drm/i915: Look for active requests earlier in the reset path

And store the active request so that we only search for it once.

v2: Check for request completion inside _prepare_engine, don't use
ECANCELED, remove unnecessary null checks (Chris).

v3: Capture active requests during reset_prepare and store it the
engine hangcheck obj.

v4: Rename commit, change i915_gem_reset_request to just confirm the
active_request is still incomplete, instead of engine_stalled (Chris).

v5: With style; pass the active request to gem_reset_engine, keep single
return in reset_prepare_engine (Chris).

v6: Moved before reset-engine code appears (Chris)

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> (v5)
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170615201828.23144-2-michel.thierry@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620095751.13127-3-chris@chris-wilson.co.uk
This commit is contained in:
Michel Thierry 2017-06-20 10:57:44 +01:00 committed by Chris Wilson
parent d5367307d4
commit c64992e035
2 changed files with 9 additions and 7 deletions

View File

@ -2839,7 +2839,7 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
/* Ensure irq handler finishes, and not run again. */
for_each_engine(engine, dev_priv, id) {
struct drm_i915_gem_request *request;
struct drm_i915_gem_request *request = NULL;
/* Prevent the signaler thread from updating the request
* state (by calling dma_fence_signal) as we are processing
@ -2871,6 +2871,8 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
if (request && request->fence.error == -EIO)
err = -EIO; /* Previous reset failed! */
}
engine->hangcheck.active_request = request;
}
i915_gem_revoke_fences(dev_priv);
@ -2924,7 +2926,7 @@ static void engine_skip_context(struct drm_i915_gem_request *request)
static bool i915_gem_reset_request(struct drm_i915_gem_request *request)
{
/* Read once and return the resolution */
const bool guilty = engine_stalled(request->engine);
const bool guilty = !i915_gem_request_completed(request);
/* The guilty request will get skipped on a hung engine.
*
@ -2958,11 +2960,9 @@ static bool i915_gem_reset_request(struct drm_i915_gem_request *request)
return guilty;
}
static void i915_gem_reset_engine(struct intel_engine_cs *engine)
static void i915_gem_reset_engine(struct intel_engine_cs *engine,
struct drm_i915_gem_request *request)
{
struct drm_i915_gem_request *request;
request = i915_gem_find_active_request(engine);
if (request && i915_gem_reset_request(request)) {
DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n",
engine->name, request->global_seqno);
@ -2988,7 +2988,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
for_each_engine(engine, dev_priv, id) {
struct i915_gem_context *ctx;
i915_gem_reset_engine(engine);
i915_gem_reset_engine(engine, engine->hangcheck.active_request);
ctx = fetch_and_zero(&engine->last_retired_context);
if (ctx)
engine->context_unpin(engine, ctx);
@ -3012,6 +3012,7 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
lockdep_assert_held(&dev_priv->drm.struct_mutex);
for_each_engine(engine, dev_priv, id) {
engine->hangcheck.active_request = NULL;
tasklet_enable(&engine->irq_tasklet);
kthread_unpark(engine->breadcrumbs.signaler);
}

View File

@ -121,6 +121,7 @@ struct intel_engine_hangcheck {
unsigned long action_timestamp;
int deadlock;
struct intel_instdone instdone;
struct drm_i915_gem_request *active_request;
bool stalled;
};