perf tools: add support for libpfm4
Subsystems (4)
Ian Rogers
reviewerv12 cover perf tools: add support for libpfm4
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net.
With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match:
$ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles ....
v12 changes NO_LIBPFM4 as a make option to LIBPFM4, ie opt-in rather
than opt-out of feature detection and build support. Suggested by [email protected]. It also moves passing the ASCIIDOC_EXTRA argument into its own commit.
v11 reformats the perf list output.
v10 addresses review comments from [email protected].
v9 removes some unnecessary #ifs.
v8 addresses review comments from [email protected].
Breaks the patch into 4, adds a test and moves the libpfm code into its own file. perf list encoding tries to be closer to existing.
v7 rebases and adds fallback code for libpfm4 events.
The fallback code is to force user only priv level in case the perf_event_open() syscall failed for permissions reason. the fallback forces a user privilege level restriction on the event string, so depending on the syntax either u or :u is needed.
But libpfm4 can use a : or . as the separator, so simply searching for ':' vs. '/' is not good enough to determine the syntax needed. Therefore, this patch introduces a new evsel boolean field to mark events coming from libpfm4. The field is then used to adjust the fallback string.
v6 was a rebase.
v5 was a rebase.
v4 was a rebase on
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git
branch perf/core and re-adds the tools/build/feature/test-libpfm4.c missed in v3.
v3 is against acme/perf/core and removes a diagnostic warning. v2 of this patch makes the --pfm-events man page documentation
conditional on libpfm4 behing configured. It tidies some of the documentation and adds the feature test missed in the v1 patch.
Ian Rogers (1):
perf doc: pass ASCIIDOC_EXTRA as an argument
Stephane Eranian (3):
tools feature: add support for detecting libpfm4 perf pmu: add perf_pmu__find_by_type helper perf tools: add support for libpfm4
tools/build/Makefile.feature | 3 +- tools/build/feature/Makefile | 6 +- tools/build/feature/test-libpfm4.c | 9 + tools/perf/Documentation/perf-record.txt | 11 + tools/perf/Documentation/perf-stat.txt | 10 + tools/perf/Documentation/perf-top.txt | 11 + tools/perf/Makefile.config | 13 ++ tools/perf/Makefile.perf | 8 +- tools/perf/builtin-list.c | 3 + tools/perf/builtin-record.c | 8 + tools/perf/builtin-stat.c | 8 + tools/perf/builtin-top.c | 8 + tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 9 + tools/perf/tests/pfm.c | 207 +++++++++++++++++ tools/perf/tests/tests.h | 3 + tools/perf/util/Build | 2 + tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 30 ++- tools/perf/util/parse-events.h | 4 + tools/perf/util/pfm.c | 277 +++++++++++++++++++++++ tools/perf/util/pfm.h | 43 ++++ tools/perf/util/pmu.c | 11 + tools/perf/util/pmu.h | 1 + 25 files changed, 676 insertions(+), 13 deletions(-) create mode 100644 tools/build/feature/test-libpfm4.c create mode 100644 tools/perf/tests/pfm.c create mode 100644 tools/perf/util/pfm.c create mode 100644 tools/perf/util/pfm.h
Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
Ian Rogers
reviewerPATCH v12 1/4 perf doc: pass ASCIIDOC_EXTRA as an argument
commit e9cfa47e687d ("perf doc: allow ASCIIDOC_EXTRA to be an argument") allowed ASCIIDOC_EXTRA to be passed as an option to the Documentation Makefile. This change passes ASCIIDOC_EXTRA, set by detected features or command line options, prior to doing a Documentation build. This is necessary to allow conditional compilation, based on configuration variables, in asciidoc code.
--- tools/perf/Makefile.perf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
tools/perf/Makefile.perf +3 -3
@@ -188,7 +188,7 @@ AWK = awk # non-config cases config := 1 -NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf +NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html # 'make doc' should call 'make -C Documentation all' $(DOC_TARGETS): - $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA) TAG_FOLDERS= . ../lib ../include TAG_FILES= ../../include/uapi/linux/perf_event.h
@@ -959,7 +959,7 @@ install-python_ext: # 'make install-doc' should call 'make -C Documentation install' $(INSTALL_DOC_TARGETS): - $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA) ### Cleaning rules
Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
[tip: perf/core] perf doc: Pass ASCIIDOC_EXTRA as an argument
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 4b1984491e65c9592f9f2bfbe8fb5bf4d4e51587 Gitweb: https://git.kernel.org/tip/4b1984491e65c9592f9f2bfbe8fb5bf4d4e51587 Author: Ian Rogers <[email protected]> AuthorDate: Wed, 29 Apr 2020 16:14:40 -07:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Tue, 05 May 2020 16:35:31 -03:00
perf doc: Pass ASCIIDOC_EXTRA as an argument
commit e9cfa47e687d ("perf doc: allow ASCIIDOC_EXTRA to be an argument") allowed ASCIIDOC_EXTRA to be passed as an option to the Documentation Makefile. This change passes ASCIIDOC_EXTRA, set by detected features or command line options, prior to doing a Documentation build. This is necessary to allow conditional compilation, based on configuration variables, in asciidoc code.
--- tools/perf/Makefile.perf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
tools/perf/Makefile.perf +3 -3
@@ -188,7 +188,7 @@ AWK = awk # non-config cases config := 1 -NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf +NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html # 'make doc' should call 'make -C Documentation all' $(DOC_TARGETS): - $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA) TAG_FOLDERS= . ../lib ../include TAG_FILES= ../../include/uapi/linux/perf_event.h
@@ -959,7 +959,7 @@ install-python_ext: # 'make install-doc' should call 'make -C Documentation install' $(INSTALL_DOC_TARGETS): - $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA) ### Cleaning rules
Ian Rogers
reviewerPATCH v12 2/4 tools feature: add support for detecting libpfm4
In reply to Ian RogersFrom: Stephane Eranian <[email protected]>
libpfm4 provides an alternate command line encoding of perf events.
--- tools/build/Makefile.feature | 3 ++- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-libpfm4.c | 9 +++++++++ 3 files changed, 16 insertions(+), 2 deletions(-) create mode 100644 tools/build/feature/test-libpfm4.c
tools/build/Makefile.feature +2 -1
@@ -98,7 +98,8 @@ FEATURE_TESTS_EXTRA := \ llvm \ llvm-version \ clang \ - libbpf + libbpf \ + libpfm4 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
tools/build/feature/Makefile +5 -1
@@ -69,7 +69,8 @@ FILES= \ test-libaio.bin \ test-libzstd.bin \ test-clang-bpf-global-var.bin \ - test-file-handle.bin + test-file-handle.bin \ + test-libpfm4.bin FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -331,6 +332,9 @@ $(OUTPUT)test-clang-bpf-global-var.bin: $(OUTPUT)test-file-handle.bin: $(BUILD) +$(OUTPUT)test-libpfm4.bin: + $(BUILD) -lpfm + ############################### clean:
tools/build/feature/test-libpfm4.c new file +9 -0
@@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/types.h> +#include <perfmon/pfmlib.h> + +int main (void ) +{ +pfm_initialize (); +return 0 ; +}
Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
[tip: perf/core] tools feature: Add support for detecting libpfm4
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 5ef86146de941f273d669a8e018036f549bf058c Gitweb: https://git.kernel.org/tip/5ef86146de941f273d669a8e018036f549bf058c Author: Stephane Eranian <[email protected]> AuthorDate: Wed, 29 Apr 2020 16:14:41 -07:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Tue, 05 May 2020 16:35:31 -03:00
tools feature: Add support for detecting libpfm4
libpfm4 provides an alternate command line encoding of perf events.
--- tools/build/Makefile.feature | 3 ++- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-libpfm4.c | 9 +++++++++ 3 files changed, 16 insertions(+), 2 deletions(-) create mode 100644 tools/build/feature/test-libpfm4.c
tools/build/Makefile.feature +2 -1
@@ -98,7 +98,8 @@ FEATURE_TESTS_EXTRA := \ llvm \ llvm-version \ clang \ - libbpf + libbpf \ + libpfm4 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
tools/build/feature/Makefile +5 -1
@@ -69,7 +69,8 @@ FILES= \ test-libaio.bin \ test-libzstd.bin \ test-clang-bpf-global-var.bin \ - test-file-handle.bin + test-file-handle.bin \ + test-libpfm4.bin FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -331,6 +332,9 @@ $(OUTPUT)test-clang-bpf-global-var.bin: $(OUTPUT)test-file-handle.bin: $(BUILD) +$(OUTPUT)test-libpfm4.bin: + $(BUILD) -lpfm + ############################### clean:
tools/build/feature/test-libpfm4.c new file +9 -0
@@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/types.h> +#include <perfmon/pfmlib.h> + +int main (void ) +{ +pfm_initialize (); +return 0 ; +}
Ian Rogers
reviewerPATCH v12 3/4 perf pmu: add perf_pmu__find_by_type helper
In reply to Ian RogersFrom: Stephane Eranian <[email protected]>
This is used by libpfm4 during event parsing to locate the pmu for an event.
--- tools/perf/util/pmu.c | 11 +++++++++++ tools/perf/util/pmu.h | 1 + 2 files changed, 12 insertions(+)
tools/perf/util/pmu.c +11 -0
@@ -871,6 +871,17 @@ static struct perf_pmu *pmu_find(const char *name)return NULL ; } +struct perf_pmu *perf_pmu__find_by_type (unsigned int type) +{ +struct perf_pmu *pmu; + +list_for_each_entry (pmu, &pmus, list) +if (pmu->type == type) +return pmu; + +return NULL ; +} +struct perf_pmu *perf_pmu__scan (struct perf_pmu *pmu) {/*
tools/perf/util/pmu.h +1 -0
@@ -72,6 +72,7 @@ struct perf_pmu_alias { };struct perf_pmu *perf_pmu__find (const char *name); +struct perf_pmu *perf_pmu__find_by_type (unsigned int type);int perf_pmu__config (struct perf_pmu *pmu,struct perf_event_attr *attr,struct list_head *head_terms,struct parse_events_error *error);
Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
[tip: perf/core] perf pmu: Add perf_pmu__find_by_type helper
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 3a50dc76058d7cd8315f9c712b793d81a7ff4541 Gitweb: https://git.kernel.org/tip/3a50dc76058d7cd8315f9c712b793d81a7ff4541 Author: Stephane Eranian <[email protected]> AuthorDate: Wed, 29 Apr 2020 16:14:42 -07:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Tue, 05 May 2020 16:35:31 -03:00
perf pmu: Add perf_pmu__find_by_type helper
This is used by libpfm4 during event parsing to locate the pmu for an event.
--- tools/perf/util/pmu.c | 11 +++++++++++ tools/perf/util/pmu.h | 1 + 2 files changed, 12 insertions(+)
tools/perf/util/pmu.c +11 -0
@@ -871,6 +871,17 @@ static struct perf_pmu *pmu_find(const char *name)return NULL ; } +struct perf_pmu *perf_pmu__find_by_type (unsigned int type) +{ +struct perf_pmu *pmu; + +list_for_each_entry (pmu, &pmus, list) +if (pmu->type == type) +return pmu; + +return NULL ; +} +struct perf_pmu *perf_pmu__scan (struct perf_pmu *pmu) {/*
tools/perf/util/pmu.h +1 -0
@@ -72,6 +72,7 @@ struct perf_pmu_alias { };struct perf_pmu *perf_pmu__find (const char *name); +struct perf_pmu *perf_pmu__find_by_type (unsigned int type);int perf_pmu__config (struct perf_pmu *pmu,struct perf_event_attr *attr,struct list_head *head_terms,struct parse_events_error *error);
Ian Rogers
reviewerPATCH v12 4/4 perf tools: add support for libpfm4
In reply to Ian RogersFrom: Stephane Eranian <[email protected]>
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net.
With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match:
$ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles ....
--- tools/perf/Documentation/perf-record.txt | 11 + tools/perf/Documentation/perf-stat.txt | 10 + tools/perf/Documentation/perf-top.txt | 11 + tools/perf/Makefile.config | 13 ++ tools/perf/Makefile.perf | 2 + tools/perf/builtin-list.c | 3 + tools/perf/builtin-record.c | 8 + tools/perf/builtin-stat.c | 8 + tools/perf/builtin-top.c | 8 + tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 9 + tools/perf/tests/pfm.c | 207 +++++++++++++++++ tools/perf/tests/tests.h | 3 + tools/perf/util/Build | 2 + tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 30 ++- tools/perf/util/parse-events.h | 4 + tools/perf/util/pfm.c | 277 +++++++++++++++++++++++ tools/perf/util/pfm.h | 43 ++++ 20 files changed, 645 insertions(+), 8 deletions(-) create mode 100644 tools/perf/tests/pfm.c create mode 100644 tools/perf/util/pfm.c create mode 100644 tools/perf/util/pfm.h
tools/perf/Documentation/perf-record.txt +11 -0
@@ -596,6 +596,17 @@ Make a copy of /proc/kcore and place it into a directory with the perf data file Limit the sample data max size, <size> is expected to be a number with appended unit character - B/K/M/G +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
tools/perf/Documentation/perf-stat.txt +10 -0
@@ -71,6 +71,16 @@ report:: --tid=<tid>:: stat events on existing thread id (comma separated list) +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] -a:: --all-cpus::
tools/perf/Documentation/perf-top.txt +11 -0
@@ -329,6 +329,17 @@ Default is to monitor all CPUS. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + INTERACTIVE PROMPTING KEYS --------------------------
tools/perf/Makefile.config +13 -0
@@ -1012,6 +1012,19 @@ ifdef LIBCLANGLLVM endif endif +ifdef LIBPFM4 + $(call feature_check,libpfm4) + ifeq ($(feature-libpfm4), 1) + CFLAGS += -DHAVE_LIBPFM + EXTLIBS += -lpfm + ASCIIDOC_EXTRA = -aHAVE_LIBPFM=1 + $(call detected,CONFIG_LIBPFM4) + else + msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev); + NO_LIBPFM4 := 1 + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dir
tools/perf/Makefile.perf +2 -0
@@ -118,6 +118,8 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # +# Define LIBPFM4 to enable libpfm4 events extension. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL
tools/perf/builtin-list.c +3 -0
@@ -14,6 +14,7 @@#include "util/pmu.h" #include "util/debug.h" #include "util/metricgroup.h" +#include "util/pfm.h" #include <subcmd/pager.h> #include <subcmd/parse-options.h> #include <stdio.h>
@@ -53,6 +54,8 @@ int cmd_list(int argc, const char **argv)setup_pager (); +libpfm_initialize (); +if (!raw_dump &&pager_in_use ())printf ("\nList of pre-defined events (to be used in -e):\n\n" );
tools/perf/builtin-record.c +8 -0
@@ -43,6 +43,7 @@#include "util/time-utils.h" #include "util/units.h" #include "util/bpf-event.h" +#include "util/pfm.h" #include "asm/bug.h" #include "perf.h"
@@ -2421,6 +2422,11 @@ static struct option __record_options[] = {#endif OPT_CALLBACK(0, "max-size", &record.output_max_size, "size", "Limit the maximum size of the output file", parse_output_max_size), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &record.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };
@@ -2461,6 +2467,8 @@ int cmd_record(int argc, const char **argv)if (rec->evlist ==NULL )return -ENOMEM ; +libpfm_initialize (); + err =perf_config (perf_record_config, rec);if (err)return err;
tools/perf/builtin-stat.c +8 -0
@@ -66,6 +66,7 @@#include "util/time-utils.h" #include "util/top.h" #include "util/affinity.h" +#include "util/pfm.h" #include "asm/bug.h" #include <linux/time64.h>
@@ -936,6 +937,11 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &evsel_list,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };
@@ -1874,6 +1880,8 @@ int cmd_stat(int argc, const char **argv)unsigned int interval, timeout;const char *const stat_subcommands[] = {"record" ,"report" }; +libpfm_initialize (); +setlocale (LC_ALL ,"" ); evsel_list =evlist__new ();
tools/perf/builtin-top.c +8 -0
@@ -53,6 +53,7 @@#include "util/debug.h" #include "util/ordered-events.h" +#include "util/pfm.h" #include <assert.h> #include <elf.h>
@@ -1577,6 +1578,11 @@ int cmd_top(int argc, const char **argv) "WARNING: should be used on grouped events."),OPT_BOOLEAN (0 ,"stitch-lbr" , &top.stitch_lbr,"Enable LBR callgraph stitching approach" ), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &top.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPTS_EVSWITCH (&top.evswitch), OPT_END() };
@@ -1590,6 +1596,8 @@ int cmd_top(int argc, const char **argv)if (status <0 )return status; +libpfm_initialize (); + top.annotation_opts.min_pcnt =5 ; top.annotation_opts.context =4 ;
tools/perf/tests/Build +1 -0
@@ -56,6 +56,7 @@ perf-y += mem2node.o perf-y += maps.o perf-y += time-utils-test.o perf-y += genelf.o +perf-y += pfm.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir)
tools/perf/tests/builtin-test.c +9 -0
@@ -313,6 +313,15 @@ static struct test generic_tests[] = { .desc = "maps__merge_in", .func = test__maps__merge_in, }, + { + .desc = "Test libpfm4 support", + .func = test__pfm, + .subtest = { + .skip_if_fail = true, + .get_nr = test__pfm_subtest_get_nr, + .get_desc = test__pfm_subtest_get_desc, + } + }, { .func = NULL, },
tools/perf/tests/pfm.c new file +207 -0
207 lines not on this page · raw message
tools/perf/tests/tests.h +3 -0
@@ -112,6 +112,9 @@ int test__mem2node(struct test *t, int subtest);int test__maps__merge_in (struct test *t,int subtest);int test__time_utils (struct test *t,int subtest);int test__jit_write_elf (struct test *test,int subtest); +int test__pfm (struct test *test,int subtest); +const char *test__pfm_subtest_get_desc (int subtest); +int test__pfm_subtest_get_nr (void );bool test__bp_signal_is_supported (void );bool test__bp_account_is_supported (void );
tools/perf/util/Build +2 -0
@@ -177,6 +177,8 @@ perf-$(CONFIG_LIBBPF) += bpf-event.o perf-$(CONFIG_CXX) += c++/ +perf-$(CONFIG_LIBPFM4) += pfm.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
tools/perf/util/evsel.c +1 -1
@@ -2433,7 +2433,7 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,/* Is there already the separator in the name. */ if (strchr (name,'/' ) || -strchr (name,':' )) + (strchr (name,':' ) && !evsel->is_libpfm_event)) sep ="" ;if (asprintf (&new_name,"%s%su" , name, sep) <0 )
tools/perf/util/evsel.h +1 -0
@@ -76,6 +76,7 @@ struct evsel {bool ignore_missing_thread;bool forced_leader;bool use_uncore_alias; +bool is_libpfm_event;/* parse modifier helper */ int exclude_GH;int sample_read;
tools/perf/util/parse-events.c +23 -7
@@ -36,6 +36,7 @@#include "metricgroup.h" #include "util/evsel_config.h" #include "util/event.h" +#include "util/pfm.h" #define MAX_NAME_LEN 100
@@ -344,6 +345,7 @@ static char *get_config_name(struct list_head *head_terms)static struct evsel *__add_event (struct list_head *list,int *idx,struct perf_event_attr *attr, +bool init_attr,char *name,struct perf_pmu *pmu,struct list_head *config_terms,bool auto_merge_stats,const char *cpu_list)
@@ -352,7 +354,8 @@ __add_event(struct list_head *list, int *idx,struct perf_cpu_map *cpus = pmu ? pmu->cpus : cpu_list ?perf_cpu_map__new (cpu_list) :NULL ; -event_attr_init (attr); +if (init_attr) +event_attr_init (attr); evsel =perf_evsel__new_idx (attr, *idx);if (!evsel)
@@ -370,15 +373,25 @@ __add_event(struct list_head *list, int *idx,if (config_terms)list_splice (config_terms, &evsel->config_terms); -list_add_tail (&evsel->core.node, list); +if (list) +list_add_tail (&evsel->core.node, list); +return evsel; } +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu) +{ +return __add_event (NULL , &idx, attr, false, name, pmu,NULL , false, +NULL ); +} +static int add_event (struct list_head *list,int *idx,struct perf_event_attr *attr,char *name,struct list_head *config_terms) { -return __add_event (list, idx, attr, name,NULL , config_terms, false,NULL ) ?0 : -ENOMEM ; +return __add_event (list, idx, attr, true, name,NULL , config_terms, + false,NULL ) ?0 : -ENOMEM ; } static int add_event_tool(struct list_head *list, int *idx,
@@ -390,7 +403,8 @@ static int add_event_tool(struct list_head *list, int *idx, .config = PERF_COUNT_SW_DUMMY, }; - evsel =__add_event (list, idx, &attr,NULL ,NULL ,NULL , false,"0" ); + evsel =__add_event (list, idx, &attr, true,NULL ,NULL ,NULL , false, +"0" );if (!evsel)return -ENOMEM ; evsel->tool_event = tool_event;
@@ -1446,8 +1460,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,if (!head_config) { attr.type = pmu->type; - evsel =__add_event (list, &parse_state->idx, &attr,NULL , pmu,NULL , - auto_merge_stats,NULL ); + evsel =__add_event (list, &parse_state->idx, &attr, true,NULL , + pmu,NULL , auto_merge_stats,NULL );if (evsel) { evsel->pmu_name = name ?strdup (name) :NULL ; evsel->use_uncore_alias = use_uncore_alias;
@@ -1487,7 +1501,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,return -EINVAL ; } - evsel =__add_event (list, &parse_state->idx, &attr, + evsel =__add_event (list, &parse_state->idx, &attr, true,get_config_name (head_config), pmu, &config_terms, auto_merge_stats,NULL );if (evsel) {
@@ -2794,6 +2808,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,print_sdt_events (NULL ,NULL , name_only);metricgroup__print (true, true,NULL , name_only, details_flag); + +print_libpfm_events (name_only, long_desc); }int parse_events__is_hardcoded_term (struct parse_events_term *term)
tools/perf/util/parse-events.h +4 -0
@@ -17,6 +17,7 @@ struct evlist;struct parse_events_error ;struct option ; +struct perf_pmu ;struct tracepoint_path {char *system;
@@ -186,6 +187,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,bool auto_merge_stats, bool use_alias); +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu); +int parse_events_multi_pmu_add (struct parse_events_state *parse_state,char *str,struct list_head **listp);
tools/perf/util/pfm.c new file +277 -0
277 lines not on this page · raw message
tools/perf/util/pfm.h new file +43 -0
43 lines not on this page · raw message
Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
Em Wed, Apr 29, 2020 at 04:14:43PM -0700, Ian Rogers escreveu:
Quoted 9 lines
From: Stephane Eranian <[email protected]>
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by
perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net.
Hey, I think we should not call libpfm_initialize() in all tools, better leave it to when the --pfm-event callback gets called, because the user is really using that event syntax, i.e. do it lazily, to reduce the amount of initialization that perf does, which is already excessive and needs triming down, to do more things only when they are really, really needed.
I have applied the previous, preparatory patches.
- Arnaldo
Quoted 1,008 lines
With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match:
$ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles ....Signed-off-by Stephane Eranian <[email protected]>Reviewed-by Ian Rogers <[email protected]>--- tools/perf/Documentation/perf-record.txt | 11 + tools/perf/Documentation/perf-stat.txt | 10 + tools/perf/Documentation/perf-top.txt | 11 + tools/perf/Makefile.config | 13 ++ tools/perf/Makefile.perf | 2 + tools/perf/builtin-list.c | 3 + tools/perf/builtin-record.c | 8 + tools/perf/builtin-stat.c | 8 + tools/perf/builtin-top.c | 8 + tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 9 + tools/perf/tests/pfm.c | 207 +++++++++++++++++ tools/perf/tests/tests.h | 3 + tools/perf/util/Build | 2 + tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 30 ++- tools/perf/util/parse-events.h | 4 + tools/perf/util/pfm.c | 277 +++++++++++++++++++++++ tools/perf/util/pfm.h | 43 ++++ 20 files changed, 645 insertions(+), 8 deletions(-) create mode 100644 tools/perf/tests/pfm.c create mode 100644 tools/perf/util/pfm.c create mode 100644 tools/perf/util/pfm.htools/perf/Documentation/perf-record.txt +11
-0@@ -596,6 +596,17 @@ Make a copy of /proc/kcore and place it into a directory with the perf data file Limit the sample data max size, <size> is expected to be a number with appended unit character - B/K/M/G +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]tools/perf/Documentation/perf-stat.txt +10
-0@@ -71,6 +71,16 @@ report:: --tid=<tid>:: stat events on existing thread id (comma separated list) +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] -a:: --all-cpus::tools/perf/Documentation/perf-top.txt +11
-0@@ -329,6 +329,17 @@ Default is to monitor all CPUS. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + INTERACTIVE PROMPTING KEYS --------------------------tools/perf/Makefile.config +13
-0@@ -1012,6 +1012,19 @@ ifdef LIBCLANGLLVM endif endif +ifdef LIBPFM4 + $(call feature_check,libpfm4) + ifeq ($(feature-libpfm4), 1) + CFLAGS += -DHAVE_LIBPFM + EXTLIBS += -lpfm + ASCIIDOC_EXTRA = -aHAVE_LIBPFM=1 + $(call detected,CONFIG_LIBPFM4) + else + msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev); + NO_LIBPFM4 := 1 + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dirtools/perf/Makefile.perf +2
-0@@ -118,6 +118,8 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # +# Define LIBPFM4 to enable libpfm4 events extension. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALLtools/perf/builtin-list.c +3
-0@@ -14,6 +14,7 @@#include "util/pmu.h" #include "util/debug.h" #include "util/metricgroup.h" +#include "util/pfm.h" #include <subcmd/pager.h> #include <subcmd/parse-options.h> #include <stdio.h> @@ -53,6 +54,8 @@ int cmd_list(int argc, const char **argv)setup_pager (); +libpfm_initialize (); +if (!raw_dump &&pager_in_use ())printf ("\nList of pre-defined events (to be used in -e):\n\n" );tools/perf/builtin-record.c +8
-0@@ -43,6 +43,7 @@#include "util/time-utils.h" #include "util/units.h" #include "util/bpf-event.h" +#include "util/pfm.h" #include "asm/bug.h" #include "perf.h" @@ -2421,6 +2422,11 @@ static struct option __record_options[] = {#endif OPT_CALLBACK(0, "max-size", &record.output_max_size, "size", "Limit the maximum size of the output file", parse_output_max_size), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &record.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -2461,6 +2467,8 @@ int cmd_record(int argc, const char **argv)if (rec->evlist ==NULL )return -ENOMEM ; +libpfm_initialize (); + err =perf_config (perf_record_config, rec);if (err)return err;tools/perf/builtin-stat.c +8
-0@@ -66,6 +66,7 @@#include "util/time-utils.h" #include "util/top.h" #include "util/affinity.h" +#include "util/pfm.h" #include "asm/bug.h" #include <linux/time64.h> @@ -936,6 +937,11 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &evsel_list,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -1874,6 +1880,8 @@ int cmd_stat(int argc, const char **argv)unsigned int interval, timeout;const char *const stat_subcommands[] = {"record" ,"report" }; +libpfm_initialize (); +setlocale (LC_ALL ,"" ); evsel_list =evlist__new ();tools/perf/builtin-top.c +8
-0@@ -53,6 +53,7 @@#include "util/debug.h" #include "util/ordered-events.h" +#include "util/pfm.h" #include <assert.h> #include <elf.h> @@ -1577,6 +1578,11 @@ int cmd_top(int argc, const char **argv) "WARNING: should be used on grouped events."),OPT_BOOLEAN (0 ,"stitch-lbr" , &top.stitch_lbr,"Enable LBR callgraph stitching approach" ), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &top.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPTS_EVSWITCH (&top.evswitch), OPT_END() };@@ -1590,6 +1596,8 @@ int cmd_top(int argc, const char **argv)if (status <0 )return status; +libpfm_initialize (); + top.annotation_opts.min_pcnt =5 ; top.annotation_opts.context =4 ;tools/perf/tests/Build +1
-0@@ -56,6 +56,7 @@ perf-y += mem2node.o perf-y += maps.o perf-y += time-utils-test.o perf-y += genelf.o +perf-y += pfm.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir)tools/perf/tests/builtin-test.c +9
-0@@ -313,6 +313,15 @@ static struct test generic_tests[] = { .desc = "maps__merge_in", .func = test__maps__merge_in, }, + { + .desc = "Test libpfm4 support", + .func = test__pfm, + .subtest = { + .skip_if_fail = true, + .get_nr = test__pfm_subtest_get_nr, + .get_desc = test__pfm_subtest_get_desc, + } + }, { .func = NULL, },tools/perf/tests/pfm.c new file +207
-0@@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Test support for libpfm4 event encodings. +* +* Copyright 2020 Google LLC. +*/ +#include "tests.h" +#include "util/debug.h" +#include "util/evlist.h" +#include "util/pfm.h" + +#include <linux/kernel.h> + +#ifdef HAVE_LIBPFM +static int test__pfm_events (void ); +static int test__pfm_group (void ); +#endif + +static const struct { +int (*func)(void ); +const char *desc; +} pfm_testcase_table[] = { +#ifdef HAVE_LIBPFM + { + .func = test__pfm_events, + .desc ="test of individual --pfm-events" , + }, + { + .func = test__pfm_group, + .desc ="test groups of --pfm-events" , + }, +#endif +}; + +#ifdef HAVE_LIBPFM +static int count_pfm_events (struct perf_evlist *evlist) +{ +struct perf_evsel *evsel; +int count =0 ; + +perf_evlist__for_each_entry (evlist, evsel) { + count++; + } +return count; +} + +static int test__pfm_events (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; + } table[] = { + { + .events ="" , + .nr_events =0 , + }, + { + .events ="instructions" , + .nr_events =1 , + }, + { + .events ="instructions,cycles" , + .nr_events =2 , + }, + { + .events ="stereolab" , + .nr_events =0 , + }, + { + .events ="instructions,instructions" , + .nr_events =2 , + }, + { + .events ="stereolab,instructions" , + .nr_events =0 , + }, + { + .events ="instructions,stereolab" , + .nr_events =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, +0 ); + +evlist__delete (evlist); + } +return 0 ; +} + +static int test__pfm_group (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; +int nr_groups; + } table[] = { + { + .events ="{}," , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{instructions},{}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{},{instructions}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions},{instructions}" , + .nr_events =2 , + .nr_groups =2 , + }, + { + .events ="{instructions,cycles},{instructions,cycles}" , + .nr_events =4 , + .nr_groups =2 , + }, + { + .events ="{stereolab}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events = +"{instructions,cycles},{instructions,stereolab}" , + .nr_events =3 , + .nr_groups =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, + table[i].nr_groups); + +evlist__delete (evlist); + } +return 0 ; +} +#endif + +const char *test__pfm_subtest_get_desc (int i) +{ +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return NULL ; +return pfm_testcase_table[i].desc; +} + +int test__pfm_subtest_get_nr (void ) +{ +return (int )ARRAY_SIZE (pfm_testcase_table); +} + +int test__pfm (struct test *test__maybe_unused ,int i__maybe_unused ) +{ +#ifdef HAVE_LIBPFM +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return TEST_FAIL ; +return pfm_testcase_table[i].func (); +#else +return TEST_SKIP ; +#endif +}tools/perf/tests/tests.h +3
-0@@ -112,6 +112,9 @@ int test__mem2node(struct test *t, int subtest);int test__maps__merge_in (struct test *t,int subtest);int test__time_utils (struct test *t,int subtest);int test__jit_write_elf (struct test *test,int subtest); +int test__pfm (struct test *test,int subtest); +const char *test__pfm_subtest_get_desc (int subtest); +int test__pfm_subtest_get_nr (void );bool test__bp_signal_is_supported (void );bool test__bp_account_is_supported (void );tools/perf/util/Build +2
-0@@ -177,6 +177,8 @@ perf-$(CONFIG_LIBBPF) += bpf-event.o perf-$(CONFIG_CXX) += c++/ +perf-$(CONFIG_LIBPFM4) += pfm.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"tools/perf/util/evsel.c +1
-1@@ -2433,7 +2433,7 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,/* Is there already the separator in the name. */ if (strchr (name,'/' ) || -strchr (name,':' )) + (strchr (name,':' ) && !evsel->is_libpfm_event)) sep ="" ;if (asprintf (&new_name,"%s%su" , name, sep) <0 )tools/perf/util/evsel.h +1
-0@@ -76,6 +76,7 @@ struct evsel {bool ignore_missing_thread;bool forced_leader;bool use_uncore_alias; +bool is_libpfm_event;/* parse modifier helper */ int exclude_GH;int sample_read;tools/perf/util/parse-events.c +23
-7@@ -36,6 +36,7 @@#include "metricgroup.h" #include "util/evsel_config.h" #include "util/event.h" +#include "util/pfm.h" #define MAX_NAME_LEN 100@@ -344,6 +345,7 @@ static char *get_config_name(struct list_head *head_terms)static struct evsel *__add_event (struct list_head *list,int *idx,struct perf_event_attr *attr, +bool init_attr,char *name,struct perf_pmu *pmu,struct list_head *config_terms,bool auto_merge_stats,const char *cpu_list)@@ -352,7 +354,8 @@ __add_event(struct list_head *list, int *idx,struct perf_cpu_map *cpus = pmu ? pmu->cpus : cpu_list ?perf_cpu_map__new (cpu_list) :NULL ; -event_attr_init (attr); +if (init_attr) +event_attr_init (attr); evsel =perf_evsel__new_idx (attr, *idx);if (!evsel)@@ -370,15 +373,25 @@ __add_event(struct list_head *list, int *idx,if (config_terms)list_splice (config_terms, &evsel->config_terms); -list_add_tail (&evsel->core.node, list); +if (list) +list_add_tail (&evsel->core.node, list); +return evsel; } +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu) +{ +return __add_event (NULL , &idx, attr, false, name, pmu,NULL , false, +NULL ); +} +static int add_event (struct list_head *list,int *idx,struct perf_event_attr *attr,char *name,struct list_head *config_terms) { -return __add_event (list, idx, attr, name,NULL , config_terms, false,NULL ) ?0 : -ENOMEM ; +return __add_event (list, idx, attr, true, name,NULL , config_terms, + false,NULL ) ?0 : -ENOMEM ; } static int add_event_tool(struct list_head *list, int *idx,@@ -390,7 +403,8 @@ static int add_event_tool(struct list_head *list, int *idx, .config = PERF_COUNT_SW_DUMMY, }; - evsel =__add_event (list, idx, &attr,NULL ,NULL ,NULL , false,"0" ); + evsel =__add_event (list, idx, &attr, true,NULL ,NULL ,NULL , false, +"0" );if (!evsel)return -ENOMEM ; evsel->tool_event = tool_event;@@ -1446,8 +1460,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,if (!head_config) { attr.type = pmu->type; - evsel =__add_event (list, &parse_state->idx, &attr,NULL , pmu,NULL , - auto_merge_stats,NULL ); + evsel =__add_event (list, &parse_state->idx, &attr, true,NULL , + pmu,NULL , auto_merge_stats,NULL );if (evsel) { evsel->pmu_name = name ?strdup (name) :NULL ; evsel->use_uncore_alias = use_uncore_alias;@@ -1487,7 +1501,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,return -EINVAL ; } - evsel =__add_event (list, &parse_state->idx, &attr, + evsel =__add_event (list, &parse_state->idx, &attr, true,get_config_name (head_config), pmu, &config_terms, auto_merge_stats,NULL );if (evsel) {@@ -2794,6 +2808,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,print_sdt_events (NULL ,NULL , name_only);metricgroup__print (true, true,NULL , name_only, details_flag); + +print_libpfm_events (name_only, long_desc); }int parse_events__is_hardcoded_term (struct parse_events_term *term)tools/perf/util/parse-events.h +4
-0@@ -17,6 +17,7 @@ struct evlist;struct parse_events_error ;struct option ; +struct perf_pmu ;struct tracepoint_path {char *system;@@ -186,6 +187,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,bool auto_merge_stats, bool use_alias); +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu); +int parse_events_multi_pmu_add (struct parse_events_state *parse_state,char *str,struct list_head **listp);tools/perf/util/pfm.c new file +277
-0@@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#include "util/cpumap.h" +#include "util/debug.h" +#include "util/event.h" +#include "util/evlist.h" +#include "util/evsel.h" +#include "util/parse-events.h" +#include "util/pmu.h" +#include "util/pfm.h" + +#include <string.h> +#include <linux/kernel.h> +#include <perfmon/pfmlib_perf_event.h> + +void libpfm_initialize (void ) +{ +int ret; + + ret =pfm_initialize (); +if (ret !=PFM_SUCCESS ) { +ui__warning ("libpfm failed to initialize: %s\n" , +pfm_strerror (ret)); + } +} + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset__maybe_unused ) +{ +struct evlist *evlist = *(struct evlist **)opt->value; +struct perf_event_attr attr; +struct perf_pmu *pmu; +struct evsel *evsel, *grp_leader =NULL ; +char *p, *q, *p_orig; +const char *sep; +int grp_evt =-1 ; +int ret; + + p_orig = p =strdup (str); +if (!p) +return -1 ; +/* +* force loading of the PMU list +*/ +perf_pmu__scan (NULL ); + +for (q = p;strsep (&p,",{}" ); q = p) { + sep = p ? str + (p - p_orig -1 ) :"" ; +if (*sep =='{' ) { +if (grp_evt >-1 ) { +ui__error ( +"nested event groups not supported\n" ); + goto error; + } + grp_evt++; + } + +/* no event */ +if (*q =='\0' ) +continue ; + +memset (&attr,0 ,sizeof (attr)); +event_attr_init (&attr); + + ret =pfm_get_perf_event_encoding (q,PFM_PLM0 |PFM_PLM3 , + &attr,NULL ,NULL ); + +if (ret !=PFM_SUCCESS ) { +ui__error ("failed to parse event %s : %s\n" , str, +pfm_strerror (ret)); + goto error; + } + + pmu =perf_pmu__find_by_type ((unsigned int )attr.type); + evsel =parse_events__add_event (evlist->core.nr_entries, + &attr, q, pmu); +if (evsel ==NULL ) + goto error; + + evsel->is_libpfm_event = true; + +evlist__add (evlist, evsel); + +if (grp_evt ==0 ) + grp_leader = evsel; + +if (grp_evt >-1 ) { + evsel->leader = grp_leader; + grp_leader->core.nr_members++; + grp_evt++; + } + +if (*sep =='}' ) { +if (grp_evt <0 ) { +ui__error ( +"cannot close a non-existing event group\n" ); + goto error; + } + evlist->nr_groups++; + grp_leader =NULL ; + grp_evt =-1 ; + } + } +return 0 ; +error: +free (p_orig); +return -1 ; +} + +static const char *srcs[PFM_ATTR_CTRL_MAX ] = { + [PFM_ATTR_CTRL_UNKNOWN ] ="???" , + [PFM_ATTR_CTRL_PMU ] ="PMU" , + [PFM_ATTR_CTRL_PERF_EVENT ] ="perf_event" , +}; + +static void +print_attr_flags (pfm_event_attr_info_t *info) +{ +int n =0 ; + +if (info->is_dfl) { +printf ("[default] " ); + n++; + } + +if (info->is_precise) { +printf ("[precise] " ); + n++; + } + +if (!n) +printf ("- " ); +} + +static void +print_libpfm_events_detailed (pfm_event_info_t *info,bool long_desc) +{ +pfm_event_attr_info_t ainfo; +const char *src; +int j, ret; + + ainfo.size =sizeof (ainfo); + +printf (" %s\n" , info->name); +printf (" [%s]\n" , info->desc); +if (long_desc) { +if (info->equiv) +printf (" Equiv: %s\n" , info->equiv); + +printf (" Code : 0x%" PRIx64"\n" , info->code); + } +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type ==PFM_ATTR_UMASK ) { +printf (" %s:%s\n" , info->name, ainfo.name); +printf (" [%s]\n" , ainfo.desc); + } + +if (!long_desc) +continue ; + +if (ainfo.ctrl >=PFM_ATTR_CTRL_MAX ) + ainfo.ctrl =PFM_ATTR_CTRL_UNKNOWN ; + + src = srcs[ainfo.ctrl]; +switch (ainfo.type) { +case PFM_ATTR_UMASK : +printf (" Umask : 0x%02" PRIx64" : %s: " , + ainfo.code, src); +print_attr_flags (&ainfo); +putchar ('\n' ); +break ; +case PFM_ATTR_MOD_BOOL : +printf (" Modif : %s: [%s] : %s (boolean)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_MOD_INTEGER : +printf (" Modif : %s: [%s] : %s (integer)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_NONE : +case PFM_ATTR_RAW_UMASK : +case PFM_ATTR_MAX : +default : +printf (" Attr : %s: [%s] : %s\n" , src, + ainfo.name, ainfo.desc); + } + } +} + +/* +* list all pmu::event:umask, pmu::event +* printed events may not be all valid combinations of umask for an event +*/ +static void +print_libpfm_events_raw (pfm_pmu_info_t *pinfo,pfm_event_info_t *info) +{ +pfm_event_attr_info_t ainfo; +int j, ret; +bool has_umask = false; + + ainfo.size =sizeof (ainfo); + +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type !=PFM_ATTR_UMASK ) +continue ; + +printf ("%s::%s:%s\n" , pinfo->name, info->name, ainfo.name); + has_umask = true; + } +if (!has_umask) +printf ("%s::%s\n" , pinfo->name, info->name); +} + +void print_libpfm_events (bool name_only,bool long_desc) +{ +pfm_event_info_t info; +pfm_pmu_info_t pinfo; +int i, p, ret; + +/* initialize to zero to indicate ABI version */ + info.size =sizeof (info); + pinfo.size =sizeof (pinfo); + +if (!name_only) +puts ("\nList of pre-defined events (to be used in --pfm-events):\n" ); + +pfm_for_all_pmus (p) { +bool printed_pmu = false; + + ret =pfm_get_pmu_info (p, &pinfo); +if (ret !=PFM_SUCCESS ) +continue ; + +/* only print events that are supported by host HW */ +if (!pinfo.is_present) +continue ; + +/* handled by perf directly */ +if (pinfo.pmu ==PFM_PMU_PERF_EVENT ) +continue ; + +for (i = pinfo.first_event; i !=-1 ; + i =pfm_get_event_next (i)) { + + ret =pfm_get_event_info (i,PFM_OS_PERF_EVENT_EXT , + &info); +if (ret !=PFM_SUCCESS ) +continue ; + +if (!name_only && !printed_pmu) { +printf ("%s:\n" , pinfo.name); + printed_pmu = true; + } + +if (!name_only) +print_libpfm_events_detailed (&info, long_desc); +else +print_libpfm_events_raw (&pinfo, &info); + } +if (!name_only && printed_pmu) +putchar ('\n' ); + } +}tools/perf/util/pfm.h new file +43
-0@@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#ifndef __PERF_PFM_H +#define __PERF_PFM_H + +#include <subcmd/parse-options.h> + +#ifdef HAVE_LIBPFM +void libpfm_initialize (void ); + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset); + +void print_libpfm_events (bool name_only,bool long_desc); + +#else +#include <linux/compiler.h> + +static inline void libpfm_initialize (void ) +{ +} + +static inline int parse_libpfm_events_option ( +const struct option *opt__maybe_unused , +const char *str__maybe_unused , +int unset__maybe_unused ) +{ +return 0 ; +} + +static inline void print_libpfm_events (bool name_only__maybe_unused , +bool long_desc__maybe_unused ) +{ +} + +#endif + + +#endif /* __PERF_PFM_H */ Signature · 1 line
2.26.2.303.gf8c07b1a785-goog
Signature · 1 line
- Arnaldo
Ian Rogers
reviewerQuoted 12 lines · Arnaldo Carvalho de Melo
Em Wed, Apr 29, 2020 at 04:14:43PM -0700, Ian Rogers escreveu:
Quoted 9 lines
From: Stephane Eranian <[email protected]>
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by
perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net.
Quoted 8 lines
Hey, I think we should not call
libpfm_initialize()in all tools, better leave it to when the --pfm-event callback gets called, because the user is really using that event syntax, i.e. do it lazily, to reduce the amount of initialization that perf does, which is already excessive and needs triming down, to do more things only when they are really, really needed.I have applied the previous, preparatory patches.
Thanks! I didn't see the whole set rebasing on:
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=perf/core
and so sent it all again:
https://lore.kernel.org/lkml/[email protected]/T/#u
Thanks,
Ian
Quoted 1,014 lines
- Arnaldo
Quoted 1,006 lines
With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match:
$ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles ....Signed-off-by Stephane Eranian <[email protected]>Reviewed-by Ian Rogers <[email protected]>--- tools/perf/Documentation/perf-record.txt | 11 + tools/perf/Documentation/perf-stat.txt | 10 + tools/perf/Documentation/perf-top.txt | 11 + tools/perf/Makefile.config | 13 ++ tools/perf/Makefile.perf | 2 + tools/perf/builtin-list.c | 3 + tools/perf/builtin-record.c | 8 + tools/perf/builtin-stat.c | 8 + tools/perf/builtin-top.c | 8 + tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 9 + tools/perf/tests/pfm.c | 207 +++++++++++++++++ tools/perf/tests/tests.h | 3 + tools/perf/util/Build | 2 + tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 30 ++- tools/perf/util/parse-events.h | 4 + tools/perf/util/pfm.c | 277 +++++++++++++++++++++++ tools/perf/util/pfm.h | 43 ++++ 20 files changed, 645 insertions(+), 8 deletions(-) create mode 100644 tools/perf/tests/pfm.c create mode 100644 tools/perf/util/pfm.c create mode 100644 tools/perf/util/pfm.htools/perf/Documentation/perf-record.txt +11
-0@@ -596,6 +596,17 @@ Make a copy of /proc/kcore and place it into a directory with the perf data file Limit the sample data max size, <size> is expected to be a number with appended unit character - B/K/M/G +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]tools/perf/Documentation/perf-stat.txt +10
-0@@ -71,6 +71,16 @@ report:: --tid=<tid>:: stat events on existing thread id (comma separated list) +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] -a:: --all-cpus::tools/perf/Documentation/perf-top.txt +11
-0@@ -329,6 +329,17 @@ Default is to monitor all CPUS. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + INTERACTIVE PROMPTING KEYS --------------------------tools/perf/Makefile.config +13
-0@@ -1012,6 +1012,19 @@ ifdef LIBCLANGLLVM endif endif +ifdef LIBPFM4 + $(call feature_check,libpfm4) + ifeq ($(feature-libpfm4), 1) + CFLAGS += -DHAVE_LIBPFM + EXTLIBS += -lpfm + ASCIIDOC_EXTRA = -aHAVE_LIBPFM=1 + $(call detected,CONFIG_LIBPFM4) + else + msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev); + NO_LIBPFM4 := 1 + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dirtools/perf/Makefile.perf +2
-0@@ -118,6 +118,8 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # +# Define LIBPFM4 to enable libpfm4 events extension. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALLtools/perf/builtin-list.c +3
-0@@ -14,6 +14,7 @@#include "util/pmu.h" #include "util/debug.h" #include "util/metricgroup.h" +#include "util/pfm.h" #include <subcmd/pager.h> #include <subcmd/parse-options.h> #include <stdio.h> @@ -53,6 +54,8 @@ int cmd_list(int argc, const char **argv)setup_pager (); +libpfm_initialize (); +if (!raw_dump &&pager_in_use ())printf ("\nList of pre-defined events (to be used in -e):\n\n" );tools/perf/builtin-record.c +8
-0@@ -43,6 +43,7 @@#include "util/time-utils.h" #include "util/units.h" #include "util/bpf-event.h" +#include "util/pfm.h" #include "asm/bug.h" #include "perf.h" @@ -2421,6 +2422,11 @@ static struct option __record_options[] = {#endif OPT_CALLBACK(0, "max-size", &record.output_max_size, "size", "Limit the maximum size of the output file", parse_output_max_size), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &record.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -2461,6 +2467,8 @@ int cmd_record(int argc, const char **argv)if (rec->evlist ==NULL )return -ENOMEM ; +libpfm_initialize (); + err =perf_config (perf_record_config, rec);if (err)return err;tools/perf/builtin-stat.c +8
-0@@ -66,6 +66,7 @@#include "util/time-utils.h" #include "util/top.h" #include "util/affinity.h" +#include "util/pfm.h" #include "asm/bug.h" #include <linux/time64.h> @@ -936,6 +937,11 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &evsel_list,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -1874,6 +1880,8 @@ int cmd_stat(int argc, const char **argv)unsigned int interval, timeout;const char *const stat_subcommands[] = {"record" ,"report" }; +libpfm_initialize (); +setlocale (LC_ALL ,"" ); evsel_list =evlist__new ();tools/perf/builtin-top.c +8
-0@@ -53,6 +53,7 @@#include "util/debug.h" #include "util/ordered-events.h" +#include "util/pfm.h" #include <assert.h> #include <elf.h> @@ -1577,6 +1578,11 @@ int cmd_top(int argc, const char **argv) "WARNING: should be used on grouped events."),OPT_BOOLEAN (0 ,"stitch-lbr" , &top.stitch_lbr,"Enable LBR callgraph stitching approach" ), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &top.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPTS_EVSWITCH (&top.evswitch), OPT_END() };@@ -1590,6 +1596,8 @@ int cmd_top(int argc, const char **argv)if (status <0 )return status; +libpfm_initialize (); + top.annotation_opts.min_pcnt =5 ; top.annotation_opts.context =4 ;tools/perf/tests/Build +1
-0@@ -56,6 +56,7 @@ perf-y += mem2node.o perf-y += maps.o perf-y += time-utils-test.o perf-y += genelf.o +perf-y += pfm.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir)tools/perf/tests/builtin-test.c +9
-0@@ -313,6 +313,15 @@ static struct test generic_tests[] = { .desc = "maps__merge_in", .func = test__maps__merge_in, }, + { + .desc = "Test libpfm4 support", + .func = test__pfm, + .subtest = { + .skip_if_fail = true, + .get_nr = test__pfm_subtest_get_nr, + .get_desc = test__pfm_subtest_get_desc, + } + }, { .func = NULL, },tools/perf/tests/pfm.c new file +207
-0@@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Test support for libpfm4 event encodings. +* +* Copyright 2020 Google LLC. +*/ +#include "tests.h" +#include "util/debug.h" +#include "util/evlist.h" +#include "util/pfm.h" + +#include <linux/kernel.h> + +#ifdef HAVE_LIBPFM +static int test__pfm_events (void ); +static int test__pfm_group (void ); +#endif + +static const struct { +int (*func)(void ); +const char *desc; +} pfm_testcase_table[] = { +#ifdef HAVE_LIBPFM + { + .func = test__pfm_events, + .desc ="test of individual --pfm-events" , + }, + { + .func = test__pfm_group, + .desc ="test groups of --pfm-events" , + }, +#endif +}; + +#ifdef HAVE_LIBPFM +static int count_pfm_events (struct perf_evlist *evlist) +{ +struct perf_evsel *evsel; +int count =0 ; + +perf_evlist__for_each_entry (evlist, evsel) { + count++; + } +return count; +} + +static int test__pfm_events (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; + } table[] = { + { + .events ="" , + .nr_events =0 , + }, + { + .events ="instructions" , + .nr_events =1 , + }, + { + .events ="instructions,cycles" , + .nr_events =2 , + }, + { + .events ="stereolab" , + .nr_events =0 , + }, + { + .events ="instructions,instructions" , + .nr_events =2 , + }, + { + .events ="stereolab,instructions" , + .nr_events =0 , + }, + { + .events ="instructions,stereolab" , + .nr_events =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, +0 ); + +evlist__delete (evlist); + } +return 0 ; +} + +static int test__pfm_group (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; +int nr_groups; + } table[] = { + { + .events ="{}," , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{instructions},{}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{},{instructions}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions},{instructions}" , + .nr_events =2 , + .nr_groups =2 , + }, + { + .events ="{instructions,cycles},{instructions,cycles}" , + .nr_events =4 , + .nr_groups =2 , + }, + { + .events ="{stereolab}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events = +"{instructions,cycles},{instructions,stereolab}" , + .nr_events =3 , + .nr_groups =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, + table[i].nr_groups); + +evlist__delete (evlist); + } +return 0 ; +} +#endif + +const char *test__pfm_subtest_get_desc (int i) +{ +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return NULL ; +return pfm_testcase_table[i].desc; +} + +int test__pfm_subtest_get_nr (void ) +{ +return (int )ARRAY_SIZE (pfm_testcase_table); +} + +int test__pfm (struct test *test__maybe_unused ,int i__maybe_unused ) +{ +#ifdef HAVE_LIBPFM +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return TEST_FAIL ; +return pfm_testcase_table[i].func (); +#else +return TEST_SKIP ; +#endif +}tools/perf/tests/tests.h +3
-0@@ -112,6 +112,9 @@ int test__mem2node(struct test *t, int subtest);int test__maps__merge_in (struct test *t,int subtest);int test__time_utils (struct test *t,int subtest);int test__jit_write_elf (struct test *test,int subtest); +int test__pfm (struct test *test,int subtest); +const char *test__pfm_subtest_get_desc (int subtest); +int test__pfm_subtest_get_nr (void );bool test__bp_signal_is_supported (void );bool test__bp_account_is_supported (void );tools/perf/util/Build +2
-0@@ -177,6 +177,8 @@ perf-$(CONFIG_LIBBPF) += bpf-event.o perf-$(CONFIG_CXX) += c++/ +perf-$(CONFIG_LIBPFM4) += pfm.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"tools/perf/util/evsel.c +1
-1@@ -2433,7 +2433,7 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,/* Is there already the separator in the name. */ if (strchr (name,'/' ) || -strchr (name,':' )) + (strchr (name,':' ) && !evsel->is_libpfm_event)) sep ="" ;if (asprintf (&new_name,"%s%su" , name, sep) <0 )tools/perf/util/evsel.h +1
-0@@ -76,6 +76,7 @@ struct evsel {bool ignore_missing_thread;bool forced_leader;bool use_uncore_alias; +bool is_libpfm_event;/* parse modifier helper */ int exclude_GH;int sample_read;tools/perf/util/parse-events.c +23
