summaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2019-05-15 14:00:50 +0100
committerJoonas Lahtinen <joonas.lahtinen@linux.intel.com>2019-05-20 18:28:04 +0300
commit9981927cc9e10fb4dbc24b2a5f8c17ab133859a0 (patch)
tree1ccb962c02b4e6d2c58c5561c18c8fae180240c7 /drivers/gpu
parentf312c23ff92319f5f242b69d93885c53f92030b5 (diff)
drm/i915: Bump signaler priority on adding a waiter
The handling of the no-preemption priority level imposes the restriction that we need to maintain the implied ordering even though preemption is disabled. Otherwise we may end up with an AB-BA deadlock across multiple engine due to a real preemption event reordering the no-preemption WAITs. To resolve this issue we currently promote all requests to WAIT on unsubmission, however this interferes with the timeslicing requirement that we do not apply any implicit promotion that will defeat the round-robin timeslice list. (If we automatically promote the active request it will go back to the head of the queue and not the tail!) So we need implicit promotion to prevent reordering around semaphores where we are not allowed to preempt, and we must avoid implicit promotion on unsubmission. So instead of at unsubmit, if we apply that implicit promotion on adding the dependency, we avoid the semaphore deadlock and we also reduce the gains made by the promotion for user space waiting. Furthermore, by keeping the earlier dependencies at a higher level, we reduce the search space for timeslicing without altering runtime scheduling too badly (no dependencies at all will be assigned a higher priority for rrul). v2: Limit the bump to external edges (as originally intended) i.e. between contexts and out to the user. Testcase: igt/gem_concurrent_blit 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/20190515130052.4475-3-chris@chris-wilson.co.uk (cherry picked from commit 6e7eb7a80769e7250e31652b96918cf7f3e0d285) Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/i915/i915_request.c9
-rw-r--r--drivers/gpu/drm/i915/i915_scheduler.c11
-rw-r--r--drivers/gpu/drm/i915/i915_scheduler_types.h3
-rw-r--r--drivers/gpu/drm/i915/selftests/intel_lrc.c12
4 files changed, 21 insertions, 14 deletions
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f6c78c0fa74b..f258281bf3f3 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -502,15 +502,6 @@ void __i915_request_unsubmit(struct i915_request *request)
/* We may be recursing from the signal callback of another i915 fence */
spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
- /*
- * As we do not allow WAIT to preempt inflight requests,
- * once we have executed a request, along with triggering
- * any execution callbacks, we must preserve its ordering
- * within the non-preemptible FIFO.
- */
- BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); /* only internal */
- request->sched.attr.priority |= __NO_PREEMPTION;
-
if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
i915_request_cancel_breadcrumb(request);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 3cfadb9db988..108f52e1bf35 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -383,6 +383,16 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
!node_started(signal))
node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
+ /*
+ * As we do not allow WAIT to preempt inflight requests,
+ * once we have executed a request, along with triggering
+ * any execution callbacks, we must preserve its ordering
+ * within the non-preemptible FIFO.
+ */
+ BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK);
+ if (flags & I915_DEPENDENCY_EXTERNAL)
+ __bump_priority(signal, __NO_PREEMPTION);
+
ret = true;
}
@@ -401,6 +411,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
return -ENOMEM;
if (!__i915_sched_node_add_dependency(node, signal, dep,
+ I915_DEPENDENCY_EXTERNAL |
I915_DEPENDENCY_ALLOC))
i915_dependency_free(dep);
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index f1af3916a808..4f2b2eb7c3e5 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -66,7 +66,8 @@ struct i915_dependency {
struct list_head wait_link;
struct list_head dfs_link;
unsigned long flags;
-#define I915_DEPENDENCY_ALLOC BIT(0)
+#define I915_DEPENDENCY_ALLOC BIT(0)
+#define I915_DEPENDENCY_EXTERNAL BIT(1)
};
#endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index fbee030db940..e8b0b5dbcb2c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -99,12 +99,14 @@ static int live_busywait_preempt(void *arg)
ctx_hi = kernel_context(i915);
if (!ctx_hi)
goto err_unlock;
- ctx_hi->sched.priority = INT_MAX;
+ ctx_hi->sched.priority =
+ I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
ctx_lo = kernel_context(i915);
if (!ctx_lo)
goto err_ctx_hi;
- ctx_lo->sched.priority = INT_MIN;
+ ctx_lo->sched.priority =
+ I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
if (IS_ERR(obj)) {
@@ -954,12 +956,14 @@ static int live_preempt_hang(void *arg)
ctx_hi = kernel_context(i915);
if (!ctx_hi)
goto err_spin_lo;
- ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+ ctx_hi->sched.priority =
+ I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
ctx_lo = kernel_context(i915);
if (!ctx_lo)
goto err_ctx_hi;
- ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+ ctx_lo->sched.priority =
+ I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
for_each_engine(engine, i915, id) {
struct i915_request *rq;