[PATCH 31/31] drm/i915: Do a synchronous switch-to-kernel-context on idling
Chris Wilson
chris at chris-wilson.co.uk
Wed Jan 23 00:44:02 UTC 2019
When the system idles, we switch to the kernel context as a defensive
measure (no users are harmed if the kernel context is lost). Currently,
we issue a switch to kernel context and then come back later to see if
the kernel context is still current and the system is idle. However,
if we are no longer privy to the runqueue ordering, then we have to
relax our assumptions about the logical state of the GPU and the only
way to ensure that the kernel context is currently loaded is by issuing
a request to run after all others, and wait for it to complete all while
preventing anyone else from issuing their own requests.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_gem.c | 119 ++++++++++++++------------------
1 file changed, 53 insertions(+), 66 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index dde805014b01..02e7d630110f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2986,13 +2986,6 @@ static void __sleep_rcu(struct rcu_head *rcu)
}
}
-static inline bool
-new_requests_since_last_retire(const struct drm_i915_private *i915)
-{
- return (READ_ONCE(i915->gt.active_requests) ||
- work_pending(&i915->gt.idle_work.work));
-}
-
static void assert_kernel_context_is_current(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
@@ -3001,7 +2994,8 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
if (i915_terminally_wedged(&i915->gpu_error))
return;
- GEM_BUG_ON(i915->gt.active_requests);
+ i915_retire_requests(i915);
+
for_each_engine(engine, i915, id) {
GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
GEM_BUG_ON(engine->last_retired_context !=
@@ -3009,78 +3003,77 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
}
}
+static bool switch_to_kernel_context_sync(struct drm_i915_private *i915)
+{
+ if (i915_gem_switch_to_kernel_context(i915))
+ return false;
+
+ if (i915_gem_wait_for_idle(i915, 0, HZ / 10))
+ return false;
+
+ if (wait_for(intel_engines_are_idle(i915), I915_IDLE_ENGINES_TIMEOUT))
+ return false;
+
+ assert_kernel_context_is_current(i915);
+
+ return true;
+}
+
static void
i915_gem_idle_work_handler(struct work_struct *work)
{
- struct drm_i915_private *dev_priv =
- container_of(work, typeof(*dev_priv), gt.idle_work.work);
+ struct drm_i915_private *i915 =
+ container_of(work, typeof(*i915), gt.idle_work.work);
+ typeof(i915->gt) *gt = &i915->gt;
unsigned int epoch = I915_EPOCH_INVALID;
bool rearm_hangcheck;
- if (!READ_ONCE(dev_priv->gt.awake))
+ if (!READ_ONCE(gt->awake))
return;
- if (READ_ONCE(dev_priv->gt.active_requests))
+ if (READ_ONCE(gt->active_requests))
return;
- /*
- * Flush out the last user context, leaving only the pinned
- * kernel context resident. When we are idling on the kernel_context,
- * no more new requests (with a context switch) are emitted and we
- * can finally rest. A consequence is that the idle work handler is
- * always called at least twice before idling (and if the system is
- * idle that implies a round trip through the retire worker).
- */
- mutex_lock(&dev_priv->drm.struct_mutex);
- i915_gem_switch_to_kernel_context(dev_priv);
- mutex_unlock(&dev_priv->drm.struct_mutex);
-
- GEM_TRACE("active_requests=%d (after switch-to-kernel-context)\n",
- READ_ONCE(dev_priv->gt.active_requests));
-
- /*
- * Wait for last execlists context complete, but bail out in case a
- * new request is submitted. As we don't trust the hardware, we
- * continue on if the wait times out. This is necessary to allow
- * the machine to suspend even if the hardware dies, and we will
- * try to recover in resume (after depriving the hardware of power,
- * it may be in a better mmod).
- */
- __wait_for(if (new_requests_since_last_retire(dev_priv)) return,
- intel_engines_are_idle(dev_priv),
- I915_IDLE_ENGINES_TIMEOUT * 1000,
- 10, 500);
-
rearm_hangcheck =
- cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
+ cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
- if (!mutex_trylock(&dev_priv->drm.struct_mutex)) {
+ if (!mutex_trylock(&i915->drm.struct_mutex)) {
/* Currently busy, come back later */
- mod_delayed_work(dev_priv->wq,
- &dev_priv->gt.idle_work,
+ mod_delayed_work(i915->wq,
+ >->idle_work,
msecs_to_jiffies(50));
goto out_rearm;
}
/*
- * New request retired after this work handler started, extend active
- * period until next instance of the work.
+ * Flush out the last user context, leaving only the pinned
+ * kernel context resident. Should anything unfortunate happen
+ * while we are idle (such as the GPU being power cycled), no users
+ * will be harmed.
*/
- if (new_requests_since_last_retire(dev_priv))
- goto out_unlock;
-
- epoch = __i915_gem_park(dev_priv);
+ if (!gt->active_requests && !work_pending(>->idle_work.work)) {
+ ++gt->active_requests; /* don't requeue idle */
+
+ if (!switch_to_kernel_context_sync(i915)) {
+ dev_err(i915->drm.dev,
+ "Failed to idle engines, declaring wedged!\n");
+ GEM_TRACE_DUMP();
+ i915_gem_set_wedged(i915);
+ }
+ i915_retire_requests(i915);
- assert_kernel_context_is_current(dev_priv);
+ if (!--gt->active_requests) {
+ epoch = __i915_gem_park(i915);
+ rearm_hangcheck = false;
+ }
+ }
- rearm_hangcheck = false;
-out_unlock:
- mutex_unlock(&dev_priv->drm.struct_mutex);
+ mutex_unlock(&i915->drm.struct_mutex);
out_rearm:
if (rearm_hangcheck) {
- GEM_BUG_ON(!dev_priv->gt.awake);
- i915_queue_hangcheck(dev_priv);
+ GEM_BUG_ON(!gt->awake);
+ i915_queue_hangcheck(i915);
}
/*
@@ -3091,11 +3084,11 @@ i915_gem_idle_work_handler(struct work_struct *work)
* period, and then queue a task (that will run last on the wq) to
* shrink and re-optimize the caches.
*/
- if (same_epoch(dev_priv, epoch)) {
+ if (same_epoch(i915, epoch)) {
struct sleep_rcu_work *s = kmalloc(sizeof(*s), GFP_KERNEL);
if (s) {
init_rcu_head(&s->rcu);
- s->i915 = dev_priv;
+ s->i915 = i915;
s->epoch = epoch;
call_rcu(&s->rcu, __sleep_rcu);
}
@@ -4846,17 +4839,11 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
goto err_active;
}
- err = i915_gem_switch_to_kernel_context(i915);
- if (err)
- goto err_active;
-
- if (i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED, HZ / 5)) {
- i915_gem_set_wedged(i915);
+ if (!switch_to_kernel_context_sync(i915)) {
err = -EIO; /* Caller will declare us wedged */
goto err_active;
}
-
- assert_kernel_context_is_current(i915);
+ i915_retire_requests(i915);
/*
* Immediately park the GPU so that we enable powersaving and
--
2.20.1
More information about the Intel-gfx-trybot
mailing list