-7@@ -36,6 +36,7 @@#include "metricgroup.h" #include "util/evsel_config.h" #include "util/event.h" +#include "util/pfm.h" #define MAX_NAME_LEN 100@@ -344,6 +345,7 @@ static char *get_config_name(struct list_head *head_terms)static struct evsel *__add_event (struct list_head *list,int *idx,struct perf_event_attr *attr, +bool init_attr,char *name,struct perf_pmu *pmu,struct list_head *config_terms,bool auto_merge_stats,const char *cpu_list)@@ -352,7 +354,8 @@ __add_event(struct list_head *list, int *idx,struct perf_cpu_map *cpus = pmu ? pmu->cpus : cpu_list ?perf_cpu_map__new (cpu_list) :NULL ; -event_attr_init (attr); +if (init_attr) +event_attr_init (attr); evsel =perf_evsel__new_idx (attr, *idx);if (!evsel)@@ -370,15 +373,25 @@ __add_event(struct list_head *list, int *idx,if (config_terms)list_splice (config_terms, &evsel->config_terms); -list_add_tail (&evsel->core.node, list); +if (list) +list_add_tail (&evsel->core.node, list); +return evsel; } +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu) +{ +return __add_event (NULL , &idx, attr, false, name, pmu,NULL , false, +NULL ); +} +static int add_event (struct list_head *list,int *idx,struct perf_event_attr *attr,char *name,struct list_head *config_terms) { -return __add_event (list, idx, attr, name,NULL , config_terms, false,NULL ) ?0 : -ENOMEM ; +return __add_event (list, idx, attr, true, name,NULL , config_terms, + false,NULL ) ?0 : -ENOMEM ; } static int add_event_tool(struct list_head *list, int *idx,@@ -390,7 +403,8 @@ static int add_event_tool(struct list_head *list, int *idx, .config = PERF_COUNT_SW_DUMMY, }; - evsel =__add_event (list, idx, &attr,NULL ,NULL ,NULL , false,"0" ); + evsel =__add_event (list, idx, &attr, true,NULL ,NULL ,NULL , false, +"0" );if (!evsel)return -ENOMEM ; evsel->tool_event = tool_event;@@ -1446,8 +1460,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,if (!head_config) { attr.type = pmu->type; - evsel =__add_event (list, &parse_state->idx, &attr,NULL , pmu,NULL , - auto_merge_stats,NULL ); + evsel =__add_event (list, &parse_state->idx, &attr, true,NULL , + pmu,NULL , auto_merge_stats,NULL );if (evsel) { evsel->pmu_name = name ?strdup (name) :NULL ; evsel->use_uncore_alias = use_uncore_alias;@@ -1487,7 +1501,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,return -EINVAL ; } - evsel =__add_event (list, &parse_state->idx, &attr, + evsel =__add_event (list, &parse_state->idx, &attr, true,get_config_name (head_config), pmu, &config_terms, auto_merge_stats,NULL );if (evsel) {@@ -2794,6 +2808,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,print_sdt_events (NULL ,NULL , name_only);metricgroup__print (true, true,NULL , name_only, details_flag); + +print_libpfm_events (name_only, long_desc); }int parse_events__is_hardcoded_term (struct parse_events_term *term)tools/perf/util/parse-events.h +4
-0@@ -17,6 +17,7 @@ struct evlist;struct parse_events_error ;struct option ; +struct perf_pmu ;struct tracepoint_path {char *system;@@ -186,6 +187,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,bool auto_merge_stats, bool use_alias); +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu); +int parse_events_multi_pmu_add (struct parse_events_state *parse_state,char *str,struct list_head **listp);tools/perf/util/pfm.c new file +277
-0@@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#include "util/cpumap.h" +#include "util/debug.h" +#include "util/event.h" +#include "util/evlist.h" +#include "util/evsel.h" +#include "util/parse-events.h" +#include "util/pmu.h" +#include "util/pfm.h" + +#include <string.h> +#include <linux/kernel.h> +#include <perfmon/pfmlib_perf_event.h> + +void libpfm_initialize (void ) +{ +int ret; + + ret =pfm_initialize (); +if (ret !=PFM_SUCCESS ) { +ui__warning ("libpfm failed to initialize: %s\n" , +pfm_strerror (ret)); + } +} + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset__maybe_unused ) +{ +struct evlist *evlist = *(struct evlist **)opt->value; +struct perf_event_attr attr; +struct perf_pmu *pmu; +struct evsel *evsel, *grp_leader =NULL ; +char *p, *q, *p_orig; +const char *sep; +int grp_evt =-1 ; +int ret; + + p_orig = p =strdup (str); +if (!p) +return -1 ; +/* +* force loading of the PMU list +*/ +perf_pmu__scan (NULL ); + +for (q = p;strsep (&p,",{}" ); q = p) { + sep = p ? str + (p - p_orig -1 ) :"" ; +if (*sep =='{' ) { +if (grp_evt >-1 ) { +ui__error ( +"nested event groups not supported\n" ); + goto error; + } + grp_evt++; + } + +/* no event */ +if (*q =='\0' ) +continue ; + +memset (&attr,0 ,sizeof (attr)); +event_attr_init (&attr); + + ret =pfm_get_perf_event_encoding (q,PFM_PLM0 |PFM_PLM3 , + &attr,NULL ,NULL ); + +if (ret !=PFM_SUCCESS ) { +ui__error ("failed to parse event %s : %s\n" , str, +pfm_strerror (ret)); + goto error; + } + + pmu =perf_pmu__find_by_type ((unsigned int )attr.type); + evsel =parse_events__add_event (evlist->core.nr_entries, + &attr, q, pmu); +if (evsel ==NULL ) + goto error; + + evsel->is_libpfm_event = true; + +evlist__add (evlist, evsel); + +if (grp_evt ==0 ) + grp_leader = evsel; + +if (grp_evt >-1 ) { + evsel->leader = grp_leader; + grp_leader->core.nr_members++; + grp_evt++; + } + +if (*sep =='}' ) { +if (grp_evt <0 ) { +ui__error ( +"cannot close a non-existing event group\n" ); + goto error; + } + evlist->nr_groups++; + grp_leader =NULL ; + grp_evt =-1 ; + } + } +return 0 ; +error: +free (p_orig); +return -1 ; +} + +static const char *srcs[PFM_ATTR_CTRL_MAX ] = { + [PFM_ATTR_CTRL_UNKNOWN ] ="???" , + [PFM_ATTR_CTRL_PMU ] ="PMU" , + [PFM_ATTR_CTRL_PERF_EVENT ] ="perf_event" , +}; + +static void +print_attr_flags (pfm_event_attr_info_t *info) +{ +int n =0 ; + +if (info->is_dfl) { +printf ("[default] " ); + n++; + } + +if (info->is_precise) { +printf ("[precise] " ); + n++; + } + +if (!n) +printf ("- " ); +} + +static void +print_libpfm_events_detailed (pfm_event_info_t *info,bool long_desc) +{ +pfm_event_attr_info_t ainfo; +const char *src; +int j, ret; + + ainfo.size =sizeof (ainfo); + +printf (" %s\n" , info->name); +printf (" [%s]\n" , info->desc); +if (long_desc) { +if (info->equiv) +printf (" Equiv: %s\n" , info->equiv); + +printf (" Code : 0x%" PRIx64"\n" , info->code); + } +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type ==PFM_ATTR_UMASK ) { +printf (" %s:%s\n" , info->name, ainfo.name); +printf (" [%s]\n" , ainfo.desc); + } + +if (!long_desc) +continue ; + +if (ainfo.ctrl >=PFM_ATTR_CTRL_MAX ) + ainfo.ctrl =PFM_ATTR_CTRL_UNKNOWN ; + + src = srcs[ainfo.ctrl]; +switch (ainfo.type) { +case PFM_ATTR_UMASK : +printf (" Umask : 0x%02" PRIx64" : %s: " , + ainfo.code, src); +print_attr_flags (&ainfo); +putchar ('\n' ); +break ; +case PFM_ATTR_MOD_BOOL : +printf (" Modif : %s: [%s] : %s (boolean)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_MOD_INTEGER : +printf (" Modif : %s: [%s] : %s (integer)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_NONE : +case PFM_ATTR_RAW_UMASK : +case PFM_ATTR_MAX : +default : +printf (" Attr : %s: [%s] : %s\n" , src, + ainfo.name, ainfo.desc); + } + } +} + +/* +* list all pmu::event:umask, pmu::event +* printed events may not be all valid combinations of umask for an event +*/ +static void +print_libpfm_events_raw (pfm_pmu_info_t *pinfo,pfm_event_info_t *info) +{ +pfm_event_attr_info_t ainfo; +int j, ret; +bool has_umask = false; + + ainfo.size =sizeof (ainfo); + +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type !=PFM_ATTR_UMASK ) +continue ; + +printf ("%s::%s:%s\n" , pinfo->name, info->name, ainfo.name); + has_umask = true; + } +if (!has_umask) +printf ("%s::%s\n" , pinfo->name, info->name); +} + +void print_libpfm_events (bool name_only,bool long_desc) +{ +pfm_event_info_t info; +pfm_pmu_info_t pinfo; +int i, p, ret; + +/* initialize to zero to indicate ABI version */ + info.size =sizeof (info); + pinfo.size =sizeof (pinfo); + +if (!name_only) +puts ("\nList of pre-defined events (to be used in --pfm-events):\n" ); + +pfm_for_all_pmus (p) { +bool printed_pmu = false; + + ret =pfm_get_pmu_info (p, &pinfo); +if (ret !=PFM_SUCCESS ) +continue ; + +/* only print events that are supported by host HW */ +if (!pinfo.is_present) +continue ; + +/* handled by perf directly */ +if (pinfo.pmu ==PFM_PMU_PERF_EVENT ) +continue ; + +for (i = pinfo.first_event; i !=-1 ; + i =pfm_get_event_next (i)) { + + ret =pfm_get_event_info (i,PFM_OS_PERF_EVENT_EXT , + &info); +if (ret !=PFM_SUCCESS ) +continue ; + +if (!name_only && !printed_pmu) { +printf ("%s:\n" , pinfo.name); + printed_pmu = true; + } + +if (!name_only) +print_libpfm_events_detailed (&info, long_desc); +else +print_libpfm_events_raw (&pinfo, &info); + } +if (!name_only && printed_pmu) +putchar ('\n' ); + } +}tools/perf/util/pfm.h new file +43
-1@@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#ifndef __PERF_PFM_H +#define __PERF_PFM_H + +#include <subcmd/parse-options.h> + +#ifdef HAVE_LIBPFM +void libpfm_initialize (void ); + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset); + +void print_libpfm_events (bool name_only,bool long_desc); + +#else +#include <linux/compiler.h> + +static inline void libpfm_initialize (void ) +{ +} + +static inline int parse_libpfm_events_option ( +const struct option *opt__maybe_unused , +const char *str__maybe_unused , +int unset__maybe_unused ) +{ +return 0 ; +} + +static inline void print_libpfm_events (bool name_only__maybe_unused , +bool long_desc__maybe_unused ) +{ +} + +#endif + + +#endif /* __PERF_PFM_H */ --Quoted 2 lines
2.26.2.303.gf8c07b1a785-goog
--
- Arnaldo
Ian Rogers
reviewerQuoted 22 lines · Ian Rogers
Quoted 19 lines · Arnaldo Carvalho de Melo
Em Wed, Apr 29, 2020 at 04:14:43PM -0700, Ian Rogers escreveu:
Quoted 9 lines
From: Stephane Eranian <[email protected]>
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by
perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net.Hey, I think we should not call
libpfm_initialize()in all tools, better leave it to when the --pfm-event callback gets called, because the user is really using that event syntax, i.e. do it lazily, to reduce the amount of initialization that perf does, which is already excessive and needs triming down, to do more things only when they are really, really needed.
Quoted 6 lines
Quoted 1 line
I have applied the previous, preparatory patches.
Thanks! I didn't see the whole set rebasing on:
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=perf/core
and so sent it all again:
https://lore.kernel.org/lkml/[email protected]/T/#u
I now see the preparatory patches and so I've re-sent this patch rebased on its own:
https://lore.kernel.org/lkml/[email protected]/T/#t
Thanks,
Ian
Quoted 1,017 lines
Thanks,
IanQuoted 1,014 lines
- Arnaldo
Quoted 1,006 lines
With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match:
$ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles ....Signed-off-by Stephane Eranian <[email protected]>Reviewed-by Ian Rogers <[email protected]>--- tools/perf/Documentation/perf-record.txt | 11 + tools/perf/Documentation/perf-stat.txt | 10 + tools/perf/Documentation/perf-top.txt | 11 + tools/perf/Makefile.config | 13 ++ tools/perf/Makefile.perf | 2 + tools/perf/builtin-list.c | 3 + tools/perf/builtin-record.c | 8 + tools/perf/builtin-stat.c | 8 + tools/perf/builtin-top.c | 8 + tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 9 + tools/perf/tests/pfm.c | 207 +++++++++++++++++ tools/perf/tests/tests.h | 3 + tools/perf/util/Build | 2 + tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 30 ++- tools/perf/util/parse-events.h | 4 + tools/perf/util/pfm.c | 277 +++++++++++++++++++++++ tools/perf/util/pfm.h | 43 ++++ 20 files changed, 645 insertions(+), 8 deletions(-) create mode 100644 tools/perf/tests/pfm.c create mode 100644 tools/perf/util/pfm.c create mode 100644 tools/perf/util/pfm.htools/perf/Documentation/perf-record.txt +11
-0@@ -596,6 +596,17 @@ Make a copy of /proc/kcore and place it into a directory with the perf data file Limit the sample data max size, <size> is expected to be a number with appended unit character - B/K/M/G +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]tools/perf/Documentation/perf-stat.txt +10
-0@@ -71,6 +71,16 @@ report:: --tid=<tid>:: stat events on existing thread id (comma separated list) +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] -a:: --all-cpus::tools/perf/Documentation/perf-top.txt +11
-0@@ -329,6 +329,17 @@ Default is to monitor all CPUS. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +ifdef::HAVE_LIBPFM[] +--pfm-events events:: +Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) +including support for event filters. For example '--pfm-events +inst_retired:any_p:u:c=1:i'. More than one event can be passed to the +option using the comma separator. Hardware events and generic hardware +events cannot be mixed together. The latter must be used with the -e +option. The -e option and this one can be mixed and matched. Events +can be grouped using the {} notation. +endif::HAVE_LIBPFM[] + INTERACTIVE PROMPTING KEYS --------------------------tools/perf/Makefile.config +13
-0@@ -1012,6 +1012,19 @@ ifdef LIBCLANGLLVM endif endif +ifdef LIBPFM4 + $(call feature_check,libpfm4) + ifeq ($(feature-libpfm4), 1) + CFLAGS += -DHAVE_LIBPFM + EXTLIBS += -lpfm + ASCIIDOC_EXTRA = -aHAVE_LIBPFM=1 + $(call detected,CONFIG_LIBPFM4) + else + msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev); + NO_LIBPFM4 := 1 + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dirtools/perf/Makefile.perf +2
-0@@ -118,6 +118,8 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # +# Define LIBPFM4 to enable libpfm4 events extension. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALLtools/perf/builtin-list.c +3
-0@@ -14,6 +14,7 @@#include "util/pmu.h" #include "util/debug.h" #include "util/metricgroup.h" +#include "util/pfm.h" #include <subcmd/pager.h> #include <subcmd/parse-options.h> #include <stdio.h> @@ -53,6 +54,8 @@ int cmd_list(int argc, const char **argv)setup_pager (); +libpfm_initialize (); +if (!raw_dump &&pager_in_use ())printf ("\nList of pre-defined events (to be used in -e):\n\n" );tools/perf/builtin-record.c +8
-0@@ -43,6 +43,7 @@#include "util/time-utils.h" #include "util/units.h" #include "util/bpf-event.h" +#include "util/pfm.h" #include "asm/bug.h" #include "perf.h" @@ -2421,6 +2422,11 @@ static struct option __record_options[] = {#endif OPT_CALLBACK(0, "max-size", &record.output_max_size, "size", "Limit the maximum size of the output file", parse_output_max_size), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &record.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -2461,6 +2467,8 @@ int cmd_record(int argc, const char **argv)if (rec->evlist ==NULL )return -ENOMEM ; +libpfm_initialize (); + err =perf_config (perf_record_config, rec);if (err)return err;tools/perf/builtin-stat.c +8
-0@@ -66,6 +66,7 @@#include "util/time-utils.h" #include "util/top.h" #include "util/affinity.h" +#include "util/pfm.h" #include "asm/bug.h" #include <linux/time64.h> @@ -936,6 +937,11 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &evsel_list,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPT_END () };@@ -1874,6 +1880,8 @@ int cmd_stat(int argc, const char **argv)unsigned int interval, timeout;const char *const stat_subcommands[] = {"record" ,"report" }; +libpfm_initialize (); +setlocale (LC_ALL ,"" ); evsel_list =evlist__new ();tools/perf/builtin-top.c +8
-0@@ -53,6 +53,7 @@#include "util/debug.h" #include "util/ordered-events.h" +#include "util/pfm.h" #include <assert.h> #include <elf.h> @@ -1577,6 +1578,11 @@ int cmd_top(int argc, const char **argv) "WARNING: should be used on grouped events."),OPT_BOOLEAN (0 ,"stitch-lbr" , &top.stitch_lbr,"Enable LBR callgraph stitching approach" ), +#ifdef HAVE_LIBPFM +OPT_CALLBACK (0 ,"pfm-events" , &top.evlist,"event" , +"libpfm4 event selector. use 'perf list' to list available events" , + parse_libpfm_events_option), +#endifOPTS_EVSWITCH (&top.evswitch), OPT_END() };@@ -1590,6 +1596,8 @@ int cmd_top(int argc, const char **argv)if (status <0 )return status; +libpfm_initialize (); + top.annotation_opts.min_pcnt =5 ; top.annotation_opts.context =4 ;tools/perf/tests/Build +1
-0@@ -56,6 +56,7 @@ perf-y += mem2node.o perf-y += maps.o perf-y += time-utils-test.o perf-y += genelf.o +perf-y += pfm.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir)tools/perf/tests/builtin-test.c +9
-0@@ -313,6 +313,15 @@ static struct test generic_tests[] = { .desc = "maps__merge_in", .func = test__maps__merge_in, }, + { + .desc = "Test libpfm4 support", + .func = test__pfm, + .subtest = { + .skip_if_fail = true, + .get_nr = test__pfm_subtest_get_nr, + .get_desc = test__pfm_subtest_get_desc, + } + }, { .func = NULL, },tools/perf/tests/pfm.c new file +207
-0@@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Test support for libpfm4 event encodings. +* +* Copyright 2020 Google LLC. +*/ +#include "tests.h" +#include "util/debug.h" +#include "util/evlist.h" +#include "util/pfm.h" + +#include <linux/kernel.h> + +#ifdef HAVE_LIBPFM +static int test__pfm_events (void ); +static int test__pfm_group (void ); +#endif + +static const struct { +int (*func)(void ); +const char *desc; +} pfm_testcase_table[] = { +#ifdef HAVE_LIBPFM + { + .func = test__pfm_events, + .desc ="test of individual --pfm-events" , + }, + { + .func = test__pfm_group, + .desc ="test groups of --pfm-events" , + }, +#endif +}; + +#ifdef HAVE_LIBPFM +static int count_pfm_events (struct perf_evlist *evlist) +{ +struct perf_evsel *evsel; +int count =0 ; + +perf_evlist__for_each_entry (evlist, evsel) { + count++; + } +return count; +} + +static int test__pfm_events (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; + } table[] = { + { + .events ="" , + .nr_events =0 , + }, + { + .events ="instructions" , + .nr_events =1 , + }, + { + .events ="instructions,cycles" , + .nr_events =2 , + }, + { + .events ="stereolab" , + .nr_events =0 , + }, + { + .events ="instructions,instructions" , + .nr_events =2 , + }, + { + .events ="stereolab,instructions" , + .nr_events =0 , + }, + { + .events ="instructions,stereolab" , + .nr_events =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, +0 ); + +evlist__delete (evlist); + } +return 0 ; +} + +static int test__pfm_group (void ) +{ +struct evlist *evlist; +struct option opt; +size_t i; +const struct { +const char *events; +int nr_events; +int nr_groups; + } table[] = { + { + .events ="{}," , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{instructions},{}" , + .nr_events =1 , + .nr_groups =1 , + }, + { + .events ="{},{instructions}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events ="{instructions},{instructions}" , + .nr_events =2 , + .nr_groups =2 , + }, + { + .events ="{instructions,cycles},{instructions,cycles}" , + .nr_events =4 , + .nr_groups =2 , + }, + { + .events ="{stereolab}" , + .nr_events =0 , + .nr_groups =0 , + }, + { + .events = +"{instructions,cycles},{instructions,stereolab}" , + .nr_events =3 , + .nr_groups =1 , + }, + }; + +libpfm_initialize (); + +for (i =0 ; i <ARRAY_SIZE (table); i++) { + evlist =evlist__new (); +if (evlist ==NULL ) +return -ENOMEM ; + + opt.value = evlist; +parse_libpfm_events_option (&opt, + table[i].events, +0 ); +TEST_ASSERT_EQUAL (table[i].events, +count_pfm_events (&evlist->core), + table[i].nr_events); +TEST_ASSERT_EQUAL (table[i].events, + evlist->nr_groups, + table[i].nr_groups); + +evlist__delete (evlist); + } +return 0 ; +} +#endif + +const char *test__pfm_subtest_get_desc (int i) +{ +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return NULL ; +return pfm_testcase_table[i].desc; +} + +int test__pfm_subtest_get_nr (void ) +{ +return (int )ARRAY_SIZE (pfm_testcase_table); +} + +int test__pfm (struct test *test__maybe_unused ,int i__maybe_unused ) +{ +#ifdef HAVE_LIBPFM +if (i <0 || i >= (int )ARRAY_SIZE (pfm_testcase_table)) +return TEST_FAIL ; +return pfm_testcase_table[i].func (); +#else +return TEST_SKIP ; +#endif +}tools/perf/tests/tests.h +3
-0@@ -112,6 +112,9 @@ int test__mem2node(struct test *t, int subtest);int test__maps__merge_in (struct test *t,int subtest);int test__time_utils (struct test *t,int subtest);int test__jit_write_elf (struct test *test,int subtest); +int test__pfm (struct test *test,int subtest); +const char *test__pfm_subtest_get_desc (int subtest); +int test__pfm_subtest_get_nr (void );bool test__bp_signal_is_supported (void );bool test__bp_account_is_supported (void );tools/perf/util/Build +2
-0@@ -177,6 +177,8 @@ perf-$(CONFIG_LIBBPF) += bpf-event.o perf-$(CONFIG_CXX) += c++/ +perf-$(CONFIG_LIBPFM4) += pfm.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"tools/perf/util/evsel.c +1
-1@@ -2433,7 +2433,7 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,/* Is there already the separator in the name. */ if (strchr (name,'/' ) || -strchr (name,':' )) + (strchr (name,':' ) && !evsel->is_libpfm_event)) sep ="" ;if (asprintf (&new_name,"%s%su" , name, sep) <0 )tools/perf/util/evsel.h +1
-0@@ -76,6 +76,7 @@ struct evsel {bool ignore_missing_thread;bool forced_leader;bool use_uncore_alias; +bool is_libpfm_event;/* parse modifier helper */ int exclude_GH;int sample_read;tools/perf/util/parse-events.c +23
-7@@ -36,6 +36,7 @@#include "metricgroup.h" #include "util/evsel_config.h" #include "util/event.h" +#include "util/pfm.h" #define MAX_NAME_LEN 100@@ -344,6 +345,7 @@ static char *get_config_name(struct list_head *head_terms)static struct evsel *__add_event (struct list_head *list,int *idx,struct perf_event_attr *attr, +bool init_attr,char *name,struct perf_pmu *pmu,struct list_head *config_terms,bool auto_merge_stats,const char *cpu_list)@@ -352,7 +354,8 @@ __add_event(struct list_head *list, int *idx,struct perf_cpu_map *cpus = pmu ? pmu->cpus : cpu_list ?perf_cpu_map__new (cpu_list) :NULL ; -event_attr_init (attr); +if (init_attr) +event_attr_init (attr); evsel =perf_evsel__new_idx (attr, *idx);if (!evsel)@@ -370,15 +373,25 @@ __add_event(struct list_head *list, int *idx,if (config_terms)list_splice (config_terms, &evsel->config_terms); -list_add_tail (&evsel->core.node, list); +if (list) +list_add_tail (&evsel->core.node, list); +return evsel; } +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu) +{ +return __add_event (NULL , &idx, attr, false, name, pmu,NULL , false, +NULL ); +} +static int add_event (struct list_head *list,int *idx,struct perf_event_attr *attr,char *name,struct list_head *config_terms) { -return __add_event (list, idx, attr, name,NULL , config_terms, false,NULL ) ?0 : -ENOMEM ; +return __add_event (list, idx, attr, true, name,NULL , config_terms, + false,NULL ) ?0 : -ENOMEM ; } static int add_event_tool(struct list_head *list, int *idx,@@ -390,7 +403,8 @@ static int add_event_tool(struct list_head *list, int *idx, .config = PERF_COUNT_SW_DUMMY, }; - evsel =__add_event (list, idx, &attr,NULL ,NULL ,NULL , false,"0" ); + evsel =__add_event (list, idx, &attr, true,NULL ,NULL ,NULL , false, +"0" );if (!evsel)return -ENOMEM ; evsel->tool_event = tool_event;@@ -1446,8 +1460,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,if (!head_config) { attr.type = pmu->type; - evsel =__add_event (list, &parse_state->idx, &attr,NULL , pmu,NULL , - auto_merge_stats,NULL ); + evsel =__add_event (list, &parse_state->idx, &attr, true,NULL , + pmu,NULL , auto_merge_stats,NULL );if (evsel) { evsel->pmu_name = name ?strdup (name) :NULL ; evsel->use_uncore_alias = use_uncore_alias;@@ -1487,7 +1501,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,return -EINVAL ; } - evsel =__add_event (list, &parse_state->idx, &attr, + evsel =__add_event (list, &parse_state->idx, &attr, true,get_config_name (head_config), pmu, &config_terms, auto_merge_stats,NULL );if (evsel) {@@ -2794,6 +2808,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,print_sdt_events (NULL ,NULL , name_only);metricgroup__print (true, true,NULL , name_only, details_flag); + +print_libpfm_events (name_only, long_desc); }int parse_events__is_hardcoded_term (struct parse_events_term *term)tools/perf/util/parse-events.h +4
-0@@ -17,6 +17,7 @@ struct evlist;struct parse_events_error ;struct option ; +struct perf_pmu ;struct tracepoint_path {char *system;@@ -186,6 +187,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,bool auto_merge_stats, bool use_alias); +struct evsel *parse_events__add_event (int idx,struct perf_event_attr *attr, +char *name,struct perf_pmu *pmu); +int parse_events_multi_pmu_add (struct parse_events_state *parse_state,char *str,struct list_head **listp);tools/perf/util/pfm.c new file +277
-0@@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#include "util/cpumap.h" +#include "util/debug.h" +#include "util/event.h" +#include "util/evlist.h" +#include "util/evsel.h" +#include "util/parse-events.h" +#include "util/pmu.h" +#include "util/pfm.h" + +#include <string.h> +#include <linux/kernel.h> +#include <perfmon/pfmlib_perf_event.h> + +void libpfm_initialize (void ) +{ +int ret; + + ret =pfm_initialize (); +if (ret !=PFM_SUCCESS ) { +ui__warning ("libpfm failed to initialize: %s\n" , +pfm_strerror (ret)); + } +} + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset__maybe_unused ) +{ +struct evlist *evlist = *(struct evlist **)opt->value; +struct perf_event_attr attr; +struct perf_pmu *pmu; +struct evsel *evsel, *grp_leader =NULL ; +char *p, *q, *p_orig; +const char *sep; +int grp_evt =-1 ; +int ret; + + p_orig = p =strdup (str); +if (!p) +return -1 ; +/* +* force loading of the PMU list +*/ +perf_pmu__scan (NULL ); + +for (q = p;strsep (&p,",{}" ); q = p) { + sep = p ? str + (p - p_orig -1 ) :"" ; +if (*sep =='{' ) { +if (grp_evt >-1 ) { +ui__error ( +"nested event groups not supported\n" ); + goto error; + } + grp_evt++; + } + +/* no event */ +if (*q =='\0' ) +continue ; + +memset (&attr,0 ,sizeof (attr)); +event_attr_init (&attr); + + ret =pfm_get_perf_event_encoding (q,PFM_PLM0 |PFM_PLM3 , + &attr,NULL ,NULL ); + +if (ret !=PFM_SUCCESS ) { +ui__error ("failed to parse event %s : %s\n" , str, +pfm_strerror (ret)); + goto error; + } + + pmu =perf_pmu__find_by_type ((unsigned int )attr.type); + evsel =parse_events__add_event (evlist->core.nr_entries, + &attr, q, pmu); +if (evsel ==NULL ) + goto error; + + evsel->is_libpfm_event = true; + +evlist__add (evlist, evsel); + +if (grp_evt ==0 ) + grp_leader = evsel; + +if (grp_evt >-1 ) { + evsel->leader = grp_leader; + grp_leader->core.nr_members++; + grp_evt++; + } + +if (*sep =='}' ) { +if (grp_evt <0 ) { +ui__error ( +"cannot close a non-existing event group\n" ); + goto error; + } + evlist->nr_groups++; + grp_leader =NULL ; + grp_evt =-1 ; + } + } +return 0 ; +error: +free (p_orig); +return -1 ; +} + +static const char *srcs[PFM_ATTR_CTRL_MAX ] = { + [PFM_ATTR_CTRL_UNKNOWN ] ="???" , + [PFM_ATTR_CTRL_PMU ] ="PMU" , + [PFM_ATTR_CTRL_PERF_EVENT ] ="perf_event" , +}; + +static void +print_attr_flags (pfm_event_attr_info_t *info) +{ +int n =0 ; + +if (info->is_dfl) { +printf ("[default] " ); + n++; + } + +if (info->is_precise) { +printf ("[precise] " ); + n++; + } + +if (!n) +printf ("- " ); +} + +static void +print_libpfm_events_detailed (pfm_event_info_t *info,bool long_desc) +{ +pfm_event_attr_info_t ainfo; +const char *src; +int j, ret; + + ainfo.size =sizeof (ainfo); + +printf (" %s\n" , info->name); +printf (" [%s]\n" , info->desc); +if (long_desc) { +if (info->equiv) +printf (" Equiv: %s\n" , info->equiv); + +printf (" Code : 0x%" PRIx64"\n" , info->code); + } +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type ==PFM_ATTR_UMASK ) { +printf (" %s:%s\n" , info->name, ainfo.name); +printf (" [%s]\n" , ainfo.desc); + } + +if (!long_desc) +continue ; + +if (ainfo.ctrl >=PFM_ATTR_CTRL_MAX ) + ainfo.ctrl =PFM_ATTR_CTRL_UNKNOWN ; + + src = srcs[ainfo.ctrl]; +switch (ainfo.type) { +case PFM_ATTR_UMASK : +printf (" Umask : 0x%02" PRIx64" : %s: " , + ainfo.code, src); +print_attr_flags (&ainfo); +putchar ('\n' ); +break ; +case PFM_ATTR_MOD_BOOL : +printf (" Modif : %s: [%s] : %s (boolean)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_MOD_INTEGER : +printf (" Modif : %s: [%s] : %s (integer)\n" , src, + ainfo.name, ainfo.desc); +break ; +case PFM_ATTR_NONE : +case PFM_ATTR_RAW_UMASK : +case PFM_ATTR_MAX : +default : +printf (" Attr : %s: [%s] : %s\n" , src, + ainfo.name, ainfo.desc); + } + } +} + +/* +* list all pmu::event:umask, pmu::event +* printed events may not be all valid combinations of umask for an event +*/ +static void +print_libpfm_events_raw (pfm_pmu_info_t *pinfo,pfm_event_info_t *info) +{ +pfm_event_attr_info_t ainfo; +int j, ret; +bool has_umask = false; + + ainfo.size =sizeof (ainfo); + +pfm_for_each_event_attr (j, info) { + ret =pfm_get_event_attr_info (info->idx, j, +PFM_OS_PERF_EVENT_EXT , &ainfo); +if (ret !=PFM_SUCCESS ) +continue ; + +if (ainfo.type !=PFM_ATTR_UMASK ) +continue ; + +printf ("%s::%s:%s\n" , pinfo->name, info->name, ainfo.name); + has_umask = true; + } +if (!has_umask) +printf ("%s::%s\n" , pinfo->name, info->name); +} + +void print_libpfm_events (bool name_only,bool long_desc) +{ +pfm_event_info_t info; +pfm_pmu_info_t pinfo; +int i, p, ret; + +/* initialize to zero to indicate ABI version */ + info.size =sizeof (info); + pinfo.size =sizeof (pinfo); + +if (!name_only) +puts ("\nList of pre-defined events (to be used in --pfm-events):\n" ); + +pfm_for_all_pmus (p) { +bool printed_pmu = false; + + ret =pfm_get_pmu_info (p, &pinfo); +if (ret !=PFM_SUCCESS ) +continue ; + +/* only print events that are supported by host HW */ +if (!pinfo.is_present) +continue ; + +/* handled by perf directly */ +if (pinfo.pmu ==PFM_PMU_PERF_EVENT ) +continue ; + +for (i = pinfo.first_event; i !=-1 ; + i =pfm_get_event_next (i)) { + + ret =pfm_get_event_info (i,PFM_OS_PERF_EVENT_EXT , + &info); +if (ret !=PFM_SUCCESS ) +continue ; + +if (!name_only && !printed_pmu) { +printf ("%s:\n" , pinfo.name); + printed_pmu = true; + } + +if (!name_only) +print_libpfm_events_detailed (&info, long_desc); +else +print_libpfm_events_raw (&pinfo, &info); + } +if (!name_only && printed_pmu) +putchar ('\n' ); + } +}tools/perf/util/pfm.h new file +43
-1@@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* Support for libpfm4 event encoding. +* +* Copyright 2020 Google LLC. +*/ +#ifndef __PERF_PFM_H +#define __PERF_PFM_H + +#include <subcmd/parse-options.h> + +#ifdef HAVE_LIBPFM +void libpfm_initialize (void ); + +int parse_libpfm_events_option (const struct option *opt,const char *str, +int unset); + +void print_libpfm_events (bool name_only,bool long_desc); + +#else +#include <linux/compiler.h> + +static inline void libpfm_initialize (void ) +{ +} + +static inline int parse_libpfm_events_option ( +const struct option *opt__maybe_unused , +const char *str__maybe_unused , +int unset__maybe_unused ) +{ +return 0 ; +} + +static inline void print_libpfm_events (bool name_only__maybe_unused , +bool long_desc__maybe_unused ) +{ +} + +#endif + + +#endif /* __PERF_PFM_H */ --Quoted 2 lines
2.26.2.303.gf8c07b1a785-goog
--
- Arnaldo