf = call__scnprintf, }; -static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) +static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) { struct map *map = ms->map; struct symbol *sym = ms->sym; diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c index a3f423c27cae..ede9eeade0ab 100644 --- a/tools/perf/arch/powerpc/annotate/instructions.c +++ b/tools/perf/arch/powerpc/annotate/instructions.c @@ -49,12 +49,266 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con return ops; } +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define PPC_21_30(R) (((R) >> 1) & 0x3ff) +#define PPC_22_30(R) (((R) >> 1) & 0x1ff) + +struct insn_offset { + const char *name; + int value; +}; + +/* + * There are memory instructions with opcode 31 which are + * of X Form, Example: + * ldx RT,RA,RB + * ______________________________________ + * | 31 | RT | RA | RB | 21 |/| + * -------------------------------------- + * 0 6 11 16 21 30 31 + * + * But all instructions with opcode 31 are not memory. + * Example: add RT,RA,RB + * + * Use bits 21 to 30 to check memory insns with 31 as opcode. + * In ins_array below, for ldx instruction: + * name => OP_31_XOP_LDX + * value => 21 + */ + +static struct insn_offset ins_array[] = { + { .name = "OP_31_XOP_LXSIWZX", .value = 12, }, + { .name = "OP_31_XOP_LWARX", .value = 20, }, + { .name = "OP_31_XOP_LDX", .value = 21, }, + { .name = "OP_31_XOP_LWZX", .value = 23, }, + { .name = "OP_31_XOP_LDUX", .value = 53, }, + { .name = "OP_31_XOP_LWZUX", .value = 55, }, + { .name = "OP_31_XOP_LXSIWAX", .value = 76, }, + { .name = "OP_31_XOP_LDARX", .value = 84, }, + { .name = "OP_31_XOP_LBZX", .value = 87, }, + { .name = "OP_31_XOP_LVX", .value = 103, }, + { .name = "OP_31_XOP_LBZUX", .value = 119, }, + { .name = "OP_31_XOP_STXSIWX", .value = 140, }, + { .name = "OP_31_XOP_STDX", .value = 149, }, + { .name = "OP_31_XOP_STWX", .value = 151, }, + { .name = "OP_31_XOP_STDUX", .value = 181, }, + { .name = "OP_31_XOP_STWUX", .value = 183, }, + { .name = "OP_31_XOP_STBX", .value = 215, }, + { .name = "OP_31_XOP_STVX", .value = 231, }, + { .name = "OP_31_XOP_STBUX", .value = 247, }, + { .name = "OP_31_XOP_LHZX", .value = 279, }, + { .name = "OP_31_XOP_LHZUX", .value = 311, }, + { .name = "OP_31_XOP_LXVDSX", .value = 332, }, + { .name = "OP_31_XOP_LWAX", .value = 341, }, + { .name = "OP_31_XOP_LHAX", .value = 343, }, + { .name = "OP_31_XOP_LWAUX", .value = 373, }, + { .name = "OP_31_XOP_LHAUX", .value = 375, }, + { .name = "OP_31_XOP_STHX", .value = 407, }, + { .name = "OP_31_XOP_STHUX", .value = 439, }, + { .name = "OP_31_XOP_LXSSPX", .value = 524, }, + { .name = "OP_31_XOP_LDBRX", .value = 532, }, + { .name = "OP_31_XOP_LSWX", .value = 533, }, + { .name = "OP_31_XOP_LWBRX", .value = 534, }, + { .name = "OP_31_XOP_LFSUX", .value = 567, }, + { .name = "OP_31_XOP_LXSDX", .value = 588, }, + { .name = "OP_31_XOP_LSWI", .value = 597, }, + { .name = "OP_31_XOP_LFDX", .value = 599, }, + { .name = "OP_31_XOP_LFDUX", .value = 631, }, + { .name = "OP_31_XOP_STXSSPX", .value = 652, }, + { .name = "OP_31_XOP_STDBRX", .value = 660, }, + { .name = "OP_31_XOP_STXWX", .value = 661, }, + { .name = "OP_31_XOP_STWBRX", .value = 662, }, + { .name = "OP_31_XOP_STFSX", .value = 663, }, + { .name = "OP_31_XOP_STFSUX", .value = 695, }, + { .name = "OP_31_XOP_STXSDX", .value = 716, }, + { .name = "OP_31_XOP_STSWI", .value = 725, }, + { .name = "OP_31_XOP_STFDX", .value = 727, }, + { .name = "OP_31_XOP_STFDUX", .value = 759, }, + { .name = "OP_31_XOP_LXVW4X", .value = 780, }, + { .name = "OP_31_XOP_LHBRX", .value = 790, }, + { .name = "OP_31_XOP_LXVD2X", .value = 844, }, + { .name = "OP_31_XOP_LFIWAX", .value = 855, }, + { .name = "OP_31_XOP_LFIWZX", .value = 887, }, + { .name = "OP_31_XOP_STXVW4X", .value = 908, }, + { .name = "OP_31_XOP_STHBRX", .value = 918, }, + { .name = "OP_31_XOP_STXVD2X", .value = 972, }, + { .name = "OP_31_XOP_STFIWX", .value = 983, }, +}; + +/* + * Arithmetic instructions which are having opcode as 31. + * These instructions are tracked to save the register state + * changes. Example: + * + * lwz r10,264(r3) + * add r31, r3, r3 + * lwz r9, 0(r31) + * + * Here instruction tracking needs to identify the "add" + * instruction and save data type of r3 to r31. If a sample + * is hit at next "lwz r9, 0(r31)", by this instruction tracking, + * data type of r31 can be resolved. + */ +static struct insn_offset arithmetic_ins_op_31[] = { + { .name = "SUB_CARRY_XO_FORM", .value = 8, }, + { .name = "MUL_HDW_XO_FORM1", .value = 9, }, + { .name = "ADD_CARRY_XO_FORM", .value = 10, }, + { .name = "MUL_HW_XO_FORM1", .value = 11, }, + { .name = "SUB_XO_FORM", .value = 40, }, + { .name = "MUL_HDW_XO_FORM", .value = 73, }, + { .name = "MUL_HW_XO_FORM", .value = 75, }, + { .name = "SUB_EXT_XO_FORM", .value = 136, }, + { .name = "ADD_EXT_XO_FORM", .value = 138, }, + { .name = "SUB_ZERO_EXT_XO_FORM", .value = 200, }, + { .name = "ADD_ZERO_EXT_XO_FORM", .value = 202, }, + { .name = "SUB_EXT_XO_FORM2", .value = 232, }, + { .name = "MUL_DW_XO_FORM", .value = 233, }, + { .name = "ADD_EXT_XO_FORM2", .value = 234, }, + { .name = "MUL_W_XO_FORM", .value = 235, }, + { .name = "ADD_XO_FORM", .value = 266, }, + { .name = "DIV_DW_XO_FORM1", .value = 457, }, + { .name = "DIV_W_XO_FORM1", .value = 459, }, + { .name = "DIV_DW_XO_FORM", .value = 489, }, + { .name = "DIV_W_XO_FORM", .value = 491, }, +}; + +static struct insn_offset arithmetic_two_ops[] = { + { .name = "mulli", .value = 7, }, + { .name = "subfic", .value = 8, }, + { .name = "addic", .value = 12, }, + { .name = "addic.", .value = 13, }, + { .name = "addi", .value = 14, }, + { .name = "addis", .value = 15, }, +}; + +static int cmp_offset(const void *a, const void *b) +{ + const struct insn_offset *val1 = a; + const struct insn_offset *val2 = b; + + return (val1->value - val2->value); +} + +static struct ins_ops *check_ppc_insn(struct disasm_line *dl) +{ + int raw_insn = dl->raw.raw_insn; + int opcode = PPC_OP(raw_insn); + int mem_insn_31 = PPC_21_30(raw_insn); + struct insn_offset *ret; + struct insn_offset mem_insns_31_opcode = { + "OP_31_INSN", + mem_insn_31 + }; + char name_insn[32]; + + /* + * Instructions with opcode 32 to 63 are memory + * instructions in powerpc + */ + if ((opcode & 0x20)) { + /* + * Set name in case of raw instruction to + * opcode to be used in insn-stat + */ + if (!strlen(dl->ins.name)) { + sprintf(name_insn, "%d", opcode); + dl->ins.name = strdup(name_insn); + } + return &load_store_ops; + } else if (opcode == 31) { + /* Check for memory instructions with opcode 31 */ + ret = bsearch(&mem_insns_31_opcode, ins_array, ARRAY_SIZE(ins_array), sizeof(ins_array[0]), cmp_offset); + if (ret) { + if (!strlen(dl->ins.name)) + dl->ins.name = strdup(ret->name); + return &load_store_ops; + } else { + mem_insns_31_opcode.value = PPC_22_30(raw_insn); + ret = bsearch(&mem_insns_31_opcode, arithmetic_ins_op_31, ARRAY_SIZE(arithmetic_ins_op_31), + sizeof(arithmetic_ins_op_31[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + /* Bits 21 to 30 has value 444 for "mr" insn ie, OR X form */ + if (PPC_21_30(raw_insn) == 444) + return &arithmetic_ops; + } + } else { + mem_insns_31_opcode.value = opcode; + ret = bsearch(&mem_insns_31_opcode, arithmetic_two_ops, ARRAY_SIZE(arithmetic_two_ops), + sizeof(arithmetic_two_ops[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + } + + return NULL; +} + +/* + * Instruction tracking function to track register state moves. + * Example sequence: + * ld r10,264(r3) + * mr r31,r3 + * <<after some sequence> + * ld r9,312(r31) + * + * Previous instruction sequence shows that register state of r3 + * is moved to r31. update_insn_state_powerpc tracks these state + * changes + */ +#ifdef HAVE_DWARF_SUPPORT +static void update_insn_state_powerpc(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die * cu_die __maybe_unused, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + u32 insn_offset = dl->al.offset; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + /* + * Value 444 for bits 21:30 is for "mr" + * instruction. "mr" is extended OR. So set the + * source and destination reg correctly + */ + if (PPC_21_30(dl->raw.raw_insn) == 444) { + int src_reg = src->reg1; + + src->reg1 = dst->reg1; + dst->reg1 = src_reg; + } + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + tsr->ok = false; + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->ok = true; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); +} +#endif /* HAVE_DWARF_SUPPORT */ + static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused) { if (!arch->initialized) { arch->initialized = true; arch->associate_instruction_ops = powerpc__associate_instruction_ops; arch->objdump.comment_char = '#'; + annotate_opts.show_asm_raw = true; } return 0; diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 0c4f4caf53ac..104c7ae5c433 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -98,3 +98,56 @@ int regs_query_register_offset(const char *name) return roff->ptregs_offset; return -EINVAL; } + +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define PPC_RA(a) (((a) >> 16) & 0x1f) +#define PPC_RT(t) (((t) >> 21) & 0x1f) +#define PPC_RB(b) (((b) >> 11) & 0x1f) +#define PPC_D(D) ((D) & 0xfffe) +#define PPC_DS(DS) ((DS) & 0xfffc) +#define OP_LD 58 +#define OP_STD 62 + +static int get_source_reg(u32 raw_insn) +{ + return PPC_RA(raw_insn); +} + +static int get_target_reg(u32 raw_insn) +{ + return PPC_RT(raw_insn); +} + +static int get_offset_opcode(u32 raw_insn) +{ + int opcode = PPC_OP(raw_insn); + + /* DS- form */ + if ((opcode == OP_LD) || (opcode == OP_STD)) + return PPC_DS(raw_insn); + else + return PPC_D(raw_insn); +} + +/* + * Fills the required fields for op_loc depending on if it + * is a source or target. + * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT + * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT + * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT + */ +void get_powerpc_regs(u32 raw_insn, int is_source, + struct annotated_op_loc *op_loc) +{ + if (is_source) + op_loc->reg1 = get_source_reg(raw_insn); + else + op_loc->reg1 = get_target_reg(raw_insn); + + if (op_loc->multi_regs) + op_loc->reg2 = PPC_RB(raw_insn); + + /* TODO: Implement offset handling for X Form */ + if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31)) + op_loc->offset = get_offset_opcode(raw_insn); +} diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index da5aa3e1f04c..eeac25cca699 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -2,7 +2,7 @@ #include <linux/compiler.h> static int s390_call__parse(struct arch *arch, struct ins_operands *ops, - struct map_symbol *ms) + struct map_symbol *ms, struct disasm_line *dl __maybe_unused) { char *endptr, *tok, *name; struct map *map = ms->map; @@ -52,7 +52,8 @@ static struct ins_ops s390_call_ops = { static int s390_mov__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, - struct map_symbol *ms __maybe_unused) + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *endptr; diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 5cdf457f5cbe..7b7d462c6c6b 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -206,3 +206,380 @@ static int x86__annotate_init(struct arch *arch, char *cpuid) arch->initialized = true; return err; } + +#ifdef HAVE_DWARF_SUPPORT +static void update_insn_state_x86(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die *cu_die, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + Dwarf_Die type_die; + u32 insn_offset = dl->al.offset; + int fbreg = dloc->fbreg; + int fboff = 0; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + if (ins__is_call(&dl->ins)) { + struct symbol *func = dl->ops.target.sym; + + if (func == NULL) + return; + + /* __fentry__ will preserve all registers */ + if (!strcmp(func->name, "__fentry__")) + return; + + pr_debug_dtp("call [%x] %s\n", insn_offset, func->name); + + /* Otherwise invalidate caller-saved registers after call */ + for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) { + if (state->regs[i].caller_saved) + state->regs[i].ok = false; + } + + /* Update register with the return type (if any) */ + if (die_find_func_rettype(cu_die, func->name, &type_die)) { + tsr = &state->regs[state->ret_reg]; + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("call [%x] return -> reg%d", + insn_offset, state->ret_reg); + pr_debug_type_name(&type_die, tsr->kind); + } + return; + } + + if (!strncmp(dl->ins.name, "add", 3)) { + u64 imm_value = -1ULL; + int offset; + const char *var_name = NULL; + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + + if (src->imm) + imm_value = src->offset; + else if (has_reg_type(state, src->reg1) && + state->regs[src->reg1].kind == TSR_KIND_CONST) + imm_value = state->regs[src->reg1].imm_value; + else if (src->reg1 == DWARF_REG_PC) { + u64 var_addr = annotate_calc_pcrel(dloc->ms, ip, + src->offset, dl); + + if (get_global_var_info(dloc, var_addr, + &var_name, &offset) && + !strcmp(var_name, "this_cpu_off") && + tsr->kind == TSR_KIND_CONST) { + tsr->kind = TSR_KIND_PERCPU_BASE; + imm_value = tsr->imm_value; + } + } + else + return; + + if (tsr->kind != TSR_KIND_PERCPU_BASE) + return; + + if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset, + &type_die) && offset == 0) { + /* + * This is not a pointer type, but it should be treated + * as a pointer. + */ + tsr->type = type_die; + tsr->kind = TSR_KIND_POINTER; + tsr->ok = true; + + pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d", + insn_offset, imm_value, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + return; + } + + if (strncmp(dl->ins.name, "mov", 3)) + return; + + if (dloc->fb_cfa) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 pc = map__rip_2objdump(dloc->ms->map, ip); + + if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0) + fbreg = -1; + } + + /* Case 1. register to register or segment:offset to register transfers */ + if (!src->mem_ref && !dst->mem_ref) { + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + if (dso__kernel(map__dso(dloc->ms->map)) && + src->segment == INSN_SEG_X86_GS && src->imm) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr; + int offset; + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + var_addr = src->offset; + + if (var_addr == 40) { + tsr->kind = TSR_KIND_CANARY; + tsr->ok = true; + + pr_debug_dtp("mov [%x] stack canary -> reg%d\n", + insn_offset, dst->reg1); + return; + } + + if (!get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + tsr->ok = false; + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d", + insn_offset, var_addr, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + return; + } + + if (src->imm) { + tsr->kind = TSR_KIND_CONST; + tsr->imm_value = src->offset; + tsr->ok = true; + + pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n", + insn_offset, tsr->imm_value, dst->reg1); + return; + } + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + tsr->ok = false; + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->ok = true; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Case 2. memory to register transers */ + if (src->mem_ref && !dst->mem_ref) { + int sreg = src->reg1; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + +retry: + /* Check stack variables with offset */ + if (sreg == fbreg) { + struct type_state_stack *stack; + int offset = src->offset - fboff; + + stack = find_stack_state(state, offset); + if (stack == NULL) { + tsr->ok = false; + return; + } else if (!stack->compound) { + tsr->type = stack->type; + tsr->kind = stack->kind; + tsr->ok = true; + } else if (die_get_member_type(&stack->type, + offset - stack->offset, + &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + } else { + tsr->ok = false; + return; + } + + pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", + insn_offset, -offset, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* And then dereference the pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_TYPE && + die_deref_ptr_type(&state->regs[sreg].type, + src->offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or check if it's a global variable */ + else if (sreg == DWARF_REG_PC) { + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + u64 addr; + int offset; + + addr = annotate_calc_pcrel(ms, ip, src->offset, dl); + + if (!get_global_var_type(cu_die, dloc, ip, addr, &offset, + &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + tsr->ok = false; + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d", + insn_offset, addr, dst->reg1); + pr_debug_type_name(&type_die, tsr->kind); + } + /* And check percpu access with base register */ + else if (has_reg_type(state, sreg) && + state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr = src->offset; + int offset; + + if (src->multi_regs) { + int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1; + + if (has_reg_type(state, reg2) && state->regs[reg2].ok && + state->regs[reg2].kind == TSR_KIND_CONST) + var_addr += state->regs[reg2].imm_value; + } + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + if (get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) && + die_get_member_type(&type_die, offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + if (src->multi_regs) { + pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d", + insn_offset, src->offset, src->reg1, + src->reg2, dst->reg1); + } else { + pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + } + pr_debug_type_name(&tsr->type, tsr->kind); + } else { + tsr->ok = false; + } + } + /* And then dereference the calculated pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_POINTER && + die_get_member_type(&state->regs[sreg].type, + src->offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or try another register if any */ + else if (src->multi_regs && sreg == src->reg1 && + src->reg1 != src->reg2) { + sreg = src->reg2; + goto retry; + } + else { + int offset; + const char *var_name = NULL; + + /* it might be per-cpu variable (in kernel) access */ + if (src->offset < 0) { + if (get_global_var_info(dloc, (s64)src->offset, + &var_name, &offset) && + !strcmp(var_name, "__per_cpu_offset")) { + tsr->kind = TSR_KIND_PERCPU_BASE; + + pr_debug_dtp("mov [%x] percpu base reg%d\n", + insn_offset, dst->reg1); + } + } + + tsr->ok = false; + } + } + /* Case 3. register to memory transfers */ + if (!src->mem_ref && dst->mem_ref) { + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) + return; + + /* Check stack variables with offset */ + if (dst->reg1 == fbreg) { + struct type_state_stack *stack; + int offset = dst->offset - fboff; + + tsr = &state->regs[src->reg1]; + + stack = find_stack_state(state, offset); + if (stack) { + /* + * The source register is likely to hold a type + * of member if it's a compound type. Do not + * update the stack variable type since we can + * get the member type later by using the + * die_get_member_type(). + */ + if (!stack->compound) + set_stack_state(stack, offset, tsr->kind, + &tsr->type); + } else { + findnew_stack_state(state, offset, tsr->kind, + &tsr->type); + } + + pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", + insn_offset, src->reg1, -offset); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* + * Ignore other transfers since it'd set a value in a struct + * and won't change the type. + */ + } + /* Case 4. memory to memory transfers (not handled for now) */ +} +#endif diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index b10b7f005658..efcadb7620b8 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -396,10 +396,10 @@ static void print_annotate_item_stat(struct list_head *head, const char *title) printf("total %d, ok %d (%.1f%%), bad %d (%.1f%%)\n\n", total, total_good, 100.0 * total_good / (total ?: 1), total_bad, 100.0 * total_bad / (total ?: 1)); - printf(" %-10s: %5s %5s\n", "Name", "Good", "Bad"); + printf(" %-20s: %5s %5s\n", "Name/opcode", "Good", "Bad"); printf("-----------------------------------------------------------\n"); list_for_each_entry(istat, head, list) - printf(" %-10s: %5d %5d\n", istat->name, istat->good, istat->bad); + printf(" %-20s: %5d %5d\n", istat->name, istat->good, istat->bad); printf("\n"); } @@ -795,6 +795,8 @@ int cmd_annotate(int argc, const char **argv) "Show stats for the data type annotation"), OPT_BOOLEAN(0, "insn-stat", &annotate.insn_stat, "Show instruction stats for the data type annotation"), + OPT_BOOLEAN(0, "skip-empty", &symbol_conf.skip_empty, + "Do not display empty (or dummy) events in the output"), OPT_END() }; int ret; diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index de76bbc50bfb..18f7f417ba11 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1433,7 +1433,7 @@ static int __cmd_signal(struct daemon *daemon, struct option parent_options[], } memset(&cmd, 0, sizeof(cmd)); - cmd.signal.cmd = CMD_SIGNAL, + cmd.signal.cmd = CMD_SIGNAL; cmd.signal.sig = SIGUSR2; strncpy(cmd.signal.name, name, sizeof(cmd.signal.name) - 1); diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index eb30c8eca488..a615c405d98f 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -13,6 +13,7 @@ #include <signal.h> #include <stdlib.h> #include <fcntl.h> +#include <inttypes.h> #include <math.h> #include <poll.h> #include <ctype.h> @@ -22,15 +23,18 @@ #include "debug.h" #include <subcmd/pager.h> #include <subcmd/parse-options.h> +#include <api/io.h> #include <api/fs/tracing_path.h> #include "evlist.h" #include "target.h" #include "cpumap.h" +#include "hashmap.h" #include "thread_map.h" #include "strfilter.h" #include "util/cap.h" #include "util/config.h" #include "util/ftrace.h" +#include "util/stat.h" #include "util/units.h" #include "util/parse-sublevel-options.h" @@ -59,6 +63,22 @@ static void ftrace__workload_exec_failed_signal(int signo __maybe_unused, done = true; } +static int check_ftrace_capable(void) +{ + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { + pr_err("ftrace only works for %s!