[PATCH AUTOSEL 5.4 29/35] drm/amdgpu: clean wptr on wb when gpu recovery

[Sasha Levin]

From: Yintian Tao <yttao at amd.com>

[ Upstream commit 2ab7e274b86739f4ceed5d94b6879f2d07b2802f ]

The TDR will be randomly failed due to compute ring
test failure. If the compute ring wptr & 0x7ff(ring_buf_mask)
is 0x100 then after map mqd the compute ring rptr will be
synced with 0x100. And the ring test packet size is also 0x100.
Then after invocation of amdgpu_ring_commit, the cp will not
really handle the packet on the ring buffer because rptr is equal to wptr.

Signed-off-by: Yintian Tao <yttao at amd.com>
Acked-by: Christian König <christian.koenig at amd.com>
Reviewed-by: Monk Liu <Monk.Liu at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2816d03297385..14417cebe38ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3555,6 +3555,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d85e1e559c826..40034efa64bbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3756,6 +3756,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
-- 
2.20.1