[PATCH v2 3/4] drm/amdgpu: Add option to disable implicit sync for a context.

[Tatsuyuki Ishi]

From: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>

This changes all BO usages in a submit to BOOKKEEP instead of READ,
which effectively disables implicit sync for these submits.

This is configured at a context level using the existing IOCTL.

Signed-off-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
Co-developed-by: Tatsuyuki Ishi <ishitatsuyuki at gmail.com>
Signed-off-by: Tatsuyuki Ishi <ishitatsuyuki at gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 16 +++++++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 30 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h |  1 +
 include/uapi/drm/amdgpu_drm.h           |  4 ++++
 4 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2cb814de0149..008547f97fd1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1200,8 +1200,11 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
 		struct dma_resv *resv = bo->tbo.base.resv;
 		enum amdgpu_sync_mode sync_mode;
 
-		sync_mode = amdgpu_bo_explicit_sync(bo) ?
-			AMDGPU_SYNC_EXPLICIT : AMDGPU_SYNC_NE_OWNER;
+		if (amdgpu_bo_explicit_sync(bo) || p->ctx->disable_implicit_sync)
+			sync_mode = AMDGPU_SYNC_EXPLICIT;
+		else
+			sync_mode = AMDGPU_SYNC_NE_OWNER;
+
 		r = amdgpu_sync_resv(p->adev, &p->sync, resv, sync_mode,
 				     AMDGPU_SYNC_EXPLICIT, &fpriv->vm);
 		if (r)
@@ -1322,11 +1325,16 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 			dma_resv_add_fence(gobj->resv,
 					   &p->jobs[i]->base.s_fence->finished,
-					   DMA_RESV_USAGE_READ);
+					   p->ctx->disable_implicit_sync ?
+						   DMA_RESV_USAGE_BOOKKEEP :
+						   DMA_RESV_USAGE_READ);
 		}
 
 		/* The gang leader as remembered as writer */
-		dma_resv_add_fence(gobj->resv, p->fence, DMA_RESV_USAGE_WRITE);
+		dma_resv_add_fence(gobj->resv, p->fence,
+				   p->ctx->disable_implicit_sync ?
+					   DMA_RESV_USAGE_BOOKKEEP :
+					   DMA_RESV_USAGE_WRITE);
 	}
 
 	seq = amdgpu_ctx_add_fence(p->ctx, p->entities[p->gang_leader_idx],
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 0dc9c655c4fb..fe6f30d8fd70 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -661,6 +661,30 @@ static int amdgpu_ctx_stable_pstate(struct amdgpu_device *adev,
 	return r;
 }
 
+static int amdgpu_ctx_set_implicit_sync(struct amdgpu_device *adev,
+					struct amdgpu_fpriv *fpriv, uint32_t id,
+					bool enable)
+{
+	struct amdgpu_ctx *ctx;
+	struct amdgpu_ctx_mgr *mgr;
+
+	if (!fpriv)
+		return -EINVAL;
+
+	mgr = &fpriv->ctx_mgr;
+	mutex_lock(&mgr->lock);
+	ctx = idr_find(&mgr->ctx_handles, id);
+	if (!ctx) {
+		mutex_unlock(&mgr->lock);
+		return -EINVAL;
+	}
+
+	ctx->disable_implicit_sync = !enable;
+
+	mutex_unlock(&mgr->lock);
+	return 0;
+}
+
 int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *filp)
 {
@@ -709,6 +733,12 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 			return -EINVAL;
 		r = amdgpu_ctx_stable_pstate(adev, fpriv, id, true, &stable_pstate);
 		break;
+	case AMDGPU_CTX_OP_SET_IMPLICIT_SYNC:
+		if ((args->in.flags & ~AMDGPU_CTX_IMPLICIT_SYNC_ENABLED) || args->in.priority)
+			return -EINVAL;
+		r = amdgpu_ctx_set_implicit_sync(adev, fpriv, id,
+						 args->in.flags & ~AMDGPU_CTX_IMPLICIT_SYNC_ENABLED);
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index 85376baaa92f..a330e5b65d30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -58,6 +58,7 @@ struct amdgpu_ctx {
 	unsigned long			ras_counter_ue;
 	uint32_t			stable_pstate;
 	struct amdgpu_ctx_mgr		*ctx_mgr;
+	bool				disable_implicit_sync;
 };
 
 struct amdgpu_ctx_mgr {
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 79b14828d542..6a0168436c31 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -226,6 +226,7 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_OP_QUERY_STATE2	4
 #define AMDGPU_CTX_OP_GET_STABLE_PSTATE	5
 #define AMDGPU_CTX_OP_SET_STABLE_PSTATE	6
+#define AMDGPU_CTX_OP_SET_IMPLICIT_SYNC	7
 
 /* GPU reset status */
 #define AMDGPU_CTX_NO_RESET		0
@@ -268,6 +269,9 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_STABLE_PSTATE_MIN_MCLK  3
 #define AMDGPU_CTX_STABLE_PSTATE_PEAK  4
 
+/* opt-out of implicit sync */
+#define AMDGPU_CTX_IMPLICIT_SYNC_ENABLED  1
+
 struct drm_amdgpu_ctx_in {
 	/** AMDGPU_CTX_OP_* */
 	__u32	op;
-- 
2.41.0