\n", +#ifdef HAVE_LIBCAP_SUPPORT + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" +#else + "root" +#endif + ); + return -1; + } + return 0; +} + static int __write_tracing_file(const char *name, const char *val, bool append) { char *file; @@ -228,6 +248,7 @@ static void reset_tracing_options(struct perf_ftrace *ftrace __maybe_unused) write_tracing_option_file("funcgraph-irqs", "1"); write_tracing_option_file("funcgraph-proc", "0"); write_tracing_option_file("funcgraph-abstime", "0"); + write_tracing_option_file("funcgraph-tail", "0"); write_tracing_option_file("latency-format", "0"); write_tracing_option_file("irq-info", "0"); } @@ -464,6 +485,17 @@ static int set_tracing_funcgraph_verbose(struct perf_ftrace *ftrace) return 0; } +static int set_tracing_funcgraph_tail(struct perf_ftrace *ftrace) +{ + if (!ftrace->graph_tail) + return 0; + + if (write_tracing_option_file("funcgraph-tail", "1") < 0) + return -1; + + return 0; +} + static int set_tracing_thresh(struct perf_ftrace *ftrace) { int ret; @@ -540,6 +572,11 @@ static int set_tracing_options(struct perf_ftrace *ftrace) return -1; } + if (set_tracing_funcgraph_tail(ftrace) < 0) { + pr_err("failed to set tracing option funcgraph-tail\n"); + return -1; + } + return 0; } @@ -569,18 +606,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace) .events = POLLIN, }; - if (!(perf_cap__capable(CAP_PERFMON) || - perf_cap__capable(CAP_SYS_ADMIN))) { - pr_err("ftrace only works for %s!\n", -#ifdef HAVE_LIBCAP_SUPPORT - "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" -#else - "root" -#endif - ); - return -1; - } - select_tracer(ftrace); if (reset_tracing_files(ftrace) < 0) { @@ -885,18 +910,6 @@ static int __cmd_latency(struct perf_ftrace *ftrace) }; int buckets[NUM_BUCKET] = { }; - if (!(perf_cap__capable(CAP_PERFMON) || - perf_cap__capable(CAP_SYS_ADMIN))) { - pr_err("ftrace only works for %s!\n", -#ifdef HAVE_LIBCAP_SUPPORT - "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" -#else - "root" -#endif - ); - return -1; - } - trace_fd = prepare_func_latency(ftrace); if (trace_fd < 0) goto out; @@ -950,6 +963,326 @@ out: return (done && !workload_exec_errno) ? 0 : -1; } +static size_t profile_hash(long func, void *ctx __maybe_unused) +{ + return str_hash((char *)func); +} + +static bool profile_equal(long func1, long func2, void *ctx __maybe_unused) +{ + return !strcmp((char *)func1, (char *)func2); +} + +static int prepare_func_profile(struct perf_ftrace *ftrace) +{ + ftrace->tracer = "function_graph"; + ftrace->graph_tail = 1; + + ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL); + if (ftrace->profile_hash == NULL) + return -ENOMEM; + + return 0; +} + +/* This is saved in a hashmap keyed by the function name */ +struct ftrace_profile_data { + struct stats st; +}; + +static int add_func_duration(struct perf_ftrace *ftrace, char *func, double time_ns) +{ + struct ftrace_profile_data *prof = NULL; + + if (!hashmap__find(ftrace->profile_hash, func, &prof)) { + char *key = strdup(func); + + if (key == NULL) + return -ENOMEM; + + prof = zalloc(sizeof(*prof)); + if (prof == NULL) { + free(key); + return -ENOMEM; + } + + init_stats(&prof->st); + hashmap__add(ftrace->profile_hash, key, prof); + } + + update_stats(&prof->st, time_ns); + return 0; +} + +/* + * The ftrace function_graph text output normally looks like below: + * + * CPU DURATION FUNCTION + * + * 0) | syscall_trace_enter.isra.0() { + * 0) | __audit_syscall_entry() { + * 0) | auditd_test_task() { + * 0) 0.271 us | __rcu_read_lock(); + * 0) 0.275 us | __rcu_read_unlock(); + * 0) 1.254 us | } /\* auditd_test_task *\/ + * 0) 0.279 us | ktime_get_coarse_real_ts64(); + * 0) 2.227 us | } /\* __audit_syscall_entry *\/ + * 0) 2.713 us | } /\* syscall_trace_enter.isra.0 *\/ + * + * Parse the line and get the duration and function name. + */ +static int parse_func_duration(struct perf_ftrace *ftrace, char *line, size_t len) +{ + char *p; + char *func; + double duration; + + /* skip CPU */ + p = strchr(line, ')'); + if (p == NULL) + return 0; + + /* get duration */ + p = skip_spaces(p + 1); + + /* no duration? */ + if (p == NULL || *p == '|') + return 0; + + /* skip markers like '*' or '!' for longer than ms */ + if (!isdigit(*p)) + p++; + + duration = strtod(p, &p); + + if (strncmp(p, " us", 3)) { + pr_debug("non-usec time found.. ignoring\n"); + return 0; + } + + /* + * profile stat keeps the max and min values as integer, + * convert to nsec time so that we can have accurate max. + */ + duration *= 1000; + + /* skip to the pipe */ + while (p < line + len && *p != '|') + p++; + + if (*p++ != '|') + return -EINVAL; + + /* get function name */ + func = skip_spaces(p); + + /* skip the closing bracket and the start of comment */ + if (*func == '}') + func += 5; + + /* remove semi-colon or end of comment at the end */ + p = line + len - 1; + while (!isalnum(*p) && *p != ']') { + *p = '\0'; + --p; + } + + return add_func_duration(ftrace, func, duration); +} + +enum perf_ftrace_profile_sort_key { + PFP_SORT_TOTAL = 0, + PFP_SORT_AVG, + PFP_SORT_MAX, + PFP_SORT_COUNT, + PFP_SORT_NAME, +}; + +static enum perf_ftrace_profile_sort_key profile_sort = PFP_SORT_TOTAL; + +static int cmp_profile_data(const void *a, const void *b) +{ + const struct hashmap_entry *e1 = *(const struct hashmap_entry **)a; + const struct hashmap_entry *e2 = *(const struct hashmap_entry **)b; + struct ftrace_profile_data *p1 = e1->pvalue; + struct ftrace_profile_data *p2 = e2->pvalue; + double v1, v2; + + switch (profile_sort) { + case PFP_SORT_NAME: + return strcmp(e1->pkey, e2->pkey); + case PFP_SORT_AVG: + v1 = p1->st.mean; + v2 = p2->st.mean; + break; + case PFP_SORT_MAX: + v1 = p1->st.max; + v2 = p2->st.max; + break; + case PFP_SORT_COUNT: + v1 = p1->st.n; + v2 = p2->st.n; + break; + case PFP_SORT_TOTAL: + default: + v1 = p1->st.n * p1->st.mean; + v2 = p2->st.n * p2->st.mean; + break; + } + + if (v1 > v2) + return -1; + else + return 1; +} + +static void print_profile_result(struct perf_ftrace *ftrace) +{ + struct hashmap_entry *entry, **profile; + size_t i, nr, bkt; + + nr = hashmap__size(ftrace->profile_hash); + if (nr == 0) + return; + + profile = calloc(nr, sizeof(*profile)); + if (profile == NULL) { + pr_err("failed to allocate memory for the result\n"); + return; + } + + i = 0; + hashmap__for_each_entry(ftrace->profile_hash, entry, bkt) + profile[i++] = entry; + + assert(i == nr); + + //cmp_profile_data(profile[0], profile[1]); + qsort(profile, nr, sizeof(*profile), cmp_profile_data); + + printf("# %10s %10s %10s %10s %s\n", + "Total (us)", "Avg (us)", "Max (us)", "Count", "Function"); + + for (i = 0; i < nr; i++) { + const char *name = profile[i]->pkey; + struct ftrace_profile_data *p = profile[i]->pvalue; + + printf("%12.3f %10.3f %6"PRIu64".%03"PRIu64" %10.0f %s\n", + p->st.n * p->st.mean / 1000, p->st.mean / 1000, + p->st.max / 1000, p->st.max % 1000, p->st.n, name); + } + + free(profile); + + hashmap__for_each_entry(ftrace->profile_hash, entry, bkt) { + free((char *)entry->pkey); + free(entry->pvalue); + } + + hashmap__free(ftrace->profile_hash); + ftrace->profile_hash = NULL; +} + +static int __cmd_profile(struct perf_ftrace *ftrace) +{ + char *trace_file; + int trace_fd; + char buf[4096]; + struct io io; + char *line = NULL; + size_t line_len = 0; + + if (prepare_func_profile(ftrace) < 0) { + pr_err("failed to prepare func profiler\n"); + goto out; + } + + if (reset_tracing_files(ftrace) < 0) { + pr_err("failed to reset ftrace\n"); + goto out; + } + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + goto out; + + if (set_tracing_options(ftrace) < 0) + return -1; + + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { + pr_err("failed to set current_tracer to %s\n", ftrace->tracer); + goto out_reset; + } + + setup_pager(); + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + trace_fd = open(trace_file, O_RDONLY); + + put_tracing_file(trace_file); + + if (trace_fd < 0) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + goto out_close_fd; + } + + evlist__start_workload(ftrace->evlist); + + io__init(&io, trace_fd, buf, sizeof(buf)); + io.timeout_ms = -1; + + while (!done && !io.eof) { + if (io__getline(&io, &line, &line_len) < 0) + break; + + if (parse_func_duration(ftrace, line, line_len) < 0) + break; + } + + write_tracing_file("tracing_on", "0"); + + if (workload_exec_errno) { + const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf)); + /* flush stdout first so below error msg appears at the end. */ + fflush(stdout); + pr_err("workload failed: %s\n", emsg); + goto out_free_line; + } + + /* read remaining buffer contents */ + io.timeout_ms = 0; + while (!io.eof) { + if (io__getline(&io, &line, &line_len) < 0) + break; + + if (parse_func_duration(ftrace, line, line_len) < 0) + break; + } + + print_profile_result(ftrace); + +out_free_line: + free(line); +out_close_fd: + close(trace_fd); +out_reset: + reset_tracing_files(ftrace); +out: + return (done && !workload_exec_errno) ? 0 : -1; +} + static int perf_ftrace_config(const char *var, const char *value, void *cb) { struct perf_ftrace *ftrace = cb; @@ -1099,6 +1432,7 @@ static int parse_graph_tracer_opts(const struct option *opt, { .name = "verbose", .value_ptr = &ftrace->graph_verbose }, { .name = "thresh", .value_ptr = &ftrace->graph_thresh }, { .name = "depth", .value_ptr = &ftrace->graph_depth }, + { .name = "tail", .value_ptr = &ftrace->graph_tail }, { .name = NULL, } }; @@ -1112,10 +1446,35 @@ static int parse_graph_tracer_opts(const struct option *opt, return 0; } +static int parse_sort_key(const struct option *opt, const char *str, int unset) +{ + enum perf_ftrace_profile_sort_key *key = (void *)opt->value; + + if (unset) + return 0; + + if (!strcmp(str, "total")) + *key = PFP_SORT_TOTAL; + else if (!strcmp(str, "avg")) + *key = PFP_SORT_AVG; + else if (!strcmp(str, "max")) + *key = PFP_SORT_MAX; + else if (!strcmp(str, "count")) + *key = PFP_SORT_COUNT; + else if (!strcmp(str, "name")) + *key = PFP_SORT_NAME; + else { + pr_err("Unknown sort key: %s\n", str); + return -1; + } + return 0; +} + enum perf_ftrace_subcommand { PERF_FTRACE_NONE, PERF_FTRACE_TRACE, PERF_FTRACE_LATENCY, + PERF_FTRACE_PROFILE, }; int cmd_ftrace(int argc, const char **argv) @@ -1181,13 +1540,31 @@ int cmd_ftrace(int argc, const char **argv) "Use nano-second histogram"), OPT_PARENT(common_options), }; + const struct option profile_options[] = { + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "Trace given functions using function tracer", + parse_filter_func), + OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func", + "Do not trace given functions", parse_filter_func), + OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func", + "Trace given functions using function_graph tracer", + parse_filter_func), + OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func", + "Set nograph filter on given functions", parse_filter_func), + OPT_CALLBACK('m', "buffer-size", &ftrace.percpu_buffer_size, "size", + "Size of per cpu buffer, needs to use a B, K, M or G suffix.", parse_buffer_size), + OPT_CALLBACK('s', "sort", &profile_sort, "key", + "Sort result by key: total (default), avg, max, count, name.", + parse_sort_key), + OPT_PARENT(common_options), + }; const struct option *options = ftrace_options; const char * const ftrace_usage[] = { "perf ftrace [<options>] [<command>]", "perf ftrace [<options>] -- [<command>] [<options>]", - "perf ftrace {trace|latency} [<options>] [<command>]", - "perf ftrace {trace|latency} [<options>] -- [<command>] [<options>]", + "perf ftrace {trace|latency|profile} [<options>] [<command>]", + "perf ftrace {trace|latency|profile} [<options>] -- [<command>] [<options>]", NULL }; enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE; @@ -1202,6 +1579,10 @@ int cmd_ftrace(int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGPIPE, sig_handler); + ret = check_ftrace_capable(); + if (ret < 0) + return -1; + ret = perf_config(perf_ftrace_config, &ftrace); if (ret < 0) return -1; @@ -1212,6 +1593,9 @@ int cmd_ftrace(int argc, const char **argv) } else if (!strcmp(argv[1], "latency")) { subcmd = PERF_FTRACE_LATENCY; options = latency_options; + } else if (!strcmp(argv[1], "profile")) { + subcmd = PERF_FTRACE_PROFILE; + options = profile_options; } if (subcmd != PERF_FTRACE_NONE) { @@ -1247,6 +1631,9 @@ int cmd_ftrace(int argc, const char **argv) } cmd_func = __cmd_latency; break; + case PERF_FTRACE_PROFILE: + cmd_func = __cmd_profile; + break; case PERF_FTRACE_NONE: default: pr_err("Invalid subcommand\n"); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index a212678d47be..7b4a5d56d279 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -2069,7 +2069,7 @@ static int __cmd_inject(struct perf_inject *inject) */ inject->tool.finished_init = host__finished_init; /* Obey finished round ordering */ - inject->tool.finished_round = host__finished_round, + inject->tool.finished_round = host__finished_round; /* Keep track of which CPU a VCPU is runnng on */ inject->tool.context_switch = host__context_switch; /* diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 863fcd735dae..efa700d14c98 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -19,6 +19,7 @@ #include "util/symbol.h" #include "util/pmus.h" #include "util/sample.h" +#include "util/sort.h" #include "util/string2.h" #include "util/util.h" #include <linux/err.h> @@ -28,12 +29,16 @@ struct perf_mem { struct perf_tool tool; - char const *input_name; + const char *input_name; + const char *sort_key; bool hide_unresolved; bool dump_raw; bool force; bool phys_addr; bool data_page_size; + bool all_kernel; + bool all_user; + bool data_type; int operation; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -62,33 +67,19 @@ static int parse_record_events(const struct option *opt, return 0; } -static const char * const __usage[] = { - "perf mem record [<options>] [<command>]", - "perf mem record [<options>] -- <command> [<options>]", - NULL -}; - -static const char * const *record_mem_usage = __usage; - -static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) +static int __cmd_record(int argc, const char **argv, struct perf_mem *mem, + const struct option *options) { int rec_argc, i = 0, j; int start, end; const char **rec_argv; int ret; - bool all_user = false, all_kernel = false; struct perf_mem_event *e; struct perf_pmu *pmu; - struct option options[] = { - OPT_CALLBACK('e', "event", &mem, "event", - "event selector. use 'perf mem record -e list' to list available events", - parse_record_events), - OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show counter open errors, etc)"), - OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"), - OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"), - OPT_END() + const char * const record_usage[] = { + "perf mem record [<options>] [<command>]", + "perf mem record [<options>] -- <command> [<options>]", + NULL }; pmu = perf_mem_events_find_pmu(); @@ -102,7 +93,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) return -1; } - argc = parse_options(argc, argv, options, record_mem_usage, + argc = parse_options(argc, argv, options, record_usage, PARSE_OPT_KEEP_UNKNOWN); /* Max number of arguments multiplied by number of PMUs that can support them. */ @@ -158,10 +149,10 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) goto out; end = i; - if (all_user) + if (mem->all_user) rec_argv[i++] = "--all-user"; - if (all_kernel) + if (mem->all_kernel) rec_argv[i++] = "--all-kernel"; if (mem->cpu_list) { @@ -319,16 +310,21 @@ out_delete: perf_session__delete(session); return ret; } + static char *get_sort_order(struct perf_mem *mem) { bool has_extra_options = (mem->phys_addr | mem->data_page_size) ? true : false; char sort[128]; + if (mem->sort_key) + scnprintf(sort, sizeof(sort), "--sort=%s", mem->sort_key); + else if (mem->data_type) + strcpy(sort, "--sort=mem,snoop,tlb,type"); /* * there is no weight (cost) associated with stores, so don't print * the column */ - if (!(mem->operation & MEM_OPERATION_LOAD)) { + else if (!(mem->operation & MEM_OPERATION_LOAD)) { strcpy(sort, "--sort=mem,sym,dso,symbol_daddr," "dso_daddr,tlb,locked"); } else if (has_extra_options) { @@ -343,14 +339,26 @@ static char *get_sort_order(struct perf_mem *mem) if (mem->data_page_size) strcat(sort, ",data_page_size"); + /* make sure it has 'type' sort key even -s option is used */ + if (mem->data_type && !strstr(sort, "type")) + strcat(sort, ",type"); + return strdup(sort); } -static int report_events(int argc, const char **argv, struct perf_mem *mem) +static int __cmd_report(int argc, const char **argv, struct perf_mem *mem, + const struct option *options) { const char **rep_argv; int ret, i = 0, j, rep_argc; char *new_sort_order; + const char * const report_usage[] = { + "perf mem report [<options>]", + NULL + }; + + argc = parse_options(argc, argv, options, report_usage, + PARSE_OPT_KEEP_UNKNOWN); if (mem->dump_raw) return report_raw_events(mem); @@ -368,10 +376,11 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) if (new_sort_order) rep_argv[i++] = new_sort_order; - for (j = 1; j < argc; j++, i++) + for (j = 0; j < argc; j++, i++) rep_argv[i] = argv[j]; ret = cmd_report(i, rep_argv); + free(new_sort_order); free(rep_argv); return ret; } @@ -470,26 +479,45 @@ int cmd_mem(int argc, const char **argv) */ .operation = MEM_OPERATION_LOAD | MEM_OPERATION_STORE, }; + char *sort_order_help = sort_help("sort by key(s):", SORT_MODE__MEMORY); const struct option mem_options[] = { OPT_CALLBACK('t', "type", &mem.operation, "type", "memory operations(load,store) Default load,store", parse_mem_ops), + OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", + "list of cpus to profile"), + OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"), + OPT_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"), + OPT_END() + }; + const struct option record_options[] = { + OPT_CALLBACK('e', "event", &mem, "event", + "event selector. use 'perf mem record -e list' to list available events", + parse_record_events), + OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"), + OPT_BOOLEAN('U', "all-user", &mem.all_user, "collect only user level data"), + OPT_BOOLEAN('K', "all-kernel", &mem.all_kernel, "collect only kernel level data"), + OPT_PARENT(mem_options) + }; + const struct option report_options[] = { OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw, "dump raw samples in ASCII"), OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved, "Only display entries resolved to a symbol"), OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", - "list of cpus to profile"), OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added" " between columns '.' is reserved."), - OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"), - OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"), - OPT_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"), - OPT_END() + OPT_STRING('s', "sort", &mem.sort_key, "key[,key2...]", + sort_order_help), + OPT_BOOLEAN('T', "type-profile", &mem.data_type, + "Show data-type profile result"), + OPT_PARENT(mem_options) }; const char *const mem_subcommands[] = { "record", "report", NULL }; const char *mem_usage[] = { @@ -498,7 +526,7 @@ int cmd_mem(int argc, const char **argv) }; argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, - mem_usage, PARSE_OPT_KEEP_UNKNOWN); + mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation)) usage_with_options(mem_usage, mem_options); @@ -511,9 +539,9 @@ int cmd_mem(int argc, const char **argv) } if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) - return __cmd_record(argc, argv, &mem); + return __cmd_record(argc, argv, &mem, record_options); else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) - return report_events(argc, argv, &mem); + return __cmd_report(argc, argv, &mem, report_options); else usage_with_options(mem_usage, mem_options); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a94516e8c522..72345d1e54b0 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -171,6 +171,7 @@ struct record { bool timestamp_filename; bool timestamp_boundary; bool off_cpu; + const char *filter_action; struct switch_output switch_output; unsigned long long samples; unsigned long output_max_size; /* = 0: unlimited */ @@ -1389,7 +1390,7 @@ try_again: "even with a suitable vmlinux or kallsyms file.\n\n"); } - if (evlist__apply_filters(evlist, &pos)) { + if (evlist__apply_filters(evlist, &pos, &opts->target)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter ?: "BPF", evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); @@ -3557,6 +3558,8 @@ static struct option __record_options[] = { "write collected trace data into several data files using parallel threads", record__parse_threads), OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"), + OPT_STRING(0, "setup-filter", &record.filter_action, "pin|unpin", + "BPF filter action"), OPT_END() }; @@ -4086,6 +4089,18 @@ int cmd_record(int argc, const char **argv) pr_warning("WARNING: --timestamp-filename option is not available in parallel streaming mode.