drm/amdgpu: Increase soft IH ring size

Retry faults are delegated to soft IH ring and then processed by
deferred worker. Current soft IH ring size PAGE_SIZE can store 128
entries, which may overflow and drop retry faults, causes HW stucks
because the retry fault is not recovered.

Increase soft IH ring size to 8KB, enough to store 256 CAM entries
because we clear the CAM entry after handling the retry fault from soft
ring.

Define macro IH_RING_SIZE and IH_SW_RING_SIZE to remove duplicate
constant.

Show warning message if soft IH ring overflows with CAM enabled because
this should not happen.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 5 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index dd1c2eded6b9..6c6184f0dbc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -27,6 +27,9 @@
 /* Maximum number of IVs processed at once */
 #define AMDGPU_IH_MAX_NUM_IVS	32
 
+#define IH_RING_SIZE	(256 * 1024)
+#define IH_SW_RING_SIZE	(8 * 1024)	/* enough for 256 CAM entries */
+
 struct amdgpu_device;
 struct amdgpu_iv_entry;
 
@@ -97,8 +100,8 @@ struct amdgpu_ih_funcs {
 int amdgpu_ih_ring_init(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
 			unsigned ring_size, bool use_bus_addr);
 void amdgpu_ih_ring_fini(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih);
-void amdgpu_ih_ring_write(struct amdgpu_ih_ring *ih, const uint32_t *iv,
-			  unsigned int num_dw);
+void amdgpu_ih_ring_write(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
+			  const uint32_t *iv, unsigned int num_dw);
 int amdgpu_ih_wait_on_checkpoint_process_ts(struct amdgpu_device *adev,
 					    struct amdgpu_ih_ring *ih);
 int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih);