drm/i915: Invert the GEM wakeref hierarchy

In the current scheme, on submitting a request we take a single global
GEM wakeref, which trickles down to wake up all GT power domains. This
is undesirable as we would like to be able to localise our power
management to the available power domains and to remove the global GEM
operations from the heart of the driver. (The intent there is to push
global GEM decisions to the boundary as used by the GEM user interface.)

Now during request construction, each request is responsible via its
logical context to acquire a wakeref on each power domain it intends to
utilize. Currently, each request takes a wakeref on the engine(s) and
the engines themselves take a chipset wakeref. This gives us a
transition on each engine which we can extend if we want to insert more
powermangement control (such as soft rc6). The global GEM operations
that currently require a struct_mutex are reduced to listening to pm
events from the chipset GT wakeref. As we reduce the struct_mutex
requirement, these listeners should evaporate.

Perhaps the biggest immediate change is that this removes the
struct_mutex requirement around GT power management, allowing us greater
flexibility in request construction. Another important knock-on effect,
is that by tracking engine usage, we can insert a switch back to the
kernel context on that engine immediately, avoiding any extra delay or
inserting global synchronisation barriers. This makes tracking when an
engine and its associated contexts are idle much easier -- important for
when we forgo our assumed execution ordering and need idle barriers to
unpin used contexts. In the process, it means we remove a large chunk of
code whose only purpose was to switch back to the kernel context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190424200717.1686-5-chris@chris-wilson.co.uk

1 files changed, 2 insertions, 83 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 3eb1a664b5fa..76ed74e75d82 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -824,26 +824,6 @@ int i915_gem_vm_destroy_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-static struct i915_request *
-last_request_on_engine(struct i915_timeline *timeline,
-		       struct intel_engine_cs *engine)
-{
-	struct i915_request *rq;
-
-	GEM_BUG_ON(timeline == &engine->timeline);
-
-	rq = i915_active_request_raw(&timeline->last_request,
-				     &engine->i915->drm.struct_mutex);
-	if (rq && rq->engine->mask & engine->mask) {
-		GEM_TRACE("last request on engine %s: %llx:%llu\n",
-			  engine->name, rq->fence.context, rq->fence.seqno);
-		GEM_BUG_ON(rq->timeline != timeline);
-		return rq;
-	}
-
-	return NULL;
-}
-
 struct context_barrier_task {
 	struct i915_active base;
 	void (*task)(void *data);
@@ -871,7 +851,6 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 	struct drm_i915_private *i915 = ctx->i915;
 	struct context_barrier_task *cb;
 	struct intel_context *ce, *next;
-	intel_wakeref_t wakeref;
 	int err = 0;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -884,7 +863,6 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 	i915_active_init(i915, &cb->base, cb_retire);
 	i915_active_acquire(&cb->base);
 
-	wakeref = intel_runtime_pm_get(i915);
 	rbtree_postorder_for_each_entry_safe(ce, next, &ctx->hw_contexts, node) {
 		struct intel_engine_cs *engine = ce->engine;
 		struct i915_request *rq;
@@ -914,7 +892,6 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 		if (err)
 			break;
 	}
-	intel_runtime_pm_put(i915, wakeref);
 
 	cb->task = err ? NULL : task; /* caller needs to unwind instead */
 	cb->data = data;
@@ -924,54 +901,6 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 	return err;
 }
 
-int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915,
-				      intel_engine_mask_t mask)
-{
-	struct intel_engine_cs *engine;
-
-	GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake));
-
-	lockdep_assert_held(&i915->drm.struct_mutex);
-	GEM_BUG_ON(!i915->kernel_context);
-
-	/* Inoperable, so presume the GPU is safely pointing into the void! */
-	if (i915_terminally_wedged(i915))
-		return 0;
-
-	for_each_engine_masked(engine, i915, mask, mask) {
-		struct intel_ring *ring;
-		struct i915_request *rq;
-
-		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
-
-		/* Queue this switch after all other activity */
-		list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
-			struct i915_request *prev;
-
-			prev = last_request_on_engine(ring->timeline, engine);
-			if (!prev)
-				continue;
-
-			if (prev->gem_context == i915->kernel_context)
-				continue;
-
-			GEM_TRACE("add barrier on %s for %llx:%lld\n",
-				  engine->name,
-				  prev->fence.context,
-				  prev->fence.seqno);
-			i915_sw_fence_await_sw_fence_gfp(&rq->submit,
-							 &prev->submit,
-							 I915_FENCE_GFP);
-		}
-
-		i915_request_add(rq);
-	}
-
-	return 0;
-}
-
 static int get_ppgtt(struct drm_i915_file_private *file_priv,
 		     struct i915_gem_context *ctx,
 		     struct drm_i915_gem_context_param *args)
@@ -1169,9 +1098,7 @@ static int gen8_emit_rpcs_config(struct i915_request *rq,
 static int
 gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 {
-	struct drm_i915_private *i915 = ce->engine->i915;
 	struct i915_request *rq;
-	intel_wakeref_t wakeref;
 	int ret;
 
 	lockdep_assert_held(&ce->pin_mutex);
@@ -1185,14 +1112,9 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	if (!intel_context_is_pinned(ce))
 		return 0;
 
-	/* Submitting requests etc needs the hw awake. */
-	wakeref = intel_runtime_pm_get(i915);
-
 	rq = i915_request_create(ce->engine->kernel_context);
-	if (IS_ERR(rq)) {
-		ret = PTR_ERR(rq);
-		goto out_put;
-	}
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 
 	/* Queue this switch after all other activity by this context. */
 	ret = i915_active_request_set(&ce->ring->timeline->last_request, rq);
@@ -1216,9 +1138,6 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 
 out_add:
 	i915_request_add(rq);
-out_put:
-	intel_runtime_pm_put(i915, wakeref);
-
 	return ret;
 }