\n"); } + if (rec->filter_action) { + if (!strcmp(rec->filter_action, "pin")) + err = perf_bpf_filter__pin(); + else if (!strcmp(rec->filter_action, "unpin")) + err = perf_bpf_filter__unpin(); + else { + pr_warning("Unknown BPF filter action: %s\n", rec->filter_action); + err = -EINVAL; + } + goto out_opts; + } + /* * Allow aliases to facilitate the lookup of symbols for address * filters. Refer to auxtrace_parse_filters(). @@ -4242,13 +4257,13 @@ int cmd_record(int argc, const char **argv) err = __cmd_record(&record, argc, argv); out: - evlist__delete(rec->evlist); + record__free_thread_masks(rec, rec->nr_threads); + rec->nr_threads = 0; symbol__exit(); auxtrace_record__free(rec->itr); out_opts: - record__free_thread_masks(rec, rec->nr_threads); - rec->nr_threads = 0; evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close); + evlist__delete(rec->evlist); return err; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6edc0d4ce6fb..930052961c1a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1301,8 +1301,8 @@ int cmd_report(int argc, const char **argv) .socket_filter = -1, .skip_empty = true, }; - char *sort_order_help = sort_help("sort by key(s):"); - char *field_order_help = sort_help("output field(s): overhead period sample "); + char *sort_order_help = sort_help("sort by key(s):", SORT_MODE__NORMAL); + char *field_order_help = sort_help("output field(s):", SORT_MODE__NORMAL); const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 661832756a24..1f92445f7480 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -833,7 +833,7 @@ try_again_reset: return -1; } - if (evlist__apply_filters(evsel_list, &counter)) { + if (evlist__apply_filters(evsel_list, &counter, &target)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e8cbbf10d361..d1a06a88d693 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1055,7 +1055,7 @@ try_again: } } - if (evlist__apply_filters(evlist, &counter)) { + if (evlist__apply_filters(evlist, &counter, &opts->target)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter ?: "BPF", evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 8449f2beb54d..ef951ce1a0dd 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -19,6 +19,7 @@ #ifdef HAVE_LIBBPF_SUPPORT #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include <bpf/btf.h> #ifdef HAVE_BPF_SKEL #include "bpf_skel/augmented_raw_syscalls.skel.h" #endif @@ -110,6 +111,9 @@ struct syscall_arg_fmt { const char *name; u16 nr_entries; // for arrays bool show_zero; +#ifdef HAVE_LIBBPF_SUPPORT + const struct btf_type *type; +#endif }; struct syscall_fmt { @@ -140,6 +144,9 @@ struct trace { #ifdef HAVE_BPF_SKEL struct augmented_raw_syscalls_bpf *skel; #endif +#ifdef HAVE_LIBBPF_SUPPORT + struct btf *btf; +#endif struct record_opts opts; struct evlist *evlist; struct machine *host; @@ -204,6 +211,20 @@ struct trace { } oe; }; +static void trace__load_vmlinux_btf(struct trace *trace __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + if (trace->btf != NULL) + return; + + trace->btf = btf__load_vmlinux_btf(); + if (verbose > 0) { + fprintf(trace->output, trace->btf ? "vmlinux BTF loaded\n" : + "Failed to load vmlinux BTF\n"); + } +#endif +} + struct tp_field { int offset; union { @@ -887,6 +908,125 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, #define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags +#ifdef HAVE_LIBBPF_SUPPORT +static void syscall_arg_fmt__cache_btf_enum(struct syscall_arg_fmt *arg_fmt, struct btf *btf, char *type) +{ + int id; + + type = strstr(type, "enum "); + if (type == NULL) + return; + + type += 5; // skip "enum " to get the enumeration name + + id = btf__find_by_name(btf, type); + if (id < 0) + return; + + arg_fmt->type = btf__type_by_id(btf, id); +} + +static bool syscall_arg__strtoul_btf_enum(char *bf, size_t size, struct syscall_arg *arg, u64 *val) +{ + const struct btf_type *bt = arg->fmt->type; + struct btf *btf = arg->trace->btf; + struct btf_enum *be = btf_enum(bt); + + for (int i = 0; i < btf_vlen(bt); ++i, ++be) { + const char *name = btf__name_by_offset(btf, be->name_off); + int max_len = max(size, strlen(name)); + + if (strncmp(name, bf, max_len) == 0) { + *val = be->val; + return true; + } + } + + return false; +} + +static bool syscall_arg__strtoul_btf_type(char *bf, size_t size, struct syscall_arg *arg, u64 *val) +{ + const struct btf_type *bt; + char *type = arg->type_name; + struct btf *btf; + + trace__load_vmlinux_btf(arg->trace); + + btf = arg->trace->btf; + if (btf == NULL) + return false; + + if (arg->fmt->type == NULL) { + // See if this is an enum + syscall_arg_fmt__cache_btf_enum(arg->fmt, btf, type); + } + + // Now let's see if we have a BTF type resolved + bt = arg->fmt->type; + if (bt == NULL) + return false; + + // If it is an enum: + if (btf_is_enum(arg->fmt->type)) + return syscall_arg__strtoul_btf_enum(bf, size, arg, val); + + return false; +} + +static size_t btf_enum_scnprintf(const struct btf_type *type, struct btf *btf, char *bf, size_t size, int val) +{ + struct btf_enum *be = btf_enum(type); + const int nr_entries = btf_vlen(type); + + for (int i = 0; i < nr_entries; ++i, ++be) { + if (be->val == val) { + return scnprintf(bf, size, "%s", + btf__name_by_offset(btf, be->name_off)); + } + } + + return 0; +} + +static size_t trace__btf_scnprintf(struct trace *trace, struct syscall_arg_fmt *arg_fmt, char *bf, + size_t size, int val, char *type) +{ + if (trace->btf == NULL) + return 0; + + if (arg_fmt->type == NULL) { + // Check if this is an enum and if we have the BTF type for it. + syscall_arg_fmt__cache_btf_enum(arg_fmt, trace->btf, type); + } + + // Did we manage to find a BTF type for the syscall/tracepoint argument? + if (arg_fmt->type == NULL) + return 0; + + if (btf_is_enum(arg_fmt->type)) + return btf_enum_scnprintf(arg_fmt->type, trace->btf, bf, size, val); + + return 0; +} + +#else // HAVE_LIBBPF_SUPPORT +static size_t trace__btf_scnprintf(struct trace *trace __maybe_unused, struct syscall_arg_fmt *arg_fmt __maybe_unused, + char *bf __maybe_unused, size_t size __maybe_unused, int val __maybe_unused, + char *type __maybe_unused) +{ + return 0; +} + +static bool syscall_arg__strtoul_btf_type(char *bf __maybe_unused, size_t size __maybe_unused, + struct syscall_arg *arg __maybe_unused, u64 *val __maybe_unused) +{ + return false; +} +#endif // HAVE_LIBBPF_SUPPORT + +#define STUL_BTF_TYPE syscall_arg__strtoul_btf_type + #define STRARRAY(name, array) \ { .scnprintf = SCA_STRARRAY, \ .strtoul = STUL_STRARRAY, \ @@ -1238,6 +1378,7 @@ struct syscall { bool is_exit; bool is_open; bool nonexistent; + bool use_btf; struct tep_format_field *args; const char *name; const struct syscall_fmt *fmt; @@ -1744,7 +1885,8 @@ static const struct syscall_arg_fmt *syscall_arg_fmt__find_by_name(const char *n } static struct tep_format_field * -syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field *field) +syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field *field, + bool *use_btf) { struct tep_format_field *last_field = NULL; int len; @@ -1782,6 +1924,9 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field * 7 unsigned long */ arg->scnprintf = SCA_FD; + } else if (strstr(field->type, "enum") && use_btf != NULL) { + *use_btf = true; + arg->strtoul = STUL_BTF_TYPE; } else { const struct syscall_arg_fmt *fmt = syscall_arg_fmt__find_by_name(field->name); @@ -1798,7 +1943,8 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field static int syscall__set_arg_fmts(struct syscall *sc) { - struct tep_format_field *last_field = syscall_arg_fmt__init_array(sc->arg_fmt, sc->args); + struct tep_format_field *last_field = syscall_arg_fmt__init_array(sc->arg_fmt, sc->args, + &sc->use_btf); if (last_field) sc->args_size = last_field->offset + last_field->size; @@ -1811,6 +1957,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) char tp_name[128]; struct syscall *sc; const char *name = syscalltbl__name(trace->sctbl, id); + int err; #ifdef HAVE_SYSCALL_TABLE_SUPPORT if (trace->syscalls.table == NULL) { @@ -1883,15 +2030,21 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat"); - return syscall__set_arg_fmts(sc); + err = syscall__set_arg_fmts(sc); + + /* after calling syscall__set_arg_fmts() we'll know whether use_btf is true */ + if (sc->use_btf) + trace__load_vmlinux_btf(trace); + + return err; } -static int evsel__init_tp_arg_scnprintf(struct evsel *evsel) +static int evsel__init_tp_arg_scnprintf(struct evsel *evsel, bool *use_btf) { struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel); if (fmt != NULL) { - syscall_arg_fmt__init_array(fmt, evsel->tp_format->format.fields); + syscall_arg_fmt__init_array(fmt, evsel->tp_format->format.fields, use_btf); return 0; } @@ -2050,7 +2203,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, unsigned char *args, void *augmented_args, int augmented_args_size, struct trace *trace, struct thread *thread) { - size_t printed = 0; + size_t printed = 0, btf_printed; unsigned long val; u8 bit = 1; struct syscall_arg arg = { @@ -2093,9 +2246,13 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, /* * Suppress this argument if its value is zero and show_zero * property isn't set. + * + * If it has a BTF type, then override the zero suppression knob + * as the common case is for zero in an enum to have an associated entry. */ if (val == 0 && !trace->show_zeros && - !(sc->arg_fmt && sc->arg_fmt[arg.idx].show_zero)) + !(sc->arg_fmt && sc->arg_fmt[arg.idx].show_zero) && + !(sc->arg_fmt && sc->arg_fmt[arg.idx].strtoul == STUL_BTF_TYPE)) continue; printed += scnprintf(bf + printed, size - printed, "%s", printed ? ", " : ""); @@ -2103,6 +2260,13 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, if (trace->show_arg_names) printed += scnprintf(bf + printed, size - printed, "%s: ", field->name); + btf_printed = trace__btf_scnprintf(trace, &sc->arg_fmt[arg.idx], bf + printed, + size - printed, val, field->type); + if (btf_printed) { + printed += btf_printed; + continue; + } + printed += syscall_arg_fmt__scnprintf_val(&sc->arg_fmt[arg.idx], bf + printed, size - printed, &arg, val); } @@ -2749,7 +2913,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, size_t size = sizeof(bf); struct tep_format_field *field = evsel->tp_format->format.fields; struct syscall_arg_fmt *arg = __evsel__syscall_arg_fmt(evsel); - size_t printed = 0; + size_t printed = 0, btf_printed; unsigned long val; u8 bit = 1; struct syscall_arg syscall_arg = { @@ -2791,7 +2955,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, val = syscall_arg_fmt__mask_val(arg, &syscall_arg, val); /* Suppress this argument if its value is zero and show_zero property isn't set. */ - if (val == 0 && !trace->show_zeros && !arg->show_zero) + if (val == 0 && !trace->show_zeros && !arg->show_zero && arg->strtoul != STUL_BTF_TYPE) continue; printed += scnprintf(bf + printed, size - printed, "%s", printed ? ", " : ""); @@ -2799,6 +2963,12 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, if (trace->show_arg_names) printed += scnprintf(bf + printed, size - printed, "%s: ", field->name); + btf_printed = trace__btf_scnprintf(trace, arg, bf + printed, size - printed, val, field->type); + if (btf_printed) { + printed += btf_printed; + continue; + } + printed += syscall_arg_fmt__scnprintf_val(arg, bf + printed, size - printed, &syscall_arg, val); } @@ -3680,7 +3850,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe, return __trace__deliver_event(trace, event->event); } -static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel *evsel, char *arg) +static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel *evsel, char *arg, + char **type) { struct tep_format_field *field; struct syscall_arg_fmt *fmt = __evsel__syscall_arg_fmt(evsel); @@ -3689,13 +3860,15 @@ static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel return NULL; for (field = evsel->tp_format->format.fields; field; field = field->next, ++fmt) - if (strcmp(field->name, arg) == 0) + if (strcmp(field->name, arg) == 0) { + *type = field->type; return fmt; + } return NULL; } -static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel *evsel) +static int trace__expand_filter(struct trace *trace, struct evsel *evsel) { char *tok, *left = evsel->filter, *new_filter = evsel->filter; @@ -3728,14 +3901,14 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel struct syscall_arg_fmt *fmt; int left_size = tok - left, right_size = right_end - right; - char arg[128]; + char arg[128], *type; while (isspace(left[left_size - 1])) --left_size; scnprintf(arg, sizeof(arg), "%.*s", left_size, left); - fmt = evsel__find_syscall_arg_fmt_by_name(evsel, arg); + fmt = evsel__find_syscall_arg_fmt_by_name(evsel, arg, &type); if (fmt == NULL) { pr_err("\"%s\" not found in \"%s\", can't set filter \"%s\"\n", arg, evsel->name, evsel->filter); @@ -3748,6 +3921,9 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel if (fmt->strtoul) { u64 val; struct syscall_arg syscall_arg = { + .trace = trace, + .fmt = fmt, + .type_name = type, .parm = fmt->parm, }; @@ -3959,7 +4135,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = trace__expand_filters(trace, &evsel); if (err) goto out_delete_evlist; - err = evlist__apply_filters(evlist, &evsel); + err = evlist__apply_filters(evlist, &evsel, &trace->opts.target); if (err < 0) goto out_error_apply_filters; @@ -4451,7 +4627,7 @@ static void evsel__set_syscall_arg_fmt(struct evsel *evsel, const char *name) } } -static int evlist__set_syscall_tp_fields(struct evlist *evlist) +static int evlist__set_syscall_tp_fields(struct evlist *evlist, bool *use_btf) { struct evsel *evsel; @@ -4460,7 +4636,7 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist) continue; if (strcmp(evsel->tp_format->system, "syscalls")) { - evsel__init_tp_arg_scnprintf(evsel); + evsel__init_tp_arg_scnprintf(evsel, use_btf); continue; } @@ -4938,11 +5114,16 @@ skip_augmentation: } if (trace.evlist->core.nr_entries > 0) { + bool use_btf = false; + evlist__set_default_evsel_handler(trace.evlist, trace__event_handler); - if (evlist__set_syscall_tp_fields(trace.evlist)) { + if (evlist__set_syscall_tp_fields(trace.evlist, &use_btf)) { perror("failed to set syscalls:* tracepoint fields"); goto out; } + + if (use_btf) + trace__load_vmlinux_btf(&trace); } if (trace.sort_events) { diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 1d18bb89402e..d941bc9d16e9 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -11,6 +11,8 @@ METRIC_TEST_PY = pmu-events/metric_test.py EMPTY_PMU_EVENTS_C = pmu-events/empty-pmu-events.c PMU_EVENTS_C = $(OUTPUT)pmu-events/pmu-events.c METRIC_TEST_LOG = $(OUTPUT)pmu-events/metric_test.log +TEST_EMPTY_PMU_EVENTS_C = $(OUTPUT)pmu-events/test-empty-pmu-events.c +EMPTY_PMU_EVENTS_TEST_LOG = $(OUTPUT)pmu-events/empty-pmu-events.log ifeq ($(JEVENTS_ARCH),) JEVENTS_ARCH=$(SRCARCH) @@ -31,7 +33,15 @@ $(METRIC_TEST_LOG): $(METRIC_TEST_PY) $(METRIC_PY) $(call rule_mkdir) $(Q)$(call echo-cmd,test)$(PYTHON) $< 2> $@ || (cat $@ && false) -$(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) +$(TEST_EMPTY_PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) + $(call rule_mkdir) + $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) none none pmu-events/arch $@ + +$(EMPTY_PMU_EVENTS_TEST_LOG): $(EMPTY_PMU_EVENTS_C) $(TEST_EMPTY_PMU_EVENTS_C) + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)diff -u $^ 2> $@ || (cat $@ && false) + +$(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) $(EMPTY_PMU_EVENTS_TEST_LOG) $(call rule_mkdir) $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@ endif diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json index 18d1f2f76a23..9fe697d12fe0 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json @@ -78,9 +78,6 @@ "ArchStdEvent": "OP_RETIRED" }, { - "ArchStdEvent": "OP_SPEC" - }, - { "PublicDescription": "Operation speculatively executed, NOP", "EventCode": "0x100", "EventName": "NOP_SPEC", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index 5977f5e64212..53660c279286 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -75,6 +75,11 @@ "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, + { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL", "BriefDescription": "Vector store instruction completed." diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index fcf8a8ebe7bd..3789304cb363 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -95,11 +95,6 @@ "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { - "EventCode": "0x44054", - "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instruction completed." - }, - { "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL", "BriefDescription": "A branch completed. All branches are included." @@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." + }, + { + "EventCode": "0x00000038BC", + "EventName": "PM_ISYNC_CMPL", + "BriefDescription": "Isync completion count per thread." + }, + { + "EventCode": "0x000000C088", + "EventName": "PM_LD0_32B_FIN", + "BriefDescription": "256-bit load finished in the LD0 load execution unit." + }, + { + "EventCode": "0x000000C888", + "EventName": "PM_LD1_32B_FIN", + "BriefDescription": "256-bit load finished in the LD1 load execution unit." + }, + { + "EventCode": "0x000000C090", + "EventName": "PM_LD0_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C890", + "EventName": "PM_LD1_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C0A4", + "EventName": "PM_ST0_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8A4", + "EventName": "PM_ST1_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8B8", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest." + }, + { + "EventCode": "0x000000D0B4", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + { + "EventCode": "0x000000F880", + "EventName": "PM_SNOOP_TLBIE_CYC", + "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU." + }, + { + "EventCode": "0x000000F084", + "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC", + "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked." + }, + { + "EventCode": "0x000000F884", + "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC", + "BriefDescription": "TLBIE snoop cycles in which older stores are still draining." + }, + { + "EventCode": "0x000000F088", + "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC", + "BriefDescription": "TLBIE snoop cycles in which older loads are still draining." + }, + { + "EventCode": "0x000000F08C", + "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC", + "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation." + }, + { + "EventCode": "0x0000004884", + "EventName": "PM_NO_FETCH_IBUF_FULL_CYC", + "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers." + }, + { + "EventCode": "0x00000048B4", + "EventName": "PM_BR_TKN_UNCOND_FIN", + "BriefDescription": "An unconditional branch finished. All unconditional branches are taken." + }, + { + "EventCode": "0x0B0000016080", + "EventName": "PM_L2_TLBIE_SLBIE_START", + "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000016880", + "EventName": "PM_L2_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_TLBIE_SLBIE_SENT to obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000026880", + "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: 'inflight' means SnpTLB has been sent to core(ie doesn't include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a 'hottemp' delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ] diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 13727421d424..c592079982fb 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -1,196 +1,193 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * An empty pmu-events.c file used when there is no architecture json files in - * arch or when the jevents.py script cannot be run. - * - * The test cpu/soc is provided for testing. - */ -#include "pmu-events/pmu-events.h" + +/* SPDX-License-Identifier: GPL-2.0 */ +/* THIS FILE WAS AUTOGENERATED BY jevents.py arch=none model=none ! */ + +#include <pmu-events/pmu-events.h> #include "util/header.h" #include "util/pmu.h" #include <string.h> #include <stddef.h> -static const struct pmu_event pmu_events__test_soc_cpu[] = { - { - .name = "l3_cache_rd", - .event = "event=0x40", - .desc = "L3 cache access, read", - .topic = "cache", - .long_desc = "Attributable Level 3 cache access, read", - }, - { - .name = "segment_reg_loads.any", - .event = "event=0x6,period=200000,umask=0x80", - .desc = "Number of segment register loads", - .topic = "other", - }, - { - .name = "dispatch_blocked.any", - .event = "event=0x9,period=200000,umask=0x20", - .desc = "Memory cluster signals to block micro-op dispatch for any reason", - .topic = "other", - }, - { - .name = "eist_trans", - .event = "event=0x3a,period=200000,umask=0x0", - .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", - .topic = "other", - }, - { - .name = "uncore_hisi_ddrc.flux_wcmd", - .event = "event=0x2", - .desc = "DDRC write commands. Unit: hisi_sccl,ddrc ", - .topic = "uncore", - .long_desc = "DDRC write commands", - .pmu = "hisi_sccl,ddrc", - }, - { - .name = "unc_cbo_xsnp_response.miss_eviction", - .event = "event=0x22,umask=0x81", - .desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core. Unit: uncore_cbox ", - .topic = "uncore", - .long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core", - .pmu = "uncore_cbox", - }, - { - .name = "event-hyphen", - .event = "event=0xe0,umask=0x00", - .desc = "UNC_CBO_HYPHEN. Unit: uncore_cbox ", - .topic = "uncore", - .long_desc = "UNC_CBO_HYPHEN", - .pmu = "uncore_cbox", - }, - { - .name = "event-two-hyph", - .event = "event=0xc0,umask=0x00", - .desc = "UNC_CBO_TWO_HYPH. Unit: uncore_cbox ", - .topic = "uncore", - .long_desc = "UNC_CBO_TWO_HYPH", - .pmu = "uncore_cbox", - }, - { - .name = "uncore_hisi_l3c.rd_hit_cpipe", - .event = "event=0x7", - .desc = "Total read hits. Unit: hisi_sccl,l3c ", - .topic = "uncore", - .long_desc = "Total read hits", - .pmu = "hisi_sccl,l3c", - }, - { - .name = "uncore_imc_free_running.cache_miss", - .event = "event=0x12", - .desc = "Total cache misses. Unit: uncore_imc_free_running ", - .topic = "uncore", - .long_desc = "Total cache misses", - .pmu = "uncore_imc_free_running", - }, - { - .name = "uncore_imc.cache_hits", - .event = "event=0x34", - .desc = "Total cache hits. Unit: uncore_imc ", - .topic = "uncore", - .long_desc = "Total cache hits", - .pmu = "uncore_imc", - }, - { - .name = "bp_l1_btb_correct", - .event = "event=0x8a", - .desc = "L1 BTB Correction", - .topic = "branch", - }, - { - .name = "bp_l2_btb_correct", - .event = "event=0x8b", - .desc = "L2 BTB Correction", - .topic = "branch", - }, - { - .name = 0, - .event = 0, - .desc = 0, - }, +struct compact_pmu_event { + int offset; }; -static const struct pmu_metric pmu_metrics__test_soc_cpu[] = { - { - .metric_expr = "1 / IPC", - .metric_name = "CPI", - }, - { - .metric_expr = "inst_retired.any / cpu_clk_unhalted.thread", - .metric_name = "IPC", - .metric_group = "group1", - }, - { - .metric_expr = "idq_uops_not_delivered.core / (4 * (( ( cpu_clk_unhalted.thread / 2 ) * " - "( 1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk ) )))", - .metric_name = "Frontend_Bound_SMT", - }, - { - .metric_expr = "l1d\\-loads\\-misses / inst_retired.any", - .metric_name = "dcache_miss_cpi", - }, - { - .metric_expr = "l1i\\-loads\\-misses / inst_retired.any", - .metric_name = "icache_miss_cycles", - }, - { - .metric_expr = "(dcache_miss_cpi + icache_miss_cycles)", - .metric_name = "cache_miss_cycles", - .metric_group = "group1", - }, - { - .metric_expr = "l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit", - .metric_name = "DCache_L2_All_Hits", - }, - { - .metric_expr = "max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + " - "l2_rqsts.pf_miss + l2_rqsts.rfo_miss", - .metric_name = "DCache_L2_All_Miss", - }, - { - .metric_expr = "DCache_L2_All_Hits + DCache_L2_All_Miss", - .metric_name = "DCache_L2_All", - }, - { - .metric_expr = "d_ratio(DCache_L2_All_Hits, DCache_L2_All)", - .metric_name = "DCache_L2_Hits", - }, - { - .metric_expr = "d_ratio(DCache_L2_All_Miss, DCache_L2_All)", - .metric_name = "DCache_L2_Misses", - }, - { - .metric_expr = "ipc + M2", - .metric_name = "M1", - }, - { - .metric_expr = "ipc + M1", - .metric_name = "M2", - }, - { - .metric_expr = "1/M3", - .metric_name = "M3", - }, - { - .metric_expr = "64 * l1d.replacement / 1000000000 / duration_time", - .metric_name = "L1D_Cache_Fill_BW", - }, - { - .metric_expr = 0, - .metric_name = 0, - }, +struct pmu_table_entry { + const struct compact_pmu_event *entries; + uint32_t num_entries; + struct compact_pmu_event pmu_name; +}; + +static const char *const big_c_string = +/* offset=0 */ "default_core\000" +/* offset=13 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000" +/* offset=72 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000" +/* offset=131 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000" +/* offset=226 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000" +/* offset=325 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000" +/* offset=455 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000" +/* offset=570 */ "hisi_sccl,ddrc\000" +/* offset=585 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000" +/* offset=671 */ "uncore_cbox\000" +/* offset=683 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000" +/* offset=914 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000" +/* offset=979 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000" +/* offset=1050 */ "hisi_sccl,l3c\000" +/* offset=1064 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000" +/* offset=1144 */ "uncore_imc_free_running\000" +/* offset=1168 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000" +/* offset=1263 */ "uncore_imc\000" +/* offset=1274 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000" +/* offset=1352 */ "uncore_sys_ddr_pmu\000" +/* offset=1371 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000" +/* offset=1444 */ "uncore_sys_ccn_pmu\000" +/* offset=1463 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000" +/* offset=1537 */ "uncore_sys_cmn_pmu\000" +/* offset=1556 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000" +/* offset=1696 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000" +/* offset=1718 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000" +/* offset=1781 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000" +/* offset=1947 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" +/* offset=2011 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" +/* offset=2078 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000" +/* offset=2149 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000" +/* offset=2243 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000" +/* offset=2377 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000" +/* offset=2441 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000" +/* offset=2509 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000" +/* offset=2579 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000" +/* offset=2601 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000" +/* offset=2623 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000" +/* offset=2643 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000" +; + +static const struct compact_pmu_event pmu_events__test_soc_cpu_default_core[] = { +{ 13 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000 */ +{ 72 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000 */ +{ 325 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000 */ +{ 455 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000 */ +{ 131 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000 */ +{ 226 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_ddrc[] = { +{ 585 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_l3c[] = { +{ 1064 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_cbox[] = { +{ 914 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000 */ +{ 979 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000 */ +{ 683 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc[] = { +{ 1274 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc_free_running[] = { +{ 1168 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000 */ + +}; + +const struct pmu_table_entry pmu_events__test_soc_cpu[] = { +{ + .entries = pmu_events__test_soc_cpu_default_core, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_default_core), + .pmu_name = { 0 /* default_core\000 */ }, +}, +{ + .entries = pmu_events__test_soc_cpu_hisi_sccl_ddrc, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_ddrc), + .pmu_name = { 570 /* hisi_sccl,ddrc\000 */ }, +}, +{ + .entries = pmu_events__test_soc_cpu_hisi_sccl_l3c, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_l3c), + .pmu_name = { 1050 /* hisi_sccl,l3c\000 */ }, +}, +{ + .entries = pmu_events__test_soc_cpu_uncore_cbox, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_cbox), + .pmu_name = { 671 /* uncore_cbox\000 */ }, +}, +{ + .entries = pmu_events__test_soc_cpu_uncore_imc, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc), + .pmu_name = { 1263 /* uncore_imc\000 */ }, +}, +{ + .entries = pmu_events__test_soc_cpu_uncore_imc_free_running, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc_free_running), + .pmu_name = { 1144 /* uncore_imc_free_running\000 */ }, +}, }; +static const struct compact_pmu_event pmu_metrics__test_soc_cpu_default_core[] = { +{ 1696 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */ +{ 2377 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */ +{ 2149 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */ +{ 2243 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */ +{ 2441 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ +{ 2509 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ +{ 1781 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */ +{ 1718 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */ +{ 2643 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */ +{ 2579 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */ +{ 2601 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */ +{ 2623 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */ +{ 2078 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */ +{ 1947 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ +{ 2011 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ + +}; + +const struct pmu_table_entry pmu_metrics__test_soc_cpu[] = { +{ + .entries = pmu_metrics__test_soc_cpu_default_core, + .num_entries = ARRAY_SIZE(pmu_metrics__test_soc_cpu_default_core), + .pmu_name = { 0 /* default_core\000 */ }, +}, +}; + +static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ccn_pmu[] = { +{ 1463 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_cmn_pmu[] = { +{ 1556 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000 */ +}; +static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ddr_pmu[] = { +{ 1371 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000 */ + +}; + +const struct pmu_table_entry pmu_events__test_soc_sys[] = { +{ + .entries = pmu_events__test_soc_sys_uncore_sys_ccn_pmu, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ccn_pmu), + .pmu_name = { 1444 /* uncore_sys_ccn_pmu\000 */ }, +}, +{ + .entries = pmu_events__test_soc_sys_uncore_sys_cmn_pmu, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_cmn_pmu), + .pmu_name = { 1537 /* uncore_sys_cmn_pmu\000 */ }, +}, +{ + .entries = pmu_events__test_soc_sys_uncore_sys_ddr_pmu, + .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ddr_pmu), + .pmu_name = { 1352 /* uncore_sys_ddr_pmu\000 */ }, +}, +}; + + /* Struct used to make the PMU event table implementation opaque to callers. */ struct pmu_events_table { - const struct pmu_event *entries; + const struct pmu_table_entry *pmus; + uint32_t num_pmus; }; /* Struct used to make the PMU metric table implementation opaque to callers. */ struct pmu_metrics_table { - const struct pmu_metric *entries; + const struct pmu_table_entry *pmus; + uint32_t num_pmus; }; /* @@ -202,92 +199,191 @@ struct pmu_metrics_table { * The cpuid can contain any character other than the comma. */ struct pmu_events_map { - const char *arch; - const char *cpuid; - const struct pmu_events_table event_table; - const struct pmu_metrics_table metric_table; + const char *arch; + const char *cpuid; + struct pmu_events_table event_table; + struct pmu_metrics_table metric_table; }; /* * Global table mapping each known CPU for the architecture to its * table of PMU events. */ -static const struct pmu_events_map pmu_events_map[] = { - { - .arch = "testarch", - .cpuid = "testcpu", - .event_table = { pmu_events__test_soc_cpu }, - .metric_table = { pmu_metrics__test_soc_cpu }, - }, - { - .arch = 0, - .cpuid = 0, - .event_table = { 0 }, - .metric_table = { 0 }, - }, -}; - -static const struct pmu_event pmu_events__test_soc_sys[] = { - { - .name = "sys_ddr_pmu.write_cycles", - .event = "event=0x2b", - .desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu ", - .compat = "v8", - .topic = "uncore", - .pmu = "uncore_sys_ddr_pmu", - }, - { - .name = "sys_ccn_pmu.read_cycles", - .event = "config=0x2c", - .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", - .compat = "0x01", - .topic = "uncore", - .pmu = "uncore_sys_ccn_pmu", - }, - { - .name = "sys_cmn_pmu.hnf_cache_miss", - .event = "eventid=0x1,type=0x5", - .desc = "Counts total cache misses in first lookup result (high priority). Unit: uncore_sys_cmn_pmu ", - .compat = "(434|436|43c|43a).*", - .topic = "uncore", - .pmu = "uncore_sys_cmn_pmu", - }, - { - .name = 0, - .event = 0, - .desc = 0, - }, +const struct pmu_events_map pmu_events_map[] = { +{ + .arch = "testarch", + .cpuid = "testcpu", + .event_table = { + .pmus = pmu_events__test_soc_cpu, + .num_pmus = ARRAY_SIZE(pmu_events__test_soc_cpu), + }, + .metric_table = { + .pmus = pmu_metrics__test_soc_cpu, + .num_pmus = ARRAY_SIZE(pmu_metrics__test_soc_cpu), + } +}, +{ + .arch = 0, + .cpuid = 0, + .event_table = { 0, 0 }, + .metric_table = { 0, 0 }, +} }; struct pmu_sys_events { const char *name; - const struct pmu_events_table table; + struct pmu_events_table event_table; + struct pmu_metrics_table metric_table; }; static const struct pmu_sys_events pmu_sys_event_tables[] = { { - .table = { pmu_events__test_soc_sys }, + .event_table = { + .pmus = pmu_events__test_soc_sys, + .num_pmus = ARRAY_SIZE(pmu_events__test_soc_sys) + }, .name = "pmu_events__test_soc_sys", }, { - .table = { 0 } + .event_table = { 0, 0 }, + .metric_table = { 0, 0 }, }, }; -int pmu_events_table__for_each_event(const struct pmu_events_table *table, struct perf_pmu *pmu, - pmu_event_iter_fn fn, void *data) +static void decompress_event(int offset, struct pmu_event *pe) +{ + const char *p = &big_c_string[offset]; + + pe->name = (*p == '\0' ? NULL : p); + while (*p++); + pe->topic = (*p == '\0' ? NULL : p); + while (*p++); + pe->desc = (*p == '\0' ? NULL : p); + while (*p++); + pe->event = (*p == '\0' ? NULL : p); + while (*p++); + pe->compat = (*p == '\0' ? NULL : p); + while (*p++); + pe->deprecated = *p - '0'; + p++; + pe->perpkg = *p - '0'; + p++; + pe->unit = (*p == '\0' ? NULL : p); + while (*p++); + pe->long_desc = (*p == '\0' ? NULL : p); +} + +static void decompress_metric(int offset, struct pmu_metric *pm) { - for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { - int ret; + const char *p = &big_c_string[offset]; + + pm->metric_name = (*p == '\0' ? NULL : p); + while (*p++); + pm->metric_group = (*p == '\0' ? NULL : p); + while (*p++); + pm->metric_expr = (*p == '\0' ? NULL : p); + while (*p++); + pm->metric_threshold = (*p == '\0' ? NULL : p); + while (*p++); + pm->desc = (*p == '\0' ? NULL : p); + while (*p++); + pm->long_desc = (*p == '\0' ? NULL : p); + while (*p++); + pm->unit = (*p == '\0' ? NULL : p); + while (*p++); + pm->compat = (*p == '\0' ? NULL : p); + while (*p++); + pm->metricgroup_no_group = (*p == '\0' ? NULL : p); + while (*p++); + pm->default_metricgroup_name = (*p == '\0' ? NULL : p); + while (*p++); + pm->aggr_mode = *p - '0'; + p++; + pm->event_grouping = *p - '0'; +} - if (pmu && !pmu__name_match(pmu, pe->pmu)) +static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *table, + const struct pmu_table_entry *pmu, + pmu_event_iter_fn fn, + void *data) +{ + int ret; + struct pmu_event pe = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + + for (uint32_t i = 0; i < pmu->num_entries; i++) { + decompress_event(pmu->entries[i].offset, &pe); + if (!pe.name) continue; + ret = fn(&pe, table, data); + if (ret) + return ret; + } + return 0; + } + +static int pmu_events_table__find_event_pmu(const struct pmu_events_table *table, + const struct pmu_table_entry *pmu, + const char *name, + pmu_event_iter_fn fn, + void *data) +{ + struct pmu_event pe = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + int low = 0, high = pmu->num_entries - 1; - ret = fn(pe, table, data); - if (ret) - return ret; - } - return 0; + while (low <= high) { + int cmp, mid = (low + high) / 2; + + decompress_event(pmu->entries[mid].offset, &pe); + + if (!pe.name && !name) + goto do_call; + + if (!pe.name && name) { + low = mid + 1; + continue; + } + if (pe.name && !name) { + high = mid - 1; + continue; + } + + cmp = strcasecmp(pe.name, name); + if (cmp < 0) { + low = mid + 1; + continue; + } + if (cmp > 0) { + high = mid - 1; + continue; + } + do_call: + return fn ? fn(&pe, table, data) : 0; + } + return PMU_EVENTS__NOT_FOUND; +} + +int pmu_events_table__for_each_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + pmu_event_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + int ret; + + if (pmu && !pmu__name_match(pmu, pmu_name)) + continue; + + ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); + if (pmu || ret) + return ret; + } + return 0; } int pmu_events_table__find_event(const struct pmu_events_table *table, @@ -296,14 +392,19 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, void *data) { - for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { - if (pmu && !pmu__name_match(pmu, pe->pmu)) + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + int ret; + + if (!pmu__name_match(pmu, pmu_name)) continue; - if (!strcasecmp(pe->name, name)) - return fn(pe, table, data); - } - return -1000; + ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); + if (ret != PMU_EVENTS__NOT_FOUND) + return ret; + } + return PMU_EVENTS__NOT_FOUND; } size_t pmu_events_table__num_events(const struct pmu_events_table *table, @@ -311,160 +412,253 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, { size_t count = 0; - for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { - if (pmu && !pmu__name_match(pmu, pe->pmu)) - continue; + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - count++; - } + if (pmu__name_match(pmu, pmu_name)) + count += table_pmu->num_entries; + } return count; } -int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, - void *data) +static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table *table, + const struct pmu_table_entry *pmu, + pmu_metric_iter_fn fn, + void *data) +{ + int ret; + struct pmu_metric pm = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + + for (uint32_t i = 0; i < pmu->num_entries; i++) { + decompress_metric(pmu->entries[i].offset, &pm); + if (!pm.metric_expr) + continue; + ret = fn(&pm, table, data); + if (ret) + return ret; + } + return 0; +} + +int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, + pmu_metric_iter_fn fn, + void *data) { - for (const struct pmu_metric *pm = &table->entries[0]; pm->metric_expr; pm++) { - int ret = fn(pm, table, data); + for (size_t i = 0; i < table->num_pmus; i++) { + int ret = pmu_metrics_table__for_each_metric_pmu(table, &table->pmus[i], + fn, data); + + if (ret) + return ret; + } + return 0; +} - if (ret) - return ret; - } - return 0; +static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu) +{ + static struct { + const struct pmu_events_map *map; + struct perf_pmu *pmu; + } last_result; + static struct { + const struct pmu_events_map *map; + char *cpuid; + } last_map_search; + static bool has_last_result, has_last_map_search; + const struct pmu_events_map *map = NULL; + char *cpuid = NULL; + size_t i; + + if (has_last_result && last_result.pmu == pmu) + return last_result.map; + + cpuid = perf_pmu__getcpuid(pmu); + + /* + * On some platforms which uses cpus map, cpuid can be NULL for + * PMUs other than CORE PMUs. + */ + if (!cpuid) + goto out_update_last_result; + + if (has_last_map_search && !strcmp(last_map_search.cpuid, cpuid)) { + map = last_map_search.map; + free(cpuid); + } else { + i = 0; + for (;;) { + map = &pmu_events_map[i++]; + + if (!map->arch) { + map = NULL; + break; + } + + if (!strcmp_cpuid_str(map->cpuid, cpuid)) + break; + } + free(last_map_search.cpuid); + last_map_search.cpuid = cpuid; + last_map_search.map = map; + has_last_map_search = true; + } +out_update_last_result: + last_result.pmu = pmu; + last_result.map = map; + has_last_result = true; + return map; } const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) { - const struct pmu_events_table *table = NULL; - char *cpuid = perf_pmu__getcpuid(pmu); - int i; + const struct pmu_events_map *map = map_for_pmu(pmu); - /* on some platforms which uses cpus map, cpuid can be NULL for - * PMUs other than CORE PMUs. - */ - if (!cpuid) - return NULL; + if (!map) + return NULL; - i = 0; - for (;;) { - const struct pmu_events_map *map = &pmu_events_map[i++]; + if (!pmu) + return &map->event_table; - if (!map->cpuid) - break; + for (size_t i = 0; i < map->event_table.num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->event_table; - break; - } - } - free(cpuid); - return table; + if (pmu__name_match(pmu, pmu_name)) + return &map->event_table; + } + return NULL; } const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu) { - const struct pmu_metrics_table *table = NULL; - char *cpuid = perf_pmu__getcpuid(pmu); - int i; + const struct pmu_events_map *map = map_for_pmu(pmu); - /* on some platforms which uses cpus map, cpuid can be NULL for - * PMUs other than CORE PMUs. - */ - if (!cpuid) - return NULL; + if (!map) + return NULL; - i = 0; - for (;;) { - const struct pmu_events_map *map = &pmu_events_map[i++]; + if (!pmu) + return &map->metric_table; - if (!map->cpuid) - break; + for (size_t i = 0; i < map->metric_table.num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->metric_table; - break; - } - } - free(cpuid); - return table; + if (pmu__name_match(pmu, pmu_name)) + return &map->metric_table; + } + return NULL; } const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid) { - for (const struct pmu_events_map *tables = &pmu_events_map[0]; - tables->arch; - tables++) { - if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) - return &tables->event_table; - } - return NULL; + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) + return &tables->event_table; + } + return NULL; } const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid) { - for (const struct pmu_events_map *tables = &pmu_events_map[0]; - tables->arch; - tables++) { - if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) - return &tables->metric_table; - } - return NULL; + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) + return &tables->metric_table; + } + return NULL; } int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data) { - for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_events_table__for_each_event(&tables->event_table, - /*pmu=*/ NULL, fn, data); - - if (ret) - return ret; - } - return 0; + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + int ret = pmu_events_table__for_each_event(&tables->event_table, + /*pmu=*/ NULL, fn, data); + + if (ret) + return ret; + } + return 0; } int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data) { - for (const struct pmu_events_map *tables = &pmu_events_map[0]; - tables->arch; - tables++) { - int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); - - if (ret) - return ret; - } - return 0; + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); + + if (ret) + return ret; + } + return 0; } const struct pmu_events_table *find_sys_events_table(const char *name) { - for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; - tables->name; - tables++) { - if (!strcmp(tables->name, name)) - return &tables->table; - } - return NULL; + for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + tables->name; + tables++) { + if (!strcmp(tables->name, name)) + return &tables->event_table; + } + return NULL; } int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data) { - for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; - tables->name; - tables++) { - int ret = pmu_events_table__for_each_event(&tables->table, /*pmu=*/ NULL, fn, data); - - if (ret) - return ret; - } - return 0; + for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + tables->name; + tables++) { + int ret = pmu_events_table__for_each_event(&tables->event_table, + /*pmu=*/ NULL, fn, data); + + if (ret) + return ret; + } + return 0; } -int pmu_for_each_sys_metric(pmu_metric_iter_fn fn __maybe_unused, void *data __maybe_unused) +int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data) { - return 0; + for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + tables->name; + tables++) { + int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); + + if (ret) + return ret; + } + return 0; } -const char *describe_metricgroup(const char *group __maybe_unused) +static const int metricgroups[][2] = { + +}; + +const char *describe_metricgroup(const char *group) { - return NULL; + int low = 0, high = (int)ARRAY_SIZE(metricgroups) - 1; + + while (low <= high) { + int mid = (low + high) / 2; + const char *mgroup = &big_c_string[metricgroups[mid][0]]; + int cmp = strcmp(mgroup, group); + + if (cmp == 0) { + return &big_c_string[metricgroups[mid][1]]; + } else if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + } + } + return NULL; } diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ac9b7ca41856..1d96b2204e52 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -503,8 +503,11 @@ def print_pending_events() -> None: first = True last_pmu = None + last_name = None pmus = set() for event in sorted(_pending_events, key=event_cmp_key): + if last_pmu and last_pmu == event.pmu: + assert event.name != last_name, f"Duplicate event: {last_pmu}/{last_name}/ in {_pending_events_tblname}" if event.pmu != last_pmu: if not first: _args.output_file.write('};\n') @@ -516,6 +519,7 @@ def print_pending_events() -> None: pmus.add((event.pmu, pmu_name)) _args.output_file.write(event.to_c_string(metric=False)) + last_name = event.name _pending_events = [] _args.output_file.write(f""" @@ -906,7 +910,7 @@ static int pmu_events_table__find_event_pmu(const struct pmu_events_table *table do_call: return fn ? fn(&pe, table, data) : 0; } - return -1000; + return PMU_EVENTS__NOT_FOUND; } int pmu_events_table__for_each_event(const struct pmu_events_table *table, @@ -944,10 +948,10 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); - if (ret != -1000) + if (ret != PMU_EVENTS__NOT_FOUND) return ret; } - return -1000; + return PMU_EVENTS__NOT_FOUND; } size_t pmu_events_table__num_events(const struct pmu_events_table *table, @@ -1256,6 +1260,10 @@ such as "arm/cortex-a34".''', 'output_file', type=argparse.FileType('w', encoding='utf-8'), nargs='?', default=sys.stdout) _args = ap.parse_args() + _args.output_file.write(f""" +/* SPDX-License-Identifier: GPL-2.0 */ +/* THIS FILE WAS AUTOGENERATED BY jevents.py arch={_args.arch} model={_args.model} ! */ +""") _args.output_file.write(""" #include <pmu-events/pmu-events.h> #include "util/header.h" @@ -1281,7 +1289,7 @@ struct pmu_table_entry { if item.name == _args.arch or _args.arch == 'all' or item.name == 'test': archs.append(item.name) - if len(archs) < 2: + if len(archs) < 2 and _args.arch != 'none': raise IOError(f'Missing architecture directory \'{_args.arch}\'') archs.sort() diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index f5aa96f1685c..5435ad92180c 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -70,6 +70,8 @@ struct pmu_metric { struct pmu_events_table; struct pmu_metrics_table; +#define PMU_EVENTS__NOT_FOUND -1000 + typedef int (*pmu_event_iter_fn)(const struct pmu_event *pe, const struct pmu_events_table *table, void *data); @@ -82,6 +84,13 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, struct perf_pmu *pmu, pmu_event_iter_fn fn, void *data); +/* + * Search for table and entry matching with pmu__name_match. Each matching event + * has fn called on it. 0 implies to success/continue the search while non-zero + * means to terminate. The special value PMU_EVENTS__NOT_FOUND is used to + * indicate no event was found in one of the tables which doesn't terminate the + * search of all tables. + */ int pmu_events_table__find_event(const struct pmu_events_table *table, struct perf_pmu *pmu, const char *name, diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py index d973c2baed1c..7aff02d84ffb 100755 --- a/tools/perf/scripts/python/arm-cs-trace-disasm.py +++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py @@ -192,17 +192,16 @@ def process_event(param_dict): ip = sample["ip"] addr = sample["addr"] + if (options.verbose == True): + print("Event type: %s" % name) + print_sample(sample) + # Initialize CPU data if it's empty, and directly return back # if this is the first tracing event for this CPU. if (cpu_data.get(str(cpu) + 'addr') == None): cpu_data[str(cpu) + 'addr'] = addr return - - if (options.verbose == True): - print("Event type: %s" % name) - print_sample(sample) - # If cannot find dso so cannot dump assembler, bail out if (dso == '[unknown]'): return diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index c3d84b67ca8e..470a9709427d 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -152,6 +152,7 @@ static struct test_workload *workloads[] = { &workload__sqrtloop, &workload__brstack, &workload__datasym, + &workload__landlock, }; static int num_subtests(const struct test_suite *t) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index a1f8adf85367..8a9edf758f10 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -70,6 +70,7 @@ make_python_perf_so := $(python_perf_so) make_debug := DEBUG=1 make_nondistro := BUILD_NONDISTRO=1 make_extra_tests := EXTRA_TESTS=1 +make_jevents_all := JEVENTS_ARCH=all make_no_bpf_skel := BUILD_BPF_SKEL=0 make_gen_vmlinux_h := GEN_VMLINUX_H=1 make_no_libperl := NO_LIBPERL=1 @@ -140,6 +141,7 @@ run += make_python_perf_so run += make_debug run += make_nondistro run += make_extra_tests +run += make_jevents_all run += make_no_bpf_skel run += make_gen_vmlinux_h run += make_no_libperl diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 40132655ccd1..0b2f04a55d7b 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -18,9 +18,6 @@ #include <sys/stat.h> #include <sys/types.h> -/* Fake PMUs created in temp directory. */ -static LIST_HEAD(test_pmus); - /* Cleanup test PMU directory. */ static int test_pmu_put(const char *dir, struct perf_pmu *pmu) { diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py index a2d235252183..0b94216c9c46 100644 --- a/tools/perf/tests/shell/lib/perf_metric_validation.py +++ b/tools/perf/tests/shell/lib/perf_metric_validation.py @@ -95,7 +95,7 @@ class Validator: indent=4) def get_results(self, idx: int = 0): - return self.results[idx] + return self.results.get(idx) def get_bounds(self, lb, ub, error, alias={}, ridx: int = 0) -> list: """ @@ -173,7 +173,10 @@ class Validator: pcnt = 0 tcnt = 0 rerun = list() - for name, val in self.get_results().items(): + results = self.get_results() + if not results: + return + for name, val in results.items(): if val < 0: negmetric[name] = val rerun.append(name) @@ -532,6 +535,9 @@ class Validator: ''' if not self.collectlist: self.parse_perf_metrics() + if not self.metrics: + print("No metric found for testing") + return 0 self.create_rules() for i in range(0, len(self.workloads)): self.wlidx = i diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh index 31c593966e8c..c5882d620db7 100755 --- a/tools/perf/tests/shell/record_bpf_filter.sh +++ b/tools/perf/tests/shell/record_bpf_filter.sh @@ -22,15 +22,16 @@ trap trap_cleanup EXIT TERM INT test_bpf_filter_priv() { echo "Checking BPF-filter privilege" - if [ "$(id -u)" != 0 ] - then - echo "bpf-filter test [Skipped permission]" - err=2 - return - fi if ! perf record -e task-clock --filter 'period > 1' \ -o /dev/null --quiet true 2>&1 then + if [ "$(id -u)" != 0 ] + then + echo "try 'sudo perf record --setup-filter pin' first." + echo "bpf-filter test [Skipped permission]" + err=2 + return + fi echo "bpf-filter test [Skipped missing BPF support]" err=2 return diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh index c1a603653662..d3e2958d2242 100755 --- a/tools/perf/tests/shell/script.sh +++ b/tools/perf/tests/shell/script.sh @@ -61,7 +61,10 @@ _end_of_file_ esac perf record $cmd_flags -o "${perfdatafile}" true + # Disable lsan to avoid warnings about python memory leaks. + export ASAN_OPTIONS=detect_leaks=0 perf script -i "${perfdatafile}" -s "${db_test}" + export ASAN_OPTIONS= echo "DB test [Success]" } diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh index 92d15154ba79..cb02bf23e6a5 100755 --- a/tools/perf/tests/shell/test_task_analyzer.sh +++ b/tools/perf/tests/shell/test_task_analyzer.sh @@ -11,6 +11,9 @@ if [ -e "$perfdir/scripts/python/Perf-Trace-Util" ]; then export PERF_EXEC_PATH=$perfdir fi +# Disable lsan to avoid warnings about python memory leaks. +export ASAN_OPTIONS=detect_leaks=0 + cleanup() { rm -f perf.data rm -f perf.data.old diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh new file mode 100755 index 000000000000..7d407b52bea5 --- /dev/null +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -0,0 +1,61 @@ +#!/bin/sh +# perf trace enum augmentation tests +# SPDX-License-Identifier: GPL-2.0 + +err=0 +set -e + +syscall="landlock_add_rule" +non_syscall="timer:hrtimer_init,timer:hrtimer_start" + +TESTPROG="perf test -w landlock" + +. "$(dirname $0)"/lib/probe.sh +skip_if_no_perf_trace || exit 2 + +check_vmlinux() { + echo "Checking if vmlinux exists" + if ! ls /sys/kernel/btf/vmlinux 1>/dev/null 2>&1 + then + echo "trace+enum test [Skipped missing vmlinux BTF support]" + err=2 + fi +} + +trace_landlock() { + echo "Tracing syscall ${syscall}" + + # test flight just to see if landlock_add_rule and libbpf are available + $TESTPROG + + if perf trace -e $syscall $TESTPROG 2>&1 | \ + grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*" + then + err=0 + else + err=1 + fi +} + +trace_non_syscall() { + echo "Tracing non-syscall tracepoint ${non-syscall}" + if perf trace -e $non_syscall --max-events=1 2>&1 | \ + grep -q -E '.*timer:hrtimer_.*\(.*mode: HRTIMER_MODE_.*\)$' + then + err=0 + else + err=1 + fi +} + +check_vmlinux + +if [ $err = 0 ]; then + trace_landlock +fi + +if [ $err = 0 ]; then + trace_non_syscall +fi + +exit $err diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 3aa7701ee0e9..6ea2be86b7bf 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -205,6 +205,7 @@ DECLARE_WORKLOAD(leafloop); DECLARE_WORKLOAD(sqrtloop); DECLARE_WORKLOAD(brstack); DECLARE_WORKLOAD(datasym); +DECLARE_WORKLOAD(landlock); extern const char *dso_to_test; extern const char *test_objdump_path; diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build index 48bf0d3b0f3d..5af17206f04d 100644 --- a/tools/perf/tests/workloads/Build +++ b/tools/perf/tests/workloads/Build @@ -6,6 +6,7 @@ perf-test-y += leafloop.o perf-test-y += sqrtloop.o perf-test-y += brstack.o perf-test-y += datasym.o +perf-test-y += landlock.o CFLAGS_sqrtloop.o = -g -O0 -fno-inline -U_FORTIFY_SOURCE CFLAGS_leafloop.o = -g -O0 -fno-inline -fno-omit-frame-pointer -U_FORTIFY_SOURCE diff --git a/tools/perf/tests/workloads/landlock.c b/tools/perf/tests/workloads/landlock.c new file mode 100644 index 000000000000..e2b5ef647c09 --- /dev/null +++ b/tools/perf/tests/workloads/landlock.c @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/compiler.h> +#include <linux/types.h> +#include <unistd.h> +#include "../tests.h" + +/* This workload was initially added to test enum augmentation with BTF in perf + * trace because its the only syscall that has an enum argument. Since it is + * a recent addition to the Linux kernel (at the time of the introduction of this + * 'perf test' workload) we just add the required types and defines here instead + * of including linux/landlock, that isn't available in older systems. + * + * We are not interested in the the result of the syscall, just in intercepting + * its arguments. + */ + +#ifndef __NR_landlock_add_rule +#define __NR_landlock_add_rule 445 +#endif + +#ifndef LANDLOCK_ACCESS_FS_READ_FILE +#define LANDLOCK_ACCESS_FS_READ_FILE (1ULL << 2) + +#define LANDLOCK_RULE_PATH_BENEATH 1 + +struct landlock_path_beneath_attr { + __u64 allowed_access; + __s32 parent_fd; +}; +#endif + +#ifndef LANDLOCK_ACCESS_NET_CONNECT_TCP +#define LANDLOCK_ACCESS_NET_CONNECT_TCP (1ULL << 1) + +#define LANDLOCK_RULE_NET_PORT 2 + +struct landlock_net_port_attr { + __u64 allowed_access; + __u64 port; +}; +#endif + +static int landlock(int argc __maybe_unused, const char **argv __maybe_unused) +{ + int fd = 11, flags = 45; + + struct landlock_path_beneath_attr path_beneath_attr = { + .allowed_access = LANDLOCK_ACCESS_FS_READ_FILE, + .parent_fd = 14, + }; + + struct landlock_net_port_attr net_port_attr = { + .port = 19, + .allowed_access = LANDLOCK_ACCESS_NET_CONNECT_TCP, + }; + + syscall(__NR_landlock_add_rule, fd, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath_attr, flags); + + syscall(__NR_landlock_add_rule, fd, LANDLOCK_RULE_NET_PORT, + &net_port_attr, flags); + + return 0; +} + +DEFINE_WORKLOAD(landlock); diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 78d10d92d351..3ed11e18ee2d 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -113,6 +113,7 @@ struct syscall_arg { struct thread *thread; struct trace *trace; void *parm; + char *type_name; u16 len; u8 idx; u8 mask; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ea986430241e..fe991a81256b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -985,7 +985,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, browser.b.width = notes->src->widths.max_line_len; browser.b.nr_entries = notes->src->nr_entries; - browser.b.entries = ¬es->src->source, + browser.b.entries = ¬es->src->source; browser.b.width += 18; /* Percentage */ if (annotate_opts.hide_src_code) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 0f18fe81ef0b..b24360c04aae 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -13,6 +13,7 @@ perf-util-y += copyfile.o perf-util-y += ctype.o perf-util-y += db-export.o perf-util-y += disasm.o +perf-util-y += disasm_bpf.o perf-util-y += env.o perf-util-y += event.o perf-util-y += evlist.o diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c index 965da6c0b542..734acdd8c4b7 100644 --- a/tools/perf/util/annotate-data.c +++ b/tools/perf/util/annotate-data.c @@ -31,15 +31,6 @@ static void delete_var_types(struct die_var_type *var_types); -enum type_state_kind { - TSR_KIND_INVALID = 0, - TSR_KIND_TYPE, - TSR_KIND_PERCPU_BASE, - TSR_KIND_CONST, - TSR_KIND_POINTER, - TSR_KIND_CANARY, -}; - #define pr_debug_dtp(fmt, ...) \ do { \ if (debug_type_profile) \ @@ -48,7 +39,7 @@ do { \ pr_debug3(fmt, ##__VA_ARGS__); \ } while (0) -static void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind) +void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind) { struct strbuf sb; char *str; @@ -140,49 +131,7 @@ static void pr_debug_location(Dwarf_Die *die, u64 pc, int reg) } } -/* - * Type information in a register, valid when @ok is true. - * The @caller_saved registers are invalidated after a function call. - */ -struct type_state_reg { - Dwarf_Die type; - u32 imm_value; - bool ok; - bool caller_saved; - u8 kind; -}; - -/* Type information in a stack location, dynamically allocated */ -struct type_state_stack { - struct list_head list; - Dwarf_Die type; - int offset; - int size; - bool compound; - u8 kind; -}; - -/* FIXME: This should be arch-dependent */ -#define TYPE_STATE_MAX_REGS 16 - -/* - * State table to maintain type info in each register and stack location. - * It'll be updated when new variable is allocated or type info is moved - * to a new location (register or stack). As it'd be used with the - * shortest path of basic blocks, it only maintains a single table. - */ -struct type_state { - /* state of general purpose registers */ - struct type_state_reg regs[TYPE_STATE_MAX_REGS]; - /* state of stack location */ - struct list_head stack_vars; - /* return value register */ - int ret_reg; - /* stack pointer register */ - int stack_reg; -}; - -static bool has_reg_type(struct type_state *state, int reg) +bool has_reg_type(struct type_state *state, int reg) { return (unsigned)reg < ARRAY_SIZE(state->regs); } @@ -441,7 +390,7 @@ static int check_variable(struct data_loc_info *dloc, Dwarf_Die *var_die, return 0; } -static struct type_state_stack *find_stack_state(struct type_state *state, +struct type_state_stack *find_stack_state(struct type_state *state, int offset) { struct type_state_stack *stack; @@ -457,7 +406,7 @@ static struct type_state_stack *find_stack_state(struct type_state *state, return NULL; } -static void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, +void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, Dwarf_Die *type_die) { int tag; @@ -484,7 +433,7 @@ static void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, } } -static struct type_state_stack *findnew_stack_state(struct type_state *state, +struct type_state_stack *findnew_stack_state(struct type_state *state, int offset, u8 kind, Dwarf_Die *type_die) { @@ -588,7 +537,7 @@ void global_var_type__tree_delete(struct rb_root *root) } } -static bool get_global_var_info(struct data_loc_info *dloc, u64 addr, +bool get_global_var_info(struct data_loc_info *dloc, u64 addr, const char **var_name, int *var_offset) { struct addr_location al; @@ -662,7 +611,7 @@ static void global_var__collect(struct data_loc_info *dloc) } } -static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc, +bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc, u64 ip, u64 var_addr, int *var_offset, Dwarf_Die *type_die) { @@ -773,381 +722,6 @@ static void update_var_state(struct type_state *state, struct data_loc_info *dlo } } -static void update_insn_state_x86(struct type_state *state, - struct data_loc_info *dloc, Dwarf_Die *cu_die, - struct disasm_line *dl) -{ - struct annotated_insn_loc loc; - struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; - struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; - struct type_state_reg *tsr; - Dwarf_Die type_die; - u32 insn_offset = dl->al.offset; - int fbreg = dloc->fbreg; - int fboff = 0; - - if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) - return; - - if (ins__is_call(&dl->ins)) { - struct symbol *func = dl->ops.target.sym; - - if (func == NULL) - return; - - /* __fentry__ will preserve all registers */ - if (!strcmp(func->name, "__fentry__")) - return; - - pr_debug_dtp("call [%x] %s\n", insn_offset, func->name); - - /* Otherwise invalidate caller-saved registers after call */ - for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) { - if (state->regs[i].caller_saved) - state->regs[i].ok = false; - } - - /* Update register with the return type (if any) */ - if (die_find_func_rettype(cu_die, func->name, &type_die)) { - tsr = &state->regs[state->ret_reg]; - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - pr_debug_dtp("call [%x] return -> reg%d", - insn_offset, state->ret_reg); - pr_debug_type_name(&type_die, tsr->kind); - } - return; - } - - if (!strncmp(dl->ins.name, "add", 3)) { - u64 imm_value = -1ULL; - int offset; - const char *var_name = NULL; - struct map_symbol *ms = dloc->ms; - u64 ip = ms->sym->start + dl->al.offset; - - if (!has_reg_type(state, dst->reg1)) - return; - - tsr = &state->regs[dst->reg1]; - - if (src->imm) - imm_value = src->offset; - else if (has_reg_type(state, src->reg1) && - state->regs[src->reg1].kind == TSR_KIND_CONST) - imm_value = state->regs[src->reg1].imm_value; - else if (src->reg1 == DWARF_REG_PC) { - u64 var_addr = annotate_calc_pcrel(dloc->ms, ip, - src->offset, dl); - - if (get_global_var_info(dloc, var_addr, - &var_name, &offset) && - !strcmp(var_name, "this_cpu_off") && - tsr->kind == TSR_KIND_CONST) { - tsr->kind = TSR_KIND_PERCPU_BASE; - imm_value = tsr->imm_value; - } - } - else - return; - - if (tsr->kind != TSR_KIND_PERCPU_BASE) - return; - - if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset, - &type_die) && offset == 0) { - /* - * This is not a pointer type, but it should be treated - * as a pointer. - */ - tsr->type = type_die; - tsr->kind = TSR_KIND_POINTER; - tsr->ok = true; - - pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d", - insn_offset, imm_value, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - } - return; - } - - if (strncmp(dl->ins.name, "mov", 3)) - return; - - if (dloc->fb_cfa) { - u64 ip = dloc->ms->sym->start + dl->al.offset; - u64 pc = map__rip_2objdump(dloc->ms->map, ip); - - if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0) - fbreg = -1; - } - - /* Case 1. register to register or segment:offset to register transfers */ - if (!src->mem_ref && !dst->mem_ref) { - if (!has_reg_type(state, dst->reg1)) - return; - - tsr = &state->regs[dst->reg1]; - if (dso__kernel(map__dso(dloc->ms->map)) && - src->segment == INSN_SEG_X86_GS && src->imm) { - u64 ip = dloc->ms->sym->start + dl->al.offset; - u64 var_addr; - int offset; - - /* - * In kernel, %gs points to a per-cpu region for the - * current CPU. Access with a constant offset should - * be treated as a global variable access. - */ - var_addr = src->offset; - - if (var_addr == 40) { - tsr->kind = TSR_KIND_CANARY; - tsr->ok = true; - - pr_debug_dtp("mov [%x] stack canary -> reg%d\n", - insn_offset, dst->reg1); - return; - } - - if (!get_global_var_type(cu_die, dloc, ip, var_addr, - &offset, &type_die) || - !die_get_member_type(&type_die, offset, &type_die)) { - tsr->ok = false; - return; - } - - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d", - insn_offset, var_addr, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - return; - } - - if (src->imm) { - tsr->kind = TSR_KIND_CONST; - tsr->imm_value = src->offset; - tsr->ok = true; - - pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n", - insn_offset, tsr->imm_value, dst->reg1); - return; - } - - if (!has_reg_type(state, src->reg1) || - !state->regs[src->reg1].ok) { - tsr->ok = false; - return; - } - - tsr->type = state->regs[src->reg1].type; - tsr->kind = state->regs[src->reg1].kind; - tsr->ok = true; - - pr_debug_dtp("mov [%x] reg%d -> reg%d", - insn_offset, src->reg1, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - } - /* Case 2. memory to register transers */ - if (src->mem_ref && !dst->mem_ref) { - int sreg = src->reg1; - - if (!has_reg_type(state, dst->reg1)) - return; - - tsr = &state->regs[dst->reg1]; - -retry: - /* Check stack variables with offset */ - if (sreg == fbreg) { - struct type_state_stack *stack; - int offset = src->offset - fboff; - - stack = find_stack_state(state, offset); - if (stack == NULL) { - tsr->ok = false; - return; - } else if (!stack->compound) { - tsr->type = stack->type; - tsr->kind = stack->kind; - tsr->ok = true; - } else if (die_get_member_type(&stack->type, - offset - stack->offset, - &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - } else { - tsr->ok = false; - return; - } - - pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", - insn_offset, -offset, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - } - /* And then dereference the pointer if it has one */ - else if (has_reg_type(state, sreg) && state->regs[sreg].ok && - state->regs[sreg].kind == TSR_KIND_TYPE && - die_deref_ptr_type(&state->regs[sreg].type, - src->offset, &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", - insn_offset, src->offset, sreg, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - } - /* Or check if it's a global variable */ - else if (sreg == DWARF_REG_PC) { - struct map_symbol *ms = dloc->ms; - u64 ip = ms->sym->start + dl->al.offset; - u64 addr; - int offset; - - addr = annotate_calc_pcrel(ms, ip, src->offset, dl); - - if (!get_global_var_type(cu_die, dloc, ip, addr, &offset, - &type_die) || - !die_get_member_type(&type_die, offset, &type_die)) { - tsr->ok = false; - return; - } - - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d", - insn_offset, addr, dst->reg1); - pr_debug_type_name(&type_die, tsr->kind); - } - /* And check percpu access with base register */ - else if (has_reg_type(state, sreg) && - state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) { - u64 ip = dloc->ms->sym->start + dl->al.offset; - u64 var_addr = src->offset; - int offset; - - if (src->multi_regs) { - int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1; - - if (has_reg_type(state, reg2) && state->regs[reg2].ok && - state->regs[reg2].kind == TSR_KIND_CONST) - var_addr += state->regs[reg2].imm_value; - } - - /* - * In kernel, %gs points to a per-cpu region for the - * current CPU. Access with a constant offset should - * be treated as a global