CoreSight

coresight@lists.linaro.org

4 participants
2643 discussions

Re: [PATCH v4 02/48] perf stat: Add aggr creators that are passed a cpu.

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:05PM -0800, Ian Rogers escreveu: > The cpu_map and index can get confused. Add variants of the cpu_map__get > routines that are passed a cpu. Make the existing cpu_map__get routines > use the new functions with a view to remove them when no longer used. > > Reviewed-by: James Clark <james.clark(a)arm.com> > Signed-off-by: Ian Rogers <irogers(a)google.com> > --- > tools/perf/util/cpumap.c | 79 +++++++++++++++++++++++----------------- > tools/perf/util/cpumap.h | 6 ++- > 2 files changed, 51 insertions(+), 34 deletions(-) > > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > index 87d3eca9b872..49fba2c53822 100644 > --- a/tools/perf/util/cpumap.c > +++ b/tools/perf/util/cpumap.c > @@ -128,21 +128,23 @@ int cpu_map__get_socket_id(int cpu) > return ret ?: value; > } > > -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > - void *data __maybe_unused) > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data __maybe_unused) > { > - int cpu; > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > - > id.socket = cpu_map__get_socket_id(cpu); > return id; > } > > +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > + void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); > + > + return cpu_map__get_socket_aggr_by_cpu(map->map[idx], data); > +} > + This 'idx < 0' wasn't in the original code nor is described in the comment log message, please avoid doing this, this may be harmless or even a good hardening, but either way would be interesting to have it in a separate patch. This eases review as in the end this code is just a refactoring, moving things around but in the end should be equivalent code. There are a few more, please consider this and if you agree, to speed things up I can make the changes here, if I think this won't fallout in changes to subsequent patches touching this area. - Arnaldo > static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) > { > struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; > @@ -200,15 +202,10 @@ int cpu_map__get_die_id(int cpu) > return ret ?: value; > } > > -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data) > { > - int cpu, die; > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > - > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > + struct aggr_cpu_id id; > + int die; > > die = cpu_map__get_die_id(cpu); > /* There is no die_id on legacy system. */ > @@ -220,7 +217,7 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > * with the socket ID and then add die to > * make a unique ID. > */ > - id = cpu_map__get_socket(map, idx, data); > + id = cpu_map__get_socket_aggr_by_cpu(cpu, data); > if (cpu_map__aggr_cpu_id_is_empty(id)) > return id; > > @@ -228,6 +225,15 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > return id; > } > > +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, > + void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); Ditto > + > + return cpu_map__get_die_aggr_by_cpu(map->map[idx], data); > +} > + > int cpu_map__get_core_id(int cpu) > { > int value, ret = cpu__get_topology_int(cpu, "core_id", &value); > @@ -239,20 +245,13 @@ int cpu_map__get_node_id(int cpu) > return cpu__get_node(cpu); > } > > -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data) > { > - int cpu; > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > - > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > - > - cpu = cpu_map__get_core_id(cpu); > + struct aggr_cpu_id id; > + int core = cpu_map__get_core_id(cpu); > > /* cpu_map__get_die returns a struct with socket and die set*/ > - id = cpu_map__get_die(map, idx, data); > + id = cpu_map__get_die_aggr_by_cpu(cpu, data); > if (cpu_map__aggr_cpu_id_is_empty(id)) > return id; > > @@ -260,19 +259,33 @@ struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *da > * core_id is relative to socket and die, we need a global id. > * So we combine the result from cpu_map__get_die with the core id > */ > - id.core = cpu; > + id.core = core; > return id; > + > } > > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) > +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); Ditto > + > + return cpu_map__get_core_aggr_by_cpu(map->map[idx], data); > +} > + > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data __maybe_unused) > { > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > + id.node = cpu_map__get_node_id(cpu); > + return id; > +} > + > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data) > +{ > if (idx < 0 || idx >= map->nr) > - return id; > + return cpu_map__empty_aggr_cpu_id(); > > - id.node = cpu_map__get_node_id(map->map[idx]); > - return id; > + return cpu_map__get_node_aggr_by_cpu(map->map[idx], data); > } > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > index a27eeaf086e8..c62d67704425 100644 > --- a/tools/perf/util/cpumap.h > +++ b/tools/perf/util/cpumap.h > @@ -31,13 +31,17 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); > size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); > size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); > int cpu_map__get_socket_id(int cpu); > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_die_id(int cpu); > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_core_id(int cpu); > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_node_id(int cpu); > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data); > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); > int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); > int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

4 years, 1 month

Re: [PATCH v3 06/48] perf cpumap: Switch cpu_map__build_map to cpu function

by Arnaldo Carvalho de Melo

Em Mon, Jan 10, 2022 at 02:29:58PM -0800, Ian Rogers escreveu: > On Mon, Jan 10, 2022 at 1:34 PM Arnaldo Carvalho de Melo > <acme(a)kernel.org> wrote: > > > > Em Mon, Jan 10, 2022 at 06:23:09PM -0300, Arnaldo Carvalho de Melo escreveu: > > > Em Mon, Jan 10, 2022 at 06:03:04PM -0300, Arnaldo Carvalho de Melo escreveu: > > > > Em Mon, Jan 10, 2022 at 05:46:52PM -0300, Arnaldo Carvalho de Melo escreveu: > > > > > At this point we need to remove the now unused perf_env__get_cpu(), and > > > > > then deal with the fallout in the following patches that needlessly > > > > > modify this unused function. > > > > > > > > > > Doing that now. > > > > > > > > Done, force pushed to tmp.perf/perf_cpu, now it is going again thru the > > > > build containers, a better start now: > > > > > So far so good: > > > > perf test ok, just that one that is failing, but before this series as > > well: > > > > 89: perf all metricgroups test : FAILED! > > Could you add the verbose output? I suspect it is fixed by this: > https://lore.kernel.org/lkml/20211223183948.3423989-1-irogers@google.com/ I'll try it. BTW, here are the final tests, problems with arm 32 and 64-bit, I'll go thru them tomorrow, to fix in the cset the problem appears, so that we keep it bisectable, else you can get what I have in tmp.perf/perf_cpu, fix it and tomorrow I'll retest. 27 85.67 debian:11 : Ok gcc (Debian 10.2.1-6) 10.2.1 20210110 , Debian clang version 11.0.1-2 28 98.65 debian:experimental : Ok gcc (Debian 11.2.0-13) 11.2.0 , Debian clang version 13.0.0-9+b2 29 8.69 debian:experimental-x-arm64 : FAIL gcc version 11.2.0 (Debian 11.2.0-9) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:35: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') 18 | if (pmu->cpus->nr != cpu__max_cpu()) | ~~~~~~~~~~~~~ ^~ ~~~~~~~~~~~~~~ | | | | int struct perf_cpu make[5]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: util] Error 2 make[4]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: arm64] Error 2 make[3]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: arch] Error 2 30 19.15 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110 31 21.25 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 10.2.1-6) 10.2.1 20210110 32 22.45 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 11.2.0-9) 11.2.0 33 21.86 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) , clang version 3.5.0 (tags/RELEASE_350/final) 34 55.88 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) , clang version 3.7.0 (tags/RELEASE_370/final) 35 67.12 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) , clang version 3.8.1 (tags/RELEASE_381/final) 36 17.53 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 37 68.11 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) , clang version 3.9.1 (tags/RELEASE_391/final) 38 80.15 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2) , clang version 4.0.1 (tags/RELEASE_401/final) 39 80.54 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6) , clang version 5.0.2 (tags/RELEASE_502/final) 40 91.48 fedora:28 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2) , clang version 6.0.1 (tags/RELEASE_601/final) 41 96.71 fedora:29 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2) , clang version 7.0.1 (Fedora 7.0.1-6.fc29) 42 100.71 fedora:30 : Ok gcc (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2) , clang version 8.0.0 (Fedora 8.0.0-3.fc30) 43 94.09 fedora:31 : Ok gcc (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2) , clang version 9.0.1 (Fedora 9.0.1-4.fc31) 44 87.49 fedora:32 : Ok gcc (GCC) 10.3.1 20210422 (Red Hat 10.3.1-1) , clang version 10.0.1 (Fedora 10.0.1-3.fc32) 45 85.99 fedora:33 : Ok gcc (GCC) 10.3.1 20210422 (Red Hat 10.3.1-1) , clang version 11.0.0 (Fedora 11.0.0-3.fc33) 46 88.89 fedora:34 : Ok gcc (GCC) 11.2.1 20210728 (Red Hat 11.2.1-1) , clang version 12.0.1 (Fedora 12.0.1-1.fc34) 47 19.84 fedora:34-x-ARC-glibc : Ok arc-linux-gcc (ARC HS GNU/Linux glibc toolchain 2019.03-rc1) 8.3.1 20190225 48 17.93 fedora:34-x-ARC-uClibc : Ok arc-linux-gcc (ARCv2 ISA Linux uClibc toolchain 2019.03-rc1) 8.3.1 20190225 49 91.33 fedora:35 : Ok gcc (GCC) 11.2.1 20211203 (Red Hat 11.2.1-7) , clang version 13.0.0 (Fedora 13.0.0-3.fc35) 50 99.83 fedora:rawhide : Ok gcc (GCC) 11.2.1 20211203 (Red Hat 11.2.1-7) , clang version 13.0.0 (Fedora 13.0.0-5.fc36) 51 79.16 gentoo-stage3:latest : Ok gcc (Gentoo 11.2.0 p1) 11.2.0 , clang version 13.0.0 52 68.81 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0 , clang version 3.9.1 (tags/RELEASE_391/final) 53 38.50 mageia:7 : FAIL clang version 8.0.0 (Mageia 8.0.0-1.mga7) yychar = yylex (&yylval, &yylloc, scanner); ^ #define yylex parse_events_lex ^ 1 error generated. make[3]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: util] Error 2 54 89.20 manjaro:base : Ok gcc (GCC) 11.1.0 , clang version 13.0.0 55 6.18 openmandriva:cooker : FAIL gcc version 11.2.0 20210728 (OpenMandriva) (GCC) In file included from builtin-bench.c:22: bench/bench.h:66:19: error: conflicting types for 'pthread_attr_setaffinity_np'; have 'int(pthread_attr_t *, size_t, cpu_set_t *)' {aka 'int(pthread_attr_t *, long unsigned int, cpu_set_t *)'} 66 | static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from bench/bench.h:64, from builtin-bench.c:22: /usr/include/pthread.h:394:12: note: previous declaration of 'pthread_attr_setaffinity_np' with type 'int(pthread_attr_t *, size_t, const cpu_set_t *)' {aka 'int(pthread_attr_t *, long unsigned int, const cpu_set_t *)'} 394 | extern int pthread_attr_setaffinity_np (pthread_attr_t *__attr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf 56 100.50 opensuse:15.0 : Ok gcc (SUSE Linux) 7.4.1 20190905 [gcc-7-branch revision 275407] , clang version 5.0.1 (tags/RELEASE_501/final 312548) 57 107.92 opensuse:15.1 : Ok gcc (SUSE Linux) 7.5.0 , clang version 7.0.1 (tags/RELEASE_701/final 349238) 58 102.71 opensuse:15.2 : Ok gcc (SUSE Linux) 7.5.0 , clang version 9.0.1 59 113.86 opensuse:15.3 : Ok gcc (SUSE Linux) 7.5.0 , clang version 11.0.1 60 114.75 opensuse:15.4 : Ok gcc (SUSE Linux) 7.5.0 , clang version 11.0.1 61 129.42 opensuse:tumbleweed : Ok gcc (SUSE Linux) 11.2.1 20211124 [revision 7510c23c1ec53aa4a62705f0384079661342ff7b] , clang version 13.0.0 62 94.32 oraclelinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4.0.1) , clang version 12.0.1 (Red Hat 12.0.1-4.0.1.module+el8.5.0+20428+2b4ecd47) 63 94.81 rockylinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4) , clang version 12.0.1 (Red Hat 12.0.1-4.module+el8.5.0+715+58f51d49) 64 71.11 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 , clang version 3.8.0-2ubuntu4 (tags/RELEASE_380/final) 65 6.89 ubuntu:16.04-x-arm : FAIL gcc version 5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) arch/arm/util/cs-etm.c: In function 'cs_etm_set_option': arch/arm/util/cs-etm.c:206:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:207:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:208:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c: In function 'cs_etm_info_priv_size': arch/arm/util/cs-etm.c:525:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:526:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:527:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:539:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:540:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c: In function 'cs_etm_info_fill': arch/arm/util/cs-etm.c:725:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(event_cpus, i) && ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:726:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:746:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) ^ arch/arm/util/cs-etm.c:747:34: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(cpu_map, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm' failed make[4]: *** [arm] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 66 6.99 ubuntu:16.04-x-arm64 : FAIL gcc version 5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:21: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') if (pmu->cpus->nr != cpu__max_cpu()) ^ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm64' failed make[4]: *** [arm64] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 67 18.54 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 68 19.04 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 69 18.93 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 70 19.04 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 71 76.32 ubuntu:18.04 : Ok gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 , clang version 6.0.0-1ubuntu2 (tags/RELEASE_600/final) 72 7.49 ubuntu:18.04-x-arm : FAIL gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) arch/arm/util/cs-etm.c: In function 'cs_etm_set_option': arch/arm/util/cs-etm.c:206:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:207:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:208:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c: In function 'cs_etm_info_priv_size': arch/arm/util/cs-etm.c:525:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:526:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:527:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:539:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:540:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c: In function 'cs_etm_info_fill': arch/arm/util/cs-etm.c:725:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(event_cpus, i) && ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:726:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:746:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:747:34: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(cpu_map, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm' failed make[4]: *** [arm] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 73 7.49 ubuntu:18.04-x-arm64 : FAIL gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:21: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') if (pmu->cpus->nr != cpu__max_cpu()) ~~~~~~~~~~~~~ ^~ ~~~~~~~~~~~~~~ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm64' failed make[4]: *** [arm64] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 74 16.73 ubuntu:18.04-x-m68k : Ok m68k-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 75 19.94 ubuntu:18.