diff options
Diffstat (limited to 'tools/perf/arch/arm')
| -rw-r--r-- | tools/perf/arch/arm/include/arch-tests.h | 7 | ||||
| -rw-r--r-- | tools/perf/arch/arm/include/perf_regs.h | 42 | ||||
| -rw-r--r-- | tools/perf/arch/arm/tests/arch-tests.c | 16 | ||||
| -rw-r--r-- | tools/perf/arch/arm/tests/vectors-page.c | 5 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/auxtrace.c | 167 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/cs-etm.c | 424 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/perf_regs.c | 2 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/pmu.c | 5 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/unwind-libdw.c | 6 | ||||
| -rw-r--r-- | tools/perf/arch/arm/util/unwind-libunwind.c | 4 |
10 files changed, 342 insertions, 336 deletions
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h index 90ec4c8cb880..452b3d904521 100644 --- a/tools/perf/arch/arm/include/arch-tests.h +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -2,11 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -#ifdef HAVE_DWARF_UNWIND_SUPPORT -struct thread; -struct perf_sample; -#endif - -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index ed20e0253e25..99a06550e25d 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP -static inline const char *perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_ARM_R0: - return "r0"; - case PERF_REG_ARM_R1: - return "r1"; - case PERF_REG_ARM_R2: - return "r2"; - case PERF_REG_ARM_R3: - return "r3"; - case PERF_REG_ARM_R4: - return "r4"; - case PERF_REG_ARM_R5: - return "r5"; - case PERF_REG_ARM_R6: - return "r6"; - case PERF_REG_ARM_R7: - return "r7"; - case PERF_REG_ARM_R8: - return "r8"; - case PERF_REG_ARM_R9: - return "r9"; - case PERF_REG_ARM_R10: - return "r10"; - case PERF_REG_ARM_FP: - return "fp"; - case PERF_REG_ARM_IP: - return "ip"; - case PERF_REG_ARM_SP: - return "sp"; - case PERF_REG_ARM_LR: - return "lr"; - case PERF_REG_ARM_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c index 6848101a855f..69561111cc6f 100644 --- a/tools/perf/arch/arm/tests/arch-tests.c +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -3,18 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .desc = "Vectors page", - .func = test__vectors_page, - }, - { - .func = NULL, - }, + &suite__vectors_page, + NULL, }; diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c index 7ffdd79971c8..55a835837466 100644 --- a/tools/perf/arch/arm/tests/vectors-page.c +++ b/tools/perf/arch/arm/tests/vectors-page.c @@ -9,8 +9,7 @@ #define VECTORS__MAP_NAME "[vectors]" -int test__vectors_page(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__vectors_page(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { void *start, *end; @@ -22,3 +21,5 @@ int test__vectors_page(struct test *test __maybe_unused, return TEST_OK; } + +DEFINE_SUITE("Vectors page", vectors_page); diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 0a6e75b8777a..deeb163999ce 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -4,16 +4,19 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <dirent.h> #include <stdbool.h> #include <linux/coresight-pmu.h> #include <linux/zalloc.h> +#include <api/fs/fs.h> -#include "../../util/auxtrace.h" -#include "../../util/debug.h" -#include "../../util/evlist.h" -#include "../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/debug.h" +#include "../../../util/evlist.h" +#include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" +#include "hisi-ptt.h" static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) { @@ -50,43 +53,114 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) return arm_spe_pmus; } +static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err) +{ + const char *sysfs = sysfs__mountpoint(); + struct perf_pmu **hisi_ptt_pmus = NULL; + struct dirent *dent; + char path[PATH_MAX]; + DIR *dir = NULL; + int idx = 0; + + snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + dir = opendir(path); + if (!dir) { + pr_err("can't read directory '%s'\n", EVENT_SOURCE_DEVICE_PATH); + *err = -EINVAL; + return NULL; + } + + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME)) + (*nr_ptts)++; + } + + if (!(*nr_ptts)) + goto out; + + hisi_ptt_pmus = zalloc(sizeof(struct perf_pmu *) * (*nr_ptts)); + if (!hisi_ptt_pmus) { + pr_err("hisi_ptt alloc failed\n"); + *err = -ENOMEM; + goto out; + } + + rewinddir(dir); + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) { + hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name); + if (hisi_ptt_pmus[idx]) + idx++; + } + } + +out: + closedir(dir); + return hisi_ptt_pmus; +} + +static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus, + int pmu_nr, struct evsel *evsel) +{ + int i; + + if (!pmus) + return NULL; + + for (i = 0; i < pmu_nr; i++) { + if (evsel->core.attr.type == pmus[i]->type) + return pmus[i]; + } + + return NULL; +} + struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { - struct perf_pmu *cs_etm_pmu; + struct perf_pmu *cs_etm_pmu = NULL; + struct perf_pmu **arm_spe_pmus = NULL; + struct perf_pmu **hisi_ptt_pmus = NULL; struct evsel *evsel; - bool found_etm = false; - bool found_spe = false; - static struct perf_pmu **arm_spe_pmus = NULL; - static int nr_spes = 0; - int i = 0; + struct perf_pmu *found_etm = NULL; + struct perf_pmu *found_spe = NULL; + struct perf_pmu *found_ptt = NULL; + int auxtrace_event_cnt = 0; + int nr_spes = 0; + int nr_ptts = 0; if (!evlist) return NULL; cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); - - if (!arm_spe_pmus) - arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); + arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); + hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err); evlist__for_each_entry(evlist, evsel) { - if (cs_etm_pmu && - evsel->core.attr.type == cs_etm_pmu->type) - found_etm = true; - - if (!nr_spes) - continue; - - for (i = 0; i < nr_spes; i++) { - if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = true; - break; - } - } + if (cs_etm_pmu && !found_etm) + found_etm = find_pmu_for_event(&cs_etm_pmu, 1, evsel); + + if (arm_spe_pmus && !found_spe) + found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel); + + if (hisi_ptt_pmus && !found_ptt) + found_ptt = find_pmu_for_event(hisi_ptt_pmus, nr_ptts, evsel); } - if (found_etm && found_spe) { - pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n"); + free(arm_spe_pmus); + free(hisi_ptt_pmus); + + if (found_etm) + auxtrace_event_cnt++; + + if (found_spe) + auxtrace_event_cnt++; + + if (found_ptt) + auxtrace_event_cnt++; + + if (auxtrace_event_cnt > 1) { + pr_err("Concurrent AUX trace operation not currently supported\n"); *err = -EOPNOTSUPP; return NULL; } @@ -96,7 +170,10 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); + + if (found_ptt) + return hisi_ptt_recording_init(err, found_ptt); #endif /* @@ -108,3 +185,35 @@ struct auxtrace_record *err = 0; return NULL; } + +#if defined(__arm__) +u64 compat_auxtrace_mmap__read_head(struct auxtrace_mmap *mm) +{ + struct perf_event_mmap_page *pc = mm->userpg; + u64 result; + + __asm__ __volatile__( +" ldrd %0, %H0, [%1]" + : "=&r" (result) + : "r" (&pc->aux_head), "Qo" (pc->aux_head) + ); + + return result; +} + +int compat_auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail) +{ + struct perf_event_mmap_page *pc = mm->userpg; + + /* Ensure all reads are done before we write the tail out */ + smp_mb(); + + __asm__ __volatile__( +" strd %2, %H2, [%1]" + : "=Qo" (pc->aux_tail) + : "r" (&pc->aux_tail), "r" (tail) + ); + + return 0; +} +#endif diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 941f814820b8..a346d5f3dafa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,18 +16,19 @@ #include <linux/zalloc.h> #include "cs-etm.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/auxtrace.h" -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/evsel_config.h" -#include "../../util/pmu.h" -#include "../../util/cs-etm.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/perf_api_probe.h" +#include "../../../util/evsel_config.h" +#include "../../../util/pmu.h" +#include "../../../util/cs-etm.h" #include <internal/lib.h> // page_size -#include "../../util/session.h" +#include "../../../util/session.h" #include <errno.h> #include <stdlib.h> @@ -37,8 +38,6 @@ struct cs_etm_recording { struct auxtrace_record itr; struct perf_pmu *cs_etm_pmu; struct evlist *evlist; - int wrapped_cnt; - bool *wrapped; bool snapshot_mode; size_t snapshot_size; }; @@ -48,15 +47,17 @@ static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { [CS_ETM_ETMIDR] = "mgmt/etmidr", }; -static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = { +static const char * const metadata_etmv4_ro[] = { [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0", [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1", [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2", [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8", [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus", + [CS_ETE_TRCDEVARCH] = "mgmt/trcdevarch" }; static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); +static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu); static int cs_etm_set_context_id(struct auxtrace_record *itr, struct evsel *evsel, int cpu) @@ -66,6 +67,7 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err = -EINVAL; u32 val; + u64 contextid; ptr = container_of(itr, struct cs_etm_recording, itr); cs_etm_pmu = ptr->cs_etm_pmu; @@ -73,7 +75,7 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, if (!cs_etm_is_etmv4(itr, cpu)) goto out; - /* Get a handle on TRCIRD2 */ + /* Get a handle on TRCIDR2 */ snprintf(path, PATH_MAX, "cpu%d/%s", cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); @@ -85,25 +87,59 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, goto out; } + /* User has configured for PID tracing, respects it. */ + contextid = evsel->core.attr.config & + (BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_CTXTID2)); + /* - * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing - * is supported: - * 0b00000 Context ID tracing is not supported. - * 0b00100 Maximum of 32-bit Context ID size. - * All other values are reserved. + * If user doesn't configure the contextid format, parse PMU format and + * enable PID tracing according to the "contextid" format bits: + * + * If bit ETM_OPT_CTXTID is set, trace CONTEXTIDR_EL1; + * If bit ETM_OPT_CTXTID2 is set, trace CONTEXTIDR_EL2. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { - err = -EINVAL; - goto out; + if (!contextid) + contextid = perf_pmu__format_bits(&cs_etm_pmu->format, + "contextid"); + + if (contextid & BIT(ETM_OPT_CTXTID)) { + /* + * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID + * tracing is supported: + * 0b00000 Context ID tracing is not supported. + * 0b00100 Maximum of 32-bit Context ID size. + * All other values are reserved. + */ + val = BMVAL(val, 5, 9); + if (!val || val != 0x4) { + pr_err("%s: CONTEXTIDR_EL1 isn't supported\n", + CORESIGHT_ETM_PMU_NAME); + err = -EINVAL; + goto out; + } + } + + if (contextid & BIT(ETM_OPT_CTXTID2)) { + /* + * TRCIDR2.VMIDOPT[30:29] != 0 and + * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid) + * We can't support CONTEXTIDR in VMID if the size of the + * virtual context id is < 32bit. + * Any value of VMIDSIZE >= 4 (i.e, > 32bit) is fine for us. + */ + if (!BMVAL(val, 29, 30) || BMVAL(val, 10, 14) < 4) { + pr_err("%s: CONTEXTIDR_EL2 isn't supported\n", + CORESIGHT_ETM_PMU_NAME); + err = -EINVAL; + goto out; + } } /* All good, let the kernel know */ - evsel->core.attr.config |= (1 << ETM_OPT_CTXTID); + evsel->core.attr.config |= contextid; err = 0; out: - return err; } @@ -155,30 +191,36 @@ out: return err; } +#define ETM_SET_OPT_CTXTID (1 << 0) +#define ETM_SET_OPT_TS (1 << 1) +#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS) + static int cs_etm_set_option(struct auxtrace_record *itr, struct evsel *evsel, u32 option) { int i, err = -EINVAL; - struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus; + struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* Set option of each CPU we have */ - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(event_cpus, i) || - !cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; - if (option & ETM_OPT_CTXTID) { + if (option & BIT(ETM_OPT_CTXTID)) { err = cs_etm_set_context_id(itr, evsel, i); if (err) goto out; } - if (option & ETM_OPT_TS) { + if (option & BIT(ETM_OPT_TS)) { err = cs_etm_set_timestamp(itr, evsel, i); if (err) goto out; } - if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS)) + if (option & ~(BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS))) /* Nothing else is currently supported */ goto out; } @@ -215,7 +257,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, struct evsel *evsel) { char msg[BUFSIZ], path[PATH_MAX], *sink; - struct perf_evsel_config_term *term; + struct evsel_config_term *term; int ret = -EINVAL; u32 hash; @@ -223,7 +265,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, return 0; list_for_each_entry(term, &evsel->config_terms, list) { - if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG) + if (term->type != EVSEL__CONFIG_TERM_DRV_CFG) continue; sink = term->val.str; @@ -232,7 +274,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, ret = perf_pmu__scan_file(pmu, path, "%x", &hash); if (ret != 1) { pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n", - sink, perf_evsel__name(evsel), errno, + sink, evsel__name(evsel), errno, str_error_r(errno, msg, sizeof(msg))); return ret; } @@ -242,10 +284,10 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, } /* - * No sink was provided on the command line - for _now_ treat - * this as an error. + * No sink was provided on the command line - allow the CoreSight + * system to look for a default */ - return ret; + return 0; } static int cs_etm_recording_options(struct auxtrace_record *itr, @@ -257,14 +299,15 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; struct evsel *evsel, *cs_etm_evsel = NULL; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); int err = 0; ptr->evlist = evlist; ptr->snapshot_mode = opts->auxtrace_snapshot_mode; - if (perf_can_record_switch_events()) + if (!record_opts__no_switch_events(opts) && + perf_can_record_switch_events()) opts->record_switch_events = true; evlist__for_each_entry(evlist, evsel) { @@ -276,6 +319,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq = 0; evsel->core.attr.sample_period = 1; + evsel->needs_auxtrace_mmap = true; cs_etm_evsel = evsel; opts->full_auxtrace = true; } @@ -337,7 +381,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); } - /* Snapshost size can't be bigger than the auxtrace area */ + /* Snapshot 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", @@ -366,25 +410,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } - /* 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); @@ -393,7 +418,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace * event must come first. */ - perf_evlist__to_front(evlist, cs_etm_evsel); + evlist__to_front(evlist, cs_etm_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the @@ -401,10 +426,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * when a context switch happened. */ if (!perf_cpu_map__empty(cpus)) { - perf_evsel__set_sample_bit(cs_etm_evsel, CPU); + evsel__set_sample_bit(cs_etm_evsel, CPU); err = cs_etm_set_option(itr, cs_etm_evsel, - ETM_OPT_CTXTID | ETM_OPT_TS); + BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS)); if (err) goto out; } @@ -413,19 +438,19 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, if (opts->full_auxtrace) { struct evsel *tracking_evsel; - err = parse_events(evlist, "dummy:u", NULL); + err = parse_event(evlist, "dummy:u"); if (err) goto out; tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ if (!perf_cpu_map__empty(cpus)) - perf_evsel__set_sample_bit(tracking_evsel, TIME); + evsel__set_sample_bit(tracking_evsel, TIME); } out: @@ -483,6 +508,11 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr) config |= BIT(ETM4_CFG_BIT_TS); if (config_opts & BIT(ETM_OPT_RETSTK)) config |= BIT(ETM4_CFG_BIT_RETSTK); + if (config_opts & BIT(ETM_OPT_CTXTID2)) + config |= BIT(ETM4_CFG_BIT_VMID) | + BIT(ETM4_CFG_BIT_VMID_OPT); + if (config_opts & BIT(ETM_OPT_BRANCH_BROADCAST)) + config |= BIT(ETM4_CFG_BIT_BB); return config; } @@ -492,29 +522,37 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, struct evlist *evlist __maybe_unused) { int i; - int etmv3 = 0, etmv4 = 0; - struct perf_cpu_map *event_cpus = evlist->core.cpus; + int etmv3 = 0, etmv4 = 0, ete = 0; + struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ if (!perf_cpu_map__empty(event_cpus)) { - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(event_cpus, i) || - !cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; - if (cs_etm_is_etmv4(itr, i)) + if (cs_etm_is_ete(itr, i)) + ete++; + else if (cs_etm_is_etmv4(itr, i)) etmv4++; else etmv3++; } } else { /* get configuration for all CPUs in the system */ - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(online_cpus, cpu)) continue; - if (cs_etm_is_etmv4(itr, i)) + if (cs_etm_is_ete(itr, i)) + ete++; + else if (cs_etm_is_etmv4(itr, i)) etmv4++; else etmv3++; @@ -524,6 +562,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, perf_cpu_map__put(online_cpus); return (CS_ETM_HEADER_SIZE + + (ete * CS_ETE_PRIV_SIZE) + (etmv4 * CS_ETMV4_PRIV_SIZE) + (etmv3 * CS_ETMV3_PRIV_SIZE)); } @@ -566,45 +605,78 @@ static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path) return val; } +#define TRCDEVARCH_ARCHPART_SHIFT 0 +#define TRCDEVARCH_ARCHPART_MASK GENMASK(11, 0) +#define TRCDEVARCH_ARCHPART(x) (((x) & TRCDEVARCH_ARCHPART_MASK) >> TRCDEVARCH_ARCHPART_SHIFT) + +#define TRCDEVARCH_ARCHVER_SHIFT 12 +#define TRCDEVARCH_ARCHVER_MASK GENMASK(15, 12) +#define TRCDEVARCH_ARCHVER(x) (((x) & TRCDEVARCH_ARCHVER_MASK) >> TRCDEVARCH_ARCHVER_SHIFT) + +static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu) +{ + struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETE_TRCDEVARCH]); + + /* + * ETE if ARCHVER is 5 (ARCHVER is 4 for ETM) and ARCHPART is 0xA13. + * See ETM_DEVARCH_ETE_ARCH in coresight-etm4x.h + */ + return TRCDEVARCH_ARCHVER(trcdevarch) == 5 && TRCDEVARCH_ARCHPART(trcdevarch) == 0xA13; +} + +static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, int cpu) +{ + struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + /* Get trace configuration register */ + data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr); + /* Get traceID from the framework */ + data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu); + /* Get read-only information from sysFS */ + data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); + data[CS_ETMV4_TRCIDR1] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR1]); + data[CS_ETMV4_TRCIDR2] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); + data[CS_ETMV4_TRCIDR8] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR8]); + data[CS_ETMV4_TRCAUTHSTATUS] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCAUTHSTATUS]); +} + static void cs_etm_get_metadata(int cpu, u32 *offset, struct auxtrace_record *itr, struct perf_record_auxtrace_info *info) { - u32 increment; + u32 increment, nr_trc_params; u64 magic; struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; /* first see what kind of tracer this cpu is affined to */ - if (cs_etm_is_etmv4(itr, cpu)) { - magic = __perf_cs_etmv4_magic; - /* Get trace configuration register */ - info->priv[*offset + CS_ETMV4_TRCCONFIGR] = - cs_etmv4_get_config(itr); - /* Get traceID from the framework */ - info->priv[*offset + CS_ETMV4_TRCTRACEIDR] = - coresight_get_trace_id(cpu); - /* Get read-only information from sysFS */ - info->priv[*offset + CS_ETMV4_TRCIDR0] = + if (cs_etm_is_ete(itr, cpu)) { + magic = __perf_cs_ete_magic; + /* ETE uses the same registers as ETMv4 plus TRCDEVARCH */ + cs_etm_save_etmv4_header(&info->priv[*offset], itr, cpu); + info->priv[*offset + CS_ETE_TRCDEVARCH] = cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); - info->priv[*offset + CS_ETMV4_TRCIDR1] = - cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro[CS_ETMV4_TRCIDR1]); - info->priv[*offset + CS_ETMV4_TRCIDR2] = - cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); - info->priv[*offset + CS_ETMV4_TRCIDR8] = - cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro[CS_ETMV4_TRCIDR8]); - info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] = - cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro - [CS_ETMV4_TRCAUTHSTATUS]); + metadata_etmv4_ro[CS_ETE_TRCDEVARCH]); + + /* How much space was used */ + increment = CS_ETE_PRIV_MAX; + nr_trc_params = CS_ETE_PRIV_MAX - CS_ETM_COMMON_BLK_MAX_V1; + } else if (cs_etm_is_etmv4(itr, cpu)) { + magic = __perf_cs_etmv4_magic; + cs_etm_save_etmv4_header(&info->priv[*offset], itr, cpu); /* How much space was used */ increment = CS_ETMV4_PRIV_MAX; + nr_trc_params = CS_ETMV4_PRIV_MAX - CS_ETMV4_TRCCONFIGR; } else { magic = __perf_cs_etmv3_magic; /* Get configuration register */ @@ -622,11 +694,13 @@ static void cs_etm_get_metadata(int cpu, u32 *offset, /* How much space was used */ increment = CS_ETM_PRIV_MAX; + nr_trc_params = CS_ETM_PRIV_MAX - CS_ETM_ETMCR; } /* Build generic header portion */ info->priv[*offset + CS_ETM_MAGIC] = magic; info->priv[*offset + CS_ETM_CPU] = cpu; + info->priv[*offset + CS_ETM_NR_TRC_PARAMS] = nr_trc_params; /* Where the next CPU entry should start from */ *offset += increment; } @@ -640,7 +714,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, u32 offset; u64 nr_cpu, type; struct perf_cpu_map *cpu_map; - struct perf_cpu_map *event_cpus = session->evlist->core.cpus; + struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); @@ -658,8 +732,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, } else { /* Make sure all specified CPUs are online */ for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) { - if (cpu_map__has(event_cpus, i) && - !cpu_map__has(online_cpus, i)) + struct perf_cpu cpu = { .cpu = i, }; + + if (perf_cpu_map__has(event_cpus, cpu) && + !perf_cpu_map__has(online_cpus, cpu)) return -EINVAL; } @@ -672,147 +748,21 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, /* First fill out the session header */ info->type = PERF_AUXTRACE_CS_ETM; - info->priv[CS_HEADER_VERSION_0] = 0; + info->priv[CS_HEADER_VERSION] = CS_HEADER_CURRENT_VERSION; info->priv[CS_PMU_TYPE_CPUS] = type << 32; info->priv[CS_PMU_TYPE_CPUS] |= nr_cpu; info->priv[CS_ETM_SNAPSHOT] = ptr->snapshot_mode; offset = CS_ETM_SNAPSHOT + 1; - for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) - if (cpu_map__has(cpu_map, i)) - cs_etm_get_metadata(i, &offset, itr, info); - - perf_cpu_map__put(online_cpus); - - return 0; -} - -static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx) -{ - bool *wrapped; - int cnt = ptr->wrapped_cnt; - - /* Make @ptr->wrapped as big as @idx */ - while (cnt <= idx) - cnt++; - - /* - * Free'ed in cs_etm_recording_free(). Using realloc() to avoid - * cross compilation problems where the host's system supports - * reallocarray() but not the target. - */ - wrapped = realloc(ptr->wrapped, cnt * sizeof(bool)); - if (!wrapped) - return -ENOMEM; - - wrapped[cnt - 1] = false; - ptr->wrapped_cnt = cnt; - ptr->wrapped = wrapped; - - return 0; -} - -static bool cs_etm_buffer_has_wrapped(unsigned char *buffer, - size_t buffer_size, u64 head) -{ - u64 i, watermark; - u64 *buf = (u64 *)buffer; - size_t buf_size = buffer_size; - - /* - * We want to look the very last 512 byte (chosen arbitrarily) in - * the ring buffer. - */ - watermark = buf_size - 512; - - /* - * @head is continuously increasing - if its value is equal or greater - * than the size of the ring buffer, it has wrapped around. - */ - if (head >= buffer_size) - return true; - - /* - * The value of @head is somewhere within the size of the ring buffer. - * This can be that there hasn't been enough data to fill the ring - * buffer yet or the trace time was so long that @head has numerically - * wrapped around. To find we need to check if we have data at the very - * end of the ring buffer. We can reliably do this because mmap'ed - * pages are zeroed out and there is a fresh mapping with every new - * session. - */ - - /* @head is less than 512 byte from the end of the ring buffer */ - if (head > watermark) - watermark = head; + for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) { + struct perf_cpu cpu = { .cpu = i, }; - /* - * Speed things up by using 64 bit transactions (see "u64 *buf" above) - */ - watermark >>= 3; - buf_size >>= 3; - - /* - * If we find trace data at the end of the ring buffer, @head has - * been there and has numerically wrapped around at least once. - */ - for (i = watermark; i < buf_size; i++) - if (buf[i]) - return true; - - return false; -} - -static int cs_etm_find_snapshot(struct auxtrace_record *itr, - int idx, struct auxtrace_mmap *mm, - unsigned char *data, - u64 *head, u64 *old) -{ - int err; - bool wrapped; - struct cs_etm_recording *ptr = - container_of(itr, struct cs_etm_recording, itr); - - /* - * Allocate memory to keep track of wrapping if this is the first - * time we deal with this *mm. - */ - if (idx >= ptr->wrapped_cnt) { - err = cs_etm_alloc_wrapped_array(ptr, idx); - if (err) - return err; - } - - /* - * Check to see if *head has wrapped around. If it hasn't only the - * amount of data between *head and *old is snapshot'ed to avoid - * bloating the perf.data file with zeros. But as soon as *head has - * wrapped around the entire size of the AUX ring buffer it taken. - */ - wrapped = ptr->wrapped[idx]; - if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) { - wrapped = true; - ptr->wrapped[idx] = true; + if (perf_cpu_map__has(cpu_map, cpu)) + cs_etm_get_metadata(i, &offset, itr, info); } - 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); - - /* No wrap has occurred, we can just use *head and *old. */ - if (!wrapped) - return 0; - - /* - * *head has wrapped around - adjust *head and *old to pickup the - * entire content of the AUX buffer. - */ - if (*head >= mm->len) { - *old = *head - mm->len; - } else { - *head += mm->len; - *old = *head - mm->len; - } + perf_cpu_map__put(online_cpus); return 0; } @@ -854,7 +804,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr) struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); - zfree(&ptr->wrapped); free(ptr); } @@ -882,7 +831,6 @@ struct auxtrace_record *cs_etm_record_init(int *err) 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; diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index bbc297a7e2e3..887c8addc491 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,8 @@ #include <linux/string.h> #include "arm-spe.h" -#include "../../util/pmu.h" +#include "hisi-ptt.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) @@ -22,6 +23,8 @@ struct perf_event_attr #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { return arm_spe_pmu_default_config(pmu); + } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { + pmu->selectable = true; #endif } diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 36ba4c69c3c5..b7692cb0c733 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 3a550225dfaf..438906bf0014 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,8 +3,8 @@ #include <errno.h> #include <libunwind.h> #include "perf_regs.h" -#include "../../util/unwind.h" -#include "../../util/debug.h" +#include "../../../util/unwind.h" +#include "../../../util/debug.h" int libunwind__arch_reg_id(int regnum) { |