variable access. - */ - if (get_global_var_type(cu_die, dloc, ip, var_addr, - &offset, &type_die) && - die_get_member_type(&type_die, offset, &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - if (src->multi_regs) { - pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d", - insn_offset, src->offset, src->reg1, - src->reg2, dst->reg1); - } else { - pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d", - insn_offset, src->offset, sreg, dst->reg1); - } - pr_debug_type_name(&tsr->type, tsr->kind); - } else { - tsr->ok = false; - } - } - /* And then dereference the calculated pointer if it has one */ - else if (has_reg_type(state, sreg) && state->regs[sreg].ok && - state->regs[sreg].kind == TSR_KIND_POINTER && - die_get_member_type(&state->regs[sreg].type, - src->offset, &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - tsr->ok = true; - - pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d", - insn_offset, src->offset, sreg, dst->reg1); - pr_debug_type_name(&tsr->type, tsr->kind); - } - /* Or try another register if any */ - else if (src->multi_regs && sreg == src->reg1 && - src->reg1 != src->reg2) { - sreg = src->reg2; - goto retry; - } - else { - int offset; - const char *var_name = NULL; - - /* it might be per-cpu variable (in kernel) access */ - if (src->offset < 0) { - if (get_global_var_info(dloc, (s64)src->offset, - &var_name, &offset) && - !strcmp(var_name, "__per_cpu_offset")) { - tsr->kind = TSR_KIND_PERCPU_BASE; - - pr_debug_dtp("mov [%x] percpu base reg%d\n", - insn_offset, dst->reg1); - } - } - - tsr->ok = false; - } - } - /* Case 3. register to memory transfers */ - if (!src->mem_ref && dst->mem_ref) { - if (!has_reg_type(state, src->reg1) || - !state->regs[src->reg1].ok) - return; - - /* Check stack variables with offset */ - if (dst->reg1 == fbreg) { - struct type_state_stack *stack; - int offset = dst->offset - fboff; - - tsr = &state->regs[src->reg1]; - - stack = find_stack_state(state, offset); - if (stack) { - /* - * The source register is likely to hold a type - * of member if it's a compound type. Do not - * update the stack variable type since we can - * get the member type later by using the - * die_get_member_type(). - */ - if (!stack->compound) - set_stack_state(stack, offset, tsr->kind, - &tsr->type); - } else { - findnew_stack_state(state, offset, tsr->kind, - &tsr->type); - } - - pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", - insn_offset, src->reg1, -offset); - pr_debug_type_name(&tsr->type, tsr->kind); - } - /* - * Ignore other transfers since it'd set a value in a struct - * and won't change the type. - */ - } - /* Case 4. memory to memory transfers (not handled for now) */ -} - /** * update_insn_state - Update type state for an instruction * @state: type state table @@ -1166,8 +740,8 @@ retry: static void update_insn_state(struct type_state *state, struct data_loc_info *dloc, Dwarf_Die *cu_die, struct disasm_line *dl) { - if (arch__is(dloc->arch, "x86")) - update_insn_state_x86(state, dloc, cu_die, dl); + if (dloc->arch->update_insn_state) + dloc->arch->update_insn_state(state, dloc, cu_die, dl); } /* @@ -1506,6 +1080,13 @@ out: return ret; } +static int arch_supports_insn_tracking(struct data_loc_info *dloc) +{ + if ((arch__is(dloc->arch, "x86")) || (arch__is(dloc->arch, "powerpc"))) + return 1; + return 0; +} + /* * Construct a list of basic blocks for each scope with variables and try to find * the data type by updating a type state table through instructions. @@ -1520,7 +1101,7 @@ static int find_data_type_block(struct data_loc_info *dloc, int ret = -1; /* TODO: other architecture support */ - if (!arch__is(dloc->arch, "x86")) + if (!arch_supports_insn_tracking(dloc)) return -1; prev_dst_ip = dst_ip = dloc->ip; diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 0a57d9f5ee78..992b7ce4bd11 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -6,6 +6,12 @@ #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/types.h> +#include "dwarf-regs.h" +#include "annotate.h" + +#ifdef HAVE_DWARF_SUPPORT +#include "debuginfo.h" +#endif struct annotated_op_loc; struct debuginfo; @@ -15,6 +21,23 @@ struct hist_entry; struct map_symbol; struct thread; +#define pr_debug_dtp(fmt, ...) \ +do { \ + if (debug_type_profile) \ + pr_info(fmt, ##__VA_ARGS__); \ + else \ + pr_debug3(fmt, ##__VA_ARGS__); \ +} while (0) + +enum type_state_kind { + TSR_KIND_INVALID = 0, + TSR_KIND_TYPE, + TSR_KIND_PERCPU_BASE, + TSR_KIND_CONST, + TSR_KIND_POINTER, + TSR_KIND_CANARY, +}; + /** * struct annotated_member - Type of member field * @node: List entry in the parent list @@ -143,6 +166,51 @@ struct annotated_data_stat { extern struct annotated_data_stat ann_data_stat; #ifdef HAVE_DWARF_SUPPORT +/* + * Type information in a register, valid when @ok is true. + * The @caller_saved registers are invalidated after a function call. + */ +struct type_state_reg { + Dwarf_Die type; + u32 imm_value; + bool ok; + bool caller_saved; + u8 kind; +}; + +/* Type information in a stack location, dynamically allocated */ +struct type_state_stack { + struct list_head list; + Dwarf_Die type; + int offset; + int size; + bool compound; + u8 kind; +}; + +/* FIXME: This should be arch-dependent */ +#ifdef __powerpc__ +#define TYPE_STATE_MAX_REGS 32 +#else +#define TYPE_STATE_MAX_REGS 16 +#endif + +/* + * State table to maintain type info in each register and stack location. + * It'll be updated when new variable is allocated or type info is moved + * to a new location (register or stack). As it'd be used with the + * shortest path of basic blocks, it only maintains a single table. + */ +struct type_state { + /* state of general purpose registers */ + struct type_state_reg regs[TYPE_STATE_MAX_REGS]; + /* state of stack location */ + struct list_head stack_vars; + /* return value register */ + int ret_reg; + /* stack pointer register */ + int stack_reg; +}; /* Returns data type at the location (ip, reg, offset) */ struct annotated_data_type *find_data_type(struct data_loc_info *dloc); @@ -160,6 +228,21 @@ void global_var_type__tree_delete(struct rb_root *root); int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel); +bool has_reg_type(struct type_state *state, int reg); +struct type_state_stack *findnew_stack_state(struct type_state *state, + int offset, u8 kind, + Dwarf_Die *type_die); +void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, + Dwarf_Die *type_die); +struct type_state_stack *find_stack_state(struct type_state *state, + int offset); +bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc, + u64 ip, u64 var_addr, int *var_offset, + Dwarf_Die *type_die); +bool get_global_var_info(struct data_loc_info *dloc, u64 addr, + const char **var_name, int *var_offset); +void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind); + #else /* HAVE_DWARF_SUPPORT */ static inline struct annotated_data_type * diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 1451caf25e77..eafe8d65052e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -699,13 +699,13 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start int percent_type) { struct disasm_line *dl = container_of(al, struct disasm_line, al); + struct annotation *notes = symbol__annotation(sym); static const char *prev_line; if (al->offset != -1) { double max_percent = 0.0; int i, nr_percent = 1; const char *color; - struct annotation *notes = symbol__annotation(sym); for (i = 0; i < al->data_nr; i++) { double percent; @@ -775,14 +775,11 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start } else if (max_lines && printed >= max_lines) return 1; else { - int width = symbol_conf.show_total_period ? 12 : 8; + int width = annotation__pcnt_width(notes); if (queue) return -1; - if (evsel__is_group_event(evsel)) - width *= evsel->core.nr_members; - if (!*al->line) printf(" %*s:\n", width, " "); else @@ -851,6 +848,10 @@ static void annotation__calc_percent(struct annotation *notes, BUG_ON(i >= al->data_nr); + if (symbol_conf.skip_empty && + evsel__hists(evsel)->stats.nr_samples == 0) + continue; + data = &al->data[i++]; calc_percent(notes, evsel, data, al->offset, end); @@ -904,7 +905,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, .options = &annotate_opts, }; struct arch *arch = NULL; - int err; + int err, nr; err = evsel__get_arch(evsel, &arch); if (err < 0) @@ -925,6 +926,19 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, return -1; } + nr = 0; + if (evsel__is_group_event(evsel)) { + struct evsel *pos; + + for_each_group_evsel(pos, evsel) { + if (symbol_conf.skip_empty && + evsel__hists(pos)->stats.nr_samples == 0) + continue; + nr++; + } + } + notes->src->nr_events = nr ? nr : 1; + if (annotate_opts.full_addr) notes->src->start = map__objdump_2mem(ms->map, ms->sym->start); else @@ -1106,7 +1120,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) int more = 0; bool context = opts->context; u64 len; - int width = symbol_conf.show_total_period ? 12 : 8; + int width = annotation__pcnt_width(notes); int graph_dotted_len; char buf[512]; @@ -1122,7 +1136,6 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) len = symbol__size(sym); if (evsel__is_group_event(evsel)) { - width *= evsel->core.nr_members; evsel__group_desc(evsel, buf, sizeof(buf)); evsel_name = buf; } @@ -1594,13 +1607,12 @@ bool ui__has_annotation(void) static double annotation_line__max_percent(struct annotation_line *al, - struct annotation *notes, unsigned int percent_type) { double percent_max = 0.0; int i; - for (i = 0; i < notes->src->nr_events; i++) { + for (i = 0; i < al->data_nr; i++) { double percent; percent = annotation_data__percent(&al->data[i], @@ -1672,7 +1684,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati void (*obj__write_graph)(void *obj, int graph)) { - double percent_max = annotation_line__max_percent(al, notes, percent_type); + double percent_max = annotation_line__max_percent(al, percent_type); int pcnt_width = annotation__pcnt_width(notes), cycles_width = annotation__cycles_width(notes); bool show_title = false; @@ -1690,7 +1702,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati if (al->offset != -1 && percent_max != 0.0) { int i; - for (i = 0; i < notes->src->nr_events; i++) { + for (i = 0; i < al->data_nr; i++) { double percent; percent = annotation_data__percent(&al->data[i], percent_type); @@ -1699,10 +1711,10 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati if (symbol_conf.show_total_period) { obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period); } else if (symbol_conf.show_nr_samples) { - obj__printf(obj, "%6" PRIu64 " ", + obj__printf(obj, "%7" PRIu64 " ", al->data[i].he.nr_samples); } else { - obj__printf(obj, "%6.2f ", percent); + obj__printf(obj, "%7.2f ", percent); } } } else { @@ -1843,10 +1855,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); size_t size = symbol__size(sym); - int nr_pcnt = 1, err; - - if (evsel__is_group_event(evsel)) - nr_pcnt = evsel->core.nr_members; + int err; err = symbol__annotate(ms, evsel, parch); if (err) @@ -1862,8 +1871,6 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return err; annotation__init_column_widths(notes, sym); - notes->src->nr_events = nr_pcnt; - annotation__update_column_widths(notes); sym->annotate2 = 1; @@ -2123,20 +2130,33 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, for_each_insn_op_loc(loc, i, op_loc) { const char *insn_str = ops->source.raw; bool multi_regs = ops->source.multi_regs; + bool mem_ref = ops->source.mem_ref; if (i == INSN_OP_TARGET) { insn_str = ops->target.raw; multi_regs = ops->target.multi_regs; + mem_ref = ops->target.mem_ref; } /* Invalidate the register by default */ op_loc->reg1 = -1; op_loc->reg2 = -1; - if (insn_str == NULL) - continue; + if (insn_str == NULL) { + if (!arch__is(arch, "powerpc")) + continue; + } - if (strchr(insn_str, arch->objdump.memory_ref_char)) { + /* + * For powerpc, call get_powerpc_regs function which extracts the + * required fields for op_loc, ie reg1, reg2, offset from the + * raw instruction. + */ + if (arch__is(arch, "powerpc")) { + op_loc->mem_ref = mem_ref; + op_loc->multi_regs = multi_regs; + get_powerpc_regs(dl->raw.raw_insn, !i, op_loc); + } else if (strchr(insn_str, arch->objdump.memory_ref_char)) { op_loc->mem_ref = true; op_loc->multi_regs = multi_regs; extract_reg_offset(arch, insn_str, op_loc); @@ -2216,7 +2236,7 @@ static struct annotated_item_stat *annotate_data_stat(struct list_head *head, return NULL; istat->name = strdup(name); - if (istat->name == NULL) { + if ((istat->name == NULL) || (!strlen(istat->name))) { free(istat); return NULL; } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index d5c821c22f79..64e70d716ff1 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -113,7 +113,10 @@ struct annotation_line { struct disasm_line { struct ins ins; struct ins_operands ops; - + union { + u8 bytes[4]; + u32 raw_insn; + } raw; /* This needs to be at the end. */ struct annotation_line al; }; @@ -336,7 +339,7 @@ static inline int annotation__cycles_width(struct annotation *notes) static inline int annotation__pcnt_width(struct annotation *notes) { - return (symbol_conf.show_total_period ? 12 : 7) * notes->src->nr_events; + return (symbol_conf.show_total_period ? 12 : 8) * notes->src->nr_events; } static inline bool annotation_line__filter(struct annotation_line *al) diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 04f98b6bb291..c5eb0b7eec19 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -1,12 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> #include <bpf/bpf.h> #include <linux/err.h> +#include <api/fs/fs.h> #include <internal/xyarray.h> +#include <perf/threadmap.h> #include "util/debug.h" #include "util/evsel.h" +#include "util/target.h" #include "util/bpf-filter.h" #include <util/bpf-filter-flex.h> @@ -20,6 +26,9 @@ #define __PERF_SAMPLE_TYPE(tt, st, opt) { tt, #st, opt } #define PERF_SAMPLE_TYPE(_st, opt) __PERF_SAMPLE_TYPE(PBF_TERM_##_st, PERF_SAMPLE_##_st, opt) +/* Index in the pinned 'filters' map. Should be released after use. */ +static int pinned_filter_idx = -1; + static const struct perf_sample_info { enum perf_bpf_filter_term type; const char *name; @@ -44,6 +53,8 @@ static const struct perf_sample_info { PERF_SAMPLE_TYPE(DATA_PAGE_SIZE, "--data-page-size"), }; +static int get_pinned_fd(const char *name); + static const struct perf_sample_info *get_sample_info(enum perf_bpf_filter_term type) { size_t i; @@ -91,73 +102,238 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr * return -1; } -int perf_bpf_filter__prepare(struct evsel *evsel) +static int get_filter_entries(struct evsel *evsel, struct perf_bpf_filter_entry *entry) { - int i, x, y, fd; - struct sample_filter_bpf *skel; - struct bpf_program *prog; - struct bpf_link *link; + int i = 0; struct perf_bpf_filter_expr *expr; - skel = sample_filter_bpf__open_and_load(); - if (!skel) { - pr_err("Failed to load perf sample-filter BPF skeleton\n"); - return -1; - } - - i = 0; - fd = bpf_map__fd(skel->maps.filters); list_for_each_entry(expr, &evsel->bpf_filters, list) { - struct perf_bpf_filter_entry entry = { - .op = expr->op, - .part = expr->part, - .term = expr->term, - .value = expr->val, - }; - if (check_sample_flags(evsel, expr) < 0) - return -1; + return -EINVAL; + + if (i == MAX_FILTERS) + return -E2BIG; - bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + entry[i].op = expr->op; + entry[i].part = expr->part; + entry[i].term = expr->term; + entry[i].value = expr->val; i++; if (expr->op == PBF_OP_GROUP_BEGIN) { struct perf_bpf_filter_expr *group; list_for_each_entry(group, &expr->groups, list) { - struct perf_bpf_filter_entry group_entry = { - .op = group->op, - .part = group->part, - .term = group->term, - .value = group->val, - }; - bpf_map_update_elem(fd, &i, &group_entry, BPF_ANY); + if (i == MAX_FILTERS) + return -E2BIG; + + entry[i].op = group->op; + entry[i].part = group->part; + entry[i].term = group->term; + entry[i].value = group->val; i++; } - memset(&entry, 0, sizeof(entry)); - entry.op = PBF_OP_GROUP_END; - bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + if (i == MAX_FILTERS) + return -E2BIG; + + entry[i].op = PBF_OP_GROUP_END; i++; } } - if (i > MAX_FILTERS) { - pr_err("Too many filters: %d (max = %d)\n", i, MAX_FILTERS); + if (i < MAX_FILTERS) { + /* to terminate the loop early */ + entry[i].op = PBF_OP_DONE; + i++; + } + return 0; +} + +static int convert_to_tgid(int tid) +{ + char path[128]; + char *buf, *p, *q; + int tgid; + size_t len; + + scnprintf(path, sizeof(path), "%d/status", tid); + if (procfs__read_str(path, &buf, &len) < 0) + return -1; + + p = strstr(buf, "Tgid:"); + if (p == NULL) { + free(buf); + return -1; + } + + tgid = strtol(p + 6, &q, 0); + free(buf); + if (*q != '\n') + return -1; + + return tgid; +} + +static int update_pid_hash(struct evsel *evsel, struct perf_bpf_filter_entry *entry) +{ + int filter_idx; + int fd, nr, last; + struct perf_thread_map *threads; + + fd = get_pinned_fd("filters"); + if (fd < 0) { + pr_debug("cannot get fd for 'filters' map\n"); + return fd; + } + + /* Find the first available entry in the filters map */ + for (filter_idx = 0; filter_idx < MAX_FILTERS; filter_idx++) { + if (bpf_map_update_elem(fd, &filter_idx, entry, BPF_NOEXIST) == 0) { + pinned_filter_idx = filter_idx; + break; + } + } + close(fd); + + if (filter_idx == MAX_FILTERS) { + pr_err("Too many users for the filter map\n"); + return -EBUSY; + } + + threads = perf_evsel__threads(&evsel->core); + if (threads == NULL) { + pr_err("Cannot get the thread list of the event\n"); + return -EINVAL; + } + + /* save the index to a hash map */ + fd = get_pinned_fd("pid_hash"); + if (fd < 0) + return fd; + + last = -1; + nr = perf_thread_map__nr(threads); + for (int i = 0; i < nr; i++) { + int pid = perf_thread_map__pid(threads, i); + int tgid; + + /* it actually needs tgid, let's get tgid from /proc. */ + tgid = convert_to_tgid(pid); + if (tgid < 0) { + /* the thread may be dead, ignore. */ + continue; + } + + if (tgid == last) + continue; + last = tgid; + + if (bpf_map_update_elem(fd, &tgid, &filter_idx, BPF_ANY) < 0) { + pr_err("Failed to update the pid hash\n"); + close(fd); + return -1; + } + pr_debug("pid hash: %d -> %d\n", tgid, filter_idx); + } + close(fd); + return 0; +} + +int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target) +{ + int i, x, y, fd, ret; + struct sample_filter_bpf *skel = NULL; + struct bpf_program *prog; + struct bpf_link *link; + struct perf_bpf_filter_entry *entry; + bool needs_pid_hash = !target__has_cpu(target) && !target->uid_str; + + entry = calloc(MAX_FILTERS, sizeof(*entry)); + if (entry == NULL) return -1; + + ret = get_filter_entries(evsel, entry); + if (ret < 0) { + pr_err("Failed to process filter entries\n"); + goto err; + } + + if (needs_pid_hash && geteuid() != 0) { + int zero = 0; + + /* The filters map is shared among other processes */ + ret = update_pid_hash(evsel, entry); + if (ret < 0) + goto err; + + fd = get_pinned_fd("dropped"); + if (fd < 0) { + ret = fd; + goto err; + } + + /* Reset the lost count */ + bpf_map_update_elem(fd, &pinned_filter_idx, &zero, BPF_ANY); + close(fd); + + fd = get_pinned_fd("perf_sample_filter"); + if (fd < 0) { + ret = fd; + goto err; + } + + for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { + for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { + ret = ioctl(FD(evsel, x, y), PERF_EVENT_IOC_SET_BPF, fd); + if (ret < 0) { + pr_err("Failed to attach perf sample-filter\n"); + goto err; + } + } + } + + close(fd); + free(entry); + return 0; } + + skel = sample_filter_bpf__open_and_load(); + if (!skel) { + ret = -errno; + pr_err("Failed to load perf sample-filter BPF skeleton\n"); + goto err; + } + + i = 0; + fd = bpf_map__fd(skel->maps.filters); + + /* The filters map has only one entry in this case */ + if (bpf_map_update_elem(fd, &i, entry, BPF_ANY) < 0) { + ret = -errno; + pr_err("Failed to update the filter map\n"); + goto err; + } + prog = skel->progs.perf_sample_filter; for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { link = bpf_program__attach_perf_event(prog, FD(evsel, x, y)); if (IS_ERR(link)) { pr_err("Failed to attach perf sample-filter program\n"); - return PTR_ERR(link); + ret = PTR_ERR(link); + goto err; } } } + free(entry); evsel->bpf_skel = skel; return 0; + +err: + free(entry); + sample_filter_bpf__destroy(skel); + return ret; } int perf_bpf_filter__destroy(struct evsel *evsel) @@ -169,14 +345,39 @@ int perf_bpf_filter__destroy(struct evsel *evsel) free(expr); } sample_filter_bpf__destroy(evsel->bpf_skel); + + if (pinned_filter_idx >= 0) { + int fd = get_pinned_fd("filters"); + + bpf_map_delete_elem(fd, &pinned_filter_idx); + pinned_filter_idx = -1; + close(fd); + } + return 0; } u64 perf_bpf_filter__lost_count(struct evsel *evsel) { - struct sample_filter_bpf *skel = evsel->bpf_skel; + int count = 0; + + if (list_empty(&evsel->bpf_filters)) + return 0; - return skel ? skel->bss->dropped : 0; + if (pinned_filter_idx >= 0) { + int fd = get_pinned_fd("dropped"); + + bpf_map_lookup_elem(fd, &pinned_filter_idx, &count); + close(fd); + } else if (evsel->bpf_skel) { + struct sample_filter_bpf *skel = evsel->bpf_skel; + int fd = bpf_map__fd(skel->maps.dropped); + int idx = 0; + + bpf_map_lookup_elem(fd, &idx, &count); + } + + return count; } struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term term, @@ -212,3 +413,134 @@ int perf_bpf_filter__parse(struct list_head *expr_head, const char *str) return ret; } + +int perf_bpf_filter__pin(void) +{ + struct sample_filter_bpf *skel; + char *path = NULL; + int dir_fd, ret = -1; + + skel = sample_filter_bpf__open(); + if (!skel) { + ret = -errno; + pr_err("Failed to open perf sample-filter BPF skeleton\n"); + goto err; + } + + /* pinned program will use pid-hash */ + bpf_map__set_max_entries(skel->maps.filters, MAX_FILTERS); + bpf_map__set_max_entries(skel->maps.pid_hash, MAX_PIDS); + bpf_map__set_max_entries(skel->maps.dropped, MAX_FILTERS); + skel->rodata->use_pid_hash = 1; + + if (sample_filter_bpf__load(skel) < 0) { + ret = -errno; + pr_err("Failed to load perf sample-filter BPF skeleton\n"); + goto err; + } + + if (asprintf(&path, "%s/fs/bpf/%s", sysfs__mountpoint(), + PERF_BPF_FILTER_PIN_PATH) < 0) { + ret = -errno; + pr_err("Failed to allocate pathname in the BPF-fs\n"); + goto err; + } + + ret = bpf_object__pin(skel->obj, path); + if (ret < 0) { + pr_err("Failed to pin BPF filter objects\n"); + goto err; + } + + /* setup access permissions for the pinned objects */ + dir_fd = open(path, O_PATH); + if (dir_fd < 0) { + bpf_object__unpin(skel->obj, path); + ret = dir_fd; + goto err; + } + + /* BPF-fs root has the sticky bit */ + if (fchmodat(dir_fd, "..", 01755, 0) < 0) { + pr_debug("chmod for BPF-fs failed\n"); + ret = -errno; + goto err_close; + } + + /* perf_filter directory */ + if (fchmodat(dir_fd, ".", 0755, 0) < 0) { + pr_debug("chmod for perf_filter directory failed?