From patchwork Wed Aug 15 12:28:23 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10566515 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 1C61B13B6 for ; Wed, 15 Aug 2018 12:28:34 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 0AC0029FAB for ; Wed, 15 Aug 2018 12:28:34 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id F187029FB7; Wed, 15 Aug 2018 12:28:33 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.2 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 852EE29FAB for ; Wed, 15 Aug 2018 12:28:33 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 0A49289A16; Wed, 15 Aug 2018 12:28:33 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from fireflyinternet.com (mail.fireflyinternet.com [109.228.58.192]) by gabe.freedesktop.org (Postfix) with ESMTPS id 3CA6989A16 for ; Wed, 15 Aug 2018 12:28:31 +0000 (UTC) X-Default-Received-SPF: pass (skip=forwardok (res=PASS)) x-ip-name=78.156.65.138; Received: from haswell.alporthouse.com (unverified [78.156.65.138]) by fireflyinternet.com (Firefly Internet (M1)) with ESMTP id 12923376-1500050 for multiple; Wed, 15 Aug 2018 13:28:28 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Wed, 15 Aug 2018 13:28:23 +0100 Message-Id: <20180815122823.15344-1-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.18.0 Subject: [Intel-gfx] [PATCH] drm/i915/selftests: Basic stress test for rapid context switching X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP We need to exercise the HW and submission paths for switching contexts rapidly to check that features such as execlists' wa_tail are adequate. Plus it's an interesting baseline latency metric. Signed-off-by: Chris Wilson --- .../gpu/drm/i915/selftests/i915_gem_context.c | 185 ++++++++++++++++++ 1 file changed, 185 insertions(+) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index 1c92560d35da..d8004bf5a4f0 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -22,6 +22,8 @@ * */ +#include + #include "../i915_selftest.h" #include "i915_random.h" #include "igt_flush_test.h" @@ -32,6 +34,188 @@ #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32)) +struct live_test { + struct drm_i915_private *i915; + const char *func; + const char *name; + + unsigned int reset_count; +}; + +static int begin_live_test(struct live_test *t, + struct drm_i915_private *i915, + const char *func, + const char *name) +{ + int err; + + t->i915 = i915; + t->func = func; + t->name = name; + + err = i915_gem_wait_for_idle(i915, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + if (err) { + pr_err("%s(%s): failed to idle before, with err=%d!", + func, name, err); + return err; + } + + i915->gpu_error.missed_irq_rings = 0; + t->reset_count = i915_reset_count(&i915->gpu_error); + + return 0; +} + +static int end_live_test(struct live_test *t) +{ + struct drm_i915_private *i915 = t->i915; + + i915_retire_requests(i915); + + if (wait_for(intel_engines_are_idle(i915), 10)) { + pr_err("%s(%s): GPU not idle\n", t->func, t->name); + return -EIO; + } + + if (t->reset_count != i915_reset_count(&i915->gpu_error)) { + pr_err("%s(%s): GPU was reset %d times!\n", + t->func, t->name, + i915_reset_count(&i915->gpu_error) - t->reset_count); + return -EIO; + } + + if (i915->gpu_error.missed_irq_rings) { + pr_err("%s(%s): Missed interrupts on engines %lx\n", + t->func, t->name, i915->gpu_error.missed_irq_rings); + return -EIO; + } + + return 0; +} + +static int live_nop_switch(void *arg) +{ + const unsigned int nctx = 1024; + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context **ctx; + enum intel_engine_id id; + struct drm_file *file; + struct live_test t; + unsigned long n; + int err = -ENODEV; + + /* + * Create as many contexts as we can feasibly get away with + * and check we can switch between them rapidly. + * + * Serves as very simple stress test for submission and HW switching + * between contexts. + */ + + if (!DRIVER_CAPS(i915)->has_logical_contexts) + return 0; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&i915->drm.struct_mutex); + + ctx = kcalloc(sizeof(*ctx), nctx, GFP_KERNEL); + if (!ctx) { + err = -ENOMEM; + goto out_unlock; + } + + for (n = 0; n < nctx; n++) { + ctx[n] = i915_gem_create_context(i915, file->driver_priv); + if (IS_ERR(ctx[n])) { + err = PTR_ERR(ctx[n]); + goto out_unlock; + } + } + + for_each_engine(engine, i915, id) { + struct i915_request *request; + unsigned long end_time, prime; + ktime_t times[2] = {}; + + times[0] = ktime_get_raw(); + for (n = 0; n < nctx; n++) { + request = i915_request_alloc(engine, ctx[n]); + i915_request_add(request); + } + i915_request_wait(request, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + times[1] = ktime_get_raw(); + + pr_info("Populated %d contexts on %s in %lluns\n", + nctx, engine->name, ktime_to_ns(times[1] - times[0])); + + err = begin_live_test(&t, i915, __func__, engine->name); + if (err) + goto out_unlock; + + end_time = jiffies + i915_selftest.timeout_jiffies; + for_each_prime_number_from(prime, 2, 8192) { + times[1] = ktime_get_raw(); + + for (n = 0; n < prime; n++) { + request = i915_request_alloc(engine, + ctx[n % nctx]); + if (IS_ERR(request)) { + err = PTR_ERR(request); + goto out_unlock; + } + + /* + * This space is left intentionally blank. + * + * We do not actually want to perform any + * action with this request, we just want + * to measure the latency in allocation + * and submission of our breadcrumbs - + * ensuring that the bare request is sufficient + * for the system to work (i.e. proper HEAD + * tracking of the rings, interrupt handling, + * etc). It also gives us the lowest bounds + * for latency. + */ + + i915_request_add(request); + } + i915_request_wait(request, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + + times[1] = ktime_sub(ktime_get_raw(), times[1]); + if (prime == 2) + times[0] = times[1]; + + if (__igt_timeout(end_time, NULL)) + break; + } + + err = end_live_test(&t); + if (err) + goto out_unlock; + + pr_info("Switch latencies on %s: 1 = %lluns, %lu = %lluns\n", + engine->name, + ktime_to_ns(times[0]), + prime - 1, div64_u64(ktime_to_ns(times[1]), prime - 1)); + } + +out_unlock: + mutex_unlock(&i915->drm.struct_mutex); + mock_file_free(i915, file); + return err; +} + static struct i915_vma * gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value) { @@ -713,6 +897,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv) { static const struct i915_subtest tests[] = { SUBTEST(igt_switch_to_kernel_context), + SUBTEST(live_nop_switch), SUBTEST(igt_ctx_exec), SUBTEST(igt_ctx_readonly), };