From 49821aff4cec8057c5f8530fea0976eb5d75aa6d Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 22 Dec 2021 14:35:32 -0800
Subject: drm/i915/execlists: Weak parallel submission support for execlists
Git-commit: a88afcfa258672601eda5966439d2fc310a34cb7
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

A weak implementation of parallel submission (multi-bb execbuf IOCTL) for
execlists. Doing as little as possible to support this interface for
execlists - basically just passing submit fences between each request
generated and virtual engines are not allowed. This is on par with what
is there for the existing (hopefully soon deprecated) bonding interface.

We perma-pin these execlists contexts to align with GuC implementation.

v2:
 (John Harrison)
  - Drop siblings array as num_siblings must be 1
v3:
 (John Harrison)
  - Drop single submission
v4:
 (John Harrison)
  - Actually drop single submission
  - Use IS_ERR check on return value from intel_context_create
  - Set last request to NULL on unpin

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211222223532.28698-1-matthew.brost@intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c   | 11 ++++--
 drivers/gpu/drm/i915/gt/intel_context.c       |  4 +-
 .../drm/i915/gt/intel_execlists_submission.c  | 38 +++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_lrc.c           |  4 ++
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c |  2 -
 5 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 2958e2be4292..bc6d59df064d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -587,10 +587,6 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
 	struct intel_engine_cs **siblings = NULL;
 	intel_engine_mask_t prev_mask;
 
-	/* FIXME: This is NIY for execlists */
-	if (!(intel_uc_uses_guc_submission(&to_gt(i915)->uc)))
-		return -ENODEV;
-
 	if (get_user(slot, &ext->engine_index))
 		return -EFAULT;
 
@@ -600,6 +596,13 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
 	if (get_user(num_siblings, &ext->num_siblings))
 		return -EFAULT;
 
+	if (!intel_uc_uses_guc_submission(&to_gt(i915)->uc) &&
+	    num_siblings != 1) {
+		drm_dbg(&i915->drm, "Only 1 sibling (%d) supported in non-GuC mode\n",
+			num_siblings);
+		return -EINVAL;
+	}
+
 	if (slot >= set->num_engines) {
 		drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
 			slot, set->num_engines);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ba083d800a08..5d0ec7c49b6a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -79,7 +79,8 @@ static int intel_context_active_acquire(struct intel_context *ce)
 
 	__i915_active_acquire(&ce->active);
 
-	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine))
+	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine) ||
+	    intel_context_is_parallel(ce))
 		return 0;
 
 	/* Preallocate tracking nodes */
@@ -563,7 +564,6 @@ void intel_context_bind_parent_child(struct intel_context *parent,
 	 * Callers responsibility to validate that this function is used
 	 * correctly but we use GEM_BUG_ON here ensure that they do.
 	 */
-	GEM_BUG_ON(!intel_engine_uses_guc(parent->engine));
 	GEM_BUG_ON(intel_context_is_pinned(parent));
 	GEM_BUG_ON(intel_context_is_child(parent));
 	GEM_BUG_ON(intel_context_is_pinned(child));
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 4a9ef688fac2..961d795220a3 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2601,6 +2601,43 @@ static void execlists_context_cancel_request(struct intel_context *ce,
 				      current->comm);
 }
 
+static struct intel_context *
+execlists_create_parallel(struct intel_engine_cs **engines,
+			  unsigned int num_siblings,
+			  unsigned int width)
+{
+	struct intel_context *parent = NULL, *ce, *err;
+	int i;
+
+	GEM_BUG_ON(num_siblings != 1);
+
+	for (i = 0; i < width; ++i) {
+		ce = intel_context_create(engines[i]);
+		if (IS_ERR(ce)) {
+			err = ce;
+			goto unwind;
+		}
+
+		if (i == 0)
+			parent = ce;
+		else
+			intel_context_bind_parent_child(parent, ce);
+	}
+
+	parent->parallel.fence_context = dma_fence_context_alloc(1);
+
+	intel_context_set_nopreempt(parent);
+	for_each_child(parent, ce)
+		intel_context_set_nopreempt(ce);
+
+	return parent;
+
+unwind:
+	if (parent)
+		intel_context_put(parent);
+	return err;
+}
+
 static const struct intel_context_ops execlists_context_ops = {
 	.flags = COPS_HAS_INFLIGHT,
 
@@ -2619,6 +2656,7 @@ static const struct intel_context_ops execlists_context_ops = {
 	.reset = lrc_reset,
 	.destroy = lrc_destroy,
 
+	.create_parallel = execlists_create_parallel,
 	.create_virtual = execlists_create_virtual,
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 91c87a3a8e0b..55f1cd94dfb9 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1069,6 +1069,10 @@ lrc_pin(struct intel_context *ce,
 
 void lrc_unpin(struct intel_context *ce)
 {
+	if (unlikely(ce->parallel.last_rq)) {
+		i915_request_put(ce->parallel.last_rq);
+		ce->parallel.last_rq = NULL;
+	}
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
 		      ce->engine);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 0c82df5ccd59..980f73b7872f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -3330,8 +3330,6 @@ static void guc_parent_context_unpin(struct intel_context *ce)
 	GEM_BUG_ON(!intel_context_is_parent(ce));
 	GEM_BUG_ON(!intel_engine_is_virtual(ce->engine));
 
-	if (ce->parallel.last_rq)
-		i915_request_put(ce->parallel.last_rq);
 	unpin_guc_id(guc, ce);
 	lrc_unpin(ce);
 }
-- 
2.38.1