From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> To: Petri Latvala <adrinael@adrinael.net>, Arkadiusz Hiler <arek@hiler.eu>, Kamil Konieczny <kamil.konieczny@linux.intel.com> Cc: igt-dev@lists.freedesktop.org, intel-gfx@lists.freedesktop.org, Chris Wilson <chris.p.wilson@linux.intel.com> Subject: [Intel-gfx] [PATCH i-g-t 1/2] i915/perf: Stress opening of new perf streams against existing contexts Date: Tue, 31 Jan 2023 10:17:30 +0100 [thread overview] Message-ID: <20230131091731.5892-2-janusz.krzysztofik@linux.intel.com> (raw) In-Reply-To: <20230131091731.5892-1-janusz.krzysztofik@linux.intel.com> From: Chris Wilson <chris.p.wilson@linux.intel.com> Try opening the perf stream while there is a flurry of activity on the system, both new and old contexts. This will exercise the ability of the driver to modify those contexts to work with perf. References: https://gitlab.freedesktop.org/drm/intel/-/issues/6333 Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com> Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> Cc: Andi Shyti <andi.shyti@linux.intel.com> --- tests/i915/perf.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tests/i915/perf.c b/tests/i915/perf.c index dd1f1ac399..e33cacc443 100644 --- a/tests/i915/perf.c +++ b/tests/i915/perf.c @@ -4885,6 +4885,71 @@ test_whitelisted_registers_userspace_config(void) i915_perf_remove_config(drm_fd, config_id); } +static void test_open_race(const struct intel_execution_engine2 *e, int timeout) +{ + int *done; + + done = mmap(0, 4096, PROT_WRITE, MAP_SHARED | MAP_ANON, -1, 0); + igt_assert(done != MAP_FAILED); + + igt_fork(child, 1) { + uint64_t properties[] = { + DRM_I915_PERF_PROP_SAMPLE_OA, true, + DRM_I915_PERF_PROP_OA_METRICS_SET, test_set->perf_oa_metrics_set, + DRM_I915_PERF_PROP_OA_FORMAT, test_set->perf_oa_format, + DRM_I915_PERF_PROP_OA_EXPONENT, oa_exp_1_millisec, + }; + struct drm_i915_perf_open_param param = { + .flags = I915_PERF_FLAG_FD_CLOEXEC, + .num_properties = sizeof(properties) / 16, + .properties_ptr = to_user_pointer(properties), + }; + unsigned long count = 0; + + do { + __perf_close(__perf_open(drm_fd, ¶m, false)); + count++; + } while (!READ_ONCE(*done)); + + igt_info("Completed %lu cycles\n", count); + } + + for (int persistence = 0; persistence <= 1; persistence++) { + igt_fork(child, sysconf(_SC_NPROCESSORS_ONLN)) { + int i915 = gem_reopen_driver(drm_fd); + + do { + igt_spin_t *spin; + uint64_t ahnd; + uint32_t ctx; + + ctx = gem_context_create_for_engine(i915, e->class, e->instance); + gem_context_set_persistence(i915, ctx, persistence); + + spin = __igt_spin_new(i915, ctx, .ahnd = ahnd); + for (int i = random() % 7; i--; ) { + if (random() & 1) { + igt_spin_end(spin); + gem_sync(i915, spin->handle); + igt_spin_reset(spin); + } + gem_execbuf(i915, &spin->execbuf); + } + + gem_context_destroy(i915, ctx); + igt_spin_free(i915, spin); + put_ahnd(ahnd); + } while (!READ_ONCE(*done)); + } + } + + sleep(timeout); + *done = 1; + igt_waitchildren(); + + munmap(done, 4096); +} + static unsigned read_i915_module_ref(void) { @@ -5259,6 +5324,15 @@ igt_main igt_subtest("whitelisted-registers-userspace-config") test_whitelisted_registers_userspace_config(); + igt_subtest_with_dynamic("open-race") { + const struct intel_execution_engine2 *e; + + for_each_physical_engine(drm_fd, e) + if (e->class == I915_ENGINE_CLASS_RENDER) + igt_dynamic_f("%s", e->name) + test_open_race(e, 5); + } + igt_fixture { /* leave sysctl options in their default state... */ write_u64_file("/proc/sys/dev/i915/oa_max_sample_rate", 100000); -- 2.25.1
WARNING: multiple messages have this Message-ID (diff)
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> To: Petri Latvala <adrinael@adrinael.net>, Arkadiusz Hiler <arek@hiler.eu>, Kamil Konieczny <kamil.konieczny@linux.intel.com> Cc: igt-dev@lists.freedesktop.org, intel-gfx@lists.freedesktop.org, Chris Wilson <chris.p.wilson@linux.intel.com> Subject: [igt-dev] [PATCH i-g-t 1/2] i915/perf: Stress opening of new perf streams against existing contexts Date: Tue, 31 Jan 2023 10:17:30 +0100 [thread overview] Message-ID: <20230131091731.5892-2-janusz.krzysztofik@linux.intel.com> (raw) In-Reply-To: <20230131091731.5892-1-janusz.krzysztofik@linux.intel.com> From: Chris Wilson <chris.p.wilson@linux.intel.com> Try opening the perf stream while there is a flurry of activity on the system, both new and old contexts. This will exercise the ability of the driver to modify those contexts to work with perf. References: https://gitlab.freedesktop.org/drm/intel/-/issues/6333 Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com> Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> Cc: Andi Shyti <andi.shyti@linux.intel.com> --- tests/i915/perf.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tests/i915/perf.c b/tests/i915/perf.c index dd1f1ac399..e33cacc443 100644 --- a/tests/i915/perf.c +++ b/tests/i915/perf.c @@ -4885,6 +4885,71 @@ test_whitelisted_registers_userspace_config(void) i915_perf_remove_config(drm_fd, config_id); } +static void test_open_race(const struct intel_execution_engine2 *e, int timeout) +{ + int *done; + + done = mmap(0, 4096, PROT_WRITE, MAP_SHARED | MAP_ANON, -1, 0); + igt_assert(done != MAP_FAILED); + + igt_fork(child, 1) { + uint64_t properties[] = { + DRM_I915_PERF_PROP_SAMPLE_OA, true, + DRM_I915_PERF_PROP_OA_METRICS_SET, test_set->perf_oa_metrics_set, + DRM_I915_PERF_PROP_OA_FORMAT, test_set->perf_oa_format, + DRM_I915_PERF_PROP_OA_EXPONENT, oa_exp_1_millisec, + }; + struct drm_i915_perf_open_param param = { + .flags = I915_PERF_FLAG_FD_CLOEXEC, + .num_properties = sizeof(properties) / 16, + .properties_ptr = to_user_pointer(properties), + }; + unsigned long count = 0; + + do { + __perf_close(__perf_open(drm_fd, ¶m, false)); + count++; + } while (!READ_ONCE(*done)); + + igt_info("Completed %lu cycles\n", count); + } + + for (int persistence = 0; persistence <= 1; persistence++) { + igt_fork(child, sysconf(_SC_NPROCESSORS_ONLN)) { + int i915 = gem_reopen_driver(drm_fd); + + do { + igt_spin_t *spin; + uint64_t ahnd; + uint32_t ctx; + + ctx = gem_context_create_for_engine(i915, e->class, e->instance); + gem_context_set_persistence(i915, ctx, persistence); + + spin = __igt_spin_new(i915, ctx, .ahnd = ahnd); + for (int i = random() % 7; i--; ) { + if (random() & 1) { + igt_spin_end(spin); + gem_sync(i915, spin->handle); + igt_spin_reset(spin); + } + gem_execbuf(i915, &spin->execbuf); + } + + gem_context_destroy(i915, ctx); + igt_spin_free(i915, spin); + put_ahnd(ahnd); + } while (!READ_ONCE(*done)); + } + } + + sleep(timeout); + *done = 1; + igt_waitchildren(); + + munmap(done, 4096); +} + static unsigned read_i915_module_ref(void) { @@ -5259,6 +5324,15 @@ igt_main igt_subtest("whitelisted-registers-userspace-config") test_whitelisted_registers_userspace_config(); + igt_subtest_with_dynamic("open-race") { + const struct intel_execution_engine2 *e; + + for_each_physical_engine(drm_fd, e) + if (e->class == I915_ENGINE_CLASS_RENDER) + igt_dynamic_f("%s", e->name) + test_open_race(e, 5); + } + igt_fixture { /* leave sysctl options in their default state... */ write_u64_file("/proc/sys/dev/i915/oa_max_sample_rate", 100000); -- 2.25.1
next prev parent reply other threads:[~2023-01-31 9:18 UTC|newest] Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-01-31 9:17 [Intel-gfx] [PATCH i-g-t 0/2] tests/i915/perf: Add stress / race exercises Janusz Krzysztofik 2023-01-31 9:17 ` [igt-dev] " Janusz Krzysztofik 2023-01-31 9:17 ` Janusz Krzysztofik [this message] 2023-01-31 9:17 ` [igt-dev] [PATCH i-g-t 1/2] i915/perf: Stress opening of new perf streams against existing contexts Janusz Krzysztofik 2023-01-31 11:59 ` [Intel-gfx] " Kamil Konieczny 2023-01-31 11:59 ` [igt-dev] " Kamil Konieczny 2023-01-31 14:14 ` [Intel-gfx] " Janusz Krzysztofik 2023-01-31 14:14 ` [igt-dev] " Janusz Krzysztofik 2023-01-31 9:17 ` [Intel-gfx] [PATCH i-g-t 2/2] tests/i915/perf: Exercise barrier race Janusz Krzysztofik 2023-01-31 9:17 ` [igt-dev] " Janusz Krzysztofik 2023-02-01 18:21 ` [Intel-gfx] " Kamil Konieczny 2023-02-01 18:21 ` [igt-dev] " Kamil Konieczny 2023-02-01 19:16 ` [Intel-gfx] " Janusz Krzysztofik 2023-02-01 19:16 ` [igt-dev] " Janusz Krzysztofik 2023-02-02 10:19 ` [Intel-gfx] " Kamil Konieczny 2023-02-02 10:19 ` [igt-dev] " Kamil Konieczny 2023-01-31 11:16 ` [igt-dev] ✓ Fi.CI.BAT: success for tests/i915/perf: Add stress / race exercises Patchwork 2023-01-31 15:08 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork 2023-01-31 16:19 ` [Intel-gfx] [igt-dev] [PATCH i-g-t 0/2] " Dixit, Ashutosh 2023-01-31 16:19 ` Dixit, Ashutosh 2023-01-31 16:55 ` [Intel-gfx] " Dixit, Ashutosh 2023-01-31 16:55 ` Dixit, Ashutosh 2023-01-31 17:56 ` [Intel-gfx] " Janusz Krzysztofik 2023-01-31 17:56 ` Janusz Krzysztofik 2023-01-31 17:36 ` [Intel-gfx] " Janusz Krzysztofik 2023-01-31 17:36 ` Janusz Krzysztofik 2023-01-31 18:36 ` [Intel-gfx] " Dixit, Ashutosh 2023-01-31 18:36 ` Dixit, Ashutosh 2023-02-01 15:51 ` [Intel-gfx] " Janusz Krzysztofik 2023-02-01 15:51 ` Janusz Krzysztofik 2023-02-03 19:21 ` [Intel-gfx] " Umesh Nerlige Ramappa 2023-02-03 19:21 ` Umesh Nerlige Ramappa 2023-02-03 20:59 ` [Intel-gfx] " Janusz Krzysztofik 2023-02-03 20:59 ` Janusz Krzysztofik
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20230131091731.5892-2-janusz.krzysztofik@linux.intel.com \ --to=janusz.krzysztofik@linux.intel.com \ --cc=adrinael@adrinael.net \ --cc=arek@hiler.eu \ --cc=chris.p.wilson@linux.intel.com \ --cc=igt-dev@lists.freedesktop.org \ --cc=intel-gfx@lists.freedesktop.org \ --cc=kamil.konieczny@linux.intel.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.