CoreSight January 2022

coresight@lists.linaro.org

8 participants
47 discussions

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);

2 years, 9 months

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

2 years, 9 months

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

2 years, 9 months

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

2 years, 9 months

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>

2 years, 9 months

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>

2 years, 9 months

Re: [PATCH V2 5/7] coresight: trbe: Work around the ignored system register writes

by Suzuki K Poulose

On 07/01/2022 01:10, Anshuman Khandual wrote: > TRBE implementations affected by Arm erratum #2064142 might fail to write > into certain system registers after the TRBE has been disabled. Under some > conditions after TRBE has been disabled, writes into certain TRBE registers > TRBLIMITR_EL1, TRBPTR_EL1, TRBBASER_EL1, TRBSR_EL1 and TRBTRG_EL1 will be > ignored and not be effected. > > Work around this problem in the TRBE driver by executing TSB CSYNC and DSB > just after the trace collection has stopped and before performing a system > register write to one of the affected registers. 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 | 54 ++++++++++++++------ > drivers/hwtracing/coresight/coresight-trbe.h | 8 --- > 3 files changed, 39 insertions(+), 25 deletions(-) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index f1651cb71ef3..b6d62672bf7d 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -780,7 +780,7 @@ config ARM64_ERRATUM_2224489 > > config ARM64_ERRATUM_2064142 > bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" > - 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 2064142. > diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c > index 276862c07e32..850e9fca6847 100644 > --- a/drivers/hwtracing/coresight/coresight-trbe.c > +++ b/drivers/hwtracing/coresight/coresight-trbe.c > @@ -91,10 +91,12 @@ 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 > > 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, > -1, /* Sentinel, must be the last entry */ > }; > > @@ -167,6 +169,11 @@ static inline bool trbe_may_write_out_of_range(struct trbe_cpudata *cpudata) > return trbe_has_erratum(cpudata, TRBE_WORKAROUND_WRITE_OUT_OF_RANGE); > } > > +static inline bool trbe_needs_drain_after_disable(struct trbe_cpudata *cpudata) > +{ > + return trbe_has_erratum(cpudata, TRBE_NEEDS_DRAIN_AFTER_DISABLE); > +} > + > static int trbe_alloc_node(struct perf_event *event) > { > if (event->cpu == -1) > @@ -174,30 +181,42 @@ static int trbe_alloc_node(struct perf_event *event) > return cpu_to_node(event->cpu); > } > > -static void trbe_drain_buffer(void) > +static inline void trbe_drain_buffer(void) > { > tsb_csync(); > dsb(nsh); > } > > -static void trbe_drain_and_disable_local(void) > +static inline void set_trbe_disabled(struct trbe_cpudata *cpudata) > { > u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); > > - trbe_drain_buffer(); > - > /* > * Disable the TRBE without clearing LIMITPTR which > * might be required for fetching the buffer limits. > */ > trblimitr &= ~TRBLIMITR_ENABLE; > write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); > + > + /* > + * Errata affected TRBE implementation will need TSB CSYNC and > + * DSB in order to prevent subsequent writes into certain TRBE > + * system registers from being ignored and not effected. > + */ minor nit: This comment could be moved to the definition of the function "trbe_needs_drain_after_disable()" to make more sense. The name is implicit here indicating, why we are doing a drain. Either ways: Reviewed-by: Suzuki K Poulose <suzuki.poulose(a)arm.com>

2 years, 9 months

Re: [PATCH V2 4/7] arm64: errata: Add detection for TRBE 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. So effectively > TRBE is broken and hence cannot be used to capture trace data. This adds > a new errata ARM64_ERRATUM_1902691 in arm64 errata framework. > > 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> > --- > Documentation/arm64/silicon-errata.rst | 2 ++ > arch/arm64/Kconfig | 18 ++++++++++++++++++ > arch/arm64/kernel/cpu_errata.c | 9 +++++++++ > arch/arm64/tools/cpucaps | 1 + > 4 files changed, 30 insertions(+) Reviewed-by: Suzuki K Poulose <suzuki.poulose(a)arm.com>

2 years, 9 months

Re: [PATCH V2 3/7] arm64: errata: Add detection for TRBE 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. This adds a new errata > ARM64_ERRATUM_2038923 in arm64 errata framework. > > 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> > --- Reviewed-by: Suzuki K Poulose <suzuki.poulose(a)arm.com> > Documentation/arm64/silicon-errata.rst | 2 ++ > arch/arm64/Kconfig | 23 +++++++++++++++++++++++ > arch/arm64/kernel/cpu_errata.c | 9 +++++++++ > arch/arm64/tools/cpucaps | 1 + > 4 files changed, 35 insertions(+) > > diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst > index c9b30e6c2b6c..e0ef3e9a4b8b 100644 > --- a/Documentation/arm64/silicon-errata.rst > +++ b/Documentation/arm64/silicon-errata.rst > @@ -54,6 +54,8 @@ stable kernels. > +----------------+-----------------+-----------------+-----------------------------+ > | ARM | Cortex-A510 | #2064142 | ARM64_ERRATUM_2064142 | > +----------------+-----------------+-----------------+-----------------------------+ > +| ARM | Cortex-A510 | #2038923 | ARM64_ERRATUM_2038923 | > ++----------------+-----------------+-----------------+-----------------------------+ > | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | > +----------------+-----------------+-----------------+-----------------------------+ > | ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index e27ccfe9fa9c..188eae6ef28d 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -796,6 +796,29 @@ config ARM64_ERRATUM_2064142 > > If unsure, say Y. > > +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 > + default y > + help > + This option adds the workaround for ARM Cortex-A510 erratum 2038923. > + > + Affected Cortex-A510 core might cause 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 in the 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. > + > + If unsure, say Y. > + > config CAVIUM_ERRATUM_22375 > bool "Cavium erratum 22375, 24313" > default y > diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c > index cbb7d5a9aee7..60b0c1f1d912 100644 > --- a/arch/arm64/kernel/cpu_errata.c > +++ b/arch/arm64/kernel/cpu_errata.c > @@ -607,6 +607,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { > ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) > }, > #endif > +#ifdef CONFIG_ARM64_ERRATUM_2038923 > + { > + .desc = "ARM erratum 2038923", > + .capability = ARM64_WORKAROUND_2038923, > + > + /* Cortex-A510 r0p0 - r0p2 */ > + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) > + }, > +#endif > { > } > }; > diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps > index fca3cb329e1d..45a06d36d080 100644 > --- a/arch/arm64/tools/cpucaps > +++ b/arch/arm64/tools/cpucaps > @@ -56,6 +56,7 @@ WORKAROUND_1463225 > WORKAROUND_1508412 > WORKAROUND_1542419 > WORKAROUND_2064142 > +WORKAROUND_2038923 > WORKAROUND_TRBE_OVERWRITE_FILL_MODE > WORKAROUND_TSB_FLUSH_FAILURE > WORKAROUND_TRBE_WRITE_OUT_OF_RANGE

2 years, 9 months

Re: [PATCH V2 2/7] arm64: errata: Add detection for TRBE ignored system register writes

by Suzuki K Poulose

2 years, 9 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight January 2022