\n"); + ret = -errno; + goto err_close; + } + + /* programs need write permission for some reason */ + if (fchmodat(dir_fd, "perf_sample_filter", 0777, 0) < 0) { + pr_debug("chmod for perf_sample_filter failed\n"); + ret = -errno; + } + /* maps */ + if (fchmodat(dir_fd, "filters", 0666, 0) < 0) { + pr_debug("chmod for filters failed\n"); + ret = -errno; + } + if (fchmodat(dir_fd, "pid_hash", 0666, 0) < 0) { + pr_debug("chmod for pid_hash failed\n"); + ret = -errno; + } + if (fchmodat(dir_fd, "dropped", 0666, 0) < 0) { + pr_debug("chmod for dropped failed\n"); + ret = -errno; + } + +err_close: + close(dir_fd); + +err: + free(path); + sample_filter_bpf__destroy(skel); + return ret; +} + +int perf_bpf_filter__unpin(void) +{ + struct sample_filter_bpf *skel; + char *path = NULL; + int ret = -1; + + skel = sample_filter_bpf__open_and_load(); + if (!skel) { + ret = -errno; + pr_err("Failed to open perf sample-filter BPF skeleton\n"); + goto err; + } + + if (asprintf(&path, "%s/fs/bpf/%s", sysfs__mountpoint(), + PERF_BPF_FILTER_PIN_PATH) < 0) { + ret = -errno; + pr_err("Failed to allocate pathname in the BPF-fs\n"); + goto err; + } + + ret = bpf_object__unpin(skel->obj, path); + +err: + free(path); + sample_filter_bpf__destroy(skel); + return ret; +} + +static int get_pinned_fd(const char *name) +{ + char *path = NULL; + int fd; + + if (asprintf(&path, "%s/fs/bpf/%s/%s", sysfs__mountpoint(), + PERF_BPF_FILTER_PIN_PATH, name) < 0) + return -1; + + fd = bpf_obj_get(path); + + free(path); + return fd; +} diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index cd6764442c16..916ed7770b73 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -16,6 +16,10 @@ struct perf_bpf_filter_expr { }; struct evsel; +struct target; + +/* path in BPF-fs for the pinned program and maps */ +#define PERF_BPF_FILTER_PIN_PATH "perf_filter" #ifdef HAVE_BPF_SKEL struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term term, @@ -23,9 +27,11 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); -int perf_bpf_filter__prepare(struct evsel *evsel); +int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target); int perf_bpf_filter__destroy(struct evsel *evsel); u64 perf_bpf_filter__lost_count(struct evsel *evsel); +int perf_bpf_filter__pin(void); +int perf_bpf_filter__unpin(void); #else /* !HAVE_BPF_SKEL */ @@ -34,7 +40,8 @@ static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unu { return -EOPNOTSUPP; } -static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) +static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused, + struct target *target __maybe_unused) { return -EOPNOTSUPP; } @@ -46,5 +53,13 @@ static inline u64 perf_bpf_filter__lost_count(struct evsel *evsel __maybe_unused { return 0; } +static inline int perf_bpf_filter__pin(void) +{ + return -EOPNOTSUPP; +} +static inline int perf_bpf_filter__unpin(void) +{ + return -EOPNOTSUPP; +} #endif /* HAVE_BPF_SKEL*/ #endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 350efa121026..e666bfd5fbdd 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -2,6 +2,7 @@ #define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H #define MAX_FILTERS 64 +#define MAX_PIDS (16 * 1024) /* supported filter operations */ enum perf_bpf_filter_op { @@ -14,6 +15,7 @@ enum perf_bpf_filter_op { PBF_OP_AND, PBF_OP_GROUP_BEGIN, PBF_OP_GROUP_END, + PBF_OP_DONE, }; enum perf_bpf_filter_term { diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index f59985101973..4c75354b84fd 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -9,13 +9,29 @@ /* BPF map that will be filled by user space */ struct filters { - __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(type, BPF_MAP_TYPE_HASH); __type(key, int); - __type(value, struct perf_bpf_filter_entry); - __uint(max_entries, MAX_FILTERS); + __type(value, struct perf_bpf_filter_entry[MAX_FILTERS]); + __uint(max_entries, 1); } filters SEC(".maps"); -int dropped; +/* tgid to filter index */ +struct pid_hash { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} pid_hash SEC(".maps"); + +/* tgid to filter index */ +struct lost_count { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} dropped SEC(".maps"); + +volatile const int use_pid_hash; void *bpf_cast_to_kern_ctx(void *) __ksym; @@ -179,39 +195,52 @@ int perf_sample_filter(void *ctx) __u64 sample_data; int in_group = 0; int group_result = 0; - int i; + int i, k; + int *losts; kctx = bpf_cast_to_kern_ctx(ctx); - for (i = 0; i < MAX_FILTERS; i++) { - int key = i; /* needed for verifier :( */ + k = 0; - entry = bpf_map_lookup_elem(&filters, &key); - if (entry == NULL) - break; - sample_data = perf_get_sample(kctx, entry); + if (use_pid_hash) { + int tgid = bpf_get_current_pid_tgid() >> 32; + int *idx; - switch (entry->op) { + idx = bpf_map_lookup_elem(&pid_hash, &tgid); + if (idx) + k = *idx; + else + goto drop; + } + + entry = bpf_map_lookup_elem(&filters, &k); + if (entry == NULL) + goto drop; + + for (i = 0; i < MAX_FILTERS; i++) { + sample_data = perf_get_sample(kctx, &entry[i]); + + switch (entry[i].op) { case PBF_OP_EQ: - CHECK_RESULT(sample_data, ==, entry->value) + CHECK_RESULT(sample_data, ==, entry[i].value) break; case PBF_OP_NEQ: - CHECK_RESULT(sample_data, !=, entry->value) + CHECK_RESULT(sample_data, !=, entry[i].value) break; case PBF_OP_GT: - CHECK_RESULT(sample_data, >, entry->value) + CHECK_RESULT(sample_data, >, entry[i].value) break; case PBF_OP_GE: - CHECK_RESULT(sample_data, >=, entry->value) + CHECK_RESULT(sample_data, >=, entry[i].value) break; case PBF_OP_LT: - CHECK_RESULT(sample_data, <, entry->value) + CHECK_RESULT(sample_data, <, entry[i].value) break; case PBF_OP_LE: - CHECK_RESULT(sample_data, <=, entry->value) + CHECK_RESULT(sample_data, <=, entry[i].value) break; case PBF_OP_AND: - CHECK_RESULT(sample_data, &, entry->value) + CHECK_RESULT(sample_data, &, entry[i].value) break; case PBF_OP_GROUP_BEGIN: in_group = 1; @@ -222,13 +251,19 @@ int perf_sample_filter(void *ctx) goto drop; in_group = 0; break; + case PBF_OP_DONE: + /* no failures so far, accept it */ + return 1; } } /* generate sample data */ return 1; drop: - __sync_fetch_and_add(&dropped, 1); + losts = bpf_map_lookup_elem(&dropped, &k); + if (losts != NULL) + __sync_fetch_and_add(losts, 1); + return 0; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 5e9fbcfad7d4..d3e9c64d17d4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1267,8 +1267,12 @@ static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) { - /* Returns 0 for the CS_ETM_DISCONTINUITY packet */ - if (packet->sample_type == CS_ETM_DISCONTINUITY) + /* + * Return 0 for packets that have no addresses so that CS_ETM_INVAL_ADDR doesn't + * appear in samples. + */ + if (packet->sample_type == CS_ETM_DISCONTINUITY || + packet->sample_type == CS_ETM_EXCEPTION) return 0; return packet->start_addr; diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index e10558b79504..22289003e16d 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -12,9 +12,11 @@ #include <subcmd/run-command.h> #include "annotate.h" +#include "annotate-data.h" #include "build-id.h" #include "debug.h" #include "disasm.h" +#include "disasm_bpf.h" #include "dso.h" #include "env.h" #include "evsel.h" @@ -35,6 +37,8 @@ static struct ins_ops mov_ops; static struct ins_ops nop_ops; static struct ins_ops lock_ops; static struct ins_ops ret_ops; +static struct ins_ops load_store_ops; +static struct ins_ops arithmetic_ops; static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name); @@ -43,6 +47,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size, static void ins__sort(struct arch *arch); static int disasm_line__parse(char *line, const char **namep, char **rawp); +static int disasm_line__parse_powerpc(struct disasm_line *dl); static __attribute__((constructor)) void symbol__init_regexpr(void) { @@ -145,10 +150,16 @@ static struct arch architectures[] = { .memory_ref_char = '(', .imm_char = '$', }, +#ifdef HAVE_DWARF_SUPPORT + .update_insn_state = update_insn_state_x86, +#endif }, { .name = "powerpc", .init = powerpc__annotate_init, +#ifdef HAVE_DWARF_SUPPORT + .update_insn_state = update_insn_state_powerpc, +#endif }, { .name = "riscv64", @@ -250,7 +261,8 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) return arch->ins_is_fused(arch, ins1, ins2); } -static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) +static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) { char *endptr, *tok, *name; struct map *map = ms->map; @@ -345,7 +357,8 @@ static inline const char *validate_comma(const char *c, struct ins_operands *ops return c; } -static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -504,7 +517,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) return 0; } -static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) +static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) { ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); if (ops->locked.ops == NULL) @@ -513,13 +527,13 @@ static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_s if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0) goto out_free_ops; - ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name); + ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name, 0); if (ops->locked.ins.ops == NULL) goto out_free_ops; if (ops->locked.ins.ops->parse && - ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0) + ops->locked.ins.ops->parse(arch, ops->locked.ops, ms, NULL) < 0) goto out_free_ops; return 0; @@ -590,7 +604,8 @@ static bool check_multi_regs(struct arch *arch, const char *op) return count > 1; } -static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused) +static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *comment, prev; @@ -668,7 +683,92 @@ static struct ins_ops mov_ops = { .scnprintf = mov__scnprintf, }; -static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused) +#define PPC_22_30(R) (((R) >> 1) & 0x1ff) +#define MINUS_EXT_XO_FORM 234 +#define SUB_EXT_XO_FORM 232 +#define ADD_ZERO_EXT_XO_FORM 202 +#define SUB_ZERO_EXT_XO_FORM 200 + +static int arithmetic__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) +{ + return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, + ops->raw); +} + +/* + * Sets the fields: multi_regs and "mem_ref". + * "mem_ref" is set for ops->source which is later used to + * fill the objdump->memory_ref-char field. This ops is currently + * used by powerpc and since binary instruction code is used to + * extract opcode, regs and offset, no other parsing is needed here. + * + * Dont set multi regs for 4 cases since it has only one operand + * for source: + * - Add to Minus One Extended XO-form ( Ex: addme, addmeo ) + * - Subtract From Minus One Extended XO-form ( Ex: subfme ) + * - Add to Zero Extended XO-form ( Ex: addze, addzeo ) + * - Subtract From Zero Extended XO-form ( Ex: subfze ) + */ +static int arithmetic__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, struct disasm_line *dl) +{ + int opcode = PPC_OP(dl->raw.raw_insn); + + ops->source.mem_ref = false; + if (opcode == 31) { + if ((opcode != MINUS_EXT_XO_FORM) && (opcode != SUB_EXT_XO_FORM) \ + && (opcode != ADD_ZERO_EXT_XO_FORM) && (opcode != SUB_ZERO_EXT_XO_FORM)) + ops->source.multi_regs = true; + } + + ops->target.mem_ref = false; + ops->target.multi_regs = false; + + return 0; +} + +static struct ins_ops arithmetic_ops = { + .parse = arithmetic__parse, + .scnprintf = arithmetic__scnprintf, +}; + +static int load_store__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) +{ + return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, + ops->raw); +} + +/* + * Sets the fields: multi_regs and "mem_ref". + * "mem_ref" is set for ops->source which is later used to + * fill the objdump->memory_ref-char field. This ops is currently + * used by powerpc and since binary instruction code is used to + * extract opcode, regs and offset, no other parsing is needed here + */ +static int load_store__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, struct disasm_line *dl __maybe_unused) +{ + ops->source.mem_ref = true; + ops->source.multi_regs = false; + /* opcode 31 is of X form */ + if (PPC_OP(dl->raw.raw_insn) == 31) + ops->source.multi_regs = true; + + ops->target.mem_ref = false; + ops->target.multi_regs = false; + + return 0; +} + +static struct ins_ops load_store_ops = { + .parse = load_store__parse, + .scnprintf = load_store__scnprintf, +}; + +static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *target, *comment, *s, prev; @@ -758,11 +858,23 @@ static void ins__sort(struct arch *arch) qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp); } -static struct ins_ops *__ins__find(struct arch *arch, const char *name) +static struct ins_ops *__ins__find(struct arch *arch, const char *name, struct disasm_line *dl) { struct ins *ins; const int nmemb = arch->nr_instructions; + if (arch__is(arch, "powerpc")) { + /* + * For powerpc, identify the instruction ops + * from the opcode using raw_insn. + */ + struct ins_ops *ops; + + ops = check_ppc_insn(dl); + if (ops) + return ops; + } + if (!arch->sorted_instructions) { ins__sort(arch); arch->sorted_instructions = true; @@ -792,9 +904,9 @@ static struct ins_ops *__ins__find(struct arch *arch, const char *name) return ins ? ins->ops : NULL; } -struct ins_ops *ins__find(struct arch *arch, const char *name) +struct ins_ops *ins__find(struct arch *arch, const char *name, struct disasm_line *dl) { - struct ins_ops *ops = __ins__find(arch, name); + struct ins_ops *ops = __ins__find(arch, name, dl); if (!ops && arch->associate_instruction_ops) ops = arch->associate_instruction_ops(arch, name); @@ -804,12 +916,12 @@ struct ins_ops *ins__find(struct arch *arch, const char *name) static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) { - dl->ins.ops = ins__find(arch, dl->ins.name); + dl->ins.ops = ins__find(arch, dl->ins.name, dl); if (!dl->ins.ops) return; - if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0) + if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms, dl) < 0) dl->ins.ops = NULL; } @@ -841,6 +953,51 @@ out: return -1; } +/* + * Parses the result captured from symbol__disassemble_* + * Example, line read from DSO file in powerpc: + * line: 38 01 81 e8 + * opcode: fetched from arch specific get_opcode_insn + * rawp_insn: e8810138 + * + * rawp_insn is used later to extract the reg/offset fields + */ +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define RAW_BYTES 11 + +static int disasm_line__parse_powerpc(struct disasm_line *dl) +{ + char *line = dl->al.line; + const char **namep = &dl->ins.name; + char **rawp = &dl->ops.raw; + char *tmp_raw_insn, *name_raw_insn = skip_spaces(line); + char *name = skip_spaces(name_raw_insn + RAW_BYTES); + int objdump = 0; + + if (strlen(line) > RAW_BYTES) + objdump = 1; + + if (name_raw_insn[0] == '\0') + return -1; + + if (objdump) { + disasm_line__parse(name, namep, rawp); + } else + *namep = ""; + + tmp_raw_insn = strndup(name_raw_insn, 11); + if (tmp_raw_insn == NULL) + return -1; + + remove_spaces(tmp_raw_insn); + + sscanf(tmp_raw_insn, "%x", &dl->raw.raw_insn); + if (objdump) + dl->raw.raw_insn = be32_to_cpu(dl->raw.raw_insn); + + return 0; +} + static void annotation_line__init(struct annotation_line *al, struct annotate_args *args, int nr) @@ -880,10 +1037,8 @@ static size_t disasm_line_size(int nr) struct disasm_line *disasm_line__new(struct annotate_args *args) { struct disasm_line *dl = NULL; - int nr = 1; - - if (evsel__is_group_event(args->evsel)) - nr = args->evsel->core.nr_members; + struct annotation *notes = symbol__annotation(args->ms.sym); + int nr = notes->src->nr_events; dl = zalloc(disasm_line_size(nr)); if (!dl) @@ -894,7 +1049,10 @@ struct disasm_line *disasm_line__new(struct annotate_args *args) goto out_delete; if (args->offset != -1) { - if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) + if (arch__is(args->arch, "powerpc")) { + if (disasm_line__parse_powerpc(dl) < 0) + goto out_free_line; + } else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) goto out_free_line; disasm_line__init_ins(dl, args->arch, &args->ms); @@ -1164,195 +1322,11 @@ fallback: return 0; } -#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) -#define PACKAGE "perf" -#include <bfd.h> -#include <dis-asm.h> -#include <bpf/bpf.h> -#include <bpf/btf.h> -#include <bpf/libbpf.h> -#include <linux/btf.h> -#include <tools/dis-asm-compat.h> - -#include "bpf-event.h" -#include "bpf-utils.h" - -static int symbol__disassemble_bpf(struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct bpf_prog_linfo *prog_linfo = NULL; - struct bpf_prog_info_node *info_node; - int len = sym->end - sym->start; - disassembler_ftype disassemble; - struct map *map = args->ms.map; - struct perf_bpil *info_linear; - struct disassemble_info info; - struct dso *dso = map__dso(map); - int pc = 0, count, sub_id; - struct btf *btf = NULL; - char tpath[PATH_MAX]; - size_t buf_size; - int nr_skip = 0; - char *buf; - bfd *bfdf; - int ret; - FILE *s; - - if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO) - return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; - - pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, - sym->name, sym->start, sym->end - sym->start); - - memset(tpath, 0, sizeof(tpath)); - perf_exe(tpath, sizeof(tpath)); - - bfdf = bfd_openr(tpath, NULL); - if (bfdf == NULL) - abort(); - - if (!bfd_check_format(bfdf, bfd_object)) - abort(); - - s = open_memstream(&buf, &buf_size); - if (!s) { - ret = errno; - goto out; - } - init_disassemble_info_compat(&info, s, - (fprintf_ftype) fprintf, - fprintf_styled); - info.arch = bfd_get_arch(bfdf); - info.mach = bfd_get_mach(bfdf); - - info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, - dso__bpf_prog(dso)->id); - if (!info_node) { - ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; - goto out; - } - info_linear = info_node->info_linear; - sub_id = dso__bpf_prog(dso)->sub_id; - - info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); - info.buffer_length = info_linear->info.jited_prog_len; - - if (info_linear->info.nr_line_info) - prog_linfo = bpf_prog_linfo__new(&info_linear->info); - - if (info_linear->info.btf_id) { - struct btf_node *node; - - node = perf_env__find_btf(dso__bpf_prog(dso)->env, - info_linear->info.btf_id); - if (node) - btf = btf__new((__u8 *)(node->data), - node->data_size); - } - - disassemble_init_for_target(&info); - -#ifdef DISASM_FOUR_ARGS_SIGNATURE - disassemble = disassembler(info.arch, - bfd_big_endian(bfdf), - info.mach, - bfdf); -#else - disassemble = disassembler(bfdf); -#endif - if (disassemble == NULL) - abort(); - - fflush(s); - do { - const struct bpf_line_info *linfo = NULL; - struct disasm_line *dl; - size_t prev_buf_size; - const char *srcline; - u64 addr; - - addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; - count = disassemble(pc, &info); - - if (prog_linfo) - linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, - addr, sub_id, - nr_skip); - - if (linfo && btf) { - srcline = btf__name_by_offset(btf, linfo->line_off); - nr_skip++; - } else - srcline = NULL; - - fprintf(s, "\n"); - prev_buf_size = buf_size; - fflush(s); - - if (!annotate_opts.hide_src_code && srcline) { - args->offset = -1; - args->line = strdup(srcline); - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - dl = disasm_line__new(args); - if (dl) { - annotation_line__add(&dl->al, - ¬es->src->source); - } - } - - args->offset = pc; - args->line = buf + prev_buf_size; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - dl = disasm_line__new(args); - if (dl) - annotation_line__add(&dl->al, ¬es->src->source); - - pc += count; - } while (count > 0 && pc < len); - - ret = 0; -out: - free(prog_linfo); - btf__free(btf); - fclose(s); - bfd_close(bfdf); - return ret; -} -#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) -static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, - struct annotate_args *args __maybe_unused) -{ - return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; -} -#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) - -static int -symbol__disassemble_bpf_image(struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct disasm_line *dl; - - args->offset = -1; - args->line = strdup("to be implemented"); - args->line_nr = 0; - args->fileloc = NULL; - dl = disasm_line__new(args); - if (dl) - annotation_line__add(&dl->al, ¬es->src->source); - - zfree(&args->line); - return 0; -} - #ifdef HAVE_LIBCAPSTONE_SUPPORT #include <capstone/capstone.h> +int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style); + static int open_capstone_handle(struct annotate_args *args, bool is_64bit, csh *handle) { @@ -1453,6 +1427,144 @@ static void print_capstone_detail(cs_insn *insn, char *buf, size_t len, } } +static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym, + struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct map *map = args->ms.map; + struct dso *dso = map__dso(map); + struct nscookie nsc; + u64 start = map__rip_2objdump(map, sym->start); + u64 end = map__rip_2objdump(map, sym->end); + u64 len = end - start; + u64 offset; + int i, fd, count; + bool is_64bit = false; + bool needs_cs_close = false; + u8 *buf = NULL; + struct find_file_offset_data data = { + .ip = start, + }; + csh handle; + char disasm_buf[512]; + struct disasm_line *dl; + u32 *line; + bool disassembler_style = false; + + if (args->options->objdump_path) + return -1; + + nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); + fd = open(filename, O_RDONLY); + nsinfo__mountns_exit(&nsc); + if (fd < 0) + return -1; + + if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, + &is_64bit) == 0) + goto err; + + if (!args->options->disassembler_style || + !strcmp(args->options->disassembler_style, "att")) + disassembler_style = true; + + if (capstone_init(maps__machine(args->ms.maps), &handle, is_64bit, disassembler_style) < 0) + goto err; + + needs_cs_close = true; + + buf = malloc(len); + if (buf == NULL) + goto err; + + count = pread(fd, buf, len, data.offset); + close(fd); + fd = -1; + + if ((u64)count != len) + goto err; + + line = (u32 *)buf; + + /* add the function address and name */ + scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", + start, sym->name); + + args->offset = -1; + args->line = disasm_buf; + args->line_nr = 0; + args->fileloc = NULL; + args->ms.sym = sym; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + /* + * TODO: enable disassm for powerpc + * count = cs_disasm(handle, buf, len, start, len, &insn); + * + * For now, only binary code is saved in disassembled line + * to be used in "type" and "typeoff" sort keys. Each raw code + * is 32 bit instruction. So use "len/4" to get the number of + * entries. + */ + count = len/4; + + for (i = 0, offset = 0; i < count; i++) { + args->offset = offset; + sprintf(args->line, "%x", line[i]); + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + offset += 4; + } + + /* It failed in the middle */ + if (offset != len) { + struct list_head *list = ¬es->src->source; + + /* Discard all lines and fallback to objdump */ + while (!list_empty(list)) { + dl = list_first_entry(list, struct disasm_line, al.node); + + list_del_init(&dl->al.node); + disasm_line__free(dl); + } + count = -1; + } + +out: + if (needs_cs_close) + cs_close(&handle); + free(buf); + return count < 0 ? count : 0; + +err: + if (fd >= 0) + close(fd); + if (needs_cs_close) { + struct disasm_line *tmp; + + /* + * It probably failed in the middle of the above loop. + * Release any resources it might add. + */ + list_for_each_entry_safe(dl, tmp, ¬es->src->source, al.node) { + list_del(&dl->al.node); + free(dl); + } + } + count = -1; + goto out; +} + static int symbol__disassemble_capstone(char *filename, struct symbol *sym, struct annotate_args *args) { @@ -1584,6 +1696,91 @@ err: } #endif +static int symbol__disassemble_raw(char *filename, struct symbol *sym, + struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct map *map = args->ms.map; + struct dso *dso = map__dso(map); + u64 start = map__rip_2objdump(map, sym->start); + u64 end = map__rip_2objdump(map, sym->end); + u64 len = end - start; + u64 offset; + int i, count; + u8 *buf = NULL; + char disasm_buf[512]; + struct disasm_line *dl; + u32 *line; + + /* Return if objdump is specified explicitly */ + if (args->options->objdump_path) + return -1; + + pr_debug("Reading raw instruction from : %s using dso__data_read_offset\n", filename); + + buf = malloc(len); + if (buf == NULL) + goto err; + + count = dso__data_read_offset(dso, NULL, sym->start, buf, len); + + line = (u32 *)buf; + + if ((u64)count != len) + goto err; + + /* add the function address and name */ + scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", + start, sym->name); + + args->offset = -1; + args->line = disasm_buf; + args->line_nr = 0; + args->fileloc = NULL; + args->ms.sym = sym; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + /* Each raw instruction is 4 byte */ + count = len/4; + + for (i = 0, offset = 0; i < count; i++) { + args->offset = offset; + sprintf(args->line, "%x", line[i]); + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + offset += 4; + } + + /* It failed in the middle */ + if (offset != len) { + struct list_head *list = ¬es->src->source; + + /* Discard all lines and fallback to objdump */ + while (!list_empty(list)) { + dl = list_first_entry(list, struct disasm_line, al.node); + + list_del_init(&dl->al.node); + disasm_line__free(dl); + } + count = -1; + } + +out: + free(buf); + return count < 0 ? count : 0; + +err: + count = -1; + goto out; +} /* * Possibly create a new version of line with tabs expanded. Returns the * existing or new line, storage is updated if a new line is allocated. If @@ -1708,6 +1905,28 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) strcpy(symfs_filename, tmp); } + /* + * For powerpc data type profiling, use the dso__data_read_offset + * to read raw instruction directly and interpret the binary code + * to understand instructions and register fields. For sort keys as + * type and typeoff, disassemble to mnemonic notation is + * not required in case of powerpc. + */ + if (arch__is(args->arch, "powerpc")) { + extern const char *sort_order; + + if (sort_order && !strstr(sort_order, "sym")) { + err = symbol__disassemble_raw(symfs_filename, sym, args); + if (err == 0) + goto out_remove_tmp; +#ifdef HAVE_LIBCAPSTONE_SUPPORT + err = symbol__disassemble_capstone_powerpc(symfs_filename, sym, args); + if (err == 0) + goto out_remove_tmp; +#endif + } + } + #ifdef HAVE_LIBCAPSTONE_SUPPORT err = symbol__disassemble_capstone(symfs_filename, sym, args); if (err == 0) diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h index 3d381a043520..f56beedeb9da 100644 --- a/tools/perf/util/disasm.h +++ b/tools/perf/util/disasm.h @@ -4,11 +4,18 @@ #include "map_symbol.h" +#ifdef HAVE_DWARF_SUPPORT +#include "dwarf-aux.h" +#endif + struct annotation_options; struct disasm_line; struct ins; struct evsel; struct symbol; +struct data_loc_info; +struct type_state; +struct disasm_line; struct arch { const char *name; @@ -32,6 +39,11 @@ struct arch { char memory_ref_char; char imm_char; } objdump; +#ifdef HAVE_DWARF_SUPPORT + void (*update_insn_state)(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die *cu_die, + struct disasm_line *dl); +#endif }; struct ins { @@ -50,6 +62,7 @@ struct ins_operands { bool offset_avail; bool outside; bool multi_regs; + bool mem_ref; } target; union { struct { @@ -57,6 +70,7 @@ struct ins_operands { char *name; u64 addr; bool multi_regs; + bool mem_ref; } source; struct { struct ins ins; @@ -71,7 +85,8 @@ struct ins_operands { struct ins_ops { void (*free)(struct ins_operands *ops); - int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms); + int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + struct disasm_line *dl); int (*scnprintf)(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name); }; @@ -90,7 +105,7 @@ struct annotate_args { struct arch *arch__find(const char *name); bool arch__is(struct arch *arch, const char *name); -struct ins_ops *ins__find(struct arch *arch, const char *name); +struct ins_ops *ins__find(struct arch *arch, const char *name, struct disasm_line *dl); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name); diff --git a/tools/perf/util/disasm_bpf.c b/tools/perf/util/disasm_bpf.c new file mode 100644 index 000000000000..1fee71c79b62 --- /dev/null +++ b/tools/perf/util/disasm_bpf.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "util/annotate.h" +#include "util/disasm_bpf.h" +#include "util/symbol.h" +#include <linux/zalloc.h> +#include <string.h> + +#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +#define PACKAGE "perf" +#include <bfd.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <dis-asm.h> +#include <errno.h> +#include <linux/btf.h> +#include <tools/dis-asm-compat.h> + +#include "util/bpf-event.h" +#include "util/bpf-utils.h" +#include "util/debug.h" +#include "util/dso.h" +#include "util/map.h" +#include "util/env.h" +#include "util/util.h" + +int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct bpf_prog_linfo *prog_linfo = NULL; + struct bpf_prog_info_node *info_node; + int len = sym->end - sym->start; + disassembler_ftype disassemble; + struct map *map = args->ms.map; + struct perf_bpil *info_linear; + struct disassemble_info info; + struct dso *dso = map__dso(map); + int pc = 0, count, sub_id; + struct btf *btf = NULL; + char tpath[PATH_MAX]; + size_t buf_size; + int nr_skip = 0; + char *buf; + bfd *bfdf; + int ret; + FILE *s; + + if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO) + return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; + + pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, + sym->name, sym->start, sym->end - sym->start); + + memset(tpath, 0, sizeof(tpath)); + perf_exe(tpath, sizeof(tpath)); + + bfdf = bfd_openr(tpath, NULL); + if (bfdf == NULL) + abort(); + + if (!bfd_check_format(bfdf, bfd_object)) + abort(); + + s = open_memstream(&buf, &buf_size); + if (!s) { + ret = errno; + goto out; + } + init_disassemble_info_compat(&info, s, + (fprintf_ftype) fprintf, + fprintf_styled); + info.arch = bfd_get_arch(bfdf); + info.mach = bfd_get_mach(bfdf); + + info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, + dso__bpf_prog(dso)->id); + if (!info_node) { + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; + goto out; + } + info_linear = info_node->info_linear; + sub_id = dso__bpf_prog(dso)->sub_id; + + info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); + info.buffer_length = info_linear->info.jited_prog_len; + + if (info_linear->info.nr_line_info) + prog_linfo = bpf_prog_linfo__new(&info_linear->info); + + if (info_linear->info.btf_id) { + struct btf_node *node; + + node = perf_env__find_btf(dso__bpf_prog(dso)->env, + info_linear->info.btf_id); + if (node) + btf = btf__new((__u8 *)(node->data), + node->data_size); + } + + disassemble_init_for_target(&info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + disassemble = disassembler(info.arch, + bfd_big_endian(bfdf), + info.mach, + bfdf); +#else + disassemble = disassembler(bfdf); +#endif + if (disassemble == NULL) + abort(); + + fflush(s); + do { + const struct bpf_line_info *linfo = NULL; + struct disasm_line *dl; + size_t prev_buf_size; + const char *srcline; + u64 addr; + + addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; + count = disassemble(pc, &info); + + if (prog_linfo) + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + addr, sub_id, + nr_skip); + + if (linfo && btf) { + srcline = btf__name_by_offset(btf, linfo->line_off); + nr_skip++; + } else + srcline = NULL; + + fprintf(s, "\n"); + prev_buf_size = buf_size; + fflush(s); + + if (!annotate_opts.hide_src_code && srcline) { + args->offset = -1; + args->line = strdup(srcline); + args->line_nr = 0; + args->fileloc = NULL; + args->ms.sym = sym; + dl = disasm_line__new(args); + if (dl) { + annotation_line__add(&dl->al, + ¬es->src->source); + } + } + + args->offset = pc; + args->line = buf + prev_buf_size; + args->line_nr = 0; + args->fileloc = NULL; + args->ms.sym = sym; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + pc += count; + } while (count > 0 && pc < len); + + ret = 0; +out: + free(prog_linfo); + btf__free(btf); + fclose(s); + bfd_close(bfdf); + return ret; +} +#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, struct annotate_args *args __maybe_unused) +{ + return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; +} +#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) + +int symbol__disassemble_bpf_image(struct symbol *sym, struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *dl; + + args->offset = -1; + args->line = strdup("to be implemented"); + args->line_nr = 0; + args->fileloc = NULL; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + zfree(&args->line); + return 0; +} diff --git a/tools/perf/util/disasm_bpf.h b/tools/perf/util/disasm_bpf.h new file mode 100644 index 000000000000..2ecb19545388 --- /dev/null +++ b/tools/perf/util/disasm_bpf.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#ifndef __PERF_DISASM_BPF_H +#define __PERF_DISASM_BPF_H + +struct symbol; +struct annotate_args; + +int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args); +int symbol__disassemble_bpf_image(struct symbol *sym, struct annotate_args *args); + +#endif /* __PERF_DISASM_BPF_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 3a719edafc7a..1417f9a23083 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1086,7 +1086,8 @@ out_delete_threads: return -1; } -int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel, + struct target *target) { struct evsel *evsel; int err = 0; @@ -1108,7 +1109,7 @@ int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) * non-tracepoint events can have BPF filters. */ if (!list_empty(&evsel->bpf_filters)) { - err = perf_bpf_filter__prepare(evsel); + err = perf_bpf_filter__prepare(evsel, target); if (err) { *err_evsel = evsel; break; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index cb91dc9117a2..cccc34da5a02 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -20,6 +20,7 @@ struct pollfd; struct thread_map; struct perf_cpu_map; struct record_opts; +struct target; /* * State machine of bkw_mmap_state: @@ -212,7 +213,8 @@ void evlist__enable_non_dummy(struct evlist *evlist); void evlist__set_selected(struct evlist *evlist, struct evsel *evsel); int evlist__create_maps(struct evlist *evlist, struct target *target); -int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel, + struct target *target); u64 __evlist__combined_sample_type(struct evlist *evlist); u64 evlist__combined_sample_type(struct evlist *evlist); diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 8719b3cb5646..c2c0500d5da9 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -107,7 +107,6 @@ out: return ++printed; } -#ifndef PYTHON_PERF int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, unsigned int print_opts, struct callchain_cursor *cursor, struct strlist *bt_stop_list, FILE *fp) @@ -248,4 +247,3 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, return printed; } -#endif /* PYTHON_PERF */ diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index 558efcb98d25..bae649ef50e8 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -6,6 +6,7 @@ #include "target.h" struct evlist; +struct hashamp; struct perf_ftrace { struct evlist *evlist; @@ -15,6 +16,7 @@ struct perf_ftrace { struct list_head notrace; struct list_head graph_funcs; struct list_head nograph_funcs; + struct hashmap *profile_hash; unsigned long percpu_buffer_size; bool inherit; bool use_nsec; @@ -25,6 +27,7 @@ struct perf_ftrace { int graph_noirqs; int graph_verbose; int graph_thresh; + int graph_tail; }; struct filter_entry { diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f028f113c4fd..f8ee1cd6929d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -476,6 +476,12 @@ static int hist_entry__init(struct hist_entry *he, he->branch_info->to.ms.map = map__get(he->branch_info->to.ms.map); } + if (he->mem_info) { + he->mem_info = mem_info__clone(template->mem_info); + if (he->mem_info == NULL) + goto err_infos; + } + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) callchain_init(he->callchain); @@ -620,12 +626,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (symbol_conf.cumulate_callchain) he_stat__add_period(he->stat_acc, period); - /* - * This mem info was allocated from sample__resolve_mem - * and will not be used anymore. - */ - mem_info__zput(entry->mem_info); - block_info__delete(entry->block_info); kvm_info__zput(entry->kvm_info); @@ -739,7 +739,7 @@ __hists__add_entry(struct hists *hists, .filtered = symbol__parent_filter(sym_parent) | al->filtered, .hists = hists, .branch_info = bi, - .mem_info = mem_info__get(mi), + .mem_info = mi, .kvm_info = ki, .block_info = block_info, .transaction = sample->transaction, diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index 01fb25a1150a..75b28dcc8317 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_DWARF_REGS_H_ #define _PERF_DWARF_REGS_H_ +#include "annotate.h" #define DWARF_REG_PC 0xd3af9c /* random number */ #define DWARF_REG_FB 0xd3affb /* random number */ @@ -31,6 +32,16 @@ static inline int get_dwarf_regnum(const char *name __maybe_unused, } #endif +#if !defined(__powerpc__) || !defined(HAVE_DWARF_SUPPORT) +static inline void get_powerpc_regs(u32 raw_insn __maybe_unused, int is_source __maybe_unused, + struct annotated_op_loc *op_loc __maybe_unused) +{ + return; +} +#else +void get_powerpc_regs(u32 raw_insn, int is_source, struct annotated_op_loc *op_loc); +#endif + #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET /* * Arch should support fetching the offset of a register in pt_regs diff --git a/tools/perf/util/map_symbol.c b/tools/perf/util/map_symbol.c index bef5079f2403..6ad2960bc289 100644 --- a/tools/perf/util/map_symbol.c +++ b/tools/perf/util/map_symbol.c @@ -13,3 +13,21 @@ void addr_map_symbol__exit(struct addr_map_symbol *ams) { map_symbol__exit(&ams->ms); } + +void map_symbol__copy(struct map_symbol *dst, struct map_symbol *src) +{ + dst->maps = maps__get(src->maps); + dst->map = map__get(src->map); + dst->sym = src->sym; +} + +void addr_map_symbol__copy(struct addr_map_symbol *dst, struct addr_map_symbol *src) +{ + map_symbol__copy(&dst->ms, &src->ms); + + dst->addr = src->addr; + dst->al_addr = src->al_addr; + dst->al_level = src->al_level; + dst->phys_addr = src->phys_addr; + dst->data_page_size = src->data_page_size; +} diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 72d5ed938ed6..e370bb32ed47 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -26,4 +26,7 @@ struct addr_map_symbol { void map_symbol__exit(struct map_symbol *ms); void addr_map_symbol__exit(struct addr_map_symbol *ams); +void map_symbol__copy(struct map_symbol *dst, struct map_symbol *src); +void addr_map_symbol__copy(struct addr_map_symbol *dst, struct addr_map_symbol *src); + #endif // __PERF_MAP_SYMBOL diff --git a/tools/perf/util/mem-info.c b/tools/perf/util/mem-info.c index 27d67721a695..d3efa9c139f2 100644 --- a/tools/perf/util/mem-info.c +++ b/tools/perf/util/mem-info.c @@ -33,3 +33,16 @@ struct mem_info *mem_info__new(void) return result; } + +struct mem_info *mem_info__clone(struct mem_info *mi) +{ + struct mem_info *result = mem_info__new(); + + if (result) { + addr_map_symbol__copy(mem_info__iaddr(result), mem_info__iaddr(mi)); + addr_map_symbol__copy(mem_info__daddr(result), mem_info__daddr(mi)); + mem_info__data_src(result)->val = mem_info__data_src(mi)->val; + } + + return result; +} diff --git a/tools/perf/util/mem-info.h b/tools/perf/util/mem-info.h index 0f68e29f311b..df75e94ed3d0 100644 --- a/tools/perf/util/mem-info.h +++ b/tools/perf/util/mem-info.h @@ -15,6 +15,7 @@ DECLARE_RC_STRUCT(mem_info) { }; struct mem_info *mem_info__new(void); +struct mem_info *mem_info__clone(struct mem_info *mi); struct mem_info *mem_info__get(struct mem_info *mi); void mem_info__put(struct mem_info *mi); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 122ee198a86e..43b02293f1d2 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -230,9 +230,7 @@ void mmap__munmap(struct mmap *map) { bitmap_free(map->affinity_mask.bits); -#ifndef PYTHON_PERF zstd_fini(&map->zstd_data); -#endif perf_mmap__aio_munmap(map); if (map->data != NULL) { @@ -295,12 +293,10 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu map->core.flush = mp->flush; -#ifndef PYTHON_PERF if (zstd_init(&map->zstd_data, mp->comp_level)) { pr_debug2("failed to init mmap compressor, error %d\n", errno); return -1; } -#endif if (mp->comp_level && !perf_mmap__aio_enabled(map)) { map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 986166bc7c78..0b38c51bd6eb 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1199,8 +1199,12 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) bool evsel__is_aux_event(const struct evsel *evsel) { - struct perf_pmu *pmu = evsel__find_pmu(evsel); + struct perf_pmu *pmu; + + if (evsel->needs_auxtrace_mmap) + return true; + pmu = evsel__find_pmu(evsel); return pmu && pmu->auxtrace; } diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 3f38c27f0157..81e0135cddf0 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -68,11 +68,12 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus struct dirent **sys_namelist = NULL; int sys_items; - put_tracing_file(events_path); if (events_fd < 0) { pr_err("Error: failed to open tracing events directory\n"); + pr_err("%s: %s\n", events_path, strerror(errno)); return; } + put_tracing_file(events_path); sys_items = tracing_events__scandir_alphasort(&sys_namelist); diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c index a950e9157d2d..a33a7726422d 100644 --- a/tools/perf/util/print_insn.c +++ b/tools/perf/util/print_insn.c @@ -32,7 +32,9 @@ size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp) #ifdef HAVE_LIBCAPSTONE_SUPPORT #include <capstone/capstone.h> -static int capstone_init(struct machine *machine, csh *cs_handle, bool is64) +int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style); + +int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style) { cs_arch arch; cs_mode mode; @@ -62,7 +64,13 @@ static int capstone_init(struct machine *machine, csh *cs_handle, bool is64) } if (machine__normalized_is(machine, "x86")) { - cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); + /* + * In case of using capstone_init while symbol__disassemble + * setting CS_OPT_SYNTAX_ATT depends if disassembler_style opts + * is set via annotation args + */ + if (disassembler_style) + cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); /* * Resolving address operands to symbols is implemented * on x86 by investigating instruction details. @@ -122,7 +130,7 @@ ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpum int ret; /* TODO: Try to initiate capstone only once but need a proper place. */ - ret = capstone_init(machine, &cs_handle, is64bit); + ret = capstone_init(machine, &cs_handle, is64bit, true); if (ret < 0) return ret; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index ab7c7ff35f9b..c4046d5d1749 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3960,7 +3960,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int add_key(sb, s[i].name, llen); } -char *sort_help(const char *prefix) +char *sort_help(const char *prefix, enum sort_mode mode) { struct strbuf sb; char *s; @@ -3972,10 +3972,12 @@ char *sort_help(const char *prefix) ARRAY_SIZE(hpp_sort_dimensions), &len); add_sort_string(&sb, common_sort_dimensions, ARRAY_SIZE(common_sort_dimensions), &len); - add_sort_string(&sb, bstack_sort_dimensions, - ARRAY_SIZE(bstack_sort_dimensions), &len); - add_sort_string(&sb, memory_sort_dimensions, - ARRAY_SIZE(memory_sort_dimensions), &len); + if (mode == SORT_MODE__NORMAL || mode == SORT_MODE__BRANCH) + add_sort_string(&sb, bstack_sort_dimensions, + ARRAY_SIZE(bstack_sort_dimensions), &len); + if (mode == SORT_MODE__NORMAL || mode == SORT_MODE__MEMORY) + add_sort_string(&sb, memory_sort_dimensions, + ARRAY_SIZE(memory_sort_dimensions), &len); s = strbuf_detach(&sb, NULL); strbuf_release(&sb); return s; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 0bd0ee3ae76b..6357bc32c5ca 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -130,7 +130,7 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); -char *sort_help(const char *prefix); +char *sort_help(const char *prefix, enum sort_mode mode); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); |