drm/i915/guc: Connect UAPI to GuC multi-lrc interface

Introduce 'set parallel submit' extension to connect UAPI to GuC
multi-lrc interface. Kernel doc in new uAPI should explain it all.

IGT: https://patchwork.freedesktop.org/patch/447008/?series=93071&rev=1
media UMD: https://github.com/intel/media-driver/pull/1252

v2:
 (Daniel Vetter)
  - Add IGT link and placeholder for media UMD link
v3:
 (Kernel test robot)
  - Fix warning in unpin engines call
 (John Harrison)
  - Reword a bunch of the kernel doc
v4:
 (John Harrison)
  - Add comment why perma-pin is done after setting gem context
  - Update some comments / docs for proto contexts
v5:
 (John Harrison)
  - Rework perma-pin comment
  - Add BUG_IN if context is pinned when setting gem context

Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
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/20211014172005.27155-17-matthew.brost@intel.com

6 files changed, 133 insertions, 26 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 8309d1141d0a..1d880303a7e4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -55,9 +55,13 @@ struct intel_context_ops {
 	void (*reset)(struct intel_context *ce);
 	void (*destroy)(struct kref *kref);
 
-	/* virtual engine/context interface */
+	/* virtual/parallel engine/context interface */
 	struct intel_context *(*create_virtual)(struct intel_engine_cs **engine,
-						unsigned int count);
+						unsigned int count,
+						unsigned long flags);
+	struct intel_context *(*create_parallel)(struct intel_engine_cs **engines,
+						 unsigned int num_siblings,
+						 unsigned int width);
 	struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine,
 					       unsigned int sibling);
 };
@@ -113,6 +117,7 @@ struct intel_context {
 #define CONTEXT_NOPREEMPT		8
 #define CONTEXT_LRCA_DIRTY		9
 #define CONTEXT_GUC_INIT		10
+#define CONTEXT_PERMA_PIN		11
 
 	struct {
 		u64 timeout_us;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d5ac49c0691e..08559ace0ada 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -282,9 +282,19 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
+#define FORCE_VIRTUAL	BIT(0)
 struct intel_context *
 intel_engine_create_virtual(struct intel_engine_cs **siblings,
-			    unsigned int count);
+			    unsigned int count, unsigned long flags);
+
+static inline struct intel_context *
+intel_engine_create_parallel(struct intel_engine_cs **engines,
+			     unsigned int num_engines,
+			     unsigned int width)
+{
+	GEM_BUG_ON(!engines[0]->cops->create_parallel);
+	return engines[0]->cops->create_parallel(engines, num_engines, width);
+}
 
 static inline bool
 intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 2eb798ad068b..ff6753ccb129 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1953,16 +1953,16 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 
 struct intel_context *
 intel_engine_create_virtual(struct intel_engine_cs **siblings,
-			    unsigned int count)
+			    unsigned int count, unsigned long flags)
 {
 	if (count == 0)
 		return ERR_PTR(-EINVAL);
 
-	if (count == 1)
+	if (count == 1 && !(flags & FORCE_VIRTUAL))
 		return intel_context_create(siblings[0]);
 
 	GEM_BUG_ON(!siblings[0]->cops->create_virtual);
-	return siblings[0]->cops->create_virtual(siblings, count);
+	return siblings[0]->cops->create_virtual(siblings, count, flags);
 }
 
 struct i915_request *
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 43a74b216efb..bedb80057046 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -201,7 +201,8 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
 }
 
 static struct intel_context *
-execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+			 unsigned long flags);
 
 static struct i915_request *
 __active_request(const struct intel_timeline * const tl,
@@ -3784,7 +3785,8 @@ unlock:
 }
 
 static struct intel_context *
-execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
+execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+			 unsigned long flags)
 {
 	struct virtual_engine *ve;
 	unsigned int n;
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 25a8c4f62b0d..b367ecfa42de 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve));
 
 	for (n = 0; n < nctx; n++) {
-		ve[n] = intel_engine_create_virtual(siblings, nsibling);
+		ve[n] = intel_engine_create_virtual(siblings, nsibling, 0);
 		if (IS_ERR(ve[n])) {
 			err = PTR_ERR(ve[n]);
 			nctx = n;
@@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_close;
@@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt,
 		i915_request_add(rq);
 	}
 
-	ce = intel_engine_create_virtual(siblings, nsibling);
+	ce = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ce)) {
 		err = PTR_ERR(ce);
 		goto out;
@@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt,
 
 	/* XXX We do not handle oversubscription and fairness with normal rq */
 	for (n = 0; n < nsibling; n++) {
-		ce = intel_engine_create_virtual(siblings, nsibling);
+		ce = intel_engine_create_virtual(siblings, nsibling, 0);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			goto out;
@@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 	if (err)
 		goto out_scratch;
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_scratch;
@@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ve = intel_engine_create_virtual(siblings, nsibling);
+	ve = intel_engine_create_virtual(siblings, nsibling, 0);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_spin;
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 938dc34e8d3a..7c12364a017a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -124,7 +124,13 @@ struct guc_virtual_engine {
 };
 
 static struct intel_context *
-guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
+guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+		   unsigned long flags);
+
+static struct intel_context *
+guc_create_parallel(struct intel_engine_cs **engines,
+		    unsigned int num_siblings,
+		    unsigned int width);
 
 #define GUC_REQUEST_SIZE 64 /* bytes */
 
@@ -2609,6 +2615,7 @@ static const struct intel_context_ops guc_context_ops = {
 	.destroy = guc_context_destroy,
 
 	.create_virtual = guc_create_virtual,
+	.create_parallel = guc_create_parallel,
 };
 
 static void submit_work_cb(struct irq_work *wrk)
@@ -2858,8 +2865,6 @@ static const struct intel_context_ops virtual_guc_context_ops = {
 	.get_sibling = guc_virtual_get_sibling,
 };
 
-/* Future patches will use this function */
-__maybe_unused
 static int guc_parent_context_pin(struct intel_context *ce, void *vaddr)
 {
 	struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
@@ -2876,8 +2881,6 @@ static int guc_parent_context_pin(struct intel_context *ce, void *vaddr)
 	return __guc_context_pin(ce, engine, vaddr);
 }
 
-/* Future patches will use this function */
-__maybe_unused
 static int guc_child_context_pin(struct intel_context *ce, void *vaddr)
 {
 	struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
@@ -2889,8 +2892,6 @@ static int guc_child_context_pin(struct intel_context *ce, void *vaddr)
 	return __guc_context_pin(ce, engine, vaddr);
 }
 
-/* Future patches will use this function */
-__maybe_unused
 static void guc_parent_context_unpin(struct intel_context *ce)
 {
 	struct intel_guc *guc = ce_to_guc(ce);
@@ -2906,8 +2907,6 @@ static void guc_parent_context_unpin(struct intel_context *ce)
 	lrc_unpin(ce);
 }
 
-/* Future patches will use this function */
-__maybe_unused
 static void guc_child_context_unpin(struct intel_context *ce)
 {
 	GEM_BUG_ON(context_enabled(ce));
@@ -2918,8 +2917,6 @@ static void guc_child_context_unpin(struct intel_context *ce)
 	lrc_unpin(ce);
 }
 
-/* Future patches will use this function */
-__maybe_unused
 static void guc_child_context_post_unpin(struct intel_context *ce)
 {
 	GEM_BUG_ON(!intel_context_is_child(ce));
@@ -2930,6 +2927,98 @@ static void guc_child_context_post_unpin(struct intel_context *ce)
 	intel_context_unpin(ce->parallel.parent);
 }
 
+static void guc_child_context_destroy(struct kref *kref)
+{
+	struct intel_context *ce = container_of(kref, typeof(*ce), ref);
+
+	__guc_context_destroy(ce);
+}
+
+static const struct intel_context_ops virtual_parent_context_ops = {
+	.alloc = guc_virtual_context_alloc,
+
+	.pre_pin = guc_context_pre_pin,
+	.pin = guc_parent_context_pin,
+	.unpin = guc_parent_context_unpin,
+	.post_unpin = guc_context_post_unpin,
+
+	.ban = guc_context_ban,
+
+	.cancel_request = guc_context_cancel_request,
+
+	.enter = guc_virtual_context_enter,
+	.exit = guc_virtual_context_exit,
+
+	.sched_disable = guc_context_sched_disable,
+
+	.destroy = guc_context_destroy,
+
+	.get_sibling = guc_virtual_get_sibling,
+};
+
+static const struct intel_context_ops virtual_child_context_ops = {
+	.alloc = guc_virtual_context_alloc,
+
+	.pre_pin = guc_context_pre_pin,
+	.pin = guc_child_context_pin,
+	.unpin = guc_child_context_unpin,
+	.post_unpin = guc_child_context_post_unpin,
+
+	.cancel_request = guc_context_cancel_request,
+
+	.enter = guc_virtual_context_enter,
+	.exit = guc_virtual_context_exit,
+
+	.destroy = guc_child_context_destroy,
+
+	.get_sibling = guc_virtual_get_sibling,
+};
+
+static struct intel_context *
+guc_create_parallel(struct intel_engine_cs **engines,
+		    unsigned int num_siblings,
+		    unsigned int width)
+{
+	struct intel_engine_cs **siblings = NULL;
+	struct intel_context *parent = NULL, *ce, *err;
+	int i, j;
+
+	siblings = kmalloc_array(num_siblings,
+				 sizeof(*siblings),
+				 GFP_KERNEL);
+	if (!siblings)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < width; ++i) {
+		for (j = 0; j < num_siblings; ++j)
+			siblings[j] = engines[i * num_siblings + j];
+
+		ce = intel_engine_create_virtual(siblings, num_siblings,
+						 FORCE_VIRTUAL);
+		if (!ce) {
+			err = ERR_PTR(-ENOMEM);
+			goto unwind;
+		}
+
+		if (i == 0) {
+			parent = ce;
+			parent->ops = &virtual_parent_context_ops;
+		} else {
+			ce->ops = &virtual_child_context_ops;
+			intel_context_bind_parent_child(parent, ce);
+		}
+	}
+
+	kfree(siblings);
+	return parent;
+
+unwind:
+	if (parent)
+		intel_context_put(parent);
+	kfree(siblings);
+	return err;
+}
+
 static bool
 guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b)
 {
@@ -3756,7 +3845,8 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
 }
 
 static struct intel_context *
-guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
+guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
+		   unsigned long flags)
 {
 	struct guc_virtual_engine *ve;
 	struct intel_guc *guc;