and no need to insert 128 nops after gfx8 vm flush anymore
because there was double SWITCH_BUFFER append to vm flush
Change-Id: I6ecec95236bd1745f2beaa1b34a075748