drm/i915: Move CSB MMIO reads out of the execlists lock

By reading the CSB (slow MMIO accesses) into a temporary local
buffer we can decrease the duration of holding the execlist
lock.

Main advantage is that during heavy batch buffer submission we
reduce the execlist lock contention, which should decrease the
latency and CPU usage between the submitting userspace process
and interrupt handling.

Downside is that we need to grab and relase the forcewake twice,
but as the below numbers will show this is completely hidden
by the primary gains.

Testing with "gem_latency -n 100" (submit batch buffers with a
hundred nops each) shows more than doubling of the throughput
and more than halving of the dispatch latency, overall latency
and CPU time spend in the submitting process.

Submitting empty batches ("gem_latency -n 0") does not seem
significantly affected by this change with throughput and CPU
time improving by half a percent, and overall latency worsening
by the same amount.

Above tests were done in a hundred runs on a big core Broadwell.

v2:
  * Overflow protection to local CSB buffer.
  * Use closer dev_priv in execlists_submit_requests. (Chris Wilson)

v3: Rebase.

v4: Added commend about irq needed to be disabled in
    execlists_submit_request. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilsno <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1458219586-20452-1-git-send-email-tvrtko.ursulin@linux.intel.com

drivers/gpu/drm/i915/intel_lrc.c

@@ -416,15 +416,25 @@ static void execlists_update_context(struct drm_i915_gem_request *rq)
 static void execlists_submit_requests(struct drm_i915_gem_request *rq0,
 				      struct drm_i915_gem_request *rq1)
 {
+	struct drm_i915_private *dev_priv = rq0->i915;
+
+	/* BUG_ON(!irqs_disabled());  */
+
 	execlists_update_context(rq0);
 
 	if (rq1)
 		execlists_update_context(rq1);
 
+	spin_lock(&dev_priv->uncore.lock);
+	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
+
 	execlists_elsp_write(rq0, rq1);
+
+	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
+	spin_unlock(&dev_priv->uncore.lock);
 }
 
-static void execlists_context_unqueue__locked(struct intel_engine_cs *engine)
+static void execlists_context_unqueue(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *req0 = NULL, *req1 = NULL;
 	struct drm_i915_gem_request *cursor, *tmp;
@@ -478,19 +488,6 @@ static void execlists_context_unqueue__locked(struct intel_engine_cs *engine)
 	execlists_submit_requests(req0, req1);
 }
 
-static void execlists_context_unqueue(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
-
-	spin_lock(&dev_priv->uncore.lock);
-	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
-
-	execlists_context_unqueue__locked(engine);
-
-	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
-	spin_unlock(&dev_priv->uncore.lock);
-}
-
 static unsigned int
 execlists_check_remove_request(struct intel_engine_cs *engine, u32 request_id)
 {
@@ -551,12 +548,10 @@ void intel_lrc_irq_handler(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->dev->dev_private;
 	u32 status_pointer;
 	unsigned int read_pointer, write_pointer;
-	u32 status = 0;
-	u32 status_id;
+	u32 csb[GEN8_CSB_ENTRIES][2];
+	unsigned int csb_read = 0, i;
 	unsigned int submit_contexts = 0;
 
-	spin_lock(&engine->execlist_lock);
-
 	spin_lock(&dev_priv->uncore.lock);
 	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
 
@@ -568,41 +563,47 @@ void intel_lrc_irq_handler(struct intel_engine_cs *engine)
 		write_pointer += GEN8_CSB_ENTRIES;
 
 	while (read_pointer < write_pointer) {
-		status = get_context_status(engine, ++read_pointer,
-				            &status_id);
+		if (WARN_ON_ONCE(csb_read == GEN8_CSB_ENTRIES))
+			break;
+		csb[csb_read][0] = get_context_status(engine, ++read_pointer,
+						      &csb[csb_read][1]);
+		csb_read++;
+	}
 
-		if (unlikely(status & GEN8_CTX_STATUS_PREEMPTED)) {
-			if (status & GEN8_CTX_STATUS_LITE_RESTORE) {
-				if (execlists_check_remove_request(engine, status_id))
+	engine->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES;
+
+	/* Update the read pointer to the old write pointer. Manual ringbuffer
+	 * management ftw </sarcasm> */
+	I915_WRITE_FW(RING_CONTEXT_STATUS_PTR(engine),
+		      _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
+				    engine->next_context_status_buffer << 8));
+
+	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
+	spin_unlock(&dev_priv->uncore.lock);
+
+	spin_lock(&engine->execlist_lock);
+
+	for (i = 0; i < csb_read; i++) {
+		if (unlikely(csb[i][0] & GEN8_CTX_STATUS_PREEMPTED)) {
+			if (csb[i][0] & GEN8_CTX_STATUS_LITE_RESTORE) {
+				if (execlists_check_remove_request(engine, csb[i][1]))
 					WARN(1, "Lite Restored request removed from queue\n");
 			} else
 				WARN(1, "Preemption without Lite Restore\n");
 		}
 
-		if (status & (GEN8_CTX_STATUS_ACTIVE_IDLE |
+		if (csb[i][0] & (GEN8_CTX_STATUS_ACTIVE_IDLE |
 		    GEN8_CTX_STATUS_ELEMENT_SWITCH))
 			submit_contexts +=
-				execlists_check_remove_request(engine,
-						               status_id);
+				execlists_check_remove_request(engine, csb[i][1]);
 	}
 
 	if (submit_contexts) {
 		if (!engine->disable_lite_restore_wa ||
-		    (status & GEN8_CTX_STATUS_ACTIVE_IDLE))
-			execlists_context_unqueue__locked(engine);
+		    (csb[i][0] & GEN8_CTX_STATUS_ACTIVE_IDLE))
+			execlists_context_unqueue(engine);
 	}
 
-	engine->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES;
-
-	/* Update the read pointer to the old write pointer. Manual ringbuffer
-	 * management ftw </sarcasm> */
-	I915_WRITE_FW(RING_CONTEXT_STATUS_PTR(engine),
-		      _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
-				    engine->next_context_status_buffer << 8));
-
-	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
-	spin_unlock(&dev_priv->uncore.lock);
-
 	spin_unlock(&engine->execlist_lock);
 
 	if (unlikely(submit_contexts > 2))