diff options
Diffstat (limited to 'tools/perf')
35 files changed, 587 insertions, 133 deletions
diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt index 52152d156ad9..79936355d819 100644 --- a/tools/perf/Documentation/jitdump-specification.txt +++ b/tools/perf/Documentation/jitdump-specification.txt @@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html -The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html +The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index de6beedb7283..3b6a2c84ea02 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -261,7 +261,7 @@ COALESCE User can specify how to sort offsets for cacheline. Following fields are available and governs the final -output fields set for caheline offsets output: +output fields set for cacheline offsets output: tid - coalesced by process TIDs pid - coalesced by process PIDs diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 184ba62420f0..db465fa7ee91 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns. "Transactions" events correspond to the start or end of transactions. The 'flags' field can be used in perf script to determine whether the event is a -tranasaction start, commit or abort. +transaction start, commit or abort. Note that "instructions", "branches" and "transactions" events depend on code flow packets which can be disabled by using the config term "branch=0". Refer diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 74d774592196..1b4d452923d7 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -44,7 +44,7 @@ COMMON OPTIONS -f:: --force:: - Don't complan, do it. + Don't complain, do it. REPORT OPTIONS -------------- diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5a1f68122f50..fa4f39d305a7 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -54,7 +54,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 0250dc61cf98..cf4b7f4b625a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -448,7 +448,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4c9310be6acc..7e6fb7cbc0f4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements. Print metrics or metricgroups specified in a comma separated list. For a group all metrics from the group are added. The events from the metrics are automatically measured. -See perf list output for the possble metrics and metricgroups. +See perf list output for the possible metrics and metricgroups. -A:: --no-aggr:: diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt index c6302df4cf29..a15b93fdcf50 100644 --- a/tools/perf/Documentation/topdown.txt +++ b/tools/perf/Documentation/topdown.txt @@ -2,7 +2,7 @@ Using TopDown metrics in user space ----------------------------------- Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown -methology to break down CPU pipeline execution into 4 bottlenecks: +methodology to break down CPU pipeline execution into 4 bottlenecks: frontend bound, backend bound, bad speculation, retiring. For more details on Topdown see [1][5] diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..14e3e8d702a0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -143,7 +143,7 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd +OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..b856afa6eb52 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h $(Q)$(MKDIR) -p $(OUTPUT)dlfilters $(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $< +.SECONDARY: $(DLFILTERS:.so=.o) + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< @@ -802,7 +804,7 @@ endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(filter-out -static,$(LDFLAGS))' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index c7c7ec0812d5..5fc6a2a3dbc5 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -8,10 +8,10 @@ #include <linux/coresight-pmu.h> #include <linux/zalloc.h> -#include "../../util/auxtrace.h" -#include "../../util/debug.h" -#include "../../util/evlist.h" -#include "../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/debug.h" +#include "../../../util/evlist.h" +#include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 515aae470e23..293a23bf8be3 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,19 +16,19 @@ #include <linux/zalloc.h> #include "cs-etm.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/auxtrace.h" -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/perf_api_probe.h" -#include "../../util/evsel_config.h" -#include "../../util/pmu.h" -#include "../../util/cs-etm.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/perf_api_probe.h" +#include "../../../util/evsel_config.h" +#include "../../../util/pmu.h" +#include "../../../util/cs-etm.h" #include <internal/lib.h> // page_size -#include "../../util/session.h" +#include "../../../util/session.h" #include <errno.h> #include <stdlib.h> diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index bbc297a7e2e3..b8b23b9dc598 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,7 @@ #include <linux/string.h> #include "arm-spe.h" -#include "../../util/pmu.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 36ba4c69c3c5..b7692cb0c733 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 3a550225dfaf..438906bf0014 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,8 +3,8 @@ #include <errno.h> #include <libunwind.h> #include "perf_regs.h" -#include "../../util/unwind.h" -#include "../../util/debug.h" +#include "../../../util/unwind.h" +#include "../../../util/debug.h" int libunwind__arch_reg_id(int regnum) { diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index eeafe97b8105..792cd75ade33 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, u8 die = ((struct iio_root_port *)evsel->priv)->die; struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); - if (count->run && count->ena) { + if (count && count->run && count->ena) { if (evsel->prev_raw_counts && !out->force_header) { struct perf_counts_values *prev_count = perf_counts(evsel->prev_raw_counts, die, 0); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0e824f7d8b19..c32c2eb16d7d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -368,16 +368,6 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } -static inline unsigned int attr_type(unsigned int type) -{ - switch (type) { - case OUTPUT_TYPE_SYNTH: - return PERF_TYPE_SYNTH; - default: - return type; - } -} - static bool output_set_by_user(void) { int j; @@ -469,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) return -EINVAL; if (PRINT_FIELD(SYM) && @@ -556,6 +546,18 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } +static struct evsel *find_first_output_type(struct evlist *evlist, + unsigned int type) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (output_type(evsel->core.attr.type) == (int)type) + return evsel; + } + return NULL; +} + /* * verify all user requested events exist and the samples * have the expected data @@ -567,7 +569,7 @@ static int perf_session__check_output_opt(struct perf_session *session) struct evsel *evsel; for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, attr_type(j)); + evsel = find_first_output_type(session->evlist, j); /* * even if fields is set to 0 (ie., show nothing) event must @@ -4037,11 +4039,15 @@ script_found: goto out_delete; uname(&uts); - if (data.is_pipe || /* assume pipe_mode indicates native_arch */ - !strcmp(uts.machine, session->header.env.arch) || - (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386"))) + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; + } else if (session->header.env.arch) { + if (!strcmp(uts.machine, session->header.env.arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386")) + native_arch = true; + } script.session = session; script__setup_sample_type(&script); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f6e87b7be5fa..f0ecfda34ece 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv) goto out; } else if (verbose) iostat_list(evsel_list, &stat_config); + if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target)) + target.system_wide = true; } if (add_default_attributes()) diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 84a0cedf1fd9..f1f2965f6775 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -1046,7 +1046,7 @@ { "EventCode": "0x4e010", "EventName": "PM_GCT_NOSLOT_IC_L3MISS", - "BriefDescription": "Gct empty for this thread due to icach l3 miss", + "BriefDescription": "Gct empty for this thread due to icache l3 miss", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..7c887d37b893 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1285,6 +1285,7 @@ int main(int argc, char *argv[]) } free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return 0; @@ -1306,6 +1307,7 @@ err_close_eventsfp: create_empty_mapping(output_file); err_out: free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return ret; } diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d9e99b3f77e6..d8ea6a88163f 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -68,3 +68,100 @@ fd=10 type=0 config=5 optional=1 + +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index 8b04a055d154..b656ab93c5bf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 4fca9f1bfbf8..97625090a1c4 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index 4bb58e1c82a6..d555042e3fbf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 @@ -174,8 +271,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event21:base-stat] -fd=21 +[event30:base-stat] +fd=30 type=3 config=512 optional=1 @@ -184,8 +281,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event22:base-stat] -fd=22 +[event31:base-stat] +fd=31 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..9b4a765e4b73 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, struct thread *thread, struct state *state) { struct addr_location al; - unsigned char buf1[BUFSZ]; - unsigned char buf2[BUFSZ]; + unsigned char buf1[BUFSZ] = {0}; + unsigned char buf2[BUFSZ] = {0}; size_t ret_len; u64 objdump_addr; const char *objdump_name; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index a288035eb362..c756284b3b13 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -20,6 +20,23 @@ /* For bsearch. We try to unwind functions in shared object. */ #include <stdlib.h> +/* + * The test will assert frames are on the stack but tail call optimizations lose + * the frame of the caller. Clang can disable this optimization on a called + * function but GCC currently (11/2020) lacks this attribute. The barrier is + * used to inhibit tail calls in these cases. + */ +#ifdef __has_attribute +#if __has_attribute(disable_tail_calls) +#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls)) +#define NO_TAIL_CALL_BARRIER +#endif +#endif +#ifndef NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory"); +#endif + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -noinline int test_dwarf_unwind__thread(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -noinline int test_dwarf_unwind__compare(void *p1, void *p2) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -noinline int test_dwarf_unwind__krava_3(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -noinline int test_dwarf_unwind__krava_2(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread) { - return