From: Adrian Hunter adrian.hunter@intel.com

mainline inclusion from mainline-v5.16-rc1 commit 8b8ff8cc3b8155c18162e8b1f70e1230db176862 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

PEBS-via-PT records contain a mask of applicable counters. To identify which event belongs to which counter, a side-band event is needed. Until now, there has been no side-band event, and consequently users were limited to using a single event.

Add such a side-band event. Note the event is optimised to output only when the counter index changes for an event. That works only so long as all PEBS-via-PT events are scheduled together, which they are for a recording session because they are in a single group.

Also no attribute bit is used to select the new event, so a new kernel is not compatible with older perf tools. The assumption being that PEBS-via-PT is sufficiently esoteric that users will not be troubled by this.

Signed-off-by: Adrian Hunter adrian.hunter@intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20210907163903.11820-2-adrian.hunter@intel.com Signed-off-by: xiabing xiabing12@h-partners.com --- arch/x86/events/core.c | 6 ++++++ arch/x86/events/intel/core.c | 16 ++++++++++++++++ arch/x86/events/perf_event.h | 1 + include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 15 +++++++++++++++ kernel/events/core.c | 30 ++++++++++++++++++++++++++++++ 6 files changed, 69 insertions(+)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 648a92e6d013..c33c90bd7c4d 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -65,6 +65,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable);

+DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); + DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); @@ -1177,6 +1179,8 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i];

+ static_call_cond(x86_pmu_assign)(event, idx); + switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: @@ -1936,6 +1940,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable);

+ static_call_update(x86_pmu_assign, x86_pmu.assign); + static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 8de383e42730..82591493fb04 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2393,6 +2393,12 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); }

+static void intel_pmu_assign_event(struct perf_event *event, int idx) +{ + if (is_pebs_pt(event)) + perf_report_aux_output_id(event, idx); +} + static void intel_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -4455,8 +4461,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value) return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; }

+static void intel_aux_output_init(void) +{ + /* Refer also intel_pmu_aux_output_match() */ + if (x86_pmu.intel_cap.pebs_output_pt_available) + x86_pmu.assign = intel_pmu_assign_event; +} + static int intel_pmu_aux_output_match(struct perf_event *event) { + /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */ if (!x86_pmu.intel_cap.pebs_output_pt_available) return 0;

@@ -5958,6 +5972,8 @@ __init int intel_pmu_init(void) if (x86_pmu.intel_cap.perf_metrics) x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;

+ intel_aux_output_init(); + return 0; }

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 11d9ab7bc792..830317dc5720 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -650,6 +650,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*assign)(struct perf_event *event, int idx); void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 39b391d6469a..86fbd9a73363 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1433,6 +1433,7 @@ perf_event_addr_filters(struct perf_event *event) }

extern void perf_event_addr_filters_sync(struct perf_event *event); +extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);

extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 4b0893023877..b0350710db6e 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1081,6 +1081,21 @@ enum perf_event_type { */ PERF_RECORD_TEXT_POKE = 20,

+ /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + PERF_RECORD_MAX, /* non-ABI */ };

diff --git a/kernel/events/core.c b/kernel/events/core.c index 28eb8152564a..93f20fb789df 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8867,6 +8867,36 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); }

+void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 hw_id; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.hw_id = hw_id; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + static int __perf_event_account_interrupt(struct perf_event *event, int throttle) {

From: James Clark james.clark@arm.com

mainline inclusion from mainline-v6.2-rc1 commit fd63091f2a0317f8943c816acf3ac5f4002adf5c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

hdr is a copy of 3 values of ptr and doesn't need to be long lived. So just use ptr instead which means the malloc and the extra error path can be removed to simplify things.

Signed-off-by: James Clark james.clark@arm.com Cc: Al Grant Al.Grant@arm.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: John Garry john.g.garry@oracle.com Cc: Leo Yan leo.yan@linaro.org Cc: Mark Rutland mark.rutland@arm.com Cc: Mathieu Poirier mathieu.poirier@linaro.org Cc: Mike Leach mike.leach@linaro.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Suzuki Poulouse suzuki.poulose@arm.com Cc: Will Deacon will@kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20221212155513.2259623-5-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: xiabing xiabing12@h-partners.com --- tools/perf/util/cs-etm.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index aab91e7b5fe5..7f9f786a5b89 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2895,7 +2895,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, int num_cpu, trcidr_idx; int err = 0; int i, j; - u64 *ptr, *hdr = NULL; + u64 *ptr = NULL; u64 **metadata = NULL; u64 hdr_version;

@@ -2922,15 +2922,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event, return -EINVAL; }

- hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_MAX); - if (!hdr) - return -ENOMEM; - - /* Extract header information - see cs-etm.h for format */ - for (i = 0; i < CS_HEADER_VERSION_MAX; i++) - hdr[i] = ptr[i]; - num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff; - pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) & + num_cpu = ptr[CS_PMU_TYPE_CPUS] & 0xffffffff; + pmu_type = (unsigned int) ((ptr[CS_PMU_TYPE_CPUS] >> 32) & 0xffffffff);

if (dump_trace) @@ -2942,10 +2935,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event, * in anything other than a sequential array is worth doing. */ traceid_list = intlist__new(NULL); - if (!traceid_list) { - err = -ENOMEM; - goto err_free_hdr; - } + if (!traceid_list) + return -ENOMEM;

metadata = zalloc(sizeof(*metadata) * num_cpu); if (!metadata) { @@ -2953,6 +2944,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event, goto err_free_traceid_list; }

+ /* Start parsing after the common part of the header */ + i = CS_HEADER_VERSION_MAX; + /* * The metadata is stored in the auxtrace_info section and encodes * the configuration of the ARM embedded trace macrocell which is @@ -3051,7 +3045,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,

etm->num_cpu = num_cpu; etm->pmu_type = pmu_type; - etm->snapshot_mode = (hdr[CS_ETM_SNAPSHOT] != 0); + etm->snapshot_mode = (ptr[CS_ETM_SNAPSHOT] != 0); etm->metadata = metadata; etm->auxtrace_type = auxtrace_info->type; etm->timeless_decoding = cs_etm__is_timeless_decoding(etm); @@ -3118,7 +3112,5 @@ int cs_etm__process_auxtrace_info(union perf_event *event, zfree(&metadata); err_free_traceid_list: intlist__delete(traceid_list); -err_free_hdr: - zfree(&hdr); return err; }

From: James Clark james.clark@arm.com

mainline inclusion from mainline-v6.2-rc1 commit 55c1de9973d665161c1c0c146ff15c6884060e19 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Printing the info doesn't have any dependency on OpenCSD, and neither does recording Coresight data. Because it's sometimes useful to look at the info for debugging, it makes sense to be able to see it on the same platform that the recording was made on.

So pull the auxtrace info printing parts into a new file that is always compiled into Perf.

Signed-off-by: James Clark james.clark@arm.com Cc: Al Grant Al.Grant@arm.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: John Garry john.g.garry@oracle.com Cc: Leo Yan leo.yan@linaro.org Cc: Mark Rutland mark.rutland@arm.com Cc: Mathieu Poirier mathieu.poirier@linaro.org Cc: Mike Leach mike.leach@linaro.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Suzuki Poulouse suzuki.poulose@arm.com Cc: Will Deacon will@kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20221212155513.2259623-6-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: xiabing xiabing12@h-partners.com --- tools/perf/util/Build | 1 + tools/perf/util/cs-etm-base.c | 174 ++++++++++++++++++++++++++++++++++ tools/perf/util/cs-etm.c | 170 ++------------------------------- tools/perf/util/cs-etm.h | 12 ++- 4 files changed, 191 insertions(+), 166 deletions(-) create mode 100644 tools/perf/util/cs-etm-base.c

diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 6bf0547bf134..b4f7189ec222 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -117,6 +117,7 @@ ifdef CONFIG_LIBOPENCSD perf-$(CONFIG_AUXTRACE) += cs-etm.o perf-$(CONFIG_AUXTRACE) += cs-etm-decoder/ endif +perf-$(CONFIG_AUXTRACE) += cs-etm-base.o

perf-y += parse-branch-options.o perf-y += dump-insn.o diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c new file mode 100644 index 000000000000..597542410854 --- /dev/null +++ b/tools/perf/util/cs-etm-base.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * File for any parts of the Coresight decoding that don't require + * OpenCSD. + */ + +#include <errno.h> +#include <inttypes.h> + +#include "cs-etm.h" + +static const char * const cs_etm_global_header_fmts[] = { + [CS_HEADER_VERSION] = " Header version %llx\n", + [CS_PMU_TYPE_CPUS] = " PMU type/num cpus %llx\n", + [CS_ETM_SNAPSHOT] = " Snapshot %llx\n", +}; + +static const char * const cs_etm_priv_fmts[] = { + [CS_ETM_MAGIC] = " Magic number %llx\n", + [CS_ETM_CPU] = " CPU %lld\n", + [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", + [CS_ETM_ETMCR] = " ETMCR %llx\n", + [CS_ETM_ETMTRACEIDR] = " ETMTRACEIDR %llx\n", + [CS_ETM_ETMCCER] = " ETMCCER %llx\n", + [CS_ETM_ETMIDR] = " ETMIDR %llx\n", +}; + +static const char * const cs_etmv4_priv_fmts[] = { + [CS_ETM_MAGIC] = " Magic number %llx\n", + [CS_ETM_CPU] = " CPU %lld\n", + [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", + [CS_ETMV4_TRCCONFIGR] = " TRCCONFIGR %llx\n", + [CS_ETMV4_TRCTRACEIDR] = " TRCTRACEIDR %llx\n", + [CS_ETMV4_TRCIDR0] = " TRCIDR0 %llx\n", + [CS_ETMV4_TRCIDR1] = " TRCIDR1 %llx\n", + [CS_ETMV4_TRCIDR2] = " TRCIDR2 %llx\n", + [CS_ETMV4_TRCIDR8] = " TRCIDR8 %llx\n", + [CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", + [CS_ETE_TRCDEVARCH] = " TRCDEVARCH %llx\n" +}; + +static const char * const param_unk_fmt = + " Unknown parameter [%d] %"PRIx64"\n"; +static const char * const magic_unk_fmt = + " Magic number Unknown %"PRIx64"\n"; + +static int cs_etm__print_cpu_metadata_v0(u64 *val, int *offset) +{ + int i = *offset, j, nr_params = 0, fmt_offset; + u64 magic; + + /* check magic value */ + magic = val[i + CS_ETM_MAGIC]; + if ((magic != __perf_cs_etmv3_magic) && + (magic != __perf_cs_etmv4_magic)) { + /* failure - note bad magic value */ + fprintf(stdout, magic_unk_fmt, magic); + return -EINVAL; + } + + /* print common header block */ + fprintf(stdout, cs_etm_priv_fmts[CS_ETM_MAGIC], val[i++]); + fprintf(stdout, cs_etm_priv_fmts[CS_ETM_CPU], val[i++]); + + if (magic == __perf_cs_etmv3_magic) { + nr_params = CS_ETM_NR_TRC_PARAMS_V0; + fmt_offset = CS_ETM_ETMCR; + /* after common block, offset format index past NR_PARAMS */ + for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) + fprintf(stdout, cs_etm_priv_fmts[j], val[i]); + } else if (magic == __perf_cs_etmv4_magic) { + nr_params = CS_ETMV4_NR_TRC_PARAMS_V0; + fmt_offset = CS_ETMV4_TRCCONFIGR; + /* after common block, offset format index past NR_PARAMS */ + for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) + fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); + } + *offset = i; + return 0; +} + +static int cs_etm__print_cpu_metadata_v1(u64 *val, int *offset) +{ + int i = *offset, j, total_params = 0; + u64 magic; + + magic = val[i + CS_ETM_MAGIC]; + /* total params to print is NR_PARAMS + common block size for v1 */ + total_params = val[i + CS_ETM_NR_TRC_PARAMS] + CS_ETM_COMMON_BLK_MAX_V1; + + if (magic == __perf_cs_etmv3_magic) { + for (j = 0; j < total_params; j++, i++) { + /* if newer record - could be excess params */ + if (j >= CS_ETM_PRIV_MAX) + fprintf(stdout, param_unk_fmt, j, val[i]); + else + fprintf(stdout, cs_etm_priv_fmts[j], val[i]); + } + } else if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) { + /* + * ETE and ETMv4 can be printed in the same block because the number of parameters + * is saved and they share the list of parameter names. ETE is also only supported + * in V1 files. + */ + for (j = 0; j < total_params; j++, i++) { + /* if newer record - could be excess params */ + if (j >= CS_ETE_PRIV_MAX) + fprintf(stdout, param_unk_fmt, j, val[i]); + else + fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); + } + } else { + /* failure - note bad magic value and error out */ + fprintf(stdout, magic_unk_fmt, magic); + return -EINVAL; + } + *offset = i; + return 0; +} + +static void cs_etm__print_auxtrace_info(u64 *val, int num) +{ + int i, cpu = 0, version, err; + + version = val[0]; + + for (i = 0; i < CS_HEADER_VERSION_MAX; i++) + fprintf(stdout, cs_etm_global_header_fmts[i], val[i]); + + for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { + if (version == 0) + err = cs_etm__print_cpu_metadata_v0(val, &i); + else if (version == 1) + err = cs_etm__print_cpu_metadata_v1(val, &i); + if (err) + return; + } +} + +/* + * Do some basic checks and print the auxtrace info header before calling + * into cs_etm__process_auxtrace_info_full() which requires OpenCSD to be + * linked in. This allows some basic debugging if OpenCSD is missing. + */ +int cs_etm__process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; + int event_header_size = sizeof(struct perf_event_header); + int num_cpu; + u64 *ptr = NULL; + u64 hdr_version; + + if (auxtrace_info->header.size < (event_header_size + INFO_HEADER_SIZE)) + return -EINVAL; + + /* First the global part */ + ptr = (u64 *) auxtrace_info->priv; + + /* Look for version of the header */ + hdr_version = ptr[0]; + if (hdr_version > CS_HEADER_CURRENT_VERSION) { + pr_err("\nCS ETM Trace: Unknown Header Version = %#" PRIx64, hdr_version); + pr_err(", version supported <= %x\n", CS_HEADER_CURRENT_VERSION); + return -EINVAL; + } + + if (dump_trace) { + num_cpu = ptr[CS_PMU_TYPE_CPUS] & 0xffffffff; + cs_etm__print_auxtrace_info(ptr, num_cpu); + } + + return cs_etm__process_auxtrace_info_full(event, session); +} diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 982ba436877a..554727076592 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2510,134 +2510,6 @@ static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) return timeless_decoding; }

-static const char * const cs_etm_global_header_fmts[] = { - [CS_HEADER_VERSION] = " Header version %llx\n", - [CS_PMU_TYPE_CPUS] = " PMU type/num cpus %llx\n", - [CS_ETM_SNAPSHOT] = " Snapshot %llx\n", -}; - -static const char * const cs_etm_priv_fmts[] = { - [CS_ETM_MAGIC] = " Magic number %llx\n", - [CS_ETM_CPU] = " CPU %lld\n", - [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", - [CS_ETM_ETMCR] = " ETMCR %llx\n", - [CS_ETM_ETMTRACEIDR] = " ETMTRACEIDR %llx\n", - [CS_ETM_ETMCCER] = " ETMCCER %llx\n", - [CS_ETM_ETMIDR] = " ETMIDR %llx\n", -}; - -static const char * const cs_etmv4_priv_fmts[] = { - [CS_ETM_MAGIC] = " Magic number %llx\n", - [CS_ETM_CPU] = " CPU %lld\n", - [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", - [CS_ETMV4_TRCCONFIGR] = " TRCCONFIGR %llx\n", - [CS_ETMV4_TRCTRACEIDR] = " TRCTRACEIDR %llx\n", - [CS_ETMV4_TRCIDR0] = " TRCIDR0 %llx\n", - [CS_ETMV4_TRCIDR1] = " TRCIDR1 %llx\n", - [CS_ETMV4_TRCIDR2] = " TRCIDR2 %llx\n", - [CS_ETMV4_TRCIDR8] = " TRCIDR8 %llx\n", - [CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", - [CS_ETE_TRCDEVARCH] = " TRCDEVARCH %llx\n" -}; - -static const char * const param_unk_fmt = - " Unknown parameter [%d] %"PRIx64"\n"; -static const char * const magic_unk_fmt = - " Magic number Unknown %"PRIx64"\n"; - -static int cs_etm__print_cpu_metadata_v0(u64 *val, int *offset) -{ - int i = *offset, j, nr_params = 0, fmt_offset; - u64 magic; - - /* check magic value */ - magic = val[i + CS_ETM_MAGIC]; - if ((magic != __perf_cs_etmv3_magic) && - (magic != __perf_cs_etmv4_magic)) { - /* failure - note bad magic value */ - fprintf(stdout, magic_unk_fmt, magic); - return -EINVAL; - } - - /* print common header block */ - fprintf(stdout, cs_etm_priv_fmts[CS_ETM_MAGIC], val[i++]); - fprintf(stdout, cs_etm_priv_fmts[CS_ETM_CPU], val[i++]); - - if (magic == __perf_cs_etmv3_magic) { - nr_params = CS_ETM_NR_TRC_PARAMS_V0; - fmt_offset = CS_ETM_ETMCR; - /* after common block, offset format index past NR_PARAMS */ - for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) - fprintf(stdout, cs_etm_priv_fmts[j], val[i]); - } else if (magic == __perf_cs_etmv4_magic) { - nr_params = CS_ETMV4_NR_TRC_PARAMS_V0; - fmt_offset = CS_ETMV4_TRCCONFIGR; - /* after common block, offset format index past NR_PARAMS */ - for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) - fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); - } - *offset = i; - return 0; -} - -static int cs_etm__print_cpu_metadata_v1(u64 *val, int *offset) -{ - int i = *offset, j, total_params = 0; - u64 magic; - - magic = val[i + CS_ETM_MAGIC]; - /* total params to print is NR_PARAMS + common block size for v1 */ - total_params = val[i + CS_ETM_NR_TRC_PARAMS] + CS_ETM_COMMON_BLK_MAX_V1; - - if (magic == __perf_cs_etmv3_magic) { - for (j = 0; j < total_params; j++, i++) { - /* if newer record - could be excess params */ - if (j >= CS_ETM_PRIV_MAX) - fprintf(stdout, param_unk_fmt, j, val[i]); - else - fprintf(stdout, cs_etm_priv_fmts[j], val[i]); - } - } else if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) { - /* - * ETE and ETMv4 can be printed in the same block because the number of parameters - * is saved and they share the list of parameter names. ETE is also only supported - * in V1 files. - */ - for (j = 0; j < total_params; j++, i++) { - /* if newer record - could be excess params */ - if (j >= CS_ETE_PRIV_MAX) - fprintf(stdout, param_unk_fmt, j, val[i]); - else - fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); - } - } else { - /* failure - note bad magic value and error out */ - fprintf(stdout, magic_unk_fmt, magic); - return -EINVAL; - } - *offset = i; - return 0; -} - -static void cs_etm__print_auxtrace_info(u64 *val, int num) -{ - int i, cpu = 0, version, err; - - version = val[0]; - - for (i = 0; i < CS_HEADER_VERSION_MAX; i++) - fprintf(stdout, cs_etm_global_header_fmts[i], val[i]); - - for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { - if (version == 0) - err = cs_etm__print_cpu_metadata_v0(val, &i); - else if (version == 1) - err = cs_etm__print_cpu_metadata_v1(val, &i); - if (err) - return; - } -} - /* * Read a single cpu parameter block from the auxtrace_info priv block. * @@ -2874,15 +2746,13 @@ static int cs_etm__queue_aux_records(struct perf_session *session) return 0; }

-int cs_etm__process_auxtrace_info(union perf_event *event, - struct perf_session *session) +int cs_etm__process_auxtrace_info_full(union perf_event *event, + struct perf_session *session) { struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; struct int_node *inode; - unsigned int pmu_type; int event_header_size = sizeof(struct perf_event_header); - int info_header_size; int total_size = auxtrace_info->header.size; int priv_size = 0; int num_cpu, trcidr_idx; @@ -2890,36 +2760,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, int i, j; u64 *ptr = NULL; u64 **metadata = NULL; - u64 hdr_version; - - /* - * sizeof(auxtrace_info_event::type) + - * sizeof(auxtrace_info_event::reserved) == 8 - */ - info_header_size = 8; - - if (total_size < (event_header_size + info_header_size)) - return -EINVAL; - - priv_size = total_size - event_header_size - info_header_size; - - /* First the global part */ - ptr = (u64 *) auxtrace_info->priv; - - /* Look for version of the header */ - hdr_version = ptr[0]; - if (hdr_version > CS_HEADER_CURRENT_VERSION) { - pr_err("\nCS ETM Trace: Unknown Header Version = %#" PRIx64, hdr_version); - pr_err(", version supported <= %x\n", CS_HEADER_CURRENT_VERSION); - return -EINVAL; - } - - num_cpu = ptr[CS_PMU_TYPE_CPUS] & 0xffffffff; - pmu_type = (unsigned int) ((ptr[CS_PMU_TYPE_CPUS] >> 32) & - 0xffffffff); - - if (dump_trace) - cs_etm__print_auxtrace_info(ptr, num_cpu);

/* * Create an RB tree for traceID-metadata tuple. Since the conversion @@ -2930,6 +2770,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (!traceid_list) return -ENOMEM;

+ /* First the global part */ + ptr = (u64 *) auxtrace_info->priv; + num_cpu = ptr[CS_PMU_TYPE_CPUS] & 0xffffffff; metadata = zalloc(sizeof(*metadata) * num_cpu); if (!metadata) { err = -ENOMEM; @@ -3008,6 +2851,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, * The following tests if the correct number of double words was * present in the auxtrace info section. */ + priv_size = total_size - event_header_size - INFO_HEADER_SIZE; if (i * 8 != priv_size) { err = -EINVAL; goto err_free_metadata; @@ -3036,7 +2880,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, etm->machine = &session->machines.host;

etm->num_cpu = num_cpu; - etm->pmu_type = pmu_type; + etm->pmu_type = (unsigned int) ((ptr[CS_PMU_TYPE_CPUS] >> 32) & 0xffffffff); etm->snapshot_mode = (ptr[CS_ETM_SNAPSHOT] != 0); etm->metadata = metadata; etm->auxtrace_type = auxtrace_info->type; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index f54834f6f9e3..d762cd150e92 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -200,9 +200,13 @@ struct cs_etm_packet_queue { #define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64)) #define CS_ETE_PRIV_SIZE (CS_ETE_PRIV_MAX * sizeof(u64))

-#ifdef HAVE_CSTRACE_SUPPORT +#define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ + sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); + +#ifdef HAVE_CSTRACE_SUPPORT int cs_etm__get_cpu(u8 trace_chan_id, int *cpu); int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt); int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq, @@ -212,10 +216,12 @@ void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id); struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id); +int cs_etm__process_auxtrace_info_full(union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused); #else static inline int -cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +cs_etm__process_auxtrace_info_full(union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) { return -1; }

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit 338a588e9db3 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The existing mechanism to assign Trace ID values to sources is limited and does not scale for larger multicore / multi trace source systems.

The API introduces functions that reserve IDs based on availabilty represented by a coresight_trace_id_map structure. This records the used and free IDs in a bitmap.

CPU bound sources such as ETMs use the coresight_trace_id_get_cpu_id coresight_trace_id_put_cpu_id pair of functions. The API will record the ID associated with the CPU. This ensures that the same ID will be re-used while perf events are active on the CPU. The put_cpu_id function will pend release of the ID until all perf cs_etm sessions are complete.

For backward compatibility the functions will attempt to use the same CPU IDs as the legacy system would have used if these are still available.

Non-cpu sources, such as the STM can use coresight_trace_id_get_system_id / coresight_trace_id_put_system_id.

Signed-off-by: Mike Leach mike.leach@linaro.org [ Fix checkpatch warning in drivers/hwtracing/coresight/coresight-trace-id.c ] Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-2-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- drivers/hwtracing/coresight/Makefile | 2 +- .../hwtracing/coresight/coresight-trace-id.c | 264 ++++++++++++++++++ .../hwtracing/coresight/coresight-trace-id.h | 156 +++++++++++ include/linux/coresight-pmu.h | 10 + 4 files changed, 431 insertions(+), 1 deletion(-) create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.c create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.h

diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index c2d6456953ad..a0984ed88996 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_CORESIGHT) += coresight.o coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \ - coresight-sysfs.o + coresight-sysfs.o coresight-trace-id.o obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o coresight-tmc-y := coresight-tmc-core.o coresight-tmc-etf.o \ coresight-tmc-etr.o diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c new file mode 100644 index 000000000000..23df04747084 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022, Linaro Limited, All rights reserved. + * Author: Mike Leach mike.leach@linaro.org + */ +#include <linux/coresight-pmu.h> +#include <linux/cpumask.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "coresight-trace-id.h" + +/* Default trace ID map. Used on systems that don't require per sink mappings */ +static struct coresight_trace_id_map id_map_default; + +/* maintain a record of the mapping of IDs and pending releases per cpu */ +static DEFINE_PER_CPU(atomic_t, cpu_id) = ATOMIC_INIT(0); +static cpumask_t cpu_id_release_pending; + +/* perf session active counter */ +static atomic_t perf_cs_etm_session_active = ATOMIC_INIT(0); + +/* lock to protect id_map and cpu data */ +static DEFINE_SPINLOCK(id_map_lock); + +/* unlocked read of current trace ID value for given CPU */ +static int _coresight_trace_id_read_cpu_id(int cpu) +{ + return atomic_read(&per_cpu(cpu_id, cpu)); +} + +/* look for next available odd ID, return 0 if none found */ +static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map) +{ + int found_id = 0, bit = 1, next_id; + + while ((bit < CORESIGHT_TRACE_ID_RES_TOP) && !found_id) { + /* + * bitmap length of CORESIGHT_TRACE_ID_RES_TOP, + * search from offset `bit`. + */ + next_id = find_next_zero_bit(id_map->used_ids, + CORESIGHT_TRACE_ID_RES_TOP, bit); + if ((next_id < CORESIGHT_TRACE_ID_RES_TOP) && (next_id & 0x1)) + found_id = next_id; + else + bit = next_id + 1; + } + return found_id; +} + +/* + * Allocate new ID and set in use + * + * if @preferred_id is a valid id then try to use that value if available. + * if @preferred_id is not valid and @prefer_odd_id is true, try for odd id. + * + * Otherwise allocate next available ID. + */ +static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map, + int preferred_id, bool prefer_odd_id) +{ + int id = 0; + + /* for backwards compatibility, cpu IDs may use preferred value */ + if (IS_VALID_CS_TRACE_ID(preferred_id) && + !test_bit(preferred_id, id_map->used_ids)) { + id = preferred_id; + goto trace_id_allocated; + } else if (prefer_odd_id) { + /* may use odd ids to avoid preferred legacy cpu IDs */ + id = coresight_trace_id_find_odd_id(id_map); + if (id) + goto trace_id_allocated; + } + + /* + * skip reserved bit 0, look at bitmap length of + * CORESIGHT_TRACE_ID_RES_TOP from offset of bit 1. + */ + id = find_next_zero_bit(id_map->used_ids, CORESIGHT_TRACE_ID_RES_TOP, 1); + if (id >= CORESIGHT_TRACE_ID_RES_TOP) + return -EINVAL; + + /* mark as used */ +trace_id_allocated: + set_bit(id, id_map->used_ids); + return id; +} + +static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + if (WARN(!test_bit(id, id_map->used_ids), "Freeing unused ID %d\n", id)) + return; + clear_bit(id, id_map->used_ids); +} + +static void coresight_trace_id_set_pend_rel(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + set_bit(id, id_map->pend_rel_ids); +} + +/* + * release all pending IDs for all current maps & clear CPU associations + * + * This currently operates on the default id map, but may be extended to + * operate on all registered id maps if per sink id maps are used. + */ +static void coresight_trace_id_release_all_pending(void) +{ + struct coresight_trace_id_map *id_map = &id_map_default; + unsigned long flags; + int cpu, bit; + + spin_lock_irqsave(&id_map_lock, flags); + for_each_set_bit(bit, id_map->pend_rel_ids, CORESIGHT_TRACE_ID_RES_TOP) { + clear_bit(bit, id_map->used_ids); + clear_bit(bit, id_map->pend_rel_ids); + } + for_each_cpu(cpu, &cpu_id_release_pending) { + atomic_set(&per_cpu(cpu_id, cpu), 0); + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + } + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (id) + goto get_cpu_id_clr_pend; + + /* + * Find a new ID. + * + * Use legacy values where possible in the dynamic trace ID allocator to + * allow older tools to continue working if they are not upgraded at the + * same time as the kernel drivers. + * + * If the generated legacy ID is invalid, or not available then the next + * available dynamic ID will be used. + */ + id = coresight_trace_id_alloc_new_id(id_map, + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu), + false); + if (!IS_VALID_CS_TRACE_ID(id)) + goto get_cpu_id_out_unlock; + + /* allocate the new id to the cpu */ + atomic_set(&per_cpu(cpu_id, cpu), id); + +get_cpu_id_clr_pend: + /* we are (re)using this ID - so ensure it is not marked for release */ + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + clear_bit(id, id_map->pend_rel_ids); + +get_cpu_id_out_unlock: + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (!id) + return; + + spin_lock_irqsave(&id_map_lock, flags); + + if (atomic_read(&perf_cs_etm_session_active)) { + /* set release at pending if perf still active */ + coresight_trace_id_set_pend_rel(id, id_map); + cpumask_set_cpu(cpu, &cpu_id_release_pending); + } else { + /* otherwise clear id */ + coresight_trace_id_free(id, id_map); + atomic_set(&per_cpu(cpu_id, cpu), 0); + } + + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + /* prefer odd IDs for system components to avoid legacy CPU IDS */ + id = coresight_trace_id_alloc_new_id(id_map, 0, true); + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map *id_map, int id) +{ + unsigned long flags; + + spin_lock_irqsave(&id_map_lock, flags); + coresight_trace_id_free(id, id_map); + spin_unlock_irqrestore(&id_map_lock, flags); +} + +/* API functions */ + +int coresight_trace_id_get_cpu_id(int cpu) +{ + return coresight_trace_id_map_get_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id); + +void coresight_trace_id_put_cpu_id(int cpu) +{ + coresight_trace_id_map_put_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id); + +int coresight_trace_id_read_cpu_id(int cpu) +{ + return _coresight_trace_id_read_cpu_id(cpu); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id); + +int coresight_trace_id_get_system_id(void) +{ + return coresight_trace_id_map_get_system_id(&id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id); + +void coresight_trace_id_put_system_id(int id) +{ + coresight_trace_id_map_put_system_id(&id_map_default, id); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); + +void coresight_trace_id_perf_start(void) +{ + atomic_inc(&perf_cs_etm_session_active); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); + +void coresight_trace_id_perf_stop(void) +{ + if (!atomic_dec_return(&perf_cs_etm_session_active)) + coresight_trace_id_release_all_pending(); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h new file mode 100644 index 000000000000..3797777d367e --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2022 Linaro Limited. All rights reserved. + * Author: Mike Leach mike.leach@linaro.org + */ + +#ifndef _CORESIGHT_TRACE_ID_H +#define _CORESIGHT_TRACE_ID_H + +/* + * Coresight trace ID allocation API + * + * With multi cpu systems, and more additional trace sources a scalable + * trace ID reservation system is required. + * + * The system will allocate Ids on a demand basis, and allow them to be + * released when done. + * + * In order to ensure that a consistent cpu / ID matching is maintained + * throughout a perf cs_etm event session - a session in progress flag will + * be maintained, and released IDs not cleared until the perf session is + * complete. This allows the same CPU to be re-allocated its prior ID. + * + * + * Trace ID maps will be created and initialised to prevent architecturally + * reserved IDs from being allocated. + * + * API permits multiple maps to be maintained - for large systems where + * different sets of cpus trace into different independent sinks. + */ + +#include <linux/bitops.h> +#include <linux/types.h> + + +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/* ID 0 is reserved */ +#define CORESIGHT_TRACE_ID_RES_0 0 + +/* ID 0x70 onwards are reserved */ +#define CORESIGHT_TRACE_ID_RES_TOP 0x70 + +/* check an ID is in the valid range */ +#define IS_VALID_CS_TRACE_ID(id) \ + ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) + +/** + * Trace ID map. + * + * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. + * Initialised so that the reserved IDs are permanently marked as + * in use. + * @pend_rel_ids: CPU IDs that have been released by the trace source but not + * yet marked as available, to allow re-allocation to the same + * CPU during a perf session. + */ +struct coresight_trace_id_map { + DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); + DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); +}; + +/* Allocate and release IDs for a single default trace ID map */ + +/** + * Read and optionally allocate a CoreSight trace ID and associate with a CPU. + * + * Function will read the current trace ID for the associated CPU, + * allocating an new ID if one is not currently allocated. + * + * Numeric ID values allocated use legacy allocation algorithm if possible, + * otherwise any available ID is used. + * + * @cpu: The CPU index to allocate for. + * + * return: CoreSight trace ID or -EINVAL if allocation impossible. + */ +int coresight_trace_id_get_cpu_id(int cpu); + +/** + * Release an allocated trace ID associated with the CPU. + * + * This will release the CoreSight trace ID associated with the CPU, + * unless a perf session is in operation. + * + * If a perf session is in operation then the ID will be marked as pending + * release. + * + * @cpu: The CPU index to release the associated trace ID. + */ +void coresight_trace_id_put_cpu_id(int cpu); + +/** + * Read the current allocated CoreSight Trace ID value for the CPU. + * + * Fast read of the current value that does not allocate if no ID allocated + * for the CPU. + * + * Used in perf context where it is known that the value for the CPU will not + * be changing, when perf starts and event on a core and outputs the Trace ID + * for the CPU as a packet in the data file. IDs cannot change during a perf + * session. + * + * This function does not take the lock protecting the ID lists, avoiding + * locking dependency issues with perf locks. + * + * @cpu: The CPU index to read. + * + * return: current value, will be 0 if unallocated. + */ +int coresight_trace_id_read_cpu_id(int cpu); + +/** + * Allocate a CoreSight trace ID for a system component. + * + * Unconditionally allocates a Trace ID, without associating the ID with a CPU. + * + * Used to allocate IDs for system trace sources such as STM. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_system_id(void); + +/** + * Release an allocated system trace ID. + * + * Unconditionally release a trace ID allocated to a system component. + * + * @id: value of trace ID allocated. + */ +void coresight_trace_id_put_system_id(int id); + +/* notifiers for perf session start and stop */ + +/** + * Notify the Trace ID allocator that a perf session is starting. + * + * Increase the perf session reference count - called by perf when setting up + * a trace event. + * + * This reference count is used by the ID allocator to ensure that trace IDs + * associated with a CPU cannot change or be released during a perf session. + */ +void coresight_trace_id_perf_start(void); + +/** + * Notify the ID allocator that a perf session is stopping. + * + * Decrease the perf session reference count. + * if this causes the count to go to zero, then all Trace IDs marked as pending + * release, will be released. + */ +void coresight_trace_id_perf_stop(void); + +#endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index b0e35eec6499..d2f4f6500ead 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -10,6 +10,16 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10

+/* + * The legacy Trace ID system based on fixed calculation from the cpu + * number. This has been replaced by drivers using a dynamic allocation + * system - but need to retain the legacy algorithm for backward comparibility + * in certain situations:- + * a) new perf running on older systems that generate the legacy mapping + * b) older tools that may not update at the same time as the kernel. + */ +#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) + /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit 4ff1fdb4125c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Adds in calls to allocate and release Trace ID for the CPUs in use by the perf session.

Adds in notifier calls to the trace ID allocator that perf events are starting and stopping.

This ensures that Trace IDs associated with CPUs remain the same throughout the perf session, and are only released when all perf sessions are complete.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-4-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 34a920fbb08d..c6ec0b2c2512 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -20,6 +20,7 @@

#include "coresight-etm-perf.h" #include "coresight-priv.h" +#include "coresight-trace-id.h"

static struct pmu etm_pmu; static bool etm_perf_up; @@ -175,8 +176,12 @@ static void free_event_data(struct work_struct *work) if (!(IS_ERR_OR_NULL(*ppath))) coresight_release_path(*ppath); *ppath = NULL; + coresight_trace_id_put_cpu_id(cpu); }

+ /* mark perf event as done for trace id allocator */ + coresight_trace_id_perf_stop(); + free_percpu(event_data->path); kfree(event_data); } @@ -228,6 +233,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, { u32 id; int cpu = event->cpu; + int trace_id; cpumask_t *mask; struct coresight_device *sink = NULL; struct etm_event_data *event_data = NULL; @@ -243,6 +249,9 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, sink = coresight_get_sink_by_id(id); }

+ /* tell the trace ID allocator that a perf event is starting up */ + coresight_trace_id_perf_start(); + mask = &event_data->mask;

/* @@ -288,6 +297,13 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, continue; }

+ /* ensure we can allocate a trace ID for this CPU */ + trace_id = coresight_trace_id_get_cpu_id(cpu); + if (!IS_VALID_CS_TRACE_ID(trace_id)) { + cpumask_clear_cpu(cpu, mask); + continue; + } + *etm_event_cpu_path_ptr(event_data, cpu) = path; }

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit df4871204e5d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The trace ID API is now used to allocate trace IDs for ETM4.x / ETE devices.

For perf sessions, these will be allocated on enable, and released on disable.

For sysfs sessions, these will be allocated on enable, but only released on reset. This allows the sysfs session to interrogate the Trace ID used after the session is over - maintaining functional consistency with the previous allocation scheme.

The trace ID will also be allocated on read of the mgmt/trctraceid file. This ensures that if perf or sysfs read this before enabling trace, the value will be the one used for the trace session.

Trace ID initialisation is removed from the _probe() function.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-6-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- .../coresight/coresight-etm4x-core.c | 73 +++++++++++++++++-- .../coresight/coresight-etm4x-sysfs.c | 27 ++++++- drivers/hwtracing/coresight/coresight-etm4x.h | 3 + 3 files changed, 93 insertions(+), 10 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 46522839e684..6099b750e782 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -40,6 +40,7 @@ #include "coresight-etm4x.h" #include "coresight-etm-perf.h" #include "coresight-self-hosted-trace.h" +#include "coresight-trace-id.h"

static int boot_enable; module_param(boot_enable, int, 0444); @@ -215,6 +216,30 @@ static int etm4_trace_id(struct coresight_device *csdev) return drvdata->trcid; }

+int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata) +{ + int trace_id; + + /* + * This will allocate a trace ID to the cpu, + * or return the one currently allocated. + * The trace id function has its own lock + */ + trace_id = coresight_trace_id_get_cpu_id(drvdata->cpu); + if (IS_VALID_CS_TRACE_ID(trace_id)) + drvdata->trcid = (u8)trace_id; + else + dev_err(&drvdata->csdev->dev, + "Failed to allocate trace ID for %s on CPU%d\n", + dev_name(&drvdata->csdev->dev), drvdata->cpu); + return trace_id; +} + +void etm4_release_trace_id(struct etmv4_drvdata *drvdata) +{ + coresight_trace_id_put_cpu_id(drvdata->cpu); +} + struct etm4_enable_arg { struct etmv4_drvdata *drvdata; int rc; @@ -692,7 +717,7 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, static int etm4_enable_perf(struct coresight_device *csdev, struct perf_event *event) { - int ret = 0; + int ret = 0, trace_id; struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);

if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) { @@ -704,6 +729,24 @@ static int etm4_enable_perf(struct coresight_device *csdev, ret = etm4_parse_event_config(drvdata, event); if (ret) goto out; + + /* + * perf allocates cpu ids as part of _setup_aux() - device needs to use + * the allocated ID. This reads the current version without allocation. + * + * This does not use the trace id lock to prevent lock_dep issues + * with perf locks - we know the ID cannot change until perf shuts down + * the session + */ + trace_id = coresight_trace_id_read_cpu_id(drvdata->cpu); + if (!IS_VALID_CS_TRACE_ID(trace_id)) { + dev_err(&drvdata->csdev->dev, "Failed to set trace ID for %s on CPU%d\n", + dev_name(&drvdata->csdev->dev), drvdata->cpu); + ret = -EINVAL; + goto out; + } + drvdata->trcid = (u8)trace_id; + /* And enable it */ ret = etm4_enable_hw(drvdata);

@@ -719,6 +762,11 @@ static int etm4_enable_sysfs(struct coresight_device *csdev)

spin_lock(&drvdata->spinlock);

+ /* sysfs needs to read and allocate a trace ID */ + ret = etm4_read_alloc_trace_id(drvdata); + if (ret < 0) + goto unlock_sysfs_enable; + /* * Executing etm4_enable_hw on the cpu whose ETM is being enabled * ensures that register writes occur when cpu is powered. @@ -730,6 +778,11 @@ static int etm4_enable_sysfs(struct coresight_device *csdev) ret = arg.rc; if (!ret) drvdata->sticky_enable = true; + + if (ret) + etm4_release_trace_id(drvdata); + +unlock_sysfs_enable: spin_unlock(&drvdata->spinlock);

if (!ret) @@ -854,6 +907,11 @@ static int etm4_disable_perf(struct coresight_device *csdev, /* TRCVICTLR::SSSTATUS, bit[9] */ filters->ssstatus = (control & BIT(9));

+ /* + * perf will release trace ids when _free_aux() is + * called at the end of the session. + */ + return 0; }

@@ -879,6 +937,13 @@ static void etm4_disable_sysfs(struct coresight_device *csdev) spin_unlock(&drvdata->spinlock); cpus_read_unlock();

+ /* + * we only release trace IDs when resetting sysfs. + * This permits sysfs users to read the trace ID after the trace + * session has completed. This maintains operational behaviour with + * prior trace id allocation method + */ + dev_dbg(&csdev->dev, "ETM tracing disabled\n"); }

@@ -1567,11 +1632,6 @@ static int etm4_dying_cpu(unsigned int cpu) return 0; }

-static void etm4_init_trace_id(struct etmv4_drvdata *drvdata) -{ - drvdata->trcid = coresight_get_trace_id(drvdata->cpu); -} - static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) { int i, ret = 0; @@ -1977,7 +2037,6 @@ static int etm4_probe(struct device *dev, void __iomem *base, u32 etm_pid) if (!desc.name) return -ENOMEM;

- etm4_init_trace_id(drvdata); etm4_set_default(&drvdata->config);

pdata = coresight_get_platform_data(dev); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index 4ce3927024ae..ae2be018ad8f 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -265,10 +265,11 @@ static ssize_t reset_store(struct device *dev, config->vmid_mask0 = 0x0; config->vmid_mask1 = 0x0;

- drvdata->trcid = drvdata->cpu + 1; - spin_unlock(&drvdata->spinlock);

+ /* for sysfs - only release trace id when resetting */ + etm4_release_trace_id(drvdata); + return size; } static DEVICE_ATTR_WO(reset); @@ -2322,6 +2323,26 @@ static struct attribute *coresight_etmv4_attrs[] = { NULL, };

+/* + * Trace ID allocated dynamically on enable - but also allocate on read + * in case sysfs or perf read before enable to ensure consistent metadata + * information for trace decode + */ +static ssize_t trctraceid_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int trace_id; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + + trace_id = etm4_read_alloc_trace_id(drvdata); + if (trace_id < 0) + return trace_id; + + return sysfs_emit(buf, "0x%x\n", trace_id); +} +static DEVICE_ATTR_RO(trctraceid); + struct etmv4_reg { struct coresight_device *csdev; u32 offset; @@ -2458,7 +2479,7 @@ static struct attribute *coresight_etmv4_mgmt_attrs[] = { coresight_etm4x_reg(trcpidr3, TRCPIDR3), coresight_etm4x_reg(trcoslsr, TRCOSLSR), coresight_etm4x_reg(trcconfig, TRCCONFIGR), - coresight_etm4x_reg(trctraceid, TRCTRACEIDR), + &dev_attr_trctraceid.attr, coresight_etm4x_reg(trcdevarch, TRCDEVARCH), NULL, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 894041f69842..97669ea32653 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -987,4 +987,7 @@ static inline bool etm4x_is_ete(struct etmv4_drvdata *drvdata) { return drvdata->arch >= ETM_ARCH_ETE; } + +int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata); +void etm4_release_trace_id(struct etmv4_drvdata *drvdata); #endif

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit 42708bac18cf category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

CoreSight sources provide a callback (.trace_id) in the standard source ops which returns the ID to the core code. This was used to check that sources all had a unique Trace ID.

Uniqueness is now gauranteed by the Trace ID allocation system, and the check code has been removed from the core.

This patch removes the unneeded and unused .trace_id source ops from the ops structure and implementations in etm3x, etm4x and stm.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-8-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- drivers/hwtracing/coresight/coresight-etm.h | 1 - .../coresight/coresight-etm3x-core.c | 37 ------------------- .../coresight/coresight-etm4x-core.c | 8 ---- drivers/hwtracing/coresight/coresight-stm.c | 8 ---- include/linux/coresight.h | 3 -- 5 files changed, 57 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h index 3667428d38b6..9a0d08b092ae 100644 --- a/drivers/hwtracing/coresight/coresight-etm.h +++ b/drivers/hwtracing/coresight/coresight-etm.h @@ -283,7 +283,6 @@ static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off) }

extern const struct attribute_group *coresight_etm_groups[]; -int etm_get_trace_id(struct etm_drvdata *drvdata); void etm_set_default(struct etm_config *config); void etm_config_trace_mode(struct etm_config *config); struct etm_config *get_etm_config(struct etm_drvdata *drvdata); diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index b8ca7cd38f15..d970d578b5be 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -451,42 +451,6 @@ static int etm_cpu_id(struct coresight_device *csdev) return drvdata->cpu; }

-int etm_get_trace_id(struct etm_drvdata *drvdata) -{ - unsigned long flags; - int trace_id = -1; - struct device *etm_dev; - - if (!drvdata) - goto out; - - etm_dev = drvdata->csdev->dev.parent; - if (!local_read(&drvdata->mode)) - return drvdata->traceid; - - pm_runtime_get_sync(etm_dev); - - spin_lock_irqsave(&drvdata->spinlock, flags); - - CS_UNLOCK(drvdata->base); - trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); - CS_LOCK(drvdata->base); - - spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(etm_dev); - -out: - return trace_id; - -} - -static int etm_trace_id(struct coresight_device *csdev) -{ - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return etm_get_trace_id(drvdata); -} - int etm_read_alloc_trace_id(struct etm_drvdata *drvdata) { int trace_id; @@ -733,7 +697,6 @@ static void etm_disable(struct coresight_device *csdev,

static const struct coresight_ops_source etm_source_ops = { .cpu_id = etm_cpu_id, - .trace_id = etm_trace_id, .enable = etm_enable, .disable = etm_disable, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 6099b750e782..870c628047b4 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -209,13 +209,6 @@ static int etm4_cpu_id(struct coresight_device *csdev) return drvdata->cpu; }

-static int etm4_trace_id(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->trcid; -} - int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata) { int trace_id; @@ -977,7 +970,6 @@ static void etm4_disable(struct coresight_device *csdev,

static const struct coresight_ops_source etm4_source_ops = { .cpu_id = etm4_cpu_id, - .trace_id = etm4_trace_id, .enable = etm4_enable, .disable = etm4_disable, }; diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 9d8229346a09..3d95da870e63 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -281,15 +281,7 @@ static void stm_disable(struct coresight_device *csdev, } }

-static int stm_trace_id(struct coresight_device *csdev) -{ - struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->traceid; -} - static const struct coresight_ops_source stm_source_ops = { - .trace_id = stm_trace_id, .enable = stm_enable, .disable = stm_disable, }; diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 36e6913e50fd..42ec64fc8d85 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -312,14 +312,11 @@ struct coresight_ops_link { * Operations available for sources. * @cpu_id: returns the value of the CPU number this component * is associated to. - * @trace_id: returns the value of the component's trace ID as known - * to the HW. * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); - int (*trace_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, u32 mode); void (*disable)(struct coresight_device *csdev,

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.4-rc1 commit 092772955568 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The information to associate Trace ID and CPU will be changing.

Drivers will start outputting this as a hardware ID packet in the data file which if present will be used in preference to the AUXINFO values.

To prepare for this we provide a helper functions to do the individual ID mapping, and one to extract the IDs from the completed metadata blocks.

Reviewed-by: James Clark james.clark@arm.com Signed-off-by: Mike Leach mike.leach@linaro.org Acked-by: Suzuki Poulouse suzuki.poulose@arm.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Darren Hart darren@os.amperecomputing.com Cc: Ganapatrao Kulkarni gankulkarni@os.amperecomputing.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Leo Yan leo.yan@linaro.org Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Will Deacon will@kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230331055645.26918-2-mike.leach@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: xiabing xiabing12@h-partners.com --- tools/include/linux/coresight-pmu.h | 5 ++ tools/perf/util/cs-etm-base.c | 3 +- tools/perf/util/cs-etm.c | 92 +++++++++++++++++++---------- tools/perf/util/cs-etm.h | 14 ++++- 4 files changed, 79 insertions(+), 35 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 5e8a5c541fe7..d74c5efe09f5 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -7,9 +7,14 @@ #ifndef _LINUX_CORESIGHT_PMU_H #define _LINUX_CORESIGHT_PMU_H

+#include <linux/bits.h> + #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10

+/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_BRANCH_BROADCAST 8 #define ETM_OPT_CYCACC 12 diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c index 282042c6e944..43e7ec008283 100644 --- a/tools/perf/util/cs-etm-base.c +++ b/tools/perf/util/cs-etm-base.c @@ -146,7 +146,8 @@ static void cs_etm__print_auxtrace_info(u64 *val, int num) for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { if (version == 0) err = cs_etm__print_cpu_metadata_v0(val, &i); - else if (version == 1) + /* printing same for both, but value bit flags added on v2 */ + else if ((version == 1) || (version == 2)) err = cs_etm__print_cpu_metadata_v1(val, &i); if (err) return; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 6fdcb0432789..fa0cb8748bce 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -193,6 +193,30 @@ int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt) return 0; }

+static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata) +{ + struct int_node *inode; + + /* Get an RB node for this CPU */ + inode = intlist__findnew(traceid_list, trace_chan_id); + + /* Something went wrong, no need to continue */ + if (!inode) + return -ENOMEM; + + /* + * The node for that CPU should not be taken. + * Back out if that's the case. + */ + if (inode->priv) + return -EINVAL; + + /* All good, associate the traceID with the metadata pointer */ + inode->priv = cpu_metadata; + + return 0; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { @@ -2746,16 +2770,45 @@ static int cs_etm__queue_aux_records(struct perf_session *session) return 0; }

+/* map trace ids to correct metadata block, from information in metadata */ +static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) +{ + u64 cs_etm_magic; + u8 trace_chan_id; + int i, err; + + for (i = 0; i < num_cpu; i++) { + cs_etm_magic = metadata[i][CS_ETM_MAGIC]; + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + default: + /* unknown magic number */ + return -EINVAL; + } + err = cs_etm__map_trace_id(trace_chan_id, metadata[i]); + if (err) + return err; + } + return 0; +} + int cs_etm__process_auxtrace_info_full(union perf_event *event, struct perf_session *session) { struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; - struct int_node *inode; int event_header_size = sizeof(struct perf_event_header); int total_size = auxtrace_info->header.size; int priv_size = 0; - int num_cpu, trcidr_idx; + int num_cpu; int err = 0; int i, j; u64 *ptr = NULL; @@ -2794,23 +2847,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, cs_etm__create_meta_blk(ptr, &i, CS_ETM_PRIV_MAX, CS_ETM_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETM_ETMTRACEIDR; - } else if (ptr[i] == __perf_cs_etmv4_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETMV4_PRIV_MAX, CS_ETMV4_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else if (ptr[i] == __perf_cs_ete_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETE_PRIV_MAX, -1); - - /* ETE shares first part of metadata with ETMv4 */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else { ui__error("CS ETM Trace: Unrecognised magic number %#"PRIx64". File could be from a newer version of perf.\n", ptr[i]); @@ -2822,26 +2865,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, err = -ENOMEM; goto err_free_metadata; } - - /* Get an RB node for this CPU */ - inode = intlist__findnew(traceid_list, metadata[j][trcidr_idx]); - - /* Something went wrong, no need to continue */ - if (!inode) { - err = -ENOMEM; - goto err_free_metadata; - } - - /* - * The node for that CPU should not be taken. - * Back out if that's the case. - */ - if (inode->priv) { - err = -EINVAL; - goto err_free_metadata; - } - /* All good, associate the traceID with the metadata pointer */ - inode->priv = metadata[j]; }

/* @@ -2919,6 +2942,11 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, if (err) goto err_delete_thread;

+ /* before aux records are queued, need to map metadata to trace IDs */ + err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + if (err) + goto err_delete_thread; + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index c9f4a85b37e9..16d53e1db50c 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -27,13 +27,17 @@ enum { /* * Update the version for new format. * - * New version 1 format adds a param count to the per cpu metadata. + * Version 1: format adds a param count to the per cpu metadata. * This allows easy adding of new metadata parameters. * Requires that new params always added after current ones. * Also allows client reader to handle file versions that are different by * checking the number of params in the file vs the number expected. + * + * Version 2: Drivers will use PERF_RECORD_AUX_OUTPUT_HW_ID to output + * CoreSight Trace ID. ...TRACEIDR metadata will be set to legacy values + * but with addition flags. */ -#define CS_HEADER_CURRENT_VERSION 1 +#define CS_HEADER_CURRENT_VERSION 2

/* Beginning of header common to both ETMv3 and V4 */ enum { @@ -93,6 +97,12 @@ enum { CS_ETE_PRIV_MAX };

+/* + * Check for valid CoreSight trace ID. If an invalid value is present in the metadata, + * then IDs are present in the hardware ID packet in the data file. + */ +#define CS_IS_VALID_TRACE_ID(id) ((id > 0) && (id < 0x70)) + /* * ETMv3 exception encoding number: * See Embedded Trace Macrocell spcification (ARM IHI 0014Q)

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit 7d30d480a691 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

CoreSight trace being updated to use the perf_report_aux_output_id() in a similar way to intel-pt.

This function in needs export visibility to allow it to be called from kernel loadable modules, which CoreSight may configured to be built as.

Signed-off-by: Mike Leach mike.leach@linaro.org Acked-by: Suzuki K Poulose suzuki.poulose@arm.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-12-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c index 93f20fb789df..061c1aaae901 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8896,6 +8896,7 @@ void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)

perf_output_end(&handle); } +EXPORT_SYMBOL_GPL(perf_report_aux_output_id);

static int __perf_event_account_interrupt(struct perf_event *event, int throttle)

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.3-rc1 commit aa19bb4c3583 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Use the perf_report_aux_output_id() call to output the CoreSight trace ID and associated CPU as a PERF_RECORD_AUX_OUTPUT_HW_ID record in the perf.data file.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230116124928.5440-14-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 7 +++++++ include/linux/coresight-pmu.h | 14 ++++++++++++++ 2 files changed, 21 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index c6ec0b2c2512..d5ab38278abf 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier mathieu.poirier@linaro.org */

+#include <linux/bitfield.h> #include <linux/coresight.h> #include <linux/coresight-pmu.h> #include <linux/cpumask.h> @@ -343,6 +344,7 @@ static void etm_event_start(struct perf_event *event, int flags) struct perf_output_handle *handle = &ctxt->handle; struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); struct list_head *path; + u64 hw_id;

if (!csdev) goto fail; @@ -388,6 +390,11 @@ static void etm_event_start(struct perf_event *event, int flags) if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) goto fail_disable_path;

+ /* output cpu / trace ID in perf record */ + hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, CS_AUX_HW_ID_CURR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, coresight_trace_id_read_cpu_id(cpu)); + perf_report_aux_output_id(event, hw_id); + out: /* Tell the perf core the event is alive */ event->hw.state = 0; diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index f73b7797ba9a..286dafc4a8d6 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -7,6 +7,8 @@ #ifndef _LINUX_CORESIGHT_PMU_H #define _LINUX_CORESIGHT_PMU_H

+#include <linux/bits.h> + #define CORESIGHT_ETM_PMU_NAME "cs_etm"

/* @@ -31,4 +33,16 @@ #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12

+/* + * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. + * Used to associate a CPU with the CoreSight Trace ID. + * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. + * [59:08] - Unused (SBZ) + * [63:60] - Version + */ +#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0) +#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_CURR_VERSION 0 + #endif

From: Suzuki K Poulose suzuki.poulose@arm.com

mainline inclusion from mainline-v6.3-rc1 commit a646ca099b18 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

With the dynamic traceid allocation scheme in, we output the AUX_OUTPUT_HWID packet every time event->start() is called. This could cause too many such records in the perf.data, while only one per CPU throughout the life time of the event is required. Make sure we only output it once.

Before this patch: $ perf report -D | grep OUTPUT_HW_ID ... AUX_OUTPUT_HW_ID events: 55 (18.3%)

After this patch:

$ perf report -D | grep OUTPUT_HW_ID ... AUX_OUTPUT_HW_ID events: 5 ( 1.9%)

Cc: Mike Leach mike.leach@linaro.org Cc: James Clark james.clark@arm.com Cc: Leo Yan leo.yan@linaro.org Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Reviewed-by: James Clark james.clark@arm.com Link: https://lore.kernel.org/r/20230120103434.864318-1-suzuki.poulose@arm.com Signed-off-by: xiabing xiabing12@h-partners.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 16 ++++++++++++---- drivers/hwtracing/coresight/coresight-etm-perf.h | 2 ++ 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index d5ab38278abf..a0f63ea0ffbb 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -390,10 +390,18 @@ static void etm_event_start(struct perf_event *event, int flags) if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) goto fail_disable_path;

- /* output cpu / trace ID in perf record */ - hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, CS_AUX_HW_ID_CURR_VERSION); - hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, coresight_trace_id_read_cpu_id(cpu)); - perf_report_aux_output_id(event, hw_id); + /* + * output cpu / trace ID in perf record, once for the lifetime + * of the event. + */ + if (!cpumask_test_cpu(cpu, &event_data->aux_hwid_done)) { + cpumask_set_cpu(cpu, &event_data->aux_hwid_done); + hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, + CS_AUX_HW_ID_CURR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, + coresight_trace_id_read_cpu_id(cpu)); + perf_report_aux_output_id(event, hw_id); + }

out: /* Tell the perf core the event is alive */ diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h index 3e4f2ad5e193..edeb91551550 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.h +++ b/drivers/hwtracing/coresight/coresight-etm-perf.h @@ -47,12 +47,14 @@ struct etm_filters { * struct etm_event_data - Coresight specifics associated to an event * @work: Handle to free allocated memory outside IRQ context. * @mask: Hold the CPU(s) this event was set for. + * @aux_hwid_done: Whether a CPU has emitted the TraceID packet or not. * @snk_config: The sink configuration. * @path: An array of path, each slot for one CPU. */ struct etm_event_data { struct work_struct work; cpumask_t mask; + cpumask_t aux_hwid_done; void *snk_config; struct list_head * __percpu *path; };

From: Mike Leach mike.leach@linaro.org

mainline inclusion from mainline-v6.5-rc1 commit 9f37d3798026 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I85PIL CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The trace ID patchset adjusted the handling of the TRCTRACEIDR register sysfs to allocate on read.

Although this was initally correct, the final version of the patch series introduced an error which resulted in the mgmt/trctraceidr file in sysfs not being visible.

This patch fixes that issue.

Fixes: df4871204e5d ("coresight: etm4x: Update ETM4 driver to use Trace ID API") Reported-by: Junhao He hejunhao3@huawei.com Link: https://lists.linaro.org/archives/list/coresight@lists.linaro.org/thread/KK3... Signed-off-by: Mike Leach mike.leach@linaro.org Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230512133054.235073-1-mike.leach@linaro.org Signed-off-by: xiabing xiabing12@h-partners.com --- .../coresight/coresight-etm4x-sysfs.c | 27 ++++++++++++------- 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index ae2be018ad8f..29479488004a 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -2341,7 +2341,6 @@ static ssize_t trctraceid_show(struct device *dev,

return sysfs_emit(buf, "0x%x\n", trace_id); } -static DEVICE_ATTR_RO(trctraceid);

struct etmv4_reg { struct coresight_device *csdev; @@ -2458,13 +2457,23 @@ coresight_etm4x_attr_reg_implemented(struct kobject *kobj, return 0; }

-#define coresight_etm4x_reg(name, offset) \ - &((struct dev_ext_attribute[]) { \ - { \ - __ATTR(name, 0444, coresight_etm4x_reg_show, NULL), \ - (void *)(unsigned long)offset \ - } \ - })[0].attr.attr +/* + * Macro to set an RO ext attribute with offset and show function. + * Offset is used in mgmt group to ensure only correct registers for + * the ETM / ETE variant are visible. + */ +#define coresight_etm4x_reg_showfn(name, offset, showfn) ( \ + &((struct dev_ext_attribute[]) { \ + { \ + __ATTR(name, 0444, showfn, NULL), \ + (void *)(unsigned long)offset \ + } \ + })[0].attr.attr \ + ) + +/* macro using the default coresight_etm4x_reg_show function */ +#define coresight_etm4x_reg(name, offset) \ + coresight_etm4x_reg_showfn(name, offset, coresight_etm4x_reg_show)

static struct attribute *coresight_etmv4_mgmt_attrs[] = { coresight_etm4x_reg(trcpdcr, TRCPDCR), @@ -2479,7 +2488,7 @@ static struct attribute *coresight_etmv4_mgmt_attrs[] = { coresight_etm4x_reg(trcpidr3, TRCPIDR3), coresight_etm4x_reg(trcoslsr, TRCOSLSR), coresight_etm4x_reg(trcconfig, TRCCONFIGR), - &dev_attr_trctraceid.attr, + coresight_etm4x_reg_showfn(trctraceid, TRCTRACEIDR, trctraceid_show), coresight_etm4x_reg(trcdevarch, TRCDEVARCH), NULL, };