| Message ID | 1452807977-8069-24-git-send-email-mathieu.poirier@linaro.org |
|---|---|
| State | New |
| Headers | show |
On 14 January 2016 at 14:46, Mathieu Poirier <mathieu.poirier@linaro.org> wrote: > Coresight ETMs are IP blocks used to perform HW assisted tracing > on a CPU core. This patch introduce the required auxiliary API > functions allowing the perf core to interact with a tracer. > > Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> > Cc: Ingo Molnar <mingo@redhat.com> > Cc: Arnaldo Carvalho de Melo <acme@kernel.org> > Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> > --- > MAINTAINERS | 3 + > tools/perf/arch/arm/util/Build | 2 +- > tools/perf/arch/arm/util/auxtrace.c | 54 +++++ > tools/perf/arch/arm/util/cs_etm.c | 466 ++++++++++++++++++++++++++++++++++++ > tools/perf/arch/arm/util/cs_etm.h | 44 ++++ > tools/perf/util/auxtrace.c | 1 + > tools/perf/util/auxtrace.h | 1 + > 7 files changed, 570 insertions(+), 1 deletion(-) > create mode 100644 tools/perf/arch/arm/util/auxtrace.c > create mode 100644 tools/perf/arch/arm/util/cs_etm.c > create mode 100644 tools/perf/arch/arm/util/cs_etm.h > > diff --git a/MAINTAINERS b/MAINTAINERS > index b2a92245eece..a81b2737ebc3 100644 > --- a/MAINTAINERS > +++ b/MAINTAINERS > @@ -1008,6 +1008,9 @@ F: Documentation/trace/coresight.txt > F: Documentation/devicetree/bindings/arm/coresight.txt > F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* > F: tools/perf/arch/arm/util/pmu.c > +F: tools/perf/arch/arm/util/auxtrace.c > +F: tools/perf/arch/arm/util/cs_etm.c > +F: tools/perf/arch/arm/util/cs_etm.h > > ARM/CORGI MACHINE SUPPORT > M: Richard Purdie <rpurdie@rpsys.net> > diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build > index 66ab0b05549c..0a25a1248f42 100644 > --- a/tools/perf/arch/arm/util/Build > +++ b/tools/perf/arch/arm/util/Build > @@ -3,4 +3,4 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o > libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o > libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o > > -libperf-$(CONFIG_AUXTRACE) += pmu.o > +libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs_etm.o > diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c > new file mode 100644 > index 000000000000..d327316f0e8a > --- /dev/null > +++ b/tools/perf/arch/arm/util/auxtrace.c > @@ -0,0 +1,54 @@ > +/* > + * Copyright(C) 2015 Linaro Limited. All rights reserved. > + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> > + * > + * This program is free software; you can redistribute it and/or modify it > + * under the terms of the GNU General Public License version 2 as published by > + * the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, but WITHOUT > + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or > + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for > + * more details. > + * > + * You should have received a copy of the GNU General Public License along with > + * this program. If not, see <http://www.gnu.org/licenses/>. > + */ > + > +#include <stdbool.h> > +#include <linux/coresight-pmu.h> > + > +#include "../../util/auxtrace.h" > +#include "../../util/evlist.h" > +#include "../../util/pmu.h" > +#include "cs_etm.h" > + > +struct auxtrace_record > +*auxtrace_record__init(struct perf_evlist *evlist, int *err) > +{ > + struct perf_pmu *cs_etm_pmu; > + struct perf_evsel *evsel; > + bool found_etm = false; > + > + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); > + > + if (evlist) { > + evlist__for_each(evlist, evsel) { > + if (cs_etm_pmu && > + evsel->attr.type == cs_etm_pmu->type) > + found_etm = true; > + } > + } > + > + if (found_etm) > + return cs_etm_record_init(err); > + > + /* > + * Clear 'err' even if we haven't found a cs_etm event - that way perf > + * record can still be used even if tracers aren't present. The NULL > + * return value will take care of telling the infrastructure HW tracing > + * isn't available. > + */ > + *err = 0; > + return NULL; > +} > diff --git a/tools/perf/arch/arm/util/cs_etm.c b/tools/perf/arch/arm/util/cs_etm.c > new file mode 100644 > index 000000000000..5710b90e23d5 > --- /dev/null > +++ b/tools/perf/arch/arm/util/cs_etm.c > @@ -0,0 +1,466 @@ > +/* > + * Copyright(C) 2015 Linaro Limited. All rights reserved. > + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> > + * > + * This program is free software; you can redistribute it and/or modify it > + * under the terms of the GNU General Public License version 2 as published by > + * the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, but WITHOUT > + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or > + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for > + * more details. > + * > + * You should have received a copy of the GNU General Public License along with > + * this program. If not, see <http://www.gnu.org/licenses/>. > + */ > + > +#include <api/fs/fs.h> > +#include <linux/bitops.h> > +#include <linux/coresight-pmu.h> > +#include <linux/kernel.h> > +#include <linux/log2.h> > +#include <linux/types.h> > + > +#include "../../perf.h" > +#include "../../util/auxtrace.h" > +#include "../../util/cpumap.h" > +#include "../../util/evlist.h" > +#include "../../util/pmu.h" > +#include "../../util/thread_map.h" > +#include "cs_etm.h" > + > +#include <stdlib.h> > + > +#define KiB(x) ((x) * 1024) > +#define MiB(x) ((x) * 1024 * 1024) > + > +struct cs_etm_recording { > + struct auxtrace_record itr; > + struct perf_pmu *cs_etm_pmu; > + struct perf_evlist *evlist; > + bool snapshot_mode; > + size_t snapshot_size; > +}; > + > +static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, > + struct record_opts *opts, > + const char *str) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + unsigned long long snapshot_size = 0; > + char *endptr; > + > + if (str) { > + snapshot_size = strtoull(str, &endptr, 0); > + if (*endptr || snapshot_size > SIZE_MAX) > + return -1; > + } > + > + opts->auxtrace_snapshot_mode = true; > + opts->auxtrace_snapshot_size = snapshot_size; > + ptr->snapshot_size = snapshot_size; > + > + return 0; > +} > + > +static int cs_etm_recording_options(struct auxtrace_record *itr, > + struct perf_evlist *evlist, > + struct record_opts *opts) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; > + struct perf_evsel *evsel, *cs_etm_evsel = NULL; > + const struct cpu_map *cpus = evlist->cpus; > + bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); > + > + ptr->evlist = evlist; > + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; > + > + evlist__for_each(evlist, evsel) { > + if (evsel->attr.type == cs_etm_pmu->type) { > + if (cs_etm_evsel) { > + pr_err("There may be only one %s event\n", > + CORESIGHT_ETM_PMU_NAME); > + return -EINVAL; > + } > + evsel->attr.freq = 0; > + evsel->attr.sample_period = 1; > + cs_etm_evsel = evsel; > + opts->full_auxtrace = true; > + } > + } > + > + /* no need to continue if at least one event of interest was found */ > + if (!cs_etm_evsel) > + return 0; > + > + if (opts->use_clockid) { > + pr_err("Cannot use clockid (-k option) with %s\n", > + CORESIGHT_ETM_PMU_NAME); > + return -EINVAL; > + } > + > + /* we are in snapshot mode */ > + if (opts->auxtrace_snapshot_mode) { > + /* > + * No size were given to '-S' or '-m,', so go with > + * the default > + */ > + if (!opts->auxtrace_snapshot_size && > + !opts->auxtrace_mmap_pages) { > + if (privileged) { > + opts->auxtrace_mmap_pages = MiB(4) / page_size; > + } else { > + opts->auxtrace_mmap_pages = > + KiB(128) / page_size; > + if (opts->mmap_pages == UINT_MAX) > + opts->mmap_pages = KiB(256) / page_size; > + } > + } else if (!opts->auxtrace_mmap_pages && !privileged && > + opts->mmap_pages == UINT_MAX) { > + opts->mmap_pages = KiB(256) / page_size; > + } > + > + /* > + * '-m,xyz' was specified but no snapshot size, so make the > + * snapshot size as big as the auxtrace mmap area. > + */ > + if (!opts->auxtrace_snapshot_size) { > + opts->auxtrace_snapshot_size = > + opts->auxtrace_mmap_pages * (size_t)page_size; > + } > + > + /* > + * -Sxyz was specified but no auxtrace mmap area, so make the > + * auxtrace mmap area big enough to fit the requested snapshot > + * size. > + */ > + if (!opts->auxtrace_mmap_pages) { > + size_t sz = opts->auxtrace_snapshot_size; > + > + sz = round_up(sz, page_size) / page_size; > + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); > + } > + > + /* Snapshost size can't be bigger than the auxtrace area */ > + if (opts->auxtrace_snapshot_size > > + opts->auxtrace_mmap_pages * (size_t)page_size) { > + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", > + opts->auxtrace_snapshot_size, > + opts->auxtrace_mmap_pages * (size_t)page_size); > + return -EINVAL; > + } > + > + /* Something went wrong somewhere - this shouldn't happen */ > + if (!opts->auxtrace_snapshot_size || > + !opts->auxtrace_mmap_pages) { > + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); > + return -EINVAL; > + } > + } > + > + /* We are in full trace mode but '-m,xyz' wasn't specified */ > + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { > + if (privileged) { > + opts->auxtrace_mmap_pages = MiB(4) / page_size; > + } else { > + opts->auxtrace_mmap_pages = KiB(128) / page_size; > + if (opts->mmap_pages == UINT_MAX) > + opts->mmap_pages = KiB(256) / page_size; > + } > + > + } > + > + /* Validate auxtrace_mmap_pages provided by user */ > + if (opts->auxtrace_mmap_pages) { > + unsigned int max_page = (KiB(128) / page_size); > + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; > + > + if (!privileged && > + opts->auxtrace_mmap_pages > max_page) { > + opts->auxtrace_mmap_pages = max_page; > + pr_err("auxtrace too big, truncating to %d\n", > + max_page); > + } > + > + if (!is_power_of_2(sz)) { > + pr_err("Invalid mmap size for %s: must be a power of 2\n", > + CORESIGHT_ETM_PMU_NAME); > + return -EINVAL; > + } > + } > + > + if (opts->auxtrace_snapshot_mode) > + pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, > + opts->auxtrace_snapshot_size); > + > + if (cs_etm_evsel) { > + /* > + * To obtain the auxtrace buffer file descriptor, the auxtrace > + * event must come first. > + */ > + perf_evlist__to_front(evlist, cs_etm_evsel); > + /* > + * In the case of per-cpu mmaps, we need the CPU on the > + * AUX event. > + */ > + if (!cpu_map__empty(cpus)) > + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); > + } > + > + /* Add dummy event to keep tracking */ > + if (opts->full_auxtrace) { > + struct perf_evsel *tracking_evsel; > + int err; > + > + err = parse_events(evlist, "dummy:u", NULL); > + if (err) > + return err; > + > + tracking_evsel = perf_evlist__last(evlist); > + perf_evlist__set_tracking_event(evlist, tracking_evsel); > + > + tracking_evsel->attr.freq = 0; > + tracking_evsel->attr.sample_period = 1; > + > + /* In per-cpu case, always need the time of mmap events etc */ > + if (!cpu_map__empty(cpus)) > + perf_evsel__set_sample_bit(tracking_evsel, TIME); > + } > + > + return 0; > +} > + > +static u64 cs_etm_get_config(struct auxtrace_record *itr) > +{ > + u64 config = 0; > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; > + struct perf_evlist *evlist = ptr->evlist; > + struct perf_evsel *evsel; > + > + evlist__for_each(evlist, evsel) { > + if (evsel->attr.type == cs_etm_pmu->type) { > + /* > + * Variable perf_event_attr::config is assigned to > + * ETMv3/PTM. The bit fields have been made to match > + * the ETMv3.5 ETRMCR register specification. See the > + * PMU_FORMAT_ATTR() declarations in > + * drivers/hwtracing/coresight/coresight-perf.c for > + * details. > + */ > + config = evsel->attr.config; > + break; > + } > + } > + > + return config; > +} > + > +static size_t > +cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, > + struct perf_evlist *evlist __maybe_unused) > +{ > + int records; > + const struct cpu_map *cpus = evlist->cpus; > + > + if (!cpu_map__empty(cpus)) { > + records = cpu_map__nr(cpus); > + goto out; > + } > + > + set_max_cpu_num(); > + records = cpu__max_cpu(); > +out: > + return records * CS_ETM_PRIV_SIZE; > +} > + > +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { > + [CS_ETM_ETMCCER] = "mgmt/etmccer", > + [CS_ETM_ETMIDR] = "mgmt/etmidr", > +}; > + > +static int cs_etm_get_metadata(int cpu, int index, > + struct auxtrace_record *itr, > + struct auxtrace_info_event *info) > +{ > + char path[PATH_MAX]; > + int offset = 0, ret = 0; > + int i, scan; > + unsigned int val; > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; > + > + offset = index * CS_ETM_PRIV_MAX; > + > + /* Build generic header portion */ > + info->priv[offset + CS_ETM_MAGIC] = __perf_cs_etm_magic; > + info->priv[offset + CS_ETM_CPU] = cpu; > + info->priv[offset + CS_ETM_SNAPSHOT] = ptr->snapshot_mode; > + > + /* Get user configurables from the session */ > + info->priv[offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); > + info->priv[offset + CS_ETM_ETMTRACEIDR] = coresight_get_trace_id(cpu); > + > + /* Get RO metadata from sysfs */ > + for (i = CS_ETM_ETMCCER; i < CS_ETM_PRIV_MAX; i++) { > + snprintf(path, PATH_MAX, "cpu%d/%s", cpu, metadata_etmv3_ro[i]); > + > + scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); > + if (scan != 1) { > + ret = -EINVAL; > + break; > + } > + > + info->priv[offset + i] = val; > + } > + > + return ret; > +} > + > +static int cs_etm_info_fill(struct auxtrace_record *itr, > + struct perf_session *session, > + struct auxtrace_info_event *auxtrace_info, > + size_t priv_size) > +{ > + int i, nr_cpu, ret = 0; > + const struct cpu_map *cpus = session->evlist->cpus; > + > + if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) > + return -EINVAL; > + > + if (!session->evlist->nr_mmaps) > + return -EINVAL; > + > + auxtrace_info->type = PERF_AUXTRACE_CS_ETM; > + > + /* cpu map is not empty, we have specific CPUs to work with */ > + if (!cpu_map__empty(cpus)) { > + for (i = 0; i < cpu_map__nr(cpus); i++) { > + ret = cs_etm_get_metadata(cpus->map[i], i, > + itr, auxtrace_info); > + if (ret) > + goto out; > + } > + } else { > + /* get configuration for all CPUs in the system */ > + nr_cpu = cpu__max_cpu(); > + for (i = 0; i < nr_cpu; i++) { > + ret = cs_etm_get_metadata(i, i, itr, auxtrace_info); > + if (ret) > + goto out; > + } > + } > + > +out: > + return ret; > +} > + > +static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, > + int idx, struct auxtrace_mmap *mm, > + unsigned char *data __maybe_unused, > + u64 *head, u64 *old) > +{ > + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", > + __func__, idx, (size_t)*old, (size_t)*head, mm->len); > + > + *old = *head; > + *head += mm->len; > + > + return 0; > +} > + > +static int cs_etm_snapshot_start(struct auxtrace_record *itr) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_evsel *evsel; > + > + evlist__for_each(ptr->evlist, evsel) { > + if (evsel->attr.type == ptr->cs_etm_pmu->type) > + return perf_evlist__disable_event(ptr->evlist, evsel); > + } > + return -EINVAL; > +} > + > +static int cs_etm_snapshot_finish(struct auxtrace_record *itr) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_evsel *evsel; > + > + evlist__for_each(ptr->evlist, evsel) { > + if (evsel->attr.type == ptr->cs_etm_pmu->type) > + return perf_evlist__enable_event(ptr->evlist, evsel); > + } > + return -EINVAL; > +} > + > +static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused) > +{ > + return (((u64) rand() << 0) & 0x00000000FFFFFFFFull) | > + (((u64) rand() << 32) & 0xFFFFFFFF00000000ull); > +} > + > +static void cs_etm_recording_free(struct auxtrace_record *itr) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + free(ptr); > +} > + > +static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) > +{ > + struct cs_etm_recording *ptr = > + container_of(itr, struct cs_etm_recording, itr); > + struct perf_evsel *evsel; > + > + evlist__for_each(ptr->evlist, evsel) { > + if (evsel->attr.type == ptr->cs_etm_pmu->type) > + return perf_evlist__enable_event_idx(ptr->evlist, > + evsel, idx); > + } > + > + return -EINVAL; > +} > + > +struct auxtrace_record *cs_etm_record_init(int *err) > +{ > + struct perf_pmu *cs_etm_pmu; > + struct cs_etm_recording *ptr; > + > + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); > + > + if (!cs_etm_pmu) { > + *err = -EINVAL; > + goto out; > + } > + > + ptr = zalloc(sizeof(struct cs_etm_recording)); > + if (!ptr) { > + *err = -ENOMEM; > + goto out; > + } > + > + ptr->cs_etm_pmu = cs_etm_pmu; > + ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; > + ptr->itr.recording_options = cs_etm_recording_options; > + ptr->itr.info_priv_size = cs_etm_info_priv_size; > + ptr->itr.info_fill = cs_etm_info_fill; > + ptr->itr.find_snapshot = cs_etm_find_snapshot; > + ptr->itr.snapshot_start = cs_etm_snapshot_start; > + ptr->itr.snapshot_finish = cs_etm_snapshot_finish; > + ptr->itr.reference = cs_etm_reference; > + ptr->itr.free = cs_etm_recording_free; > + ptr->itr.read_finish = cs_etm_read_finish; > + > + *err = 0; > + return &ptr->itr; > +out: > + return NULL; > +} > diff --git a/tools/perf/arch/arm/util/cs_etm.h b/tools/perf/arch/arm/util/cs_etm.h > new file mode 100644 > index 000000000000..7e85c1b43598 > --- /dev/null > +++ b/tools/perf/arch/arm/util/cs_etm.h > @@ -0,0 +1,44 @@ > +/* > + * Copyright(C) 2015 Linaro Limited. All rights reserved. > + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> > + * > + * This program is free software; you can redistribute it and/or modify it > + * under the terms of the GNU General Public License version 2 as published by > + * the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, but WITHOUT > + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or > + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for > + * more details. > + * > + * You should have received a copy of the GNU General Public License along with > + * this program. If not, see <http://www.gnu.org/licenses/>. > + */ > + > +#ifndef INCLUDE__PERF_CS_ETM_H__ > +#define INCLUDE__PERF_CS_ETM_H__ > + > +/* Beginning of header common to both ETMv3 and V4 */ > +enum { > + CS_ETM_MAGIC, > + CS_ETM_CPU, > + CS_ETM_SNAPSHOT, > +}; > + > +/* ETMv3/PTM metadata */ > +enum { > + /* Dynamic, configurable parameters */ > + CS_ETM_ETMCR = CS_ETM_SNAPSHOT + 1, > + CS_ETM_ETMTRACEIDR, > + /* RO, taken from sysFS */ > + CS_ETM_ETMCCER, > + CS_ETM_ETMIDR, > + CS_ETM_PRIV_MAX, > +}; > + > +static const u64 __perf_cs_etm_magic = 0x3030303030303030ULL; > +#define CS_ETM_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64)) > + > +struct auxtrace_record *cs_etm_record_init(int *err); > + > +#endif > diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c > index cc1c9ce5cc56..a6f291dbc4d9 100644 > --- a/tools/perf/util/auxtrace.c > +++ b/tools/perf/util/auxtrace.c > @@ -892,6 +892,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, > return intel_pt_process_auxtrace_info(event, session); > case PERF_AUXTRACE_INTEL_BTS: > return intel_bts_process_auxtrace_info(event, session); > + case PERF_AUXTRACE_CS_ETM: > case PERF_AUXTRACE_UNKNOWN: > default: > return -EINVAL; > diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h > index e5a8e2d4f2af..adb53e7bcabf 100644 > --- a/tools/perf/util/auxtrace.h > +++ b/tools/perf/util/auxtrace.h > @@ -41,6 +41,7 @@ enum auxtrace_type { > PERF_AUXTRACE_UNKNOWN, > PERF_AUXTRACE_INTEL_PT, > PERF_AUXTRACE_INTEL_BTS, > + PERF_AUXTRACE_CS_ETM, > }; > > enum itrace_period_type { > -- > 2.1.4 > Arnaldo, Last but not least, this is the final patch that I would like you to review before queing. It has been rebased to 4.5-rc1 here [1] for your convenience. I will be happy to use another baseline should that be more adequate for you. Thanks, Mathieu [1]. https://git.linaro.org/people/mathieu.poirier/coresight.git/shortlog/refs/heads/perf-v4.5-rc1-V8
On 29 January 2016 at 03:34, Adrian Hunter <adrian.hunter@intel.com> wrote: > On 25/01/16 23:10, Arnaldo Carvalho de Melo wrote: >> Em Mon, Jan 25, 2016 at 01:51:18PM -0700, Mathieu Poirier escreveu: >>> On 14 January 2016 at 14:46, Mathieu Poirier <mathieu.poirier@linaro.org> wrote: >>>> Coresight ETMs are IP blocks used to perform HW assisted tracing >>>> on a CPU core. This patch introduce the required auxiliary API >>>> functions allowing the perf core to interact with a tracer. >>>> >>>> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> >>>> Cc: Ingo Molnar <mingo@redhat.com> >>>> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> >>>> Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> >>>> --- >>>> MAINTAINERS | 3 + >>>> tools/perf/arch/arm/util/Build | 2 +- >>>> tools/perf/arch/arm/util/auxtrace.c | 54 +++++ >>>> tools/perf/arch/arm/util/cs_etm.c | 466 ++++++++++++++++++++++++++++++++++++ >>>> tools/perf/arch/arm/util/cs_etm.h | 44 ++++ >>>> tools/perf/util/auxtrace.c | 1 + >>>> tools/perf/util/auxtrace.h | 1 + >>>> 7 files changed, 570 insertions(+), 1 deletion(-) >>>> create mode 100644 tools/perf/arch/arm/util/auxtrace.c >>>> create mode 100644 tools/perf/arch/arm/util/cs_etm.c >>>> create mode 100644 tools/perf/arch/arm/util/cs_etm.h >>>> >>>> diff --git a/MAINTAINERS b/MAINTAINERS >>>> index b2a92245eece..a81b2737ebc3 100644 >>>> --- a/MAINTAINERS >>>> +++ b/MAINTAINERS >>>> @@ -1008,6 +1008,9 @@ F: Documentation/trace/coresight.txt >>>> F: Documentation/devicetree/bindings/arm/coresight.txt >>>> F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* >>>> F: tools/perf/arch/arm/util/pmu.c >>>> +F: tools/perf/arch/arm/util/auxtrace.c >>>> +F: tools/perf/arch/arm/util/cs_etm.c >>>> +F: tools/perf/arch/arm/util/cs_etm.h >>>> >>>> ARM/CORGI MACHINE SUPPORT >>>> M: Richard Purdie <rpurdie@rpsys.net> >>>> diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build >>>> index 66ab0b05549c..0a25a1248f42 100644 >>>> --- a/tools/perf/arch/arm/util/Build >>>> +++ b/tools/perf/arch/arm/util/Build >>>> @@ -3,4 +3,4 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o >>>> libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o >>>> libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o >>>> >>>> -libperf-$(CONFIG_AUXTRACE) += pmu.o >>>> +libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs_etm.o >>>> diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c >>>> new file mode 100644 >>>> index 000000000000..d327316f0e8a >>>> --- /dev/null >>>> +++ b/tools/perf/arch/arm/util/auxtrace.c >>>> @@ -0,0 +1,54 @@ >>>> +/* >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >>>> + * >>>> + * This program is free software; you can redistribute it and/or modify it >>>> + * under the terms of the GNU General Public License version 2 as published by >>>> + * the Free Software Foundation. >>>> + * >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >>>> + * more details. >>>> + * >>>> + * You should have received a copy of the GNU General Public License along with >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >>>> + */ >>>> + >>>> +#include <stdbool.h> >>>> +#include <linux/coresight-pmu.h> >>>> + >>>> +#include "../../util/auxtrace.h" >>>> +#include "../../util/evlist.h" >>>> +#include "../../util/pmu.h" >>>> +#include "cs_etm.h" >>>> + >>>> +struct auxtrace_record >>>> +*auxtrace_record__init(struct perf_evlist *evlist, int *err) >>>> +{ >>>> + struct perf_pmu *cs_etm_pmu; >>>> + struct perf_evsel *evsel; >>>> + bool found_etm = false; >>>> + >>>> + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); >>>> + >>>> + if (evlist) { >>>> + evlist__for_each(evlist, evsel) { >>>> + if (cs_etm_pmu && >>>> + evsel->attr.type == cs_etm_pmu->type) >>>> + found_etm = true; >>>> + } >>>> + } >>>> + >>>> + if (found_etm) >>>> + return cs_etm_record_init(err); >>>> + >>>> + /* >>>> + * Clear 'err' even if we haven't found a cs_etm event - that way perf >>>> + * record can still be used even if tracers aren't present. The NULL >>>> + * return value will take care of telling the infrastructure HW tracing >>>> + * isn't available. >>>> + */ >>>> + *err = 0; >>>> + return NULL; >>>> +} >>>> diff --git a/tools/perf/arch/arm/util/cs_etm.c b/tools/perf/arch/arm/util/cs_etm.c >>>> new file mode 100644 >>>> index 000000000000..5710b90e23d5 >>>> --- /dev/null >>>> +++ b/tools/perf/arch/arm/util/cs_etm.c >>>> @@ -0,0 +1,466 @@ >>>> +/* >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >>>> + * >>>> + * This program is free software; you can redistribute it and/or modify it >>>> + * under the terms of the GNU General Public License version 2 as published by >>>> + * the Free Software Foundation. >>>> + * >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >>>> + * more details. >>>> + * >>>> + * You should have received a copy of the GNU General Public License along with >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >>>> + */ >>>> + >>>> +#include <api/fs/fs.h> >>>> +#include <linux/bitops.h> >>>> +#include <linux/coresight-pmu.h> >>>> +#include <linux/kernel.h> >>>> +#include <linux/log2.h> >>>> +#include <linux/types.h> >>>> + >>>> +#include "../../perf.h" >>>> +#include "../../util/auxtrace.h" >>>> +#include "../../util/cpumap.h" >>>> +#include "../../util/evlist.h" >>>> +#include "../../util/pmu.h" >>>> +#include "../../util/thread_map.h" >>>> +#include "cs_etm.h" >>>> + >>>> +#include <stdlib.h> >>>> + >>>> +#define KiB(x) ((x) * 1024) >>>> +#define MiB(x) ((x) * 1024 * 1024) >>>> + >>>> +struct cs_etm_recording { >>>> + struct auxtrace_record itr; >>>> + struct perf_pmu *cs_etm_pmu; >>>> + struct perf_evlist *evlist; >>>> + bool snapshot_mode; >>>> + size_t snapshot_size; >>>> +}; >>>> + >>>> +static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, >>>> + struct record_opts *opts, >>>> + const char *str) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + unsigned long long snapshot_size = 0; >>>> + char *endptr; >>>> + >>>> + if (str) { >>>> + snapshot_size = strtoull(str, &endptr, 0); >>>> + if (*endptr || snapshot_size > SIZE_MAX) >>>> + return -1; >>>> + } >>>> + >>>> + opts->auxtrace_snapshot_mode = true; >>>> + opts->auxtrace_snapshot_size = snapshot_size; >>>> + ptr->snapshot_size = snapshot_size; >>>> + >>>> + return 0; >>>> +} >>>> + >>>> +static int cs_etm_recording_options(struct auxtrace_record *itr, >>>> + struct perf_evlist *evlist, >>>> + struct record_opts *opts) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >>>> + struct perf_evsel *evsel, *cs_etm_evsel = NULL; >>>> + const struct cpu_map *cpus = evlist->cpus; >>>> + bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); >>>> + >>>> + ptr->evlist = evlist; >>>> + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; >>>> + >>>> + evlist__for_each(evlist, evsel) { >>>> + if (evsel->attr.type == cs_etm_pmu->type) { >>>> + if (cs_etm_evsel) { >>>> + pr_err("There may be only one %s event\n", >>>> + CORESIGHT_ETM_PMU_NAME); >>>> + return -EINVAL; >>>> + } >>>> + evsel->attr.freq = 0; >>>> + evsel->attr.sample_period = 1; >>>> + cs_etm_evsel = evsel; >>>> + opts->full_auxtrace = true; >>>> + } >>>> + } >>>> + >>>> + /* no need to continue if at least one event of interest was found */ >>>> + if (!cs_etm_evsel) >>>> + return 0; >>>> + >>>> + if (opts->use_clockid) { >>>> + pr_err("Cannot use clockid (-k option) with %s\n", >>>> + CORESIGHT_ETM_PMU_NAME); >>>> + return -EINVAL; >>>> + } >>>> + >>>> + /* we are in snapshot mode */ >>>> + if (opts->auxtrace_snapshot_mode) { >>>> + /* >>>> + * No size were given to '-S' or '-m,', so go with >>>> + * the default >>>> + */ >>>> + if (!opts->auxtrace_snapshot_size && >>>> + !opts->auxtrace_mmap_pages) { >>>> + if (privileged) { >>>> + opts->auxtrace_mmap_pages = MiB(4) / page_size; >>>> + } else { >>>> + opts->auxtrace_mmap_pages = >>>> + KiB(128) / page_size; >>>> + if (opts->mmap_pages == UINT_MAX) >>>> + opts->mmap_pages = KiB(256) / page_size; >>>> + } >>>> + } else if (!opts->auxtrace_mmap_pages && !privileged && >>>> + opts->mmap_pages == UINT_MAX) { >>>> + opts->mmap_pages = KiB(256) / page_size; >>>> + } >>>> + >>>> + /* >>>> + * '-m,xyz' was specified but no snapshot size, so make the >>>> + * snapshot size as big as the auxtrace mmap area. >>>> + */ >>>> + if (!opts->auxtrace_snapshot_size) { >>>> + opts->auxtrace_snapshot_size = >>>> + opts->auxtrace_mmap_pages * (size_t)page_size; >>>> + } >>>> + >>>> + /* >>>> + * -Sxyz was specified but no auxtrace mmap area, so make the >>>> + * auxtrace mmap area big enough to fit the requested snapshot >>>> + * size. >>>> + */ >>>> + if (!opts->auxtrace_mmap_pages) { >>>> + size_t sz = opts->auxtrace_snapshot_size; >>>> + >>>> + sz = round_up(sz, page_size) / page_size; >>>> + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); >>>> + } >>>> + >>>> + /* Snapshost size can't be bigger than the auxtrace area */ >>>> + if (opts->auxtrace_snapshot_size > >>>> + opts->auxtrace_mmap_pages * (size_t)page_size) { >>>> + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", >>>> + opts->auxtrace_snapshot_size, >>>> + opts->auxtrace_mmap_pages * (size_t)page_size); >>>> + return -EINVAL; >>>> + } >>>> + >>>> + /* Something went wrong somewhere - this shouldn't happen */ >>>> + if (!opts->auxtrace_snapshot_size || >>>> + !opts->auxtrace_mmap_pages) { >>>> + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); >>>> + return -EINVAL; >>>> + } >>>> + } >>>> + >>>> + /* We are in full trace mode but '-m,xyz' wasn't specified */ >>>> + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { >>>> + if (privileged) { >>>> + opts->auxtrace_mmap_pages = MiB(4) / page_size; >>>> + } else { >>>> + opts->auxtrace_mmap_pages = KiB(128) / page_size; >>>> + if (opts->mmap_pages == UINT_MAX) >>>> + opts->mmap_pages = KiB(256) / page_size; >>>> + } >>>> + >>>> + } >>>> + >>>> + /* Validate auxtrace_mmap_pages provided by user */ >>>> + if (opts->auxtrace_mmap_pages) { >>>> + unsigned int max_page = (KiB(128) / page_size); >>>> + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; >>>> + >>>> + if (!privileged && >>>> + opts->auxtrace_mmap_pages > max_page) { >>>> + opts->auxtrace_mmap_pages = max_page; >>>> + pr_err("auxtrace too big, truncating to %d\n", >>>> + max_page); >>>> + } >>>> + >>>> + if (!is_power_of_2(sz)) { >>>> + pr_err("Invalid mmap size for %s: must be a power of 2\n", >>>> + CORESIGHT_ETM_PMU_NAME); >>>> + return -EINVAL; >>>> + } >>>> + } >>>> + >>>> + if (opts->auxtrace_snapshot_mode) >>>> + pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, >>>> + opts->auxtrace_snapshot_size); >>>> + >>>> + if (cs_etm_evsel) { >>>> + /* >>>> + * To obtain the auxtrace buffer file descriptor, the auxtrace >>>> + * event must come first. >>>> + */ >>>> + perf_evlist__to_front(evlist, cs_etm_evsel); >>>> + /* >>>> + * In the case of per-cpu mmaps, we need the CPU on the >>>> + * AUX event. >>>> + */ >>>> + if (!cpu_map__empty(cpus)) >>>> + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); >>>> + } >>>> + >>>> + /* Add dummy event to keep tracking */ >>>> + if (opts->full_auxtrace) { >>>> + struct perf_evsel *tracking_evsel; >>>> + int err; >>>> + >>>> + err = parse_events(evlist, "dummy:u", NULL); >>>> + if (err) >>>> + return err; >>>> + >>>> + tracking_evsel = perf_evlist__last(evlist); >>>> + perf_evlist__set_tracking_event(evlist, tracking_evsel); >>>> + >>>> + tracking_evsel->attr.freq = 0; >>>> + tracking_evsel->attr.sample_period = 1; >>>> + >>>> + /* In per-cpu case, always need the time of mmap events etc */ >>>> + if (!cpu_map__empty(cpus)) >>>> + perf_evsel__set_sample_bit(tracking_evsel, TIME); >>>> + } >>>> + >>>> + return 0; >>>> +} >>>> + >>>> +static u64 cs_etm_get_config(struct auxtrace_record *itr) >>>> +{ >>>> + u64 config = 0; >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >>>> + struct perf_evlist *evlist = ptr->evlist; >>>> + struct perf_evsel *evsel; >>>> + >>>> + evlist__for_each(evlist, evsel) { >>>> + if (evsel->attr.type == cs_etm_pmu->type) { >>>> + /* >>>> + * Variable perf_event_attr::config is assigned to >>>> + * ETMv3/PTM. The bit fields have been made to match >>>> + * the ETMv3.5 ETRMCR register specification. See the >>>> + * PMU_FORMAT_ATTR() declarations in >>>> + * drivers/hwtracing/coresight/coresight-perf.c for >>>> + * details. >>>> + */ >>>> + config = evsel->attr.config; >>>> + break; >>>> + } >>>> + } >>>> + >>>> + return config; >>>> +} >>>> + >>>> +static size_t >>>> +cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, >>>> + struct perf_evlist *evlist __maybe_unused) >>>> +{ >>>> + int records; >>>> + const struct cpu_map *cpus = evlist->cpus; >>>> + >>>> + if (!cpu_map__empty(cpus)) { >>>> + records = cpu_map__nr(cpus); >>>> + goto out; >>>> + } >>>> + >>>> + set_max_cpu_num(); >>>> + records = cpu__max_cpu(); >>>> +out: >>>> + return records * CS_ETM_PRIV_SIZE; >>>> +} >>>> + >>>> +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { >>>> + [CS_ETM_ETMCCER] = "mgmt/etmccer", >>>> + [CS_ETM_ETMIDR] = "mgmt/etmidr", >>>> +}; >>>> + >>>> +static int cs_etm_get_metadata(int cpu, int index, >>>> + struct auxtrace_record *itr, >>>> + struct auxtrace_info_event *info) >>>> +{ >>>> + char path[PATH_MAX]; >>>> + int offset = 0, ret = 0; >>>> + int i, scan; >>>> + unsigned int val; >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >>>> + >>>> + offset = index * CS_ETM_PRIV_MAX; >>>> + >>>> + /* Build generic header portion */ >>>> + info->priv[offset + CS_ETM_MAGIC] = __perf_cs_etm_magic; >>>> + info->priv[offset + CS_ETM_CPU] = cpu; >>>> + info->priv[offset + CS_ETM_SNAPSHOT] = ptr->snapshot_mode; >>>> + >>>> + /* Get user configurables from the session */ >>>> + info->priv[offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); >>>> + info->priv[offset + CS_ETM_ETMTRACEIDR] = coresight_get_trace_id(cpu); >>>> + >>>> + /* Get RO metadata from sysfs */ >>>> + for (i = CS_ETM_ETMCCER; i < CS_ETM_PRIV_MAX; i++) { >>>> + snprintf(path, PATH_MAX, "cpu%d/%s", cpu, metadata_etmv3_ro[i]); >>>> + >>>> + scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); >>>> + if (scan != 1) { >>>> + ret = -EINVAL; >>>> + break; >>>> + } >>>> + >>>> + info->priv[offset + i] = val; >>>> + } >>>> + >>>> + return ret; >>>> +} >>>> + >>>> +static int cs_etm_info_fill(struct auxtrace_record *itr, >>>> + struct perf_session *session, >>>> + struct auxtrace_info_event *auxtrace_info, >>>> + size_t priv_size) >>>> +{ >>>> + int i, nr_cpu, ret = 0; >>>> + const struct cpu_map *cpus = session->evlist->cpus; >>>> + >>>> + if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) >>>> + return -EINVAL; >>>> + >>>> + if (!session->evlist->nr_mmaps) >>>> + return -EINVAL; >>>> + >>>> + auxtrace_info->type = PERF_AUXTRACE_CS_ETM; >>>> + >>>> + /* cpu map is not empty, we have specific CPUs to work with */ >>>> + if (!cpu_map__empty(cpus)) { >>>> + for (i = 0; i < cpu_map__nr(cpus); i++) { >>>> + ret = cs_etm_get_metadata(cpus->map[i], i, >>>> + itr, auxtrace_info); >>>> + if (ret) >>>> + goto out; >>>> + } >>>> + } else { >>>> + /* get configuration for all CPUs in the system */ >>>> + nr_cpu = cpu__max_cpu(); >>>> + for (i = 0; i < nr_cpu; i++) { >>>> + ret = cs_etm_get_metadata(i, i, itr, auxtrace_info); >>>> + if (ret) >>>> + goto out; >>>> + } >>>> + } >>>> + >>>> +out: >>>> + return ret; >>>> +} >>>> + >>>> +static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, >>>> + int idx, struct auxtrace_mmap *mm, >>>> + unsigned char *data __maybe_unused, >>>> + u64 *head, u64 *old) >>>> +{ >>>> + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", >>>> + __func__, idx, (size_t)*old, (size_t)*head, mm->len); >>>> + >>>> + *old = *head; >>>> + *head += mm->len; >>>> + >>>> + return 0; >>>> +} >>>> + >>>> +static int cs_etm_snapshot_start(struct auxtrace_record *itr) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_evsel *evsel; >>>> + >>>> + evlist__for_each(ptr->evlist, evsel) { >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >>>> + return perf_evlist__disable_event(ptr->evlist, evsel); >>>> + } >>>> + return -EINVAL; >>>> +} >>>> + >>>> +static int cs_etm_snapshot_finish(struct auxtrace_record *itr) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_evsel *evsel; >>>> + >>>> + evlist__for_each(ptr->evlist, evsel) { >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >>>> + return perf_evlist__enable_event(ptr->evlist, evsel); >>>> + } >>>> + return -EINVAL; >>>> +} >>>> + >>>> +static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused) >>>> +{ >>>> + return (((u64) rand() << 0) & 0x00000000FFFFFFFFull) | >>>> + (((u64) rand() << 32) & 0xFFFFFFFF00000000ull); >>>> +} >>>> + >>>> +static void cs_etm_recording_free(struct auxtrace_record *itr) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + free(ptr); >>>> +} >>>> + >>>> +static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) >>>> +{ >>>> + struct cs_etm_recording *ptr = >>>> + container_of(itr, struct cs_etm_recording, itr); >>>> + struct perf_evsel *evsel; >>>> + >>>> + evlist__for_each(ptr->evlist, evsel) { >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >>>> + return perf_evlist__enable_event_idx(ptr->evlist, >>>> + evsel, idx); >>>> + } >>>> + >>>> + return -EINVAL; >>>> +} >>>> + >>>> +struct auxtrace_record *cs_etm_record_init(int *err) >>>> +{ >>>> + struct perf_pmu *cs_etm_pmu; >>>> + struct cs_etm_recording *ptr; >>>> + >>>> + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); >>>> + >>>> + if (!cs_etm_pmu) { >>>> + *err = -EINVAL; >>>> + goto out; >>>> + } >>>> + >>>> + ptr = zalloc(sizeof(struct cs_etm_recording)); >>>> + if (!ptr) { >>>> + *err = -ENOMEM; >>>> + goto out; >>>> + } >>>> + >>>> + ptr->cs_etm_pmu = cs_etm_pmu; >>>> + ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; >>>> + ptr->itr.recording_options = cs_etm_recording_options; >>>> + ptr->itr.info_priv_size = cs_etm_info_priv_size; >>>> + ptr->itr.info_fill = cs_etm_info_fill; >>>> + ptr->itr.find_snapshot = cs_etm_find_snapshot; >>>> + ptr->itr.snapshot_start = cs_etm_snapshot_start; >>>> + ptr->itr.snapshot_finish = cs_etm_snapshot_finish; >>>> + ptr->itr.reference = cs_etm_reference; >>>> + ptr->itr.free = cs_etm_recording_free; >>>> + ptr->itr.read_finish = cs_etm_read_finish; >>>> + >>>> + *err = 0; >>>> + return &ptr->itr; >>>> +out: >>>> + return NULL; >>>> +} >>>> diff --git a/tools/perf/arch/arm/util/cs_etm.h b/tools/perf/arch/arm/util/cs_etm.h >>>> new file mode 100644 >>>> index 000000000000..7e85c1b43598 >>>> --- /dev/null >>>> +++ b/tools/perf/arch/arm/util/cs_etm.h >>>> @@ -0,0 +1,44 @@ >>>> +/* >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >>>> + * >>>> + * This program is free software; you can redistribute it and/or modify it >>>> + * under the terms of the GNU General Public License version 2 as published by >>>> + * the Free Software Foundation. >>>> + * >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >>>> + * more details. >>>> + * >>>> + * You should have received a copy of the GNU General Public License along with >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >>>> + */ >>>> + >>>> +#ifndef INCLUDE__PERF_CS_ETM_H__ >>>> +#define INCLUDE__PERF_CS_ETM_H__ >>>> + >>>> +/* Beginning of header common to both ETMv3 and V4 */ >>>> +enum { >>>> + CS_ETM_MAGIC, >>>> + CS_ETM_CPU, >>>> + CS_ETM_SNAPSHOT, >>>> +}; >>>> + >>>> +/* ETMv3/PTM metadata */ >>>> +enum { >>>> + /* Dynamic, configurable parameters */ >>>> + CS_ETM_ETMCR = CS_ETM_SNAPSHOT + 1, >>>> + CS_ETM_ETMTRACEIDR, >>>> + /* RO, taken from sysFS */ >>>> + CS_ETM_ETMCCER, >>>> + CS_ETM_ETMIDR, >>>> + CS_ETM_PRIV_MAX, >>>> +}; >>>> + >>>> +static const u64 __perf_cs_etm_magic = 0x3030303030303030ULL; >>>> +#define CS_ETM_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64)) >>>> + >>>> +struct auxtrace_record *cs_etm_record_init(int *err); >>>> + >>>> +#endif >>>> diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c >>>> index cc1c9ce5cc56..a6f291dbc4d9 100644 >>>> --- a/tools/perf/util/auxtrace.c >>>> +++ b/tools/perf/util/auxtrace.c >>>> @@ -892,6 +892,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, >>>> return intel_pt_process_auxtrace_info(event, session); >>>> case PERF_AUXTRACE_INTEL_BTS: >>>> return intel_bts_process_auxtrace_info(event, session); >>>> + case PERF_AUXTRACE_CS_ETM: >>>> case PERF_AUXTRACE_UNKNOWN: >>>> default: >>>> return -EINVAL; >>>> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h >>>> index e5a8e2d4f2af..adb53e7bcabf 100644 >>>> --- a/tools/perf/util/auxtrace.h >>>> +++ b/tools/perf/util/auxtrace.h >>>> @@ -41,6 +41,7 @@ enum auxtrace_type { >>>> PERF_AUXTRACE_UNKNOWN, >>>> PERF_AUXTRACE_INTEL_PT, >>>> PERF_AUXTRACE_INTEL_BTS, >>>> + PERF_AUXTRACE_CS_ETM, >>>> }; >>>> >>>> enum itrace_period_type { >>>> -- >>>> 2.1.4 >>>> >>> >>> Arnaldo, >>> >>> Last but not least, this is the final patch that I would like you to >>> review before queing. >>> >>> It has been rebased to 4.5-rc1 here [1] for your convenience. I will >>> be happy to use another baseline should that be more adequate for you. >> >> Adrian, >> >> One more, are you ok with this? > > Looks OK, apart from adding linux/coresight-pmu.h to the manifest, but I > mentioned that on another patch. > > However there is no decoder, which begs the question, is there anything you > can actually do with the perf.data file? Might be a bit confusing for users > if they can capture traces but not use perf tools on the resulting perf.data > file? We are working on a decoding library in parallel to this work. > > Nevertheless, for what is there now: > > Acked-by: Adrian Hunter <adrian.hunter@intel.com> Thanks for the review. Mathieu >
On 29 January 2016 at 14:12, Arnaldo Carvalho de Melo <acme@kernel.org> wrote: > Em Fri, Jan 29, 2016 at 10:37:48AM -0700, Mathieu Poirier escreveu: >> On 29 January 2016 at 03:34, Adrian Hunter <adrian.hunter@intel.com> wrote: >> > On 25/01/16 23:10, Arnaldo Carvalho de Melo wrote: >> >> Em Mon, Jan 25, 2016 at 01:51:18PM -0700, Mathieu Poirier escreveu: >> >>> On 14 January 2016 at 14:46, Mathieu Poirier <mathieu.poirier@linaro.org> wrote: >> >>>> Coresight ETMs are IP blocks used to perform HW assisted tracing >> >>>> on a CPU core. This patch introduce the required auxiliary API >> >>>> functions allowing the perf core to interact with a tracer. >> >>>> >> >>>> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> >> >>>> Cc: Ingo Molnar <mingo@redhat.com> >> >>>> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> >> >>>> Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> >> >>>> --- >> >>>> MAINTAINERS | 3 + >> >>>> tools/perf/arch/arm/util/Build | 2 +- >> >>>> tools/perf/arch/arm/util/auxtrace.c | 54 +++++ >> >>>> tools/perf/arch/arm/util/cs_etm.c | 466 ++++++++++++++++++++++++++++++++++++ >> >>>> tools/perf/arch/arm/util/cs_etm.h | 44 ++++ >> >>>> tools/perf/util/auxtrace.c | 1 + >> >>>> tools/perf/util/auxtrace.h | 1 + >> >>>> 7 files changed, 570 insertions(+), 1 deletion(-) >> >>>> create mode 100644 tools/perf/arch/arm/util/auxtrace.c >> >>>> create mode 100644 tools/perf/arch/arm/util/cs_etm.c >> >>>> create mode 100644 tools/perf/arch/arm/util/cs_etm.h >> >>>> >> >>>> diff --git a/MAINTAINERS b/MAINTAINERS >> >>>> index b2a92245eece..a81b2737ebc3 100644 >> >>>> --- a/MAINTAINERS >> >>>> +++ b/MAINTAINERS >> >>>> @@ -1008,6 +1008,9 @@ F: Documentation/trace/coresight.txt >> >>>> F: Documentation/devicetree/bindings/arm/coresight.txt >> >>>> F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* >> >>>> F: tools/perf/arch/arm/util/pmu.c >> >>>> +F: tools/perf/arch/arm/util/auxtrace.c >> >>>> +F: tools/perf/arch/arm/util/cs_etm.c >> >>>> +F: tools/perf/arch/arm/util/cs_etm.h >> >>>> >> >>>> ARM/CORGI MACHINE SUPPORT >> >>>> M: Richard Purdie <rpurdie@rpsys.net> >> >>>> diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build >> >>>> index 66ab0b05549c..0a25a1248f42 100644 >> >>>> --- a/tools/perf/arch/arm/util/Build >> >>>> +++ b/tools/perf/arch/arm/util/Build >> >>>> @@ -3,4 +3,4 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o >> >>>> libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o >> >>>> libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o >> >>>> >> >>>> -libperf-$(CONFIG_AUXTRACE) += pmu.o >> >>>> +libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs_etm.o >> >>>> diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c >> >>>> new file mode 100644 >> >>>> index 000000000000..d327316f0e8a >> >>>> --- /dev/null >> >>>> +++ b/tools/perf/arch/arm/util/auxtrace.c >> >>>> @@ -0,0 +1,54 @@ >> >>>> +/* >> >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >> >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >> >>>> + * >> >>>> + * This program is free software; you can redistribute it and/or modify it >> >>>> + * under the terms of the GNU General Public License version 2 as published by >> >>>> + * the Free Software Foundation. >> >>>> + * >> >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >> >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >> >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >> >>>> + * more details. >> >>>> + * >> >>>> + * You should have received a copy of the GNU General Public License along with >> >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >> >>>> + */ >> >>>> + >> >>>> +#include <stdbool.h> >> >>>> +#include <linux/coresight-pmu.h> >> >>>> + >> >>>> +#include "../../util/auxtrace.h" >> >>>> +#include "../../util/evlist.h" >> >>>> +#include "../../util/pmu.h" >> >>>> +#include "cs_etm.h" >> >>>> + >> >>>> +struct auxtrace_record >> >>>> +*auxtrace_record__init(struct perf_evlist *evlist, int *err) >> >>>> +{ >> >>>> + struct perf_pmu *cs_etm_pmu; >> >>>> + struct perf_evsel *evsel; >> >>>> + bool found_etm = false; >> >>>> + >> >>>> + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); >> >>>> + >> >>>> + if (evlist) { >> >>>> + evlist__for_each(evlist, evsel) { >> >>>> + if (cs_etm_pmu && >> >>>> + evsel->attr.type == cs_etm_pmu->type) >> >>>> + found_etm = true; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> + if (found_etm) >> >>>> + return cs_etm_record_init(err); >> >>>> + >> >>>> + /* >> >>>> + * Clear 'err' even if we haven't found a cs_etm event - that way perf >> >>>> + * record can still be used even if tracers aren't present. The NULL >> >>>> + * return value will take care of telling the infrastructure HW tracing >> >>>> + * isn't available. >> >>>> + */ >> >>>> + *err = 0; >> >>>> + return NULL; >> >>>> +} >> >>>> diff --git a/tools/perf/arch/arm/util/cs_etm.c b/tools/perf/arch/arm/util/cs_etm.c >> >>>> new file mode 100644 >> >>>> index 000000000000..5710b90e23d5 >> >>>> --- /dev/null >> >>>> +++ b/tools/perf/arch/arm/util/cs_etm.c >> >>>> @@ -0,0 +1,466 @@ >> >>>> +/* >> >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >> >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >> >>>> + * >> >>>> + * This program is free software; you can redistribute it and/or modify it >> >>>> + * under the terms of the GNU General Public License version 2 as published by >> >>>> + * the Free Software Foundation. >> >>>> + * >> >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >> >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >> >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >> >>>> + * more details. >> >>>> + * >> >>>> + * You should have received a copy of the GNU General Public License along with >> >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >> >>>> + */ >> >>>> + >> >>>> +#include <api/fs/fs.h> >> >>>> +#include <linux/bitops.h> >> >>>> +#include <linux/coresight-pmu.h> >> >>>> +#include <linux/kernel.h> >> >>>> +#include <linux/log2.h> >> >>>> +#include <linux/types.h> >> >>>> + >> >>>> +#include "../../perf.h" >> >>>> +#include "../../util/auxtrace.h" >> >>>> +#include "../../util/cpumap.h" >> >>>> +#include "../../util/evlist.h" >> >>>> +#include "../../util/pmu.h" >> >>>> +#include "../../util/thread_map.h" >> >>>> +#include "cs_etm.h" >> >>>> + >> >>>> +#include <stdlib.h> >> >>>> + >> >>>> +#define KiB(x) ((x) * 1024) >> >>>> +#define MiB(x) ((x) * 1024 * 1024) >> >>>> + >> >>>> +struct cs_etm_recording { >> >>>> + struct auxtrace_record itr; >> >>>> + struct perf_pmu *cs_etm_pmu; >> >>>> + struct perf_evlist *evlist; >> >>>> + bool snapshot_mode; >> >>>> + size_t snapshot_size; >> >>>> +}; >> >>>> + >> >>>> +static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, >> >>>> + struct record_opts *opts, >> >>>> + const char *str) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + unsigned long long snapshot_size = 0; >> >>>> + char *endptr; >> >>>> + >> >>>> + if (str) { >> >>>> + snapshot_size = strtoull(str, &endptr, 0); >> >>>> + if (*endptr || snapshot_size > SIZE_MAX) >> >>>> + return -1; >> >>>> + } >> >>>> + >> >>>> + opts->auxtrace_snapshot_mode = true; >> >>>> + opts->auxtrace_snapshot_size = snapshot_size; >> >>>> + ptr->snapshot_size = snapshot_size; >> >>>> + >> >>>> + return 0; >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_recording_options(struct auxtrace_record *itr, >> >>>> + struct perf_evlist *evlist, >> >>>> + struct record_opts *opts) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >> >>>> + struct perf_evsel *evsel, *cs_etm_evsel = NULL; >> >>>> + const struct cpu_map *cpus = evlist->cpus; >> >>>> + bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); >> >>>> + >> >>>> + ptr->evlist = evlist; >> >>>> + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; >> >>>> + >> >>>> + evlist__for_each(evlist, evsel) { >> >>>> + if (evsel->attr.type == cs_etm_pmu->type) { >> >>>> + if (cs_etm_evsel) { >> >>>> + pr_err("There may be only one %s event\n", >> >>>> + CORESIGHT_ETM_PMU_NAME); >> >>>> + return -EINVAL; >> >>>> + } >> >>>> + evsel->attr.freq = 0; >> >>>> + evsel->attr.sample_period = 1; >> >>>> + cs_etm_evsel = evsel; >> >>>> + opts->full_auxtrace = true; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> + /* no need to continue if at least one event of interest was found */ >> >>>> + if (!cs_etm_evsel) >> >>>> + return 0; >> >>>> + >> >>>> + if (opts->use_clockid) { >> >>>> + pr_err("Cannot use clockid (-k option) with %s\n", >> >>>> + CORESIGHT_ETM_PMU_NAME); >> >>>> + return -EINVAL; >> >>>> + } >> >>>> + >> >>>> + /* we are in snapshot mode */ >> >>>> + if (opts->auxtrace_snapshot_mode) { >> >>>> + /* >> >>>> + * No size were given to '-S' or '-m,', so go with >> >>>> + * the default >> >>>> + */ >> >>>> + if (!opts->auxtrace_snapshot_size && >> >>>> + !opts->auxtrace_mmap_pages) { >> >>>> + if (privileged) { >> >>>> + opts->auxtrace_mmap_pages = MiB(4) / page_size; >> >>>> + } else { >> >>>> + opts->auxtrace_mmap_pages = >> >>>> + KiB(128) / page_size; >> >>>> + if (opts->mmap_pages == UINT_MAX) >> >>>> + opts->mmap_pages = KiB(256) / page_size; >> >>>> + } >> >>>> + } else if (!opts->auxtrace_mmap_pages && !privileged && >> >>>> + opts->mmap_pages == UINT_MAX) { >> >>>> + opts->mmap_pages = KiB(256) / page_size; >> >>>> + } >> >>>> + >> >>>> + /* >> >>>> + * '-m,xyz' was specified but no snapshot size, so make the >> >>>> + * snapshot size as big as the auxtrace mmap area. >> >>>> + */ >> >>>> + if (!opts->auxtrace_snapshot_size) { >> >>>> + opts->auxtrace_snapshot_size = >> >>>> + opts->auxtrace_mmap_pages * (size_t)page_size; >> >>>> + } >> >>>> + >> >>>> + /* >> >>>> + * -Sxyz was specified but no auxtrace mmap area, so make the >> >>>> + * auxtrace mmap area big enough to fit the requested snapshot >> >>>> + * size. >> >>>> + */ >> >>>> + if (!opts->auxtrace_mmap_pages) { >> >>>> + size_t sz = opts->auxtrace_snapshot_size; >> >>>> + >> >>>> + sz = round_up(sz, page_size) / page_size; >> >>>> + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); >> >>>> + } >> >>>> + >> >>>> + /* Snapshost size can't be bigger than the auxtrace area */ >> >>>> + if (opts->auxtrace_snapshot_size > >> >>>> + opts->auxtrace_mmap_pages * (size_t)page_size) { >> >>>> + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", >> >>>> + opts->auxtrace_snapshot_size, >> >>>> + opts->auxtrace_mmap_pages * (size_t)page_size); >> >>>> + return -EINVAL; >> >>>> + } >> >>>> + >> >>>> + /* Something went wrong somewhere - this shouldn't happen */ >> >>>> + if (!opts->auxtrace_snapshot_size || >> >>>> + !opts->auxtrace_mmap_pages) { >> >>>> + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); >> >>>> + return -EINVAL; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> + /* We are in full trace mode but '-m,xyz' wasn't specified */ >> >>>> + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { >> >>>> + if (privileged) { >> >>>> + opts->auxtrace_mmap_pages = MiB(4) / page_size; >> >>>> + } else { >> >>>> + opts->auxtrace_mmap_pages = KiB(128) / page_size; >> >>>> + if (opts->mmap_pages == UINT_MAX) >> >>>> + opts->mmap_pages = KiB(256) / page_size; >> >>>> + } >> >>>> + >> >>>> + } >> >>>> + >> >>>> + /* Validate auxtrace_mmap_pages provided by user */ >> >>>> + if (opts->auxtrace_mmap_pages) { >> >>>> + unsigned int max_page = (KiB(128) / page_size); >> >>>> + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; >> >>>> + >> >>>> + if (!privileged && >> >>>> + opts->auxtrace_mmap_pages > max_page) { >> >>>> + opts->auxtrace_mmap_pages = max_page; >> >>>> + pr_err("auxtrace too big, truncating to %d\n", >> >>>> + max_page); >> >>>> + } >> >>>> + >> >>>> + if (!is_power_of_2(sz)) { >> >>>> + pr_err("Invalid mmap size for %s: must be a power of 2\n", >> >>>> + CORESIGHT_ETM_PMU_NAME); >> >>>> + return -EINVAL; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> + if (opts->auxtrace_snapshot_mode) >> >>>> + pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, >> >>>> + opts->auxtrace_snapshot_size); >> >>>> + >> >>>> + if (cs_etm_evsel) { >> >>>> + /* >> >>>> + * To obtain the auxtrace buffer file descriptor, the auxtrace >> >>>> + * event must come first. >> >>>> + */ >> >>>> + perf_evlist__to_front(evlist, cs_etm_evsel); >> >>>> + /* >> >>>> + * In the case of per-cpu mmaps, we need the CPU on the >> >>>> + * AUX event. >> >>>> + */ >> >>>> + if (!cpu_map__empty(cpus)) >> >>>> + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); >> >>>> + } >> >>>> + >> >>>> + /* Add dummy event to keep tracking */ >> >>>> + if (opts->full_auxtrace) { >> >>>> + struct perf_evsel *tracking_evsel; >> >>>> + int err; >> >>>> + >> >>>> + err = parse_events(evlist, "dummy:u", NULL); >> >>>> + if (err) >> >>>> + return err; >> >>>> + >> >>>> + tracking_evsel = perf_evlist__last(evlist); >> >>>> + perf_evlist__set_tracking_event(evlist, tracking_evsel); >> >>>> + >> >>>> + tracking_evsel->attr.freq = 0; >> >>>> + tracking_evsel->attr.sample_period = 1; >> >>>> + >> >>>> + /* In per-cpu case, always need the time of mmap events etc */ >> >>>> + if (!cpu_map__empty(cpus)) >> >>>> + perf_evsel__set_sample_bit(tracking_evsel, TIME); >> >>>> + } >> >>>> + >> >>>> + return 0; >> >>>> +} >> >>>> + >> >>>> +static u64 cs_etm_get_config(struct auxtrace_record *itr) >> >>>> +{ >> >>>> + u64 config = 0; >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >> >>>> + struct perf_evlist *evlist = ptr->evlist; >> >>>> + struct perf_evsel *evsel; >> >>>> + >> >>>> + evlist__for_each(evlist, evsel) { >> >>>> + if (evsel->attr.type == cs_etm_pmu->type) { >> >>>> + /* >> >>>> + * Variable perf_event_attr::config is assigned to >> >>>> + * ETMv3/PTM. The bit fields have been made to match >> >>>> + * the ETMv3.5 ETRMCR register specification. See the >> >>>> + * PMU_FORMAT_ATTR() declarations in >> >>>> + * drivers/hwtracing/coresight/coresight-perf.c for >> >>>> + * details. >> >>>> + */ >> >>>> + config = evsel->attr.config; >> >>>> + break; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> + return config; >> >>>> +} >> >>>> + >> >>>> +static size_t >> >>>> +cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, >> >>>> + struct perf_evlist *evlist __maybe_unused) >> >>>> +{ >> >>>> + int records; >> >>>> + const struct cpu_map *cpus = evlist->cpus; >> >>>> + >> >>>> + if (!cpu_map__empty(cpus)) { >> >>>> + records = cpu_map__nr(cpus); >> >>>> + goto out; >> >>>> + } >> >>>> + >> >>>> + set_max_cpu_num(); >> >>>> + records = cpu__max_cpu(); >> >>>> +out: >> >>>> + return records * CS_ETM_PRIV_SIZE; >> >>>> +} >> >>>> + >> >>>> +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { >> >>>> + [CS_ETM_ETMCCER] = "mgmt/etmccer", >> >>>> + [CS_ETM_ETMIDR] = "mgmt/etmidr", >> >>>> +}; >> >>>> + >> >>>> +static int cs_etm_get_metadata(int cpu, int index, >> >>>> + struct auxtrace_record *itr, >> >>>> + struct auxtrace_info_event *info) >> >>>> +{ >> >>>> + char path[PATH_MAX]; >> >>>> + int offset = 0, ret = 0; >> >>>> + int i, scan; >> >>>> + unsigned int val; >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; >> >>>> + >> >>>> + offset = index * CS_ETM_PRIV_MAX; >> >>>> + >> >>>> + /* Build generic header portion */ >> >>>> + info->priv[offset + CS_ETM_MAGIC] = __perf_cs_etm_magic; >> >>>> + info->priv[offset + CS_ETM_CPU] = cpu; >> >>>> + info->priv[offset + CS_ETM_SNAPSHOT] = ptr->snapshot_mode; >> >>>> + >> >>>> + /* Get user configurables from the session */ >> >>>> + info->priv[offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); >> >>>> + info->priv[offset + CS_ETM_ETMTRACEIDR] = coresight_get_trace_id(cpu); >> >>>> + >> >>>> + /* Get RO metadata from sysfs */ >> >>>> + for (i = CS_ETM_ETMCCER; i < CS_ETM_PRIV_MAX; i++) { >> >>>> + snprintf(path, PATH_MAX, "cpu%d/%s", cpu, metadata_etmv3_ro[i]); >> >>>> + >> >>>> + scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); >> >>>> + if (scan != 1) { >> >>>> + ret = -EINVAL; >> >>>> + break; >> >>>> + } >> >>>> + >> >>>> + info->priv[offset + i] = val; >> >>>> + } >> >>>> + >> >>>> + return ret; >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_info_fill(struct auxtrace_record *itr, >> >>>> + struct perf_session *session, >> >>>> + struct auxtrace_info_event *auxtrace_info, >> >>>> + size_t priv_size) >> >>>> +{ >> >>>> + int i, nr_cpu, ret = 0; >> >>>> + const struct cpu_map *cpus = session->evlist->cpus; >> >>>> + >> >>>> + if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) >> >>>> + return -EINVAL; >> >>>> + >> >>>> + if (!session->evlist->nr_mmaps) >> >>>> + return -EINVAL; >> >>>> + >> >>>> + auxtrace_info->type = PERF_AUXTRACE_CS_ETM; >> >>>> + >> >>>> + /* cpu map is not empty, we have specific CPUs to work with */ >> >>>> + if (!cpu_map__empty(cpus)) { >> >>>> + for (i = 0; i < cpu_map__nr(cpus); i++) { >> >>>> + ret = cs_etm_get_metadata(cpus->map[i], i, >> >>>> + itr, auxtrace_info); >> >>>> + if (ret) >> >>>> + goto out; >> >>>> + } >> >>>> + } else { >> >>>> + /* get configuration for all CPUs in the system */ >> >>>> + nr_cpu = cpu__max_cpu(); >> >>>> + for (i = 0; i < nr_cpu; i++) { >> >>>> + ret = cs_etm_get_metadata(i, i, itr, auxtrace_info); >> >>>> + if (ret) >> >>>> + goto out; >> >>>> + } >> >>>> + } >> >>>> + >> >>>> +out: >> >>>> + return ret; >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, >> >>>> + int idx, struct auxtrace_mmap *mm, >> >>>> + unsigned char *data __maybe_unused, >> >>>> + u64 *head, u64 *old) >> >>>> +{ >> >>>> + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", >> >>>> + __func__, idx, (size_t)*old, (size_t)*head, mm->len); >> >>>> + >> >>>> + *old = *head; >> >>>> + *head += mm->len; >> >>>> + >> >>>> + return 0; >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_snapshot_start(struct auxtrace_record *itr) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_evsel *evsel; >> >>>> + >> >>>> + evlist__for_each(ptr->evlist, evsel) { >> >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >> >>>> + return perf_evlist__disable_event(ptr->evlist, evsel); >> >>>> + } >> >>>> + return -EINVAL; >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_snapshot_finish(struct auxtrace_record *itr) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_evsel *evsel; >> >>>> + >> >>>> + evlist__for_each(ptr->evlist, evsel) { >> >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >> >>>> + return perf_evlist__enable_event(ptr->evlist, evsel); >> >>>> + } >> >>>> + return -EINVAL; >> >>>> +} >> >>>> + >> >>>> +static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused) >> >>>> +{ >> >>>> + return (((u64) rand() << 0) & 0x00000000FFFFFFFFull) | >> >>>> + (((u64) rand() << 32) & 0xFFFFFFFF00000000ull); >> >>>> +} >> >>>> + >> >>>> +static void cs_etm_recording_free(struct auxtrace_record *itr) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + free(ptr); >> >>>> +} >> >>>> + >> >>>> +static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) >> >>>> +{ >> >>>> + struct cs_etm_recording *ptr = >> >>>> + container_of(itr, struct cs_etm_recording, itr); >> >>>> + struct perf_evsel *evsel; >> >>>> + >> >>>> + evlist__for_each(ptr->evlist, evsel) { >> >>>> + if (evsel->attr.type == ptr->cs_etm_pmu->type) >> >>>> + return perf_evlist__enable_event_idx(ptr->evlist, >> >>>> + evsel, idx); >> >>>> + } >> >>>> + >> >>>> + return -EINVAL; >> >>>> +} >> >>>> + >> >>>> +struct auxtrace_record *cs_etm_record_init(int *err) >> >>>> +{ >> >>>> + struct perf_pmu *cs_etm_pmu; >> >>>> + struct cs_etm_recording *ptr; >> >>>> + >> >>>> + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); >> >>>> + >> >>>> + if (!cs_etm_pmu) { >> >>>> + *err = -EINVAL; >> >>>> + goto out; >> >>>> + } >> >>>> + >> >>>> + ptr = zalloc(sizeof(struct cs_etm_recording)); >> >>>> + if (!ptr) { >> >>>> + *err = -ENOMEM; >> >>>> + goto out; >> >>>> + } >> >>>> + >> >>>> + ptr->cs_etm_pmu = cs_etm_pmu; >> >>>> + ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; >> >>>> + ptr->itr.recording_options = cs_etm_recording_options; >> >>>> + ptr->itr.info_priv_size = cs_etm_info_priv_size; >> >>>> + ptr->itr.info_fill = cs_etm_info_fill; >> >>>> + ptr->itr.find_snapshot = cs_etm_find_snapshot; >> >>>> + ptr->itr.snapshot_start = cs_etm_snapshot_start; >> >>>> + ptr->itr.snapshot_finish = cs_etm_snapshot_finish; >> >>>> + ptr->itr.reference = cs_etm_reference; >> >>>> + ptr->itr.free = cs_etm_recording_free; >> >>>> + ptr->itr.read_finish = cs_etm_read_finish; >> >>>> + >> >>>> + *err = 0; >> >>>> + return &ptr->itr; >> >>>> +out: >> >>>> + return NULL; >> >>>> +} >> >>>> diff --git a/tools/perf/arch/arm/util/cs_etm.h b/tools/perf/arch/arm/util/cs_etm.h >> >>>> new file mode 100644 >> >>>> index 000000000000..7e85c1b43598 >> >>>> --- /dev/null >> >>>> +++ b/tools/perf/arch/arm/util/cs_etm.h >> >>>> @@ -0,0 +1,44 @@ >> >>>> +/* >> >>>> + * Copyright(C) 2015 Linaro Limited. All rights reserved. >> >>>> + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> >> >>>> + * >> >>>> + * This program is free software; you can redistribute it and/or modify it >> >>>> + * under the terms of the GNU General Public License version 2 as published by >> >>>> + * the Free Software Foundation. >> >>>> + * >> >>>> + * This program is distributed in the hope that it will be useful, but WITHOUT >> >>>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or >> >>>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for >> >>>> + * more details. >> >>>> + * >> >>>> + * You should have received a copy of the GNU General Public License along with >> >>>> + * this program. If not, see <http://www.gnu.org/licenses/>. >> >>>> + */ >> >>>> + >> >>>> +#ifndef INCLUDE__PERF_CS_ETM_H__ >> >>>> +#define INCLUDE__PERF_CS_ETM_H__ >> >>>> + >> >>>> +/* Beginning of header common to both ETMv3 and V4 */ >> >>>> +enum { >> >>>> + CS_ETM_MAGIC, >> >>>> + CS_ETM_CPU, >> >>>> + CS_ETM_SNAPSHOT, >> >>>> +}; >> >>>> + >> >>>> +/* ETMv3/PTM metadata */ >> >>>> +enum { >> >>>> + /* Dynamic, configurable parameters */ >> >>>> + CS_ETM_ETMCR = CS_ETM_SNAPSHOT + 1, >> >>>> + CS_ETM_ETMTRACEIDR, >> >>>> + /* RO, taken from sysFS */ >> >>>> + CS_ETM_ETMCCER, >> >>>> + CS_ETM_ETMIDR, >> >>>> + CS_ETM_PRIV_MAX, >> >>>> +}; >> >>>> + >> >>>> +static const u64 __perf_cs_etm_magic = 0x3030303030303030ULL; >> >>>> +#define CS_ETM_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64)) >> >>>> + >> >>>> +struct auxtrace_record *cs_etm_record_init(int *err); >> >>>> + >> >>>> +#endif >> >>>> diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c >> >>>> index cc1c9ce5cc56..a6f291dbc4d9 100644 >> >>>> --- a/tools/perf/util/auxtrace.c >> >>>> +++ b/tools/perf/util/auxtrace.c >> >>>> @@ -892,6 +892,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, >> >>>> return intel_pt_process_auxtrace_info(event, session); >> >>>> case PERF_AUXTRACE_INTEL_BTS: >> >>>> return intel_bts_process_auxtrace_info(event, session); >> >>>> + case PERF_AUXTRACE_CS_ETM: >> >>>> case PERF_AUXTRACE_UNKNOWN: >> >>>> default: >> >>>> return -EINVAL; >> >>>> diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h >> >>>> index e5a8e2d4f2af..adb53e7bcabf 100644 >> >>>> --- a/tools/perf/util/auxtrace.h >> >>>> +++ b/tools/perf/util/auxtrace.h >> >>>> @@ -41,6 +41,7 @@ enum auxtrace_type { >> >>>> PERF_AUXTRACE_UNKNOWN, >> >>>> PERF_AUXTRACE_INTEL_PT, >> >>>> PERF_AUXTRACE_INTEL_BTS, >> >>>> + PERF_AUXTRACE_CS_ETM, >> >>>> }; >> >>>> >> >>>> enum itrace_period_type { >> >>>> -- >> >>>> 2.1.4 >> >>>> >> >>> >> >>> Arnaldo, >> >>> >> >>> Last but not least, this is the final patch that I would like you to >> >>> review before queing. >> >>> >> >>> It has been rebased to 4.5-rc1 here [1] for your convenience. I will >> >>> be happy to use another baseline should that be more adequate for you. >> >> >> >> Adrian, >> >> >> >> One more, are you ok with this? >> > >> > Looks OK, apart from adding linux/coresight-pmu.h to the manifest, but I >> > mentioned that on another patch. >> > >> > However there is no decoder, which begs the question, is there anything you >> > can actually do with the perf.data file? Might be a bit confusing for users >> > if they can capture traces but not use perf tools on the resulting perf.data >> > file? >> >> We are working on a decoding library in parallel to this work. > > Would be nice to be able to get both in the same patch kit, no? So that > one can both record and process the traces, verifying it all works. We are still a few weeks away from being in a position where the community can start playing with the decoding library. I can hold off on the "perf tools" patches when I queue the kernel side of the work for 4.6 but since you and Adrian have already reviewed the work it would be nice to have that part included as well. We've been playing with the perf.data files for a couple of months now and things look at the right place. This isn't surprising since we are using the same framework as X86. I think the generation of the perf.data file should be coupled with the submission of the kernel driver but would also respect a diverging point of view. Simply let me know what you prefer and I will adjust V9 accordingly. Regards, Mathieu > > - Arnaldo > >> > >> > Nevertheless, for what is there now: >> > >> > Acked-by: Adrian Hunter <adrian.hunter@intel.com> >> >> Thanks for the review. >> Mathieu >> >> >
[...] >>> > >>> > Looks OK, apart from adding linux/coresight-pmu.h to the manifest, but I >>> > mentioned that on another patch. >>> > >>> > However there is no decoder, which begs the question, is there anything you >>> > can actually do with the perf.data file? Might be a bit confusing for users >>> > if they can capture traces but not use perf tools on the resulting perf.data >>> > file? >>> >>> We are working on a decoding library in parallel to this work. >> >> Would be nice to be able to get both in the same patch kit, no? So that >> one can both record and process the traces, verifying it all works. > > We are still a few weeks away from being in a position where the > community can start playing with the decoding library. I can hold off > on the "perf tools" patches when I queue the kernel side of the work > for 4.6 but since you and Adrian have already reviewed the work it > would be nice to have that part included as well. > > We've been playing with the perf.data files for a couple of months now > and things look at the right place. This isn't surprising since we > are using the same framework as X86. > > I think the generation of the perf.data file should be coupled with > the submission of the kernel driver but would also respect a diverging > point of view. Simply let me know what you prefer and I will adjust > V9 accordingly. Arnaldo, I'm preparing V9 at this time - what's your view on the above? Thanks, Mathieu
On 2 February 2016 at 09:41, Arnaldo Carvalho de Melo <acme@kernel.org> wrote: > Em Tue, Feb 02, 2016 at 09:20:51AM -0700, Mathieu Poirier escreveu: >> [...] >> >> >>> > >> >>> > Looks OK, apart from adding linux/coresight-pmu.h to the manifest, but I >> >>> > mentioned that on another patch. >> >>> > >> >>> > However there is no decoder, which begs the question, is there anything you >> >>> > can actually do with the perf.data file? Might be a bit confusing for users >> >>> > if they can capture traces but not use perf tools on the resulting perf.data >> >>> > file? >> >>> >> >>> We are working on a decoding library in parallel to this work. >> >> >> >> Would be nice to be able to get both in the same patch kit, no? So that >> >> one can both record and process the traces, verifying it all works. >> > >> > We are still a few weeks away from being in a position where the >> > community can start playing with the decoding library. I can hold off >> > on the "perf tools" patches when I queue the kernel side of the work >> > for 4.6 but since you and Adrian have already reviewed the work it >> > would be nice to have that part included as well. >> > >> > We've been playing with the perf.data files for a couple of months now >> > and things look at the right place. This isn't surprising since we >> > are using the same framework as X86. >> > >> > I think the generation of the perf.data file should be coupled with >> > the submission of the kernel driver but would also respect a diverging >> > point of view. Simply let me know what you prefer and I will adjust >> > V9 accordingly. >> >> Arnaldo, >> >> I'm preparing V9 at this time - what's your view on the above? > > I'd say go with something we can test, i.e. if we generate a perf.data > file we can't then process to figure out if what was inserted is right, > how can we decide if it is ok? Very well - I'll hold off on the perf tools patches for now. We can make a submission of all the user space components when things are in a working order. Mathieu > > Otherwise please describe how you test it, preferably by having this in > the commit log, i.e. if you decide that using plain 'perf report -D' is > enough, state that and show the output, etc. > > - Arnaldo
diff --git a/MAINTAINERS b/MAINTAINERS index b2a92245eece..a81b2737ebc3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1008,6 +1008,9 @@ F: Documentation/trace/coresight.txt F: Documentation/devicetree/bindings/arm/coresight.txt F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* F: tools/perf/arch/arm/util/pmu.c +F: tools/perf/arch/arm/util/auxtrace.c +F: tools/perf/arch/arm/util/cs_etm.c +F: tools/perf/arch/arm/util/cs_etm.h ARM/CORGI MACHINE SUPPORT M: Richard Purdie <rpurdie@rpsys.net> diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build index 66ab0b05549c..0a25a1248f42 100644 --- a/tools/perf/arch/arm/util/Build +++ b/tools/perf/arch/arm/util/Build @@ -3,4 +3,4 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o -libperf-$(CONFIG_AUXTRACE) += pmu.o +libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs_etm.o diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c new file mode 100644 index 000000000000..d327316f0e8a --- /dev/null +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -0,0 +1,54 @@ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <stdbool.h> +#include <linux/coresight-pmu.h> + +#include "../../util/auxtrace.h" +#include "../../util/evlist.h" +#include "../../util/pmu.h" +#include "cs_etm.h" + +struct auxtrace_record +*auxtrace_record__init(struct perf_evlist *evlist, int *err) +{ + struct perf_pmu *cs_etm_pmu; + struct perf_evsel *evsel; + bool found_etm = false; + + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + + if (evlist) { + evlist__for_each(evlist, evsel) { + if (cs_etm_pmu && + evsel->attr.type == cs_etm_pmu->type) + found_etm = true; + } + } + + if (found_etm) + return cs_etm_record_init(err); + + /* + * Clear 'err' even if we haven't found a cs_etm event - that way perf + * record can still be used even if tracers aren't present. The NULL + * return value will take care of telling the infrastructure HW tracing + * isn't available. + */ + *err = 0; + return NULL; +} diff --git a/tools/perf/arch/arm/util/cs_etm.c b/tools/perf/arch/arm/util/cs_etm.c new file mode 100644 index 000000000000..5710b90e23d5 --- /dev/null +++ b/tools/perf/arch/arm/util/cs_etm.c @@ -0,0 +1,466 @@ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <api/fs/fs.h> +#include <linux/bitops.h> +#include <linux/coresight-pmu.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/types.h> + +#include "../../perf.h" +#include "../../util/auxtrace.h" +#include "../../util/cpumap.h" +#include "../../util/evlist.h" +#include "../../util/pmu.h" +#include "../../util/thread_map.h" +#include "cs_etm.h" + +#include <stdlib.h> + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) + +struct cs_etm_recording { + struct auxtrace_record itr; + struct perf_pmu *cs_etm_pmu; + struct perf_evlist *evlist; + bool snapshot_mode; + size_t snapshot_size; +}; + +static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, + struct record_opts *opts, + const char *str) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + ptr->snapshot_size = snapshot_size; + + return 0; +} + +static int cs_etm_recording_options(struct auxtrace_record *itr, + struct perf_evlist *evlist, + struct record_opts *opts) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + struct perf_evsel *evsel, *cs_etm_evsel = NULL; + const struct cpu_map *cpus = evlist->cpus; + bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); + + ptr->evlist = evlist; + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type == cs_etm_pmu->type) { + if (cs_etm_evsel) { + pr_err("There may be only one %s event\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + evsel->attr.freq = 0; + evsel->attr.sample_period = 1; + cs_etm_evsel = evsel; + opts->full_auxtrace = true; + } + } + + /* no need to continue if at least one event of interest was found */ + if (!cs_etm_evsel) + return 0; + + if (opts->use_clockid) { + pr_err("Cannot use clockid (-k option) with %s\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + + /* we are in snapshot mode */ + if (opts->auxtrace_snapshot_mode) { + /* + * No size were given to '-S' or '-m,', so go with + * the default + */ + if (!opts->auxtrace_snapshot_size && + !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = + KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && + opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + + /* + * '-m,xyz' was specified but no snapshot size, so make the + * snapshot size as big as the auxtrace mmap area. + */ + if (!opts->auxtrace_snapshot_size) { + opts->auxtrace_snapshot_size = + opts->auxtrace_mmap_pages * (size_t)page_size; + } + + /* + * -Sxyz was specified but no auxtrace mmap area, so make the + * auxtrace mmap area big enough to fit the requested snapshot + * size. + */ + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } + + /* Snapshost size can't be bigger than the auxtrace area */ + if (opts->auxtrace_snapshot_size > + opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + + /* Something went wrong somewhere - this shouldn't happen */ + if (!opts->auxtrace_snapshot_size || + !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + } + + /* We are in full trace mode but '-m,xyz' wasn't specified */ + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + + } + + /* Validate auxtrace_mmap_pages provided by user */ + if (opts->auxtrace_mmap_pages) { + unsigned int max_page = (KiB(128) / page_size); + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; + + if (!privileged && + opts->auxtrace_mmap_pages > max_page) { + opts->auxtrace_mmap_pages = max_page; + pr_err("auxtrace too big, truncating to %d\n", + max_page); + } + + if (!is_power_of_2(sz)) { + pr_err("Invalid mmap size for %s: must be a power of 2\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + } + + if (opts->auxtrace_snapshot_mode) + pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, + opts->auxtrace_snapshot_size); + + if (cs_etm_evsel) { + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, cs_etm_evsel); + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); + } + + /* Add dummy event to keep tracking */ + if (opts->full_auxtrace) { + struct perf_evsel *tracking_evsel; + int err; + + err = parse_events(evlist, "dummy:u", NULL); + if (err) + return err; + + tracking_evsel = perf_evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->attr.freq = 0; + tracking_evsel->attr.sample_period = 1; + + /* In per-cpu case, always need the time of mmap events etc */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(tracking_evsel, TIME); + } + + return 0; +} + +static u64 cs_etm_get_config(struct auxtrace_record *itr) +{ + u64 config = 0; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + struct perf_evlist *evlist = ptr->evlist; + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type == cs_etm_pmu->type) { + /* + * Variable perf_event_attr::config is assigned to + * ETMv3/PTM. The bit fields have been made to match + * the ETMv3.5 ETRMCR register specification. See the + * PMU_FORMAT_ATTR() declarations in + * drivers/hwtracing/coresight/coresight-perf.c for + * details. + */ + config = evsel->attr.config; + break; + } + } + + return config; +} + +static size_t +cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + int records; + const struct cpu_map *cpus = evlist->cpus; + + if (!cpu_map__empty(cpus)) { + records = cpu_map__nr(cpus); + goto out; + } + + set_max_cpu_num(); + records = cpu__max_cpu(); +out: + return records * CS_ETM_PRIV_SIZE; +} + +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { + [CS_ETM_ETMCCER] = "mgmt/etmccer", + [CS_ETM_ETMIDR] = "mgmt/etmidr", +}; + +static int cs_etm_get_metadata(int cpu, int index, + struct auxtrace_record *itr, + struct auxtrace_info_event *info) +{ + char path[PATH_MAX]; + int offset = 0, ret = 0; + int i, scan; + unsigned int val; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + offset = index * CS_ETM_PRIV_MAX; + + /* Build generic header portion */ + info->priv[offset + CS_ETM_MAGIC] = __perf_cs_etm_magic; + info->priv[offset + CS_ETM_CPU] = cpu; + info->priv[offset + CS_ETM_SNAPSHOT] = ptr->snapshot_mode; + + /* Get user configurables from the session */ + info->priv[offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); + info->priv[offset + CS_ETM_ETMTRACEIDR] = coresight_get_trace_id(cpu); + + /* Get RO metadata from sysfs */ + for (i = CS_ETM_ETMCCER; i < CS_ETM_PRIV_MAX; i++) { + snprintf(path, PATH_MAX, "cpu%d/%s", cpu, metadata_etmv3_ro[i]); + + scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); + if (scan != 1) { + ret = -EINVAL; + break; + } + + info->priv[offset + i] = val; + } + + return ret; +} + +static int cs_etm_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct auxtrace_info_event *auxtrace_info, + size_t priv_size) +{ + int i, nr_cpu, ret = 0; + const struct cpu_map *cpus = session->evlist->cpus; + + if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) + return -EINVAL; + + if (!session->evlist->nr_mmaps) + return -EINVAL; + + auxtrace_info->type = PERF_AUXTRACE_CS_ETM; + + /* cpu map is not empty, we have specific CPUs to work with */ + if (!cpu_map__empty(cpus)) { + for (i = 0; i < cpu_map__nr(cpus); i++) { + ret = cs_etm_get_metadata(cpus->map[i], i, + itr, auxtrace_info); + if (ret) + goto out; + } + } else { + /* get configuration for all CPUs in the system */ + nr_cpu = cpu__max_cpu(); + for (i = 0; i < nr_cpu; i++) { + ret = cs_etm_get_metadata(i, i, itr, auxtrace_info); + if (ret) + goto out; + } + } + +out: + return ret; +} + +static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, + int idx, struct auxtrace_mmap *mm, + unsigned char *data __maybe_unused, + u64 *head, u64 *old) +{ + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", + __func__, idx, (size_t)*old, (size_t)*head, mm->len); + + *old = *head; + *head += mm->len; + + return 0; +} + +static int cs_etm_snapshot_start(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evlist__disable_event(ptr->evlist, evsel); + } + return -EINVAL; +} + +static int cs_etm_snapshot_finish(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evlist__enable_event(ptr->evlist, evsel); + } + return -EINVAL; +} + +static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused) +{ + return (((u64) rand() << 0) & 0x00000000FFFFFFFFull) | + (((u64) rand() << 32) & 0xFFFFFFFF00000000ull); +} + +static void cs_etm_recording_free(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + free(ptr); +} + +static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evlist__enable_event_idx(ptr->evlist, + evsel, idx); + } + + return -EINVAL; +} + +struct auxtrace_record *cs_etm_record_init(int *err) +{ + struct perf_pmu *cs_etm_pmu; + struct cs_etm_recording *ptr; + + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + + if (!cs_etm_pmu) { + *err = -EINVAL; + goto out; + } + + ptr = zalloc(sizeof(struct cs_etm_recording)); + if (!ptr) { + *err = -ENOMEM; + goto out; + } + + ptr->cs_etm_pmu = cs_etm_pmu; + ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; + ptr->itr.recording_options = cs_etm_recording_options; + ptr->itr.info_priv_size = cs_etm_info_priv_size; + ptr->itr.info_fill = cs_etm_info_fill; + ptr->itr.find_snapshot = cs_etm_find_snapshot; + ptr->itr.snapshot_start = cs_etm_snapshot_start; + ptr->itr.snapshot_finish = cs_etm_snapshot_finish; + ptr->itr.reference = cs_etm_reference; + ptr->itr.free = cs_etm_recording_free; + ptr->itr.read_finish = cs_etm_read_finish; + + *err = 0; + return &ptr->itr; +out: + return NULL; +} diff --git a/tools/perf/arch/arm/util/cs_etm.h b/tools/perf/arch/arm/util/cs_etm.h new file mode 100644 index 000000000000..7e85c1b43598 --- /dev/null +++ b/tools/perf/arch/arm/util/cs_etm.h @@ -0,0 +1,44 @@ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef INCLUDE__PERF_CS_ETM_H__ +#define INCLUDE__PERF_CS_ETM_H__ + +/* Beginning of header common to both ETMv3 and V4 */ +enum { + CS_ETM_MAGIC, + CS_ETM_CPU, + CS_ETM_SNAPSHOT, +}; + +/* ETMv3/PTM metadata */ +enum { + /* Dynamic, configurable parameters */ + CS_ETM_ETMCR = CS_ETM_SNAPSHOT + 1, + CS_ETM_ETMTRACEIDR, + /* RO, taken from sysFS */ + CS_ETM_ETMCCER, + CS_ETM_ETMIDR, + CS_ETM_PRIV_MAX, +}; + +static const u64 __perf_cs_etm_magic = 0x3030303030303030ULL; +#define CS_ETM_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64)) + +struct auxtrace_record *cs_etm_record_init(int *err); + +#endif diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index cc1c9ce5cc56..a6f291dbc4d9 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -892,6 +892,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, return intel_pt_process_auxtrace_info(event, session); case PERF_AUXTRACE_INTEL_BTS: return intel_bts_process_auxtrace_info(event, session); + case PERF_AUXTRACE_CS_ETM: case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index e5a8e2d4f2af..adb53e7bcabf 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -41,6 +41,7 @@ enum auxtrace_type { PERF_AUXTRACE_UNKNOWN, PERF_AUXTRACE_INTEL_PT, PERF_AUXTRACE_INTEL_BTS, + PERF_AUXTRACE_CS_ETM, }; enum itrace_period_type {
Coresight ETMs are IP blocks used to perform HW assisted tracing on a CPU core. This patch introduce the required auxiliary API functions allowing the perf core to interact with a tracer. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> --- MAINTAINERS | 3 + tools/perf/arch/arm/util/Build | 2 +- tools/perf/arch/arm/util/auxtrace.c | 54 +++++ tools/perf/arch/arm/util/cs_etm.c | 466 ++++++++++++++++++++++++++++++++++++ tools/perf/arch/arm/util/cs_etm.h | 44 ++++ tools/perf/util/auxtrace.c | 1 + tools/perf/util/auxtrace.h | 1 + 7 files changed, 570 insertions(+), 1 deletion(-) create mode 100644 tools/perf/arch/arm/util/auxtrace.c create mode 100644 tools/perf/arch/arm/util/cs_etm.c create mode 100644 tools/perf/arch/arm/util/cs_etm.h -- 2.1.4