drm/i915/guc: Implement multi-lrc submission

Implement multi-lrc submission via a single workqueue entry and single
H2G. The workqueue entry contains an updated tail value for each
request, of all the contexts in the multi-lrc submission, and updates
these values simultaneously. As such, the tasklet and bypass path have
been updated to coalesce requests into a single submission.

v2:
 (John Harrison)
  - s/wqe/wqi
  - Use FIELD_PREP macros
  - Add GEM_BUG_ONs ensures length fits within field
  - Add comment / white space to intel_guc_write_barrier
 (Kernel test robot)
  - Make need_tasklet a static function
v3:
 (Docs)
  - A comment for submission_stall_reason
v4:
 (Kernel test robot)
  - Initialize return value in bypass tasklt submit function
 (John Harrison)
  - Add comment near work queue defs
  - Add BUILD_BUG_ON to ensure WQ_SIZE is a power of 2
  - Update write_barrier comment to talk about work queue
v5:
 (John Harrison)
  - Fix typo in work queue comment
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-13-matthew.brost@intel.com

drivers/gpu/drm/i915/gt/uc/intel_guc.c

@@ -756,3 +756,32 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p)
 		}
 	}
 }
+
+void intel_guc_write_barrier(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	if (i915_gem_object_is_lmem(guc->ct.vma->obj)) {
+		/*
+		 * Ensure intel_uncore_write_fw can be used rather than
+		 * intel_uncore_write.
+		 */
+		GEM_BUG_ON(guc->send_regs.fw_domains);
+
+		/*
+		 * This register is used by the i915 and GuC for MMIO based
+		 * communication. Once we are in this code CTBs are the only
+		 * method the i915 uses to communicate with the GuC so it is
+		 * safe to write to this register (a value of 0 is NOP for MMIO
+		 * communication). If we ever start mixing CTBs and MMIOs a new
+		 * register will have to be chosen. This function is also used
+		 * to enforce ordering of a work queue item write and an update
+		 * to the process descriptor. When a work queue is being used,
+		 * CTBs are also the only mechanism of communication.
+		 */
+		intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0);
+	} else {
+		/* wmb() sufficient for a barrier if in smem */
+		wmb();
+	}
+}

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -46,6 +46,15 @@ struct intel_guc {
 	 * submitted until the stalled request is processed.
 	 */
 	struct i915_request *stalled_request;
+	/**
+	 * @submission_stall_reason: reason why submission is stalled
+	 */
+	enum {
+		STALL_NONE,
+		STALL_REGISTER_CONTEXT,
+		STALL_MOVE_LRC_TAIL,
+		STALL_ADD_REQUEST,
+	} submission_stall_reason;
 
 	/* intel_guc_recv interrupt related state */
 	/** @irq_lock: protects GuC irq state */
@@ -367,4 +376,6 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc);
 
 void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
 
+void intel_guc_write_barrier(struct intel_guc *guc);
+
 #endif

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -383,28 +383,6 @@ static u32 ct_get_next_fence(struct intel_guc_ct *ct)
 	return ++ct->requests.last_fence;
 }
 
-static void write_barrier(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	if (i915_gem_object_is_lmem(guc->ct.vma->obj)) {
-		GEM_BUG_ON(guc->send_regs.fw_domains);
-		/*
-		 * This register is used by the i915 and GuC for MMIO based
-		 * communication. Once we are in this code CTBs are the only
-		 * method the i915 uses to communicate with the GuC so it is
-		 * safe to write to this register (a value of 0 is NOP for MMIO
-		 * communication). If we ever start mixing CTBs and MMIOs a new
-		 * register will have to be chosen.
-		 */
-		intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0);
-	} else {
-		/* wmb() sufficient for a barrier if in smem */
-		wmb();
-	}
-}
-
 static int ct_write(struct intel_guc_ct *ct,
 		    const u32 *action,
 		    u32 len /* in dwords */,
@@ -474,7 +452,7 @@ static int ct_write(struct intel_guc_ct *ct,
 	 * make sure H2G buffer update and LRC tail update (if this triggering a
 	 * submission) are visible before updating the descriptor tail
 	 */
-	write_barrier(ct);
+	intel_guc_write_barrier(ct_to_guc(ct));
 
 	/* update local copies */
 	ctb->tail = tail;

drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h

@@ -52,25 +52,27 @@
 
 #define GUC_DOORBELL_INVALID		256
 
-/* Work queue item header definitions */
+/*
+ * Work queue item header definitions
+ *
+ * Work queue is circular buffer used to submit complex (multi-lrc) submissions
+ * to the GuC. A work queue item is an entry in the circular buffer.
+ */
 #define WQ_STATUS_ACTIVE		1
 #define WQ_STATUS_SUSPENDED		2
 #define WQ_STATUS_CMD_ERROR		3
 #define WQ_STATUS_ENGINE_ID_NOT_USED	4
 #define WQ_STATUS_SUSPENDED_FROM_RESET	5
-#define WQ_TYPE_SHIFT			0
-#define   WQ_TYPE_BATCH_BUF		(0x1 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_PSEUDO		(0x2 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_INORDER		(0x3 << WQ_TYPE_SHIFT)
-#define   WQ_TYPE_NOOP			(0x4 << WQ_TYPE_SHIFT)
-#define WQ_TARGET_SHIFT			10
-#define WQ_LEN_SHIFT			16
-#define WQ_NO_WCFLUSH_WAIT		(1 << 27)
-#define WQ_PRESENT_WORKLOAD		(1 << 28)
-
-#define WQ_RING_TAIL_SHIFT		20
-#define WQ_RING_TAIL_MAX		0x7FF	/* 2^11 QWords */
-#define WQ_RING_TAIL_MASK		(WQ_RING_TAIL_MAX << WQ_RING_TAIL_SHIFT)
+#define WQ_TYPE_BATCH_BUF		0x1
+#define WQ_TYPE_PSEUDO			0x2
+#define WQ_TYPE_INORDER			0x3
+#define WQ_TYPE_NOOP			0x4
+#define WQ_TYPE_MULTI_LRC		0x5
+#define WQ_TYPE_MASK			GENMASK(7, 0)
+#define WQ_LEN_MASK			GENMASK(26, 16)
+
+#define WQ_GUC_ID_MASK			GENMASK(15, 0)
+#define WQ_RING_TAIL_MASK		GENMASK(28, 18)
 
 #define GUC_STAGE_DESC_ATTR_ACTIVE	BIT(0)
 #define GUC_STAGE_DESC_ATTR_PENDING_DB	BIT(1)

drivers/gpu/drm/i915/i915_request.h

@@ -139,6 +139,14 @@ enum {
 	 * the GPU. Here we track such boost requests on a per-request basis.
 	 */
 	I915_FENCE_FLAG_BOOST,
+
+	/*
+	 * I915_FENCE_FLAG_SUBMIT_PARALLEL - request with a context in a
+	 * parent-child relationship (parallel submission, multi-lrc) should
+	 * trigger a submission to the GuC rather than just moving the context
+	 * tail.
+	 */
+	I915_FENCE_FLAG_SUBMIT_PARALLEL,
 };
 
 /**