test_dwarf_unwind__krava_3(thread); + int ret; + + ret = test_dwarf_unwind__krava_3(thread); + NO_TAIL_CALL_BARRIER; + return ret; } -noinline int test_dwarf_unwind__krava_1(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread) { - return test_dwarf_unwind__krava_2(thread); + int ret; + + ret = test_dwarf_unwind__krava_2(thread); + NO_TAIL_CALL_BARRIER; + return ret; } int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 781afe42e90e..fa5bd5c20e96 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -757,25 +757,40 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, } void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down) + unsigned int row, int diff, bool arrow_down) { - unsigned int end_row; + int end_row; - if (row >= browser->top_idx) - end_row = row - browser->top_idx; - else + if (diff <= 0) return; SLsmg_set_char_set(1); if (arrow_down) { + if (row + diff <= browser->top_idx) + return; + + end_row = row + diff - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); - SLsmg_write_char(SLSMG_ULCORN_CHAR); - ui_browser__gotorc(browser, end_row, column); - SLsmg_draw_hline(2); - ui_browser__gotorc(browser, end_row + 1, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); + + while (--end_row >= 0 && end_row > (int)(row - browser->top_idx)) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_draw_vline(1); + } + + end_row = (int)(row - browser->top_idx); + if (end_row >= 0) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_hline(2); + } } else { + if (row < browser->top_idx) + return; + + end_row = row - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); ui_browser__gotorc(browser, end_row, column); diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 3678eb88f119..510ce4554050 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -51,7 +51,7 @@ void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, u64 start, u64 end); void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down); + unsigned int row, int diff, bool arrow_down); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *browser, const char *title, diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ef4da4295bf7..e81c2493efdf 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -125,13 +125,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ab->selection = al; } -static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) +static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor) { struct disasm_line *pos = list_prev_entry(cursor, al.node); const char *name; + int diff = 1; + + while (pos && pos->al.offset == -1) { + pos = list_prev_entry(pos, al.node); + if (!ab->opts->hide_src_code) + diff++; + } if (!pos) - return false; + return 0; if (ins__is_lock(&pos->ins)) name = pos->ops.locked.ins.name; @@ -139,9 +146,11 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) name = pos->ins.name; if (!name || !cursor->ins.name) - return false; + return 0; - return ins__is_fused(ab->arch, name, cursor->ins.name); + if (ins__is_fused(ab->arch, name, cursor->ins.name)) + return diff; + return 0; } static void annotate_browser__draw_current_jump(struct ui_browser *browser) @@ -155,6 +164,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) struct annotation *notes = symbol__annotation(sym); u8 pcnt_width = annotation__pcnt_width(notes); int width; + int diff = 0; /* PLT symbols contain external offsets */ if (strstr(sym->name, "@plt")) @@ -205,11 +215,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) pcnt_width + 2 + notes->widths.addr + width, from, to); - if (is_fused(ab, cursor)) { + diff = is_fused(ab, cursor); + if (diff > 0) { ui_browser__mark_fused(browser, pcnt_width + 3 + notes->widths.addr + width, - from - 1, - to > from); + from - diff, diff, to > from); } } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 683f6d63560e..1a7112a87736 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -24,7 +24,10 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" int err = btf__get_from_id(id, &btf); +#pragma GCC diagnostic pop return err ? ERR_PTR(err) : btf; } diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4fb5e90d7a57..60ce5908c664 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set, section->name, item->name); ret = fn(key, value, data); if (ret < 0) { - pr_err("Error: wrong config key-value pair %s=%s\n", + pr_err("Error in the given config file: wrong config key-value pair %s=%s\n", key, value); /* * Can't be just a 'break', as perf_config_set__for_each_entry() diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index da19be7da284..44e40bad0e33 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2149,6 +2149,7 @@ static int add_callchain_ip(struct thread *thread, al.filtered = 0; al.sym = NULL; + al.srcline = NULL; if (!cpumode) { thread__find_cpumode_addr_location(thread, ip, &al); } else { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 069c2cfdd3be..352f16076e01 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2116,7 +2116,7 @@ fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) static int __perf_session__process_decomp_events(struct perf_session *session) { s64 skip; - u64 size, file_pos = 0; + u64 size; struct decomp *decomp = session->decomp_last; if (!decomp) @@ -2132,7 +2132,7 @@ static int __perf_session__process_decomp_events(struct perf_session *session) size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, file_pos)) < 0) { + (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", decomp->file_pos + decomp->head, event->header.size, event->header.type); return -EINVAL; |