[PATCH AUTOSEL 5.5 234/542] drm/amdgpu: fix double gpu_recovery for NV of SRIOV

[Sasha Levin]

From: Monk Liu <Monk.Liu at amd.com>

[ Upstream commit 1512d064f55bace6a8e32d65009c7ea112e76a31 ]

issues:
gpu_recover() is re-entered by the mailbox interrupt
handler mxgpu_nv.c

fix:
we need to bypass the gpu_recover() invoke in mailbox
interrupt as long as the timeout is not infinite (thus the TDR
will be triggered automatically after time out, no need to invoke
gpu_recover() through mailbox interrupt.

Signed-off-by: Monk Liu <Monk.Liu at amd.com>
Reviewed-by: Emily Deng <Emily.Deng 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/mxgpu_nv.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 0d8767eb7a709..1c3a7d4bb65d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -269,7 +269,11 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery for world switch failure if no TDR */
-	if (amdgpu_device_should_recover_gpu(adev))
+	if (amdgpu_device_should_recover_gpu(adev)
+		&& (adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }
 
-- 
2.20.1