[PATCH] drm/amdgpu: set sched_hw_submission higher for KIQ (v2)

[Alex Deucher]

KIQ doesn't really use the GPU scheduler.  The base
drivers generally use the KIQ ring directly rather than
submitting IBs.  However, amdgpu_sched_hw_submission
(which defaults to 2) limits the number of outstanding
fences to 2.  KFD uses the KIQ for TLB flushes and the
2 fence limit hurts performance when there are several KFD
processes running.

v2: move some expressions to one line
    change KIQ sched_hw_submission to at least 16

Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 6c5646b..7c251ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -170,6 +170,16 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     unsigned irq_type)
 {
 	int r;
+	int sched_hw_submission = amdgpu_sched_hw_submission;
+
+	/* Set the hw submission limit higher for KIQ because
+	 * it's used for a number of gfx/compute tasks by both
+	 * KFD and KGD which may have outstanding fences and
+	 * it doesn't really use the gpu scheduler anyway;
+	 * KIQ tasks get submitted directly to the ring.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		sched_hw_submission = max(sched_hw_submission, 16);
 
 	if (ring->adev == NULL) {
 		if (adev->num_rings >= AMDGPU_MAX_RINGS)
@@ -178,8 +188,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		ring->adev = adev;
 		ring->idx = adev->num_rings++;
 		adev->rings[ring->idx] = ring;
-		r = amdgpu_fence_driver_init_ring(ring,
-			amdgpu_sched_hw_submission);
+		r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission);
 		if (r)
 			return r;
 	}
@@ -218,8 +227,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		return r;
 	}
 
-	ring->ring_size = roundup_pow_of_two(max_dw * 4 *
-					     amdgpu_sched_hw_submission);
+	ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission);
 
 	ring->buf_mask = (ring->ring_size / 4) - 1;
 	ring->ptr_mask = ring->funcs->support_64bit_ptrs ?
-- 
2.5.5