summaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2020-08-06 11:59:54 +0100
committerJani Nikula <jani.nikula@intel.com>2020-09-16 11:09:43 +0300
commitc2314b8bd4c009793b6f9d57bc8363af034e02ca (patch)
tree6b55f9b8cee5a7a9502a04a604d0a207ee369fd2 /drivers/gpu
parente7d95527f27a6d9edcffbd74eee38e5cb6b91785 (diff)
drm/i915/gem: Reduce context termination list iteration guard to RCU
As we now protect the timeline list using RCU, we can drop the timeline->mutex for guarding the list iteration during context close, as we are searching for an inflight request. Any new request will see the context is banned and not be submitted. In doing so, pull the checks for a concurrent submission of the request (notably the i915_request_completed()) under the engine spinlock, to fully serialise with __i915_request_submit()). That is in the case of preempt-to-busy where the request may be completed during the __i915_request_submit(), we need to be careful that we sample the request status after serialising so that we don't miss the request the engine is actually submitting. Fixes: 4a3174152147 ("drm/i915/gem: Refine occupancy test in kill_context()") References: d22d2d073ef8 ("drm/i915: Protect i915_request_await_start from early waits") # rcu protection of timeline->requests References: https://gitlab.freedesktop.org/drm/intel/-/issues/1622 References: https://gitlab.freedesktop.org/drm/intel/-/issues/2158 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200806105954.7766-1-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> (cherry picked from commit 736e785f9b28cd9ef2d16a80960a04fd00e64b22) Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_context.c32
1 files changed, 19 insertions, 13 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index efc4ba34c06e..ef755dd5e68f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
return __reset_engine(engine);
}
-static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+static bool
+__active_engine(struct i915_request *rq, struct intel_engine_cs **active)
{
struct intel_engine_cs *engine, *locked;
+ bool ret = false;
/*
* Serialise with __i915_request_submit() so that it sees
* is-banned?, or we know the request is already inflight.
+ *
+ * Note that rq->engine is unstable, and so we double
+ * check that we have acquired the lock on the final engine.
*/
locked = READ_ONCE(rq->engine);
spin_lock_irq(&locked->active.lock);
while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
spin_unlock(&locked->active.lock);
- spin_lock(&engine->active.lock);
locked = engine;
+ spin_lock(&locked->active.lock);
}
- engine = NULL;
- if (i915_request_is_active(rq) && rq->fence.error != -EIO)
- engine = rq->engine;
+ if (!i915_request_completed(rq)) {
+ if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+ *active = locked;
+ ret = true;
+ }
spin_unlock_irq(&locked->active.lock);
- return engine;
+ return ret;
}
static struct intel_engine_cs *active_engine(struct intel_context *ce)
@@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
if (!ce->timeline)
return NULL;
- mutex_lock(&ce->timeline->mutex);
- list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
- if (i915_request_completed(rq))
- break;
+ rcu_read_lock();
+ list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
+ if (i915_request_is_active(rq) && i915_request_completed(rq))
+ continue;
/* Check with the backend if the request is inflight */
- engine = __active_engine(rq);
- if (engine)
+ if (__active_engine(rq, &engine))
break;
}
- mutex_unlock(&ce->timeline->mutex);
+ rcu_read_unlock();
return engine;
}