drm/amdgpu/gfx9: drop unnecessary 64-bit fence flag check in KIQ
Subsystems (2)
PATCH v3 1/1 drm/amdgpu/gfx9: drop unnecessary 64-bit fence flag check in KIQ
Remove the BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT) assertion from gfx_v9_0_ring_emit_fence_kiq(). The KIQ hardware supports 64-bit fence writes; the 32-bit writeback address constraint is an upper-layer convention, not a hardware limitation. The check serves no purpose and should not be present.
Found by code inspection while investigating related BUG_ON assertions in the GFX and compute ring emission paths.
--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 --- 1 file changed, 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0 -3
@@ -5679,9 +5679,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr,struct amdgpu_device *adev = ring->adev; -/* we only allocate 32bit for each seq wb address */ -BUG_ON (flags &AMDGPU_FENCE_FLAG_64BIT ); -/* write fence seq to the "addr" */ amdgpu_ring_write (ring,PACKET3 (PACKET3_WRITE_DATA ,3 )); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
Signature · 1 line
2.43.0
Quoted 10 lines · John B. Moore
Remove the
BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT)assertion fromgfx_v9_0_ring_emit_fence_kiq(). The KIQ hardware supports 64-bit fence writes; the 32-bit writeback address constraint is an upper-layer convention, not a hardware limitation. The check serves no purpose and should not be present.Found by code inspection while investigating related
BUG_ONassertions in the GFX and compute ring emission paths.Signed-off-by John B. Moore <[email protected]>
Quoted 17 lines
--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 --- 1 file changed, 3 deletions(-)drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-3@@ -5679,9 +5679,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr,struct amdgpu_device *adev = ring->adev; -/* we only allocate 32bit for each seq wb address */ -BUG_ON (flags &AMDGPU_FENCE_FLAG_64BIT ); -/* write fence seq to the "addr" */ amdgpu_ring_write (ring,PACKET3 (PACKET3_WRITE_DATA ,3 )); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
Alex Deucher
AppliedApplied. Please double check your mail client. It seems to have mangled the patch, so I had to manually fix it up.
Thanks!
Alex
Quoted 33 lines · Christian König
Quoted 10 lines · John B. Moore
Remove the
BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT)assertion fromgfx_v9_0_ring_emit_fence_kiq(). The KIQ hardware supports 64-bit fence writes; the 32-bit writeback address constraint is an upper-layer convention, not a hardware limitation. The check serves no purpose and should not be present.Found by code inspection while investigating related
BUG_ONassertions in the GFX and compute ring emission paths.Signed-off-by John B. Moore <[email protected]>Reviewed-by Christian König <[email protected]>Quoted 17 lines
--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 --- 1 file changed, 3 deletions(-)drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-3@@ -5679,9 +5679,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr,struct amdgpu_device *adev = ring->adev; -/* we only allocate 32bit for each seq wb address */ -BUG_ON (flags &AMDGPU_FENCE_FLAG_64BIT ); -/* write fence seq to the "addr" */ amdgpu_ring_write (ring,PACKET3 (PACKET3_WRITE_DATA ,3 )); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |