diff options
Diffstat (limited to 'tools/perf/arch')
33 files changed, 449 insertions, 106 deletions
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm/include/arch-tests.h +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif 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 c7c7ec0812d5..5fc6a2a3dbc5 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -8,10 +8,10 @@ #include <linux/coresight-pmu.h> #include <linux/zalloc.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" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 515aae470e23..293a23bf8be3 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,19 +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/perf_api_probe.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> 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..b8b23b9dc598 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,7 @@ #include <linux/string.h> #include "arm-spe.h" -#include "../../util/pmu.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) 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) { diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm64/include/arch-tests.h +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c index 5b1543c98022..ad16b4f8f63e 100644 --- a/tools/perf/arch/arm64/tests/arch-tests.c +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -3,14 +3,9 @@ #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 - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index a4420d4df503..2100d46ccf5e 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -23,6 +23,7 @@ #include "../../../util/auxtrace.h" #include "../../../util/record.h" #include "../../../util/arm-spe.h" +#include <tools/libc_compat.h> // reallocarray #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -31,6 +32,8 @@ struct arm_spe_recording { struct auxtrace_record itr; struct perf_pmu *arm_spe_pmu; struct evlist *evlist; + int wrapped_cnt; + bool *wrapped; }; static void arm_spe_set_timestamp(struct auxtrace_record *itr, @@ -84,6 +87,55 @@ static int arm_spe_info_fill(struct auxtrace_record *itr, return 0; } +static void +arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts, + bool privileged) +{ + /* + * The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size nor + * snapshot size is specified, then the default is 4MiB for privileged users, 128KiB for + * unprivileged users. + * + * The default auxtrace mmap size is 4MiB/page_size for privileged users, 128KiB for + * unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages + * will be reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the + * user is likely to get an error as they exceed their mlock limmit. + */ + + /* + * No size were given to '-S' or '-m,', so go with the default + */ + if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + + /* + * '-m,xyz' was specified but no snapshot size, so make the snapshot size as big as the + * auxtrace mmap area. + */ + if (!opts->auxtrace_snapshot_size) + opts->auxtrace_snapshot_size = opts->auxtrace_mmap_pages * (size_t)page_size; + + /* + * '-Sxyz' was specified but no auxtrace mmap area, so make the auxtrace mmap area big + * enough to fit the requested snapshot size. + */ + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } +} + static int arm_spe_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) @@ -115,6 +167,36 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; + /* + * we are in snapshot mode. + */ + if (opts->auxtrace_snapshot_mode) { + /* + * Command arguments '-Sxyz' and/or '-m,xyz' are missing, so fill those in with + * default values. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) + arm_spe_snapshot_resolve_auxtrace_defaults(opts, privileged); + + /* + * 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", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + + /* + * Something went wrong somewhere - this shouldn't happen. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + } + /* We are in full trace mode but '-m,xyz' wasn't specified */ if (!opts->auxtrace_mmap_pages) { if (privileged) { @@ -138,6 +220,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } } + if (opts->auxtrace_snapshot_mode) + pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, + opts->auxtrace_snapshot_size); /* * To obtain the auxtrace buffer file descriptor, the auxtrace event @@ -166,8 +251,199 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, 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)) + if (!perf_cpu_map__empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); + evsel__set_sample_bit(tracking_evsel, CPU); + + /* also track task context switch */ + if (!record_opts__no_switch_events(opts)) + tracking_evsel->core.attr.context_switch = 1; + } + + return 0; +} + +static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, + struct record_opts *opts, + const char *str) +{ + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + + return 0; +} + +static int arm_spe_snapshot_start(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__disable(evsel); + } + return -EINVAL; +} + +static int arm_spe_snapshot_finish(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__enable(evsel); + } + return -EINVAL; +} + +static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt, new_cnt, i; + + /* + * No need to allocate, so return early. + */ + if (idx < cnt) + return 0; + + /* + * Make ptr->wrapped as big as idx. + */ + new_cnt = idx + 1; + + /* + * Free'ed in arm_spe_recording_free(). + */ + wrapped = reallocarray(ptr->wrapped, new_cnt, sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + /* + * init new allocated values. + */ + for (i = cnt; i < new_cnt; i++) + wrapped[i] = false; + + ptr->wrapped_cnt = new_cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool arm_spe_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; + + /* + * Defensively handle the case where head might be continually increasing - if its value is + * equal or greater than the size of the ring buffer, then we can safely determine it has + * wrapped around. Otherwise, continue to detect if head might have wrapped. + */ + if (head >= buffer_size) + return true; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in the ring buffer. + */ + watermark = buf_size - 512; + + /* + * 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; + + /* + * Speed things up by using 64 bit transactions (see "u64 *buf" above) + */ + watermark /= sizeof(u64); + buf_size /= sizeof(u64); + + /* + * 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 arm_spe_find_snapshot(struct auxtrace_record *itr, int idx, + struct auxtrace_mmap *mm, unsigned char *data, + u64 *head, u64 *old) +{ + int err; + bool wrapped; + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_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 = arm_spe_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 && arm_spe_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + + 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; + } return 0; } @@ -186,6 +462,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); + free(sper->wrapped); free(sper); } @@ -207,6 +484,10 @@ struct auxtrace_record *arm_spe_recording_init(int *err, sper->arm_spe_pmu = arm_spe_pmu; sper->itr.pmu = arm_spe_pmu; + sper->itr.snapshot_start = arm_spe_snapshot_start; + sper->itr.snapshot_finish = arm_spe_snapshot_finish; + sper->itr.find_snapshot = arm_spe_find_snapshot; + sper->itr.parse_snapshot_options = arm_spe_parse_snapshot_options; sper->itr.recording_options = arm_spe_recording_options; sper->itr.info_priv_size = arm_spe_info_priv_size; sper->itr.info_fill = arm_spe_info_fill; diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 2234fbd0a912..d3a18f9c85f6 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -3,7 +3,7 @@ #include "../../../util/cpumap.h" #include "../../../util/pmu.h" -struct pmu_events_map *pmu_events_map__find(void) +const struct pmu_events_map *pmu_events_map__find(void) { struct perf_pmu *pmu = NULL; diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/powerpc/include/arch-tests.h +++ b/tools/perf/arch/powerpc/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 04e5dc07e93f..93339d17acc4 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -77,6 +77,8 @@ static const char *reg_names[] = { [PERF_REG_POWERPC_PMC4] = "pmc4", [PERF_REG_POWERPC_PMC5] = "pmc5", [PERF_REG_POWERPC_PMC6] = "pmc6", + [PERF_REG_POWERPC_SDAR] = "sdar", + [PERF_REG_POWERPC_SIAR] = "siar", }; static inline const char *__perf_reg_name(int id) diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c index 8c3fbd4af817..eb98c57b5aeb 100644 --- a/tools/perf/arch/powerpc/tests/arch-tests.c +++ b/tools/perf/arch/powerpc/tests/arch-tests.c @@ -3,14 +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 = "Test dwarf unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 58b2d610aadb..e8fe36b10d20 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -40,7 +40,7 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return bufp; } -int arch_get_runtimeparam(struct pmu_event *pe) +int arch_get_runtimeparam(const struct pmu_event *pe) { int count; char path[PATH_MAX] = "/devices/hv_24x7/interface/"; diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index 16510686c138..1a9b40ea92a5 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -113,10 +113,11 @@ static int is_tracepoint_available(const char *str, struct evlist *evlist) struct parse_events_error err; int ret; - bzero(&err, sizeof(err)); + parse_events_error__init(&err); ret = parse_events(evlist, str, &err); if (err.str) - parse_events_print_error(&err, "tracepoint"); + parse_events_error__print(&err, "tracepoint"); + parse_events_error__exit(&err); return ret; } diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 8116a253f91f..8d07a78e742a 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -74,6 +74,8 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(pmc4, PERF_REG_POWERPC_PMC4), SMPL_REG(pmc5, PERF_REG_POWERPC_PMC5), SMPL_REG(pmc6, PERF_REG_POWERPC_PMC6), + SMPL_REG(sdar, PERF_REG_POWERPC_SDAR), + SMPL_REG(siar, PERF_REG_POWERPC_SIAR), SMPL_REG_END }; diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c new file mode 100644 index 000000000000..869a0eb28953 --- /dev/null +++ b/tools/perf/arch/riscv64/annotate/instructions.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "jal", 3) || + !strncmp(name, "jr", 2) || + !strncmp(name, "call", 4)) + ops = &call_ops; + else if (!strncmp(name, "ret", 3)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = riscv64__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 24ea12ec7e02..305872692bfd 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -144,9 +144,32 @@ static struct ins x86__instructions[] = { { .name = "xorps", .ops = &mov_ops, }, }; -static bool x86__ins_is_fused(struct arch *arch, const char *ins1, +static bool amd__ins_is_fused(struct arch *arch, const char *ins1, const char *ins2) { + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) +{ if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) return false; @@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; return 0; } diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 18b5500ea8bf..fe8f8dd157b4 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -370,6 +370,7 @@ 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 9599e7a3f1af..6a1a1b3c0827 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -2,15 +2,15 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -struct test; +struct test_suite; /* Tests */ -int test__rdpmc(struct test *test, int subtest); -int test__insn_x86(struct test *test, int subtest); -int test__intel_pt_pkt_decoder(struct test *test, int subtest); -int test__bp_modify(struct test *test, int subtest); -int test__x86_sample_parsing(struct test *test, int subtest); +int test__rdpmc(struct test_suite *test, int subtest); +int test__insn_x86(struct test_suite *test, int subtest); +int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); +int test__bp_modify(struct test_suite *test, int subtest); +int test__x86_sample_parsing(struct test_suite *test, int subtest); -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index 71aa67367ad6..64fb73d14d2f 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -3,39 +3,28 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { - { - .desc = "x86 rdpmc", - .func = test__rdpmc, - }, +DEFINE_SUITE("x86 rdpmc", rdpmc); +#ifdef HAVE_AUXTRACE_SUPPORT +DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86); +DEFINE_SUITE("Intel PT packet decoder", intel_pt_pkt_decoder); +#endif +#if defined(__x86_64__) +DEFINE_SUITE("x86 bp modify", bp_modify); +#endif +DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); + +struct test_suite *arch_tests[] = { + &suite__rdpmc, #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif #ifdef HAVE_AUXTRACE_SUPPORT - { - .desc = "x86 instruction decoder - new instructions", - .func = test__insn_x86, - }, - { - .desc = "Intel PT packet decoder", - .func = test__intel_pt_pkt_decoder, - }, + &suite__insn_x86, + &suite__intel_pt_pkt_decoder, #endif #if defined(__x86_64__) - { - .desc = "x86 bp modify", - .func = test__bp_modify, - }, + &suite__bp_modify, #endif - { - .desc = "x86 Sample parsing", - .func = test__x86_sample_parsing, - }, - { - .func = NULL, - }, - + &suite__x86_sample_parsing, + NULL, }; diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c index dffcf9b52153..0924ccd9e36d 100644 --- a/tools/perf/arch/x86/tests/bp-modify.c +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -204,7 +204,7 @@ out: return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; } -int test__bp_modify(struct test *test __maybe_unused, +int test__bp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 0262b0d8ccf5..94b490c434d0 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -173,7 +173,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64) * verbose (-v) option to see all the instructions and whether or not they * decoded successfully. */ -int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__insn_x86(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 27dd8cf9e060..cb5b2c6c3b3b 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -37,7 +37,7 @@ static pid_t spawn(void) * the last read counter value to avoid triggering a WARN_ON_ONCE() in * smp_call_function_many() caused by sending IPIs from NMI context. */ -int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evlist *evlist = NULL; struct evsel *evsel = NULL; diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c index c933e3dcd0a8..2fc882ab24c1 100644 --- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c @@ -289,7 +289,7 @@ static int test_one(struct test_data *d) * This test feeds byte sequences to the Intel PT packet decoder and checks the * results. Changes to the packet context are also checked. */ -int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data *d = data; int ret; diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 1ea916656a2d..498413ad9c97 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -157,7 +157,7 @@ out_close: return 0; } -int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__rdpmc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int status = 0; int wret = 0; diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c index c92db87e4479..bfbd3662b69e 100644 --- a/tools/perf/arch/x86/tests/sample-parsing.c +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -115,7 +115,7 @@ out_free: * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. */ -int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__x86_sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return do_test(PERF_SAMPLE_WEIGHT_STRUCT); } diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index 2f733cdc8dbb..ac2899a25b7a 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -1,8 +1,31 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> +#include <stdlib.h> #include "util/evsel.h" +#include "util/env.h" +#include "linux/string.h" void arch_evsel__set_sample_weight(struct evsel *evsel) { evsel__set_sample_bit(evsel, WEIGHT_STRUCT); } + +void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr) +{ + struct perf_env env = { .total_mem = 0, } ; + + if (!perf_env__cpuid(&env)) + return; + + /* + * On AMD, precise cycles event sampling internally uses IBS pmu. + * But IBS does not have filtering capabilities and perf by default + * sets exclude_guest = 1. This makes IBS pmu event init fail and + * thus perf ends up doing non-precise sampling. Avoid it by clearing + * exclude_guest. + */ + if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD")) + attr->exclude_guest = 0; + + free(env.cpuid); +} diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index eeafe97b8105..792cd75ade33 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, u8 die = ((struct iio_root_port *)evsel->priv)->die; struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); - if (count->run && count->ena) { + if (count && count->run && count->ena) { if (evsel->prev_raw_counts && !out->force_header) { struct perf_counts_values *prev_count = perf_counts(evsel->prev_raw_counts, die, 0); |