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 76 21.35 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 77 21.55 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 78 96.72 ubuntu:18.04-x-riscv64 : Ok riscv64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 79 18.24 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 80 19.54 ubuntu:18.04-x-sh4 : Ok sh4-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 81 18.34 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 82 73.64 ubuntu:20.04 : FAIL clang version 10.0.0-4ubuntu1 83 22.06 ubuntu:20.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 10.3.0-1ubuntu1~20.04) 10.3.0 84 73.74 ubuntu:20.10 : Ok gcc (Ubuntu 10.3.0-1ubuntu1~20.10) 10.3.0 , Ubuntu clang version 11.0.0-2 85 83.78 ubuntu:21.04 : Ok gcc (Ubuntu 10.3.0-1ubuntu1) 10.3.0 , Ubuntu clang version 12.0.0-3ubuntu1~21.04.2 86 86.88 ubuntu:21.10 : Ok gcc (Ubuntu 11.2.0-7ubuntu2) 11.2.0 , Ubuntu clang version 13.0.0-2 87 105.27 ubuntu:22.04 : Ok gcc (Ubuntu 11.2.0-13ubuntu1) 11.2.0 , Ubuntu clang version 13.0.0-9 BUILD_TARBALL_HEAD=16ed0580fb4d64bd59771ae7559dc307f04a0473 88 5613.66 real 95m27.836s user 1m24.038s sys 0m50.044s [perfbuilder@five ~]$ > Thanks, > Ian > > > [acme@quaco perf]$ uname -a > > Linux quaco 5.15.7-200.fc35.x86_64 #1 SMP Wed Dec 8 19:00:47 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux > > [acme@quaco perf]$ git log --oneline -1 > > 16ed0580fb4d64bd (HEAD -> perf/core, seventh/perf/core, five/perf/core, acme.korg/tmp.perf/perf_cpu) perf cpumap: Give CPUs their own type > > [acme@quaco perf]$ perf -v > > perf version 5.16.g16ed0580fb4d > > [acme@quaco perf]$ sudo su - > > [sudo] password for acme: > > [root@quaco ~]# perf -vv > > perf version 5.16.g16ed0580fb4d > > dwarf: [ on ] # HAVE_DWARF_SUPPORT > > dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT > > glibc: [ on ] # HAVE_GLIBC_SUPPORT > > syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT > > libbfd: [ on ] # HAVE_LIBBFD_SUPPORT > > libelf: [ on ] # HAVE_LIBELF_SUPPORT > > libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT > > numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT > > libperl: [ on ] # HAVE_LIBPERL_SUPPORT > > libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT > > libslang: [ on ] # HAVE_SLANG_SUPPORT > > libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT > > libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT > > libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT > > zlib: [ on ] # HAVE_ZLIB_SUPPORT > > lzma: [ on ] # HAVE_LZMA_SUPPORT > > get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT > > bpf: [ on ] # HAVE_LIBBPF_SUPPORT > > aio: [ on ] # HAVE_AIO_SUPPORT > > zstd: [ on ] # HAVE_ZSTD_SUPPORT > > libpfm4: [ OFF ] # HAVE_LIBPFM > > [root@quaco ~]# perf test > > 1: vmlinux symtab matches kallsyms : Ok > > 2: Detect openat syscall event : Ok > > 3: Detect openat syscall event on all cpus : Ok > > 4: Read samples using the mmap interface : Ok > > 5: Test data source output : Ok > > 6: Parse event definition strings : Ok > > 7: Simple expression parser : Ok > > 8: PERF_RECORD_* events & perf_sample fields : Ok > > 9: Parse perf pmu format : Ok > > 10: PMU events : > > 10.1: PMU event table sanity : Ok > > 10.2: PMU event map aliases : Ok > > 10.3: Parsing of PMU event table metrics : Ok > > 10.4: Parsing of PMU event table metrics with fake PMUs : Ok > > 11: DSO data read : Ok > > 12: DSO data cache : Ok > > 13: DSO data reopen : Ok > > 14: Roundtrip evsel->name : Ok > > 15: Parse sched tracepoints fields : Ok > > 16: syscalls:sys_enter_openat event fields : Ok > > 17: Setup struct perf_event_attr : Ok > > 18: Match and link multiple hists : Ok > > 19: 'import perf' in python : Ok > > 20: Breakpoint overflow signal handler : Ok > > 21: Breakpoint overflow sampling : Ok > > 22: Breakpoint accounting : Ok > > 23: Watchpoint : > > 23.1: Read Only Watchpoint : Skip (missing hardware support) > > 23.2: Write Only Watchpoint : Ok > > 23.3: Read / Write Watchpoint : Ok > > 23.4: Modify Watchpoint : Ok > > 24: Number of exit events of a simple workload : Ok > > 25: Software clock events period values : Ok > > 26: Object code reading : Ok > > 27: Sample parsing : Ok > > 28: Use a dummy software event to keep tracking : Ok > > 29: Parse with no sample_id_all bit set : Ok > > 30: Filter hist entries : Ok > > 31: Lookup mmap thread : Ok > > 32: Share thread maps : Ok > > 33: Sort output of hist entries : Ok > > 34: Cumulate child hist entries : Ok > > 35: Track with sched_switch : Ok > > 36: Filter fds with revents mask in a fdarray : Ok > > 37: Add fd to a fdarray, making it autogrow : Ok > > 38: kmod_path__parse : Ok > > 39: Thread map : Ok > > 40: LLVM search and compile : > > 40.1: Basic BPF llvm compile : Ok > > 40.2: kbuild searching : Ok > > 40.3: Compile source for BPF prologue generation : Ok > > 40.4: Compile source for BPF relocation : Ok > > 41: Session topology : Ok > > 42: BPF filter : > > 42.1: Basic BPF filtering : Ok > > 42.2: BPF pinning : Ok > > 42.3: BPF prologue generation : Ok > > 43: Synthesize thread map : Ok > > 44: Remove thread map : Ok > > 45: Synthesize cpu map : Ok > > 46: Synthesize stat config : Ok > > 47: Synthesize stat : Ok > > 48: Synthesize stat round : Ok > > 49: Synthesize attr update : Ok > > 50: Event times : Ok > > 51: Read backward ring buffer : Ok > > 52: Print cpu map : Ok > > 53: Merge cpu map : Ok > > 54: Probe SDT events : Ok > > 55: is_printable_array : Ok > > 56: Print bitmap : Ok > > 57: perf hooks : Ok > > 58: builtin clang support : > > 58.1: builtin clang compile C source to IR : Skip (not compiled in) > > 58.2: builtin clang compile C source to ELF object : Skip (not compiled in) > > 59: unit_number__scnprintf : Ok > > 60: mem2node : Ok > > 61: time utils : Ok > > 62: Test jit_write_elf : Ok > > 63: Test libpfm4 support : > > 63.1: test of individual --pfm-events : Skip (not compiled in) > > 63.2: test groups of --pfm-events : Skip (not compiled in) > > 64: Test api io : Ok > > 65: maps__merge_in : Ok > > 66: Demangle Java : Ok > > 67: Demangle OCaml : Ok > > 68: Parse and process metrics : Ok > > 69: PE file support : Ok > > 70: Event expansion for cgroups : Ok > > 71: Convert perf time to TSC : Ok > > 72: dlfilter C API : Ok > > 73: Sigtrap : Ok > > 74: x86 rdpmc : Ok > > 75: Test dwarf unwind : Ok > > 76: x86 instruction decoder - new instructions : Ok > > 77: Intel PT packet decoder : Ok > > 78: x86 bp modify : Ok > > 79: x86 Sample parsing : Ok > > 80: build id cache operations : Ok > > 81: daemon operations : Ok > > 82: perf pipe recording and injection test : Ok > > 83: Add vfs_getname probe to get syscall args filenames : Ok > > 84: probe libc's inet_pton & backtrace it with ping : Ok > > 85: Use vfs_getname probe to get syscall args filenames : Ok > > 86: Zstd perf.data compression/decompression : Ok > > 87: perf stat csv summary test : Ok > > 88: perf stat metrics (shadow stat) test : Ok > > 89: perf all metricgroups test : FAILED! > > 90: perf all metrics test : Ok > > 91: perf all PMU test : Ok > > 92: perf stat --bpf-counters test : Ok > > 93: Check Arm CoreSight trace data recording and synthesized samples: Skip > > 94: Check Arm SPE trace data recording and synthesized samples : Skip > > 95: Check open filename arg using perf trace + vfs_getname : Ok > > [root@quaco ~]# > > > > And the containers are ok so far: > > > > [perfbuilder@five ~]$ export BUILD_TARBALL=http://192.168.100.2/perf/perf-5.16.0.tar.xz > > [perfbuilder@five ~]$ time dm > > 1 95.61 almalinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4) , clang version 12.0.1 (Red Hat 12.0.1-4.module_el8.5.0+1025+93159d6c) > > 2 56.18 alpine:3.4 : Ok gcc (Alpine 5.3.0) 5.3.0 , clang version 3.8.0 (tags/RELEASE_380/final) > > 3 54.98 alpine:3.5 : Ok gcc (Alpine 6.2.1) 6.2.1 20160822 , clang version 3.8.1 (tags/RELEASE_381/final) > > 4 57.69 alpine:3.6 : Ok gcc (Alpine 6.3.0) 6.3.0 , clang version 4.0.0 (tags/RELEASE_400/final) > > 5 63.62 alpine:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0 , Alpine clang version 5.0.0 (tags/RELEASE_500/final) (based on LLVM 5.0.0) > > 6 64.52 alpine:3.8 : Ok gcc (Alpine 6.4.0) 6.4.0 , Alpine clang version 5.0.1 (tags/RELEASE_501/final) (based on LLVM 5.0.1) > > 7 66.54 alpine:3.9 : Ok gcc (Alpine 8.3.0) 8.3.0 , Alpine clang version 5.0.1 (tags/RELEASE_502/final) (based on LLVM 5.0.1) > > 8 91.91 alpine:3.10 : Ok gcc (Alpine 8.3.0) 8.3.0 , Alpine clang version 8.0.0 (tags/RELEASE_800/final) (based on LLVM 8.0.0) > > 9 104.93 alpine:3.11 : Ok gcc (Alpine 9.3.0) 9.3.0 , Alpine clang version 9.0.0 (https://git.alpinelinux.org/aports f7f0d2c2b8bcd6a5843401a9a702029556492689) (based on LLVM 9.0.0) > > 10 107.97 alpine:3.12 : Ok gcc (Alpine 9.3.0) 9.3.0 , Alpine clang version 10.0.0 (https://gitlab.alpinelinux.org/alpine/aports.git 7445adce501f8473efdb93b17b5eaf2f1445ed4c) > > 11 115.98 alpine:3.13 : Ok gcc (Alpine 10.2.1_pre1) 10.2.1 20201203 , Alpine clang version 10.0.1 > > 12 101.73 alpine:3.14 : Ok gcc (Alpine 10.3.1_git20210424) 10.3.1 20210424 , Alpine clang version 11.1.0 > > 13 103.35 alpine:3.15 : Ok gcc (Alpine 10.3.1_git20211027) 10.3.1 20211027 , Alpine clang version 12.0.1 > > 14 104.43 alpine:edge : Ok gcc (Alpine 11.2.1_git20211128) 11.2.1 20211128 , Alpine clang version 12.0.1 > > 15 51.06 alt:p8 : Ok x86_64-alt-linux-gcc (GCC) 5.3.1 20151207 (ALT p8 5.3.1-alt3.M80P.1) , clang version 3.8.0 (tags/RELEASE_380/final) > > 16 75.95 alt:p9 : Ok x86_64-alt-linux-gcc (GCC) 8.4.1 20200305 (ALT p9 8.4.1-alt0.p9.1) , clang version 10.0.0 > > 17 75.26 alt:p10 : Ok x86_64-alt-linux-gcc (GCC) 10.3.1 20210703 (ALT Sisyphus 10.3.1-alt2) , clang version 11.0.1 > > 18 74.85 alt:sisyphus : Ok x86_64-alt-linux-gcc (GCC) 11.2.1 20210911 (ALT Sisyphus 11.2.1-alt1) , ALT Linux Team clang version 12.0.1 > > 19 52.87 amazonlinux:1 : Ok gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2) , clang version 3.6.2 (tags/RELEASE_362/final) > > 20 85.98 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-13) , clang version 11.1.0 (Amazon Linux 2 11.1.0-1.amzn2.0.2) > > 21 79.77 archlinux:base : Ok gcc (GCC) 11.1.0 , clang version 13.0.0 > > 22 83.56 centos:8 : Ok gcc (GCC) 8.4.1 20200928 (Red Hat 8.4.1-1) , clang version 11.0.1 (Red Hat 11.0.1-1.module_el8.4.0+966+2995ef20) > > 23 98.02 centos:stream : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-3) , clang version 12.0.1 (Red Hat 12.0.1-2.module_el8.6.0+937+1cafe22c) > > 24 27.67 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 11.2.1 20211228 releases/gcc-11.2.0-618-g3b2b18144c , clang version 11.1.0 > > 25 65.92 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516 , clang version 3.8.1-24 (tags/RELEASE_381/final) > > 26 62.20 debian:10 : Ok gcc (Debian 8.3.0-6) 8.3.0 , clang version 7.0.1-8+deb10u2 (tags/RELEASE_701/final) > > 27: debian:11 > > -- - Arnaldo

4 years, 1 month

Re: [PATCH v3 06/48] perf cpumap: Switch cpu_map__build_map to cpu function

by Arnaldo Carvalho de Melo

Em Wed, Dec 29, 2021 at 11:19:48PM -0800, Ian Rogers escreveu: > Avoid error prone cpu_map + idx variant. Remove now unused functions. At this point we need to remove the now unused perf_env__get_cpu(), and then deal with the fallout in the following patches that needlessly modify this unused function. Doing that now. - Arnaldo ⬢[acme@toolbox perf]$ git diff diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 6b985abaa2d22c58..40cb3518f27e2309 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1477,22 +1477,6 @@ static void perf_stat__exit_aggr_mode(void) stat_config.cpus_aggr_map = NULL; } -static inline int perf_env__get_cpu(void *data, struct perf_cpu_map *map, int idx) -{ - struct perf_env *env = data; - int cpu; - - if (idx > map->nr) - return -1; - - cpu = map->map[idx]; - - if (cpu >= env->nr_cpus_avail) - return -1; - - return cpu; -} - static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(int cpu, void *data) { struct perf_env *env = data; > Reviewed-by: James Clark <james.clark(a)arm.com> > Signed-off-by: Ian Rogers <irogers(a)google.com> > --- > tools/perf/builtin-stat.c | 28 ++++------------------------ > tools/perf/util/cpumap.c | 12 ++++++------ > tools/perf/util/cpumap.h | 2 +- > 3 files changed, 11 insertions(+), 31 deletions(-) > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 9791ae9b1a53..6b985abaa2d2 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -1504,11 +1504,6 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_socket_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(int cpu, void *data) > { > struct perf_env *env = data; > @@ -1527,11 +1522,6 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_die_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(int cpu, void *data) > { > struct perf_env *env = data; > @@ -1551,11 +1541,6 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_core_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(int cpu, void *data) > { > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > @@ -1564,33 +1549,28 @@ static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_node_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **sockp) > { > - return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); > + return cpu_map__build_map(cpus, sockp, perf_env__get_socket_aggr_by_cpu, env); > } > > static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **diep) > { > - return cpu_map__build_map(cpus, diep, perf_env__get_die, env); > + return cpu_map__build_map(cpus, diep, perf_env__get_die_aggr_by_cpu, env); > } > > static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **corep) > { > - return cpu_map__build_map(cpus, corep, perf_env__get_core, env); > + return cpu_map__build_map(cpus, corep, perf_env__get_core_aggr_by_cpu, env); > } > > static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **nodep) > { > - return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); > + return cpu_map__build_map(cpus, nodep, perf_env__get_node_aggr_by_cpu, env); > } > > static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > index 49fba2c53822..feaf34b25efc 100644 > --- a/tools/perf/util/cpumap.c > +++ b/tools/perf/util/cpumap.c > @@ -163,7 +163,7 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) > } > > int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), > + struct aggr_cpu_id (*f)(int cpu, void *data), > void *data) > { > int nr = cpus->nr; > @@ -178,7 +178,7 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > c->nr = 0; > > for (cpu = 0; cpu < nr; cpu++) { > - s1 = f(cpus, cpu, data); > + s1 = f(cpu, data); > for (s2 = 0; s2 < c->nr; s2++) { > if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) > break; > @@ -290,22 +290,22 @@ struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *da > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) > { > - return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); > + return cpu_map__build_map(cpus, sockp, cpu_map__get_socket_aggr_by_cpu, NULL); > } > > int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) > { > - return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); > + return cpu_map__build_map(cpus, diep, cpu_map__get_die_aggr_by_cpu, NULL); > } > > int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) > { > - return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); > + return cpu_map__build_map(cpus, corep, cpu_map__get_core_aggr_by_cpu, NULL); > } > > int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) > { > - return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); > + return cpu_map__build_map(cpus, numap, cpu_map__get_node_aggr_by_cpu, NULL); > } > > /* setup simple routines to easily access node numbers given a cpu number */ > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > index c62d67704425..9648816c4255 100644 > --- a/tools/perf/util/cpumap.h > +++ b/tools/perf/util/cpumap.h > @@ -63,7 +63,7 @@ int cpu__max_present_cpu(void); > int cpu__get_node(int cpu); > > int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), > + struct aggr_cpu_id (*f)(int cpu, void *data), > void *data); > > int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

4 years, 1 month

Re: [PATCH v4 00/48] Refactor perf cpumap

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:03PM -0800, Ian Rogers escreveu: > Perf cpu map has various functions where a cpumap and index are passed > in order to load the cpu. A problem with this is that the wrong index > may be passed for the cpumap, causing problems like aggregation on the > wrong CPU: > https://lore.kernel.org/lkml/20211204023409.969668-1-irogers@google.com/ > > This patch set refactors the cpu map API, reducing it and explicitly > passing the cpu (rather than the pair) to functions that need > it. Comments are added at the same time. Changes modify the same > file/function more than once as refactoring and fixes are broken apart > for the sake of bisection. > > v2. Incorproates fixes suggested Jiri Olsa, rewrites the evlist CPU > iterator in part in a way suggested by Riccardo Mancini. The new > fixes start at patch 23. The final change was suggested by John > Garry to make the CPUs have their own struct wrapper. > > v3. Incorporates fixes suggested by Namhyung Kim. > > v4. Rebases and incorporates fixes suggested by Jiri Olsa. Did fixes in places where BUILD_BPF_SKEL=1 was failing, now, at the end of the series: ⬢[acme@toolbox perf]$ git log --oneline -1 ; time make -C tools/perf build-test 462aafa8fcbdc78f (HEAD -> perf/core) perf cpumap: Give CPUs their own type make: Entering directory '/var/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . make_static: cd . && make LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 -j32 DESTDIR=/tmp/tmp.lFrqVcqiRY make_with_gtk2: cd . && make GTK2=1 -j32 DESTDIR=/tmp/tmp.KvHmTqUGmD - /var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP: cd . && make FEATURE_DUMP_COPY=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP feature-dump cd . && make FEATURE_DUMP_COPY=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP feature-dump make_no_libelf_O: cd . && make NO_LIBELF=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.xz3LYy7WpA DESTDIR=/tmp/tmp.zVjIMpvQMM make_no_libbpf_DEBUG_O: cd . && make NO_LIBBPF=1 DEBUG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.0gxAOSjb1j DESTDIR=/tmp/tmp.kYTk1WjWWz make_no_libaudit_O: cd . && make NO_LIBAUDIT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.6hArTG9Dth DESTDIR=/tmp/tmp.hCNdYeDRCr make_no_backtrace_O: cd . && make NO_BACKTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.VtoPI58z3t DESTDIR=/tmp/tmp.SYyBBMSHSL make_no_libcrypto_O: cd . && make NO_LIBCRYPTO=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.SO1qtxJwvE DESTDIR=/tmp/tmp.AqrPw1oZfx make_with_clangllvm_O: cd . && make LIBCLANGLLVM=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.G9KVEaDv2B DESTDIR=/tmp/tmp.6CSqj0wPqJ make_with_coresight_O: cd . && make CORESIGHT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.PnVTJNHy1E DESTDIR=/tmp/tmp.k7Arerg778 make_no_libpython_O: cd . && make NO_LIBPYTHON=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.cKjvFagVL3 DESTDIR=/tmp/tmp.aCaD0hbP3O make_no_sdt_O: cd . && make NO_SDT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.EKoWnoZtl4 DESTDIR=/tmp/tmp.1gGYetcptB make_libbpf_dynamic_O: cd . && make LIBBPF_DYNAMIC=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.Nked5O10EK DESTDIR=/tmp/tmp.eo6YAEOfZO make_minimal_O: cd . && make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 NO_LIBCAP=1 NO_SYSCALL_TABLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.Z6dSqYBXfU DESTDIR=/tmp/tmp.Y4iRu634of make_install_prefix_slash_O: cd . && make install prefix=/tmp/krava/ FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.BgipDyNu70 DESTDIR=/tmp/tmp.pOwrdDYBqf make_util_pmu_bison_o_O: cd . && make util/pmu-bison.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.XeO82Ajmv6 DESTDIR=/tmp/tmp.dxQKNNBM6W make_install_O: cd . && make install FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.KuCyqzLwnA DESTDIR=/tmp/tmp.KYvqoiOKzW make_install_prefix_O: cd . && make install prefix=/tmp/krava FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.rJNNPELdri DESTDIR=/tmp/tmp.g52i9CcmnU make_install_bin_O: cd . && make install-bin FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.i118vbQuo0 DESTDIR=/tmp/tmp.90tKcjOWD8 make_perf_o_O: cd . && make perf.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.kEZMTvh3wf DESTDIR=/tmp/tmp.JYvQLdkPsp make_no_slang_O: cd . && make NO_SLANG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.WDNGH0DpdW DESTDIR=/tmp/tmp.Zfa804wClJ make_no_ui_O: cd . && make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.P4nTBNqkP4 DESTDIR=/tmp/tmp.iCLqOyrh4o make_no_newt_O: cd . && make NO_NEWT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.EdjjHoqODV DESTDIR=/tmp/tmp.jKfYRizWtm make_with_libpfm4_O: cd . && make LIBPFM4=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.r3hPAOgfId DESTDIR=/tmp/tmp.GvMmEZUc2B make_no_demangle_O: cd . && make NO_DEMANGLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.wG9f40LzG3 DESTDIR=/tmp/tmp.i76sPjSg1m make_no_libunwind_O: cd . && make NO_LIBUNWIND=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.SmFfmmB9KQ DESTDIR=/tmp/tmp.9tjMdCWMxG make_no_libbpf_O: cd . && make NO_LIBBPF=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.7jH21oP9n7 DESTDIR=/tmp/tmp.taUqTgY37S make_no_syscall_tbl_O: cd . && make NO_SYSCALL_TABLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.L2v7vi1AQl DESTDIR=/tmp/tmp.wHEA4jEpw9 make_no_libnuma_O: cd . && make NO_LIBNUMA=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.9N5pQYuRbO DESTDIR=/tmp/tmp.B0Yptb7xP6 make_util_map_o_O: cd . && make util/map.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.B8oe4jnWwB DESTDIR=/tmp/tmp.m0APlsli14 make_with_babeltrace_O: cd . && make LIBBABELTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.3G1kLTJLJx DESTDIR=/tmp/tmp.ahuDENSMsz make_debug_O: cd . && make DEBUG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.KpsvOj0KHD DESTDIR=/tmp/tmp.f2Yv9Lrorg make_no_libperl_O: cd . && make NO_LIBPERL=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.7tIufwAi4O DESTDIR=/tmp/tmp.vcBv7UYjuw make_no_libbionic_O: cd . && make NO_LIBBIONIC=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.HCJA7xCDxq DESTDIR=/tmp/tmp.us5CDSPqyO make_pure_O: cd . && make FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.eg2wCpydvg DESTDIR=/tmp/tmp.MmD1xESO2A make_doc_O: cd . && make doc FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.TqkyGrzRut DESTDIR=/tmp/tmp.ap34IVxoM9 make_no_scripts_O: cd . && make NO_LIBPYTHON=1 NO_LIBPERL=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.pRWHKzpPhv DESTDIR=/tmp/tmp.dUNhAp2rLt make_clean_all_O: cd . && make clean all FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.YnzNLLk9ID DESTDIR=/tmp/tmp.7kXr5obkmA make_no_libdw_dwarf_unwind_O: cd . && make NO_LIBDW_DWARF_UNWIND=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.GzZCxuYLwR DESTDIR=/tmp/tmp.n3YS9a9DcU make_help_O: cd . && make help FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.t7QwWVHsod DESTDIR=/tmp/tmp.NG5uSWCZzi make_no_auxtrace_O: cd . && make NO_AUXTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.wiDZkJzs8R DESTDIR=/tmp/tmp.ITtPlX0usX make_no_gtk2_O: cd . && make NO_GTK2=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.xd1x5QIckJ DESTDIR=/tmp/tmp.f6KzsHHkZH make_tags_O: cd . && make tags FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.e8oSaBuFUb DESTDIR=/tmp/tmp.4czd6ovlSB OK make: Leaving directory '/var/home/acme/git/perf/tools/perf' real 4m29.388s user 59m6.060s sys 12m19.581s ⬢[acme@toolbox perf]$ alias m='perf stat -e cycles:u,instructions:u make -k BUILD_BPF_SKEL=1 CORESIGHT=1 PYTHON=python3 O=/tmp/build/perf -C tools/perf install-bin && git status && perf test python' So 'perf test python' is done after every build, no problems with that as well. I'm now making it go thru the container builds. - Arnaldo

4 years, 1 month

Re: [PATCH v4 48/48] perf cpumap: Give CPUs their own type.

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:51PM -0800, Ian Rogers escreveu: > A common problem is confusing CPU map indices with the CPU, by wrapping > the CPU with a struct then this is avoided. This approach is similar to > atomic_t. This one needed this to build with BUILD_BPF_SKEL=1, please check, I'll soon push this to tmp.perf/perf_cpu so that you can take a look and test it. - Arnaldo diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 80d1a3a31052fe55..328479df5e16a638 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -540,7 +540,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) filter_type == BPERF_FILTER_TGID) key = evsel->core.threads->map[i].pid; else if (filter_type == BPERF_FILTER_CPU) - key = evsel->core.cpus->map[i]; + key = evsel->core.cpus->map[i].cpu; else break; @@ -584,7 +584,7 @@ static int bperf_sync_counters(struct evsel *evsel) num_cpu = all_cpu_map->nr; for (i = 0; i < num_cpu; i++) { - cpu = all_cpu_map->map[i]; + cpu = all_cpu_map->map[i].cpu; bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); } return 0; @@ -605,7 +605,7 @@ static int bperf__disable(struct evsel *evsel) static int bperf__read(struct evsel *evsel) { struct bperf_follower_bpf *skel = evsel->follower_skel; - __u32 num_cpu_bpf = cpu__max_cpu(); + __u32 num_cpu_bpf = cpu__max_cpu().cpu; struct bpf_perf_event_value values[num_cpu_bpf]; int reading_map_fd, err = 0; __u32 i; @@ -615,6 +615,7 @@ static int bperf__read(struct evsel *evsel) reading_map_fd = bpf_map__fd(skel->maps.accum_readings); for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) { + struct perf_cpu entry; __u32 cpu; err = bpf_map_lookup_elem(reading_map_fd, &i, values); @@ -624,14 +625,15 @@ static int bperf__read(struct evsel *evsel) case BPERF_FILTER_GLOBAL: assert(i == 0); - perf_cpu_map__for_each_cpu(cpu, j, all_cpu_map) { + perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) { + cpu = entry.cpu; perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; } break; case BPERF_FILTER_CPU: - cpu = evsel->core.cpus->map[i]; + cpu = evsel->core.cpus->map[i].cpu; perf_counts(evsel->counts, i, 0)->val = values[cpu].counter; perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, i, 0)->run = values[cpu].running; diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index cbc6c2bca488f6bf..631e34a0b66ff084 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist) struct cgroup *cgrp, *leader_cgrp; __u32 i, cpu; __u32 nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; int map_size, map_fd; int prog_fd, err; @@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { int fd = FD(evsel, cpu); __u32 idx = evsel->core.idx * total_cpus + - evlist->core.all_cpus->map[cpu]; + evlist->core.all_cpus->map[cpu].cpu; err = bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY); @@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist) int prog_fd = bpf_program__fd(skel->progs.trigger_read); for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; bperf_trigger_reading(prog_fd, cpu); } @@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel) { struct evlist *evlist = evsel->evlist; int i, cpu, nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; struct perf_counts_values *counts; struct bpf_perf_event_value *values; int reading_map_fd, err = 0; @@ -272,7 +272,7 @@ static int bperf_cgrp__read(struct evsel *evsel) } for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; counts = perf_counts(evsel->counts, i, 0); counts->val = values[cpu].counter; diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 28dc4c60c7884818..d756cc66eef32ae8 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -63,7 +63,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) fd = bpf_map__fd(skel->maps.cpu_filter); for (i = 0; i < ncpus; i++) { - cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i); + cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); } } @@ -122,7 +122,7 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, int i, fd, err; u32 idx; u64 *hist; - int ncpus = cpu__max_cpu(); + int ncpus = cpu__max_cpu().cpu; fd = bpf_map__fd(skel->maps.latency);

4 years, 1 month

Re: [PATCH v4 44/48] perf bpf: Rename cpu to cpu_map_idx

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:47PM -0800, Ian Rogers escreveu: > Synchronize the caller in evsel with the called function. > Shorten 3 lines of code in bperf_read by using > perf_cpu_map__for_each_cpu. > This code is frequently using variables named cpu as cpu map indices, > which doesn't matter as all CPUs are in the CPU map. It is strange in > some cases the cpumap is used at all. CC /tmp/build/perf/builtin-stat.o INSTALL trace_plugins CC /tmp/build/perf/util/evlist.o CC /tmp/build/perf/util/evsel.o CC /tmp/build/perf/util/header.o CC /tmp/build/perf/util/bpf_counter.o CC /tmp/build/perf/util/bpf_counter_cgroup.o CC /tmp/build/perf/util/bpf_ftrace.o In file included from util/cpumap.h:8, from util/bpf_counter.c:23: util/bpf_counter.c: In function ‘bperf__read’: /var/home/acme/git/perf/tools/lib/perf/include/perf/cpumap.h:27:20: error: comparison of integer expressions of different signedness: ‘__u32’ {aka ‘unsigned int’} and ‘int’ [-Werror=sign-compare] 27 | (idx) < perf_cpu_map__nr(cpus); \ | ^ util/bpf_counter.c:626:25: note: in expansion of macro ‘perf_cpu_map__for_each_cpu’ 626 | perf_cpu_map__for_each_cpu(cpu, j, all_cpu_map) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~ util/bpf_counter.c:611:21: error: unused variable ‘num_cpu’ [-Werror=unused-variable] 611 | __u32 i, j, num_cpu; | ^~~~~~~ cc1: all warnings being treated as errors make[4]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:96: /tmp/build/perf/util/bpf_counter.o] Error 1 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:139: util] Error 2 make[2]: *** [Makefile.perf:665: /tmp/build/perf/perf-in.o] Error 2 make[1]: *** [Makefile.perf:240: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/var/home/acme/git/perf/tools/perf' Performance counter stats for 'make -k BUILD_BPF_SKEL=1 CORESIGHT=1 PYTHON=python3 O=/tmp/build/perf -C tools/perf install-bin': 15,589,752,360 cycles:u 28,227,862,710 instructions:u # 1.81 insn per cycle 1.996638375 seconds time elapsed 3.567457000 seconds user 0.934840000 seconds sys ⬢[acme@toolbox perf]$ git log --oneline -1 0083ba4c6a931fd0 (HEAD) perf bpf: Rename cpu to cpu_map_idx ⬢[acme@toolbox perf]$ Trying to fix... > Signed-off-by: Ian Rogers <irogers(a)google.com> > --- > tools/perf/util/bpf_counter.c | 16 +++++++--------- > tools/perf/util/bpf_counter.h | 4 ++-- > 2 files changed, 9 insertions(+), 11 deletions(-) > > diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c > index c17d4a43ce06..ae5bd87ff020 100644 > --- a/tools/perf/util/bpf_counter.c > +++ b/tools/perf/util/bpf_counter.c > @@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel) > return 0; > } > > -static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, > +static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx, > int fd) > { > struct bpf_prog_profiler_bpf *skel; > @@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, > assert(skel != NULL); > > ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), > - &cpu, &fd, BPF_ANY); > + &cpu_map_idx, &fd, BPF_ANY); > if (ret) > return ret; > } > @@ -566,12 +566,12 @@ static int bperf__load(struct evsel *evsel, struct target *target) > return err; > } > > -static int bperf__install_pe(struct evsel *evsel, int cpu, int fd) > +static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) > { > struct bperf_leader_bpf *skel = evsel->leader_skel; > > return bpf_map_update_elem(bpf_map__fd(skel->maps.events), > - &cpu, &fd, BPF_ANY); > + &cpu_map_idx, &fd, BPF_ANY); > } > > /* > @@ -623,9 +623,7 @@ static int bperf__read(struct evsel *evsel) > case BPERF_FILTER_GLOBAL: > assert(i == 0); > > - num_cpu = all_cpu_map->nr; > - for (j = 0; j < num_cpu; j++) { > - cpu = all_cpu_map->map[j]; > + perf_cpu_map__for_each_cpu(cpu, j, all_cpu_map) { > perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; > perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; > perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; > @@ -757,11 +755,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel) > evsel->follower_skel == NULL; > } > > -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd) > +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) > { > if (bpf_counter_skip(evsel)) > return 0; > - return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd); > + return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd); > } > > int bpf_counter__load(struct evsel *evsel, struct target *target) > diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h > index 65ebaa6694fb..4dbf26408b69 100644 > --- a/tools/perf/util/bpf_counter.h > +++ b/tools/perf/util/bpf_counter.h > @@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel); > typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel, > struct target *target); > typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, > - int cpu, > + int cpu_map_idx, > int fd); > > struct bpf_counter_ops { > @@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel); > int bpf_counter__disable(struct evsel *evsel); > int bpf_counter__read(struct evsel *evsel); > void bpf_counter__destroy(struct evsel *evsel); > -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); > +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd); > > #else /* HAVE_BPF_SKEL */ > > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

4 years, 1 month

Re: [PATCH v4 17/48] perf cpumap: Remove cpu_map__cpu, use libperf function.

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:20PM -0800, Ian Rogers escreveu: > Switch the remaining few users of cpu_map__cpu to perf_cpu_map__cpu and > remove the function. > > Reviewed-by: James Clark <james.clark(a)arm.com> > Signed-off-by: Ian Rogers <irogers(a)google.com> util/bpf_ftrace.c: In function ‘perf_ftrace__latency_prepare_bpf’: util/bpf_ftrace.c:66:31: error: implicit declaration of function ‘cpu_map__cpu’; did you mean ‘cpu_map__has’? [-Werror=implicit-function-declaration] 66 | cpu = cpu_map__cpu(ftrace->evlist->core.cpus, i); | ^~~~~~~~~~~~ | cpu_map__has cc1: all warnings being treated as errors make[4]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:96: /tmp/build/perf/util/bpf_ftrace.o] Error 1 make[4]: *** Waiting for unfinished jobs.... LD /tmp/build/perf/ui/browsers/perf-in.o LD /tmp/build/perf/ui/perf-in.o LD /tmp/build/perf/util/scripting-engines/perf-in.o make[3]: *** [/var/home/acme/git/perf/tools/build/Makefile.build:139: util] Error 2 make[2]: *** [Makefile.perf:665: /tmp/build/perf/perf-in.o] Error 2 make[2]: *** Waiting for unfinished jobs.... make[1]: *** [Makefile.perf:240: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/var/home/acme/git/perf/tools/perf' Performance counter stats for 'make -k BUILD_BPF_SKEL=1 CORESIGHT=1 PYTHON=python3 O=/tmp/build/perf -C tools/perf install-bin': 163,635,422,196 cycles:u 213,602,262,800 instructions:u # 1.31 insn per cycle 3.804738555 seconds time elapsed 40.622581000 seconds user 6.589980000 seconds sys ⬢[acme@toolbox perf]$ git log --oneline -1 dfe103e757aeff79 (HEAD) perf cpumap: Remove cpu_map__cpu, use libperf function. This is the first breakage, trying to fix now. > --- > tools/perf/builtin-ftrace.c | 2 +- > tools/perf/util/cpumap.c | 9 ++------- > tools/perf/util/cpumap.h | 1 - > 3 files changed, 3 insertions(+), 9 deletions(-) > > diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c > index 2b54e2ddc80a..f16c39a37a52 100644 > --- a/tools/perf/builtin-ftrace.c > +++ b/tools/perf/builtin-ftrace.c > @@ -281,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap) > int ret; > int last_cpu; > > - last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); > + last_cpu = perf_cpu_map__cpu(cpumap, cpumap->nr - 1); > mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ > mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ > > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > index e0d7f1da5858..32f9fc2dd389 100644 > --- a/tools/perf/util/cpumap.c > +++ b/tools/perf/util/cpumap.c > @@ -485,11 +485,6 @@ bool cpu_map__has(struct perf_cpu_map *cpus, int cpu) > return perf_cpu_map__idx(cpus, cpu) != -1; > } > > -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx) > -{ > - return cpus->map[idx]; > -} > - > size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) > { > int i, cpu, start = -1; > @@ -547,7 +542,7 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) > int i, cpu; > char *ptr = buf; > unsigned char *bitmap; > - int last_cpu = cpu_map__cpu(map, map->nr - 1); > + int last_cpu = perf_cpu_map__cpu(map, map->nr - 1); > > if (buf == NULL) > return 0; > @@ -559,7 +554,7 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) > } > > for (i = 0; i < map->nr; i++) { > - cpu = cpu_map__cpu(map, i); > + cpu = perf_cpu_map__cpu(map, i); > bitmap[cpu / 8] |= 1 << (cpu % 8); > } > > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > index a053bf31a3f0..87545bcd461d 100644 > --- a/tools/perf/util/cpumap.h > +++ b/tools/perf/util/cpumap.h > @@ -80,7 +80,6 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > struct aggr_cpu_id (*f)(int cpu, void *data), > void *data); > > -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); > bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); > > bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b); > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

4 years, 1 month

Re: [PATCH v4 02/48] perf stat: Add aggr creators that are passed a cpu.

by Arnaldo Carvalho de Melo

Em Mon, Jan 10, 2022 at 09:36:49AM -0800, Ian Rogers escreveu: > On Mon, Jan 10, 2022 at 9:10 AM John Garry <john.garry(a)huawei.com> wrote: > > > > On 05/01/2022 06:13, Ian Rogers wrote: > > > > > > +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > > > + void *data) > > > +{ > > > + if (idx < 0 || idx > map->nr) > > > + return cpu_map__empty_aggr_cpu_id(); > > > + > > > + return cpu_map__get_socket_aggr_by_cpu(map->map[idx], data); > > > +} > > > + > > > > > > This is later deleted in the series. Can the series be reworked so that > > we don't add stuff and then later delete it? One reason for that > > approach is that we don't spend time reviewing something which will be > > deleted, especially in such a big series... > > Hi John, > > I think you are asking to squash: > https://lore.kernel.org/lkml/20220105061351.120843-8-irogers@google.com/ > into this change. There are other similar related changes that may > also be squashed. The changes are trying to introduce a new API and > then add changes to switch over to using it. This is with a view to > making bisection easier, have each change only do 1 thing and so on. I > believe the format of the patches is house style, but it is fine to > squash changes together too. Having sent patches to Arnaldo and having > had them split I'm reluctant to do a v5 with them squashed without him > expressing a preference. Right, sometimes this is needed, I'm getting the patchkit now to test build it in my containers and will go patch by patch reviewing. - Arnaldo > Thanks, > Ian > > > If it really makes sense to do it this way then fine. > > > > Thanks, > > John -- - Arnaldo

4 years, 1 month

Re: [PATCH V2 7/7] coresight: trbe: Work around the trace data corruption

by Suzuki K Poulose

On 07/01/2022 01:10, Anshuman Khandual wrote: > TRBE implementations affected by Arm erratum #1902691 might corrupt trace > data or deadlock, when it's being written into the memory. Workaround this > problem in the driver, by preventing TRBE initialization on affected cpus. > The firmware must have disabled the access to TRBE for the kernel on such > implementations. This will cover the kernel for any firmware that doesn't > do this already. This just updates the TRBE driver as required. > > Cc: Catalin Marinas <catalin.marinas(a)arm.com> > Cc: Will Deacon <will(a)kernel.org> > Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> > Cc: Suzuki Poulose <suzuki.poulose(a)arm.com> > Cc: coresight(a)lists.linaro.org > Cc: linux-doc(a)vger.kernel.org > Cc: linux-arm-kernel(a)lists.infradead.org > Cc: linux-kernel(a)vger.kernel.org > Signed-off-by: Anshuman Khandual <anshuman.khandual(a)arm.com> > --- > arch/arm64/Kconfig | 2 +- > drivers/hwtracing/coresight/coresight-trbe.c | 12 ++++++++++++ > 2 files changed, 13 insertions(+), 1 deletion(-) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 209e481acf0d..8a2245c3e857 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -821,7 +821,7 @@ config ARM64_ERRATUM_2038923 > > config ARM64_ERRATUM_1902691 > bool "Cortex-A510: 1902691: workaround TRBE trace corruption" > - depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in > + depends on CORESIGHT_TRBE > default y > help > This option adds the workaround for ARM Cortex-A510 erratum 1902691. > diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c > index c4cc529749f8..d2f1c68e589c 100644 > --- a/drivers/hwtracing/coresight/coresight-trbe.c > +++ b/drivers/hwtracing/coresight/coresight-trbe.c > @@ -93,12 +93,14 @@ struct trbe_buf { > #define TRBE_WORKAROUND_WRITE_OUT_OF_RANGE 1 > #define TRBE_NEEDS_DRAIN_AFTER_DISABLE 2 > #define TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE 3 > +#define TRBE_IS_BROKEN 4 > > static int trbe_errata_cpucaps[] = { > [TRBE_WORKAROUND_OVERWRITE_FILL_MODE] = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE, > [TRBE_WORKAROUND_WRITE_OUT_OF_RANGE] = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE, > [TRBE_NEEDS_DRAIN_AFTER_DISABLE] = ARM64_WORKAROUND_2064142, > [TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE] = ARM64_WORKAROUND_2038923, > + [TRBE_IS_BROKEN] = ARM64_WORKAROUND_1902691, > -1, /* Sentinel, must be the last entry */ > }; > > @@ -181,6 +183,11 @@ static inline bool trbe_needs_ctxt_sync_after_enable(struct trbe_cpudata *cpudat > return trbe_has_erratum(cpudata, TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE); > } > > +static inline bool trbe_is_broken(struct trbe_cpudata *cpudata) > +{ > + return trbe_has_erratum(cpudata, TRBE_IS_BROKEN); > +} > + > static int trbe_alloc_node(struct perf_event *event) > { > if (event->cpu == -1) > @@ -1288,6 +1295,11 @@ static void arm_trbe_probe_cpu(void *info) > */ > trbe_check_errata(cpudata); > > + if (trbe_is_broken(cpudata)) { > + pr_err("Disabling TRBE on cpu%d due to erratum\n", cpu); > + goto cpu_clear; > + } > + > /* > * If the TRBE is affected by erratum TRBE_WORKAROUND_OVERWRITE_FILL_MODE, > * we must always program the TBRPTR_EL1, 256bytes from a page Reviewed-by: Suzuki K Poulose <suzuki.poulose(a)arm.com>

4 years, 1 month

Re: [PATCH V2 6/7] coresight: trbe: Work around the invalid prohibited states

by Suzuki K Poulose

On 07/01/2022 01:10, Anshuman Khandual wrote: > TRBE implementations affected by Arm erratum #2038923 might get TRBE into > an inconsistent view on whether trace is prohibited within the CPU. As a > result, the trace buffer or trace buffer state might be corrupted. This > happens after TRBE buffer has been enabled by setting TRBLIMITR_EL1.E, > followed by just a single context synchronization event before execution > changes from a context, in which trace is prohibited to one where it isn't, > or vice versa. In these mentioned conditions, the view of whether trace is > prohibited is inconsistent between parts of the CPU, and the trace buffer > or the trace buffer state might be corrupted. > > Work around this problem in the TRBE driver by preventing an inconsistent > view of whether the trace is prohibited or not based on TRBLIMITR_EL1.E by > immediately following a change to TRBLIMITR_EL1.E with at least one ISB > instruction before an ERET, or two ISB instructions if no ERET is to take > place. This just updates the TRBE driver as required. > > Cc: Catalin Marinas <catalin.marinas(a)arm.com> > Cc: Will Deacon <will(a)kernel.org> > Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> > Cc: Suzuki Poulose <suzuki.poulose(a)arm.com> > Cc: coresight(a)lists.linaro.org > Cc: linux-doc(a)vger.kernel.org > Cc: linux-arm-kernel(a)lists.infradead.org > Cc: linux-kernel(a)vger.kernel.org > Signed-off-by: Anshuman Khandual <anshuman.khandual(a)arm.com> > --- > arch/arm64/Kconfig | 2 +- > drivers/hwtracing/coresight/coresight-trbe.c | 48 +++++++++++++++----- > 2 files changed, 37 insertions(+), 13 deletions(-) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index b6d62672bf7d..209e481acf0d 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -798,7 +798,7 @@ config ARM64_ERRATUM_2064142 > > config ARM64_ERRATUM_2038923 > bool "Cortex-A510: 2038923: workaround TRBE corruption with enable" > - depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in > + depends on CORESIGHT_TRBE > default y > help > This option adds the workaround for ARM Cortex-A510 erratum 2038923. > diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c > index 850e9fca6847..c4cc529749f8 100644 > --- a/drivers/hwtracing/coresight/coresight-trbe.c > +++ b/drivers/hwtracing/coresight/coresight-trbe.c > @@ -92,11 +92,13 @@ struct trbe_buf { > #define TRBE_WORKAROUND_OVERWRITE_FILL_MODE 0 > #define TRBE_WORKAROUND_WRITE_OUT_OF_RANGE 1 > #define TRBE_NEEDS_DRAIN_AFTER_DISABLE 2 > +#define TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE 3 > > static int trbe_errata_cpucaps[] = { > [TRBE_WORKAROUND_OVERWRITE_FILL_MODE] = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE, > [TRBE_WORKAROUND_WRITE_OUT_OF_RANGE] = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE, > [TRBE_NEEDS_DRAIN_AFTER_DISABLE] = ARM64_WORKAROUND_2064142, > + [TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE] = ARM64_WORKAROUND_2038923, > -1, /* Sentinel, must be the last entry */ > }; > > @@ -174,6 +176,11 @@ static inline bool trbe_needs_drain_after_disable(struct trbe_cpudata *cpudata) > return trbe_has_erratum(cpudata, TRBE_NEEDS_DRAIN_AFTER_DISABLE); > } > > +static inline bool trbe_needs_ctxt_sync_after_enable(struct trbe_cpudata *cpudata) > +{ > + return trbe_has_erratum(cpudata, TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE); > +} > + > static int trbe_alloc_node(struct perf_event *event) > { > if (event->cpu == -1) > @@ -187,6 +194,28 @@ static inline void trbe_drain_buffer(void) > dsb(nsh); > } > > +static inline void set_trbe_enabled(struct trbe_cpudata *cpudata, u64 trblimitr) > +{ > + /* > + * Enable the TRBE without clearing LIMITPTR which > + * might be required for fetching the buffer limits. > + */ > + trblimitr |= TRBLIMITR_ENABLE; > + write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); > + > + /* Synchronize the TRBE enable event */ > + isb(); > + > + /* > + * Errata affected TRBE implementation will need an additional > + * context synchronization in order to prevent an inconsistent > + * TRBE prohibited region view on the CPU which could possibly > + * corrupt the TRBE buffer or the TRBE state. > + */ > + if (trbe_needs_ctxt_sync_after_enable(cpudata)) > + isb(); > +} Similar to the previous patch, we may move the comment to the function where it is defined. Either ways: Reviewed-by: Suzuki K Poulose <suzuki.poulose(a)arm.com>

4 years, 1 month

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight