From: Michel Thierry <michel.thierry@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH v7 10/20] drm/i915/selftests: reset engine self tests
Date: Thu, 27 Apr 2017 16:12:50 -0700 [thread overview]
Message-ID: <20170427231300.32841-11-michel.thierry@intel.com> (raw)
In-Reply-To: <20170427231300.32841-1-michel.thierry@intel.com>
Check that we can reset specific engines, also check the fallback to
full reset if something didn't work.
v2: rebase.
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
---
drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 147 +++++++++++++++++++++++
1 file changed, 147 insertions(+)
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index aa31d6c0cdfb..f64fa0e4bb40 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -322,6 +322,56 @@ static int igt_global_reset(void *arg)
return err;
}
+static int igt_reset_engine(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ unsigned int reset_count, reset_engine_count;
+ int err = 0;
+
+ /* Check that we can issue a global GPU and engine reset */
+
+ if (!intel_has_gpu_reset(i915))
+ return 0;
+
+ if (!intel_has_reset_engine(i915))
+ return 0;
+
+ set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+
+ for_each_engine(engine, i915, id) {
+ reset_count = i915_reset_count(&i915->gpu_error);
+ reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
+ engine);
+
+ err = i915_reset_engine(engine);
+ if (err) {
+ pr_err("i915_reset_engine failed\n");
+ break;
+ }
+
+ if (i915_reset_count(&i915->gpu_error) != reset_count) {
+ pr_err("Full GPU reset recorded! (engine reset expected)\n");
+ err = -EINVAL;
+ break;
+ }
+
+ if (i915_reset_engine_count(&i915->gpu_error, engine) ==
+ reset_engine_count) {
+ pr_err("No %s engine reset recorded!\n", engine->name);
+ err = -EINVAL;
+ break;
+ }
+ }
+
+ clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+ if (i915_terminally_wedged(&i915->gpu_error))
+ err = -EIO;
+
+ return err;
+}
+
static u32 fake_hangcheck(struct drm_i915_gem_request *rq)
{
u32 reset_count;
@@ -526,13 +576,110 @@ static int igt_reset_queue(void *arg)
return err;
}
+static int igt_render_engine_reset_fallback(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_engine_cs *engine = i915->engine[RCS];
+ struct hang h;
+ struct drm_i915_gem_request *rq;
+ unsigned int reset_count, reset_engine_count;
+ int err = 0;
+
+ /* Check that we can issue a global GPU and engine reset */
+
+ if (!intel_has_gpu_reset(i915))
+ return 0;
+
+ if (!intel_has_reset_engine(i915))
+ return 0;
+
+ set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+ mutex_lock(&i915->drm.struct_mutex);
+
+ err = hang_init(&h, i915);
+ if (err)
+ goto unlock;
+
+ rq = hang_create_request(&h, engine, i915->kernel_context);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto fini;
+ }
+
+ i915_gem_request_get(rq);
+ __i915_add_request(rq, true);
+
+ /* make reset engine fail */
+ rq->fence.error = -EIO;
+
+ if (!wait_for_hang(&h, rq)) {
+ pr_err("Failed to start request %x\n", rq->fence.seqno);
+ err = -EIO;
+ goto fini;
+ }
+
+ reset_engine_count = i915_reset_engine_count(&i915->gpu_error, engine);
+ reset_count = fake_hangcheck(rq);
+
+ err = i915_reset_engine(engine);
+ if (err) {
+ pr_err("i915_reset_engine failed\n");
+ goto fini;
+ }
+
+ if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+ reset_engine_count) {
+ pr_err("render engine reset recorded! (full reset expected)\n");
+ err = -EINVAL;
+ goto fini;
+ }
+
+ if (i915_reset_count(&i915->gpu_error) == reset_count) {
+ pr_err("No full GPU reset recorded!\n");
+ err = -EINVAL;
+ goto fini;
+ }
+
+ /*
+ * by using fence.error = -EIO, full reset sets the wedged flag, do one
+ * more full reset to re-enable the hw.
+ */
+ if (i915_terminally_wedged(&i915->gpu_error)) {
+ rq->fence.error = 0;
+
+ set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
+ i915_reset(i915);
+ GEM_BUG_ON(test_bit(I915_RESET_HANDOFF,
+ &i915->gpu_error.flags));
+
+ if (i915_reset_count(&i915->gpu_error) == reset_count) {
+ pr_err("No full GPU reset recorded!\n");
+ err = -EINVAL;
+ goto fini;
+ }
+ }
+
+fini:
+ hang_fini(&h);
+unlock:
+ mutex_unlock(&i915->drm.struct_mutex);
+ clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+
+ if (i915_terminally_wedged(&i915->gpu_error))
+ return -EIO;
+
+ return err;
+}
+
int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(igt_hang_sanitycheck),
SUBTEST(igt_global_reset),
+ SUBTEST(igt_reset_engine),
SUBTEST(igt_wait_reset),
SUBTEST(igt_reset_queue),
+ SUBTEST(igt_render_engine_reset_fallback),
};
if (!intel_has_gpu_reset(i915))
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2017-04-27 23:13 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-27 23:12 [PATCH v7 00/20] Gen8+ engine-reset Michel Thierry
2017-04-27 23:12 ` [PATCH v7 01/20] drm/i915: Update i915.reset to handle engine resets Michel Thierry
2017-04-27 23:12 ` [PATCH v7 02/20] drm/i915: Modify error handler for per engine hang recovery Michel Thierry
2017-04-29 14:19 ` Chris Wilson
2017-05-08 18:31 ` Michel Thierry
2017-05-12 20:55 ` Michel Thierry
2017-05-12 21:09 ` Chris Wilson
2017-05-12 21:23 ` Michel Thierry
2017-05-15 21:14 ` [PATCH " Michel Thierry
2017-04-27 23:12 ` [PATCH v7 03/20] drm/i915: Add support for per engine reset recovery Michel Thierry
2017-04-27 23:50 ` Chris Wilson
2017-04-28 21:59 ` Michel Thierry
2017-05-04 0:26 ` Michel Thierry
2017-05-15 21:18 ` [PATCH " Michel Thierry
2017-04-27 23:12 ` [PATCH v7 04/20] drm/i915: Skip reset request if there is one already Michel Thierry
2017-04-29 14:21 ` Chris Wilson
2017-05-01 21:15 ` Michel Thierry
2017-04-27 23:12 ` [PATCH v7 05/20] drm/i915: Cancel reset-engine if we couldn't find an active request Michel Thierry
2017-04-29 14:26 ` Chris Wilson
2017-05-15 21:20 ` [PATCH " Michel Thierry
2017-05-15 21:31 ` Chris Wilson
2017-05-15 21:47 ` Chris Wilson
2017-05-15 22:25 ` Michel Thierry
2017-05-16 7:54 ` Chris Wilson
2017-05-17 0:13 ` Michel Thierry
2017-05-17 7:19 ` Chris Wilson
2017-05-17 20:41 ` [PATCH] " Michel Thierry
2017-05-17 20:52 ` Chris Wilson
2017-05-18 1:11 ` Michel Thierry
2017-05-18 7:56 ` Chris Wilson
2017-05-18 17:19 ` Michel Thierry
2017-05-18 18:22 ` [PATCH] drm/i915: Look for active requests earlier in the reset path Michel Thierry
2017-05-18 18:26 ` Michel Thierry
2017-05-18 19:55 ` Chris Wilson
2017-05-18 21:11 ` Michel Thierry
2017-05-18 21:16 ` Chris Wilson
2017-05-18 21:34 ` Michel Thierry
2017-04-27 23:12 ` [PATCH v7 06/20] drm/i915: Add engine reset count to error state Michel Thierry
2017-04-27 23:12 ` [PATCH v7 07/20] drm/i915: Export per-engine reset count info to debugfs Michel Thierry
2017-04-27 23:12 ` [PATCH v7 08/20] drm/i915: Enable Engine reset and recovery support Michel Thierry
2017-04-27 23:12 ` [PATCH v7 09/20] drm/i915: Add engine reset count in get-reset-stats ioctl Michel Thierry
2017-04-27 23:12 ` Michel Thierry [this message]
2017-04-27 23:12 ` [PATCH v7 11/20] drm/i915/guc: fix mmio whitelist mmio_start offset and add reminder Michel Thierry
2017-04-27 23:12 ` [PATCH v7 12/20] drm/i915/guc: Provide register list to be saved/restored during engine reset Michel Thierry
2017-04-27 23:58 ` Chris Wilson
2017-04-28 15:36 ` Michel Thierry
2017-04-27 23:12 ` [PATCH v7 13/20] drm/i915/guc: Rename the function that resets the GuC Michel Thierry
2017-04-28 7:40 ` Tvrtko Ursulin
2017-05-01 20:09 ` Michel Thierry
2017-04-27 23:12 ` [PATCH v7 14/20] drm/i915/guc: Add support for reset engine using GuC commands Michel Thierry
2017-04-27 23:12 ` [PATCH v7 15/20] drm/i915: Watchdog timeout: Pass GuC shared data structure during param load Michel Thierry
2017-04-27 23:12 ` [PATCH v7 16/20] drm/i915: Watchdog timeout: IRQ handler for gen8+ Michel Thierry
2017-04-27 23:12 ` [PATCH v7 17/20] drm/i915: Watchdog timeout: Ringbuffer command emission " Michel Thierry
2017-04-27 23:12 ` [PATCH v7 18/20] drm/i915: Watchdog timeout: DRM kernel interface to set the timeout Michel Thierry
2017-04-27 23:12 ` [PATCH v7 19/20] drm/i915: Watchdog timeout: Include threshold value in error state Michel Thierry
2017-04-27 23:13 ` [PATCH v7 20/20] drm/i915: Watchdog timeout: Export media reset count from GuC to debugfs Michel Thierry
2017-04-27 23:30 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev4) Patchwork
2017-05-15 21:32 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev5) Patchwork
2017-05-15 21:48 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev7) Patchwork
2017-05-17 21:09 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev8) Patchwork
2017-05-18 18:40 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev9) Patchwork
2017-05-18 21:29 ` ✓ Fi.CI.BAT: success for Gen8+ engine-reset (rev10) Patchwork
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=20170427231300.32841-11-michel.thierry@intel.com \
--to=michel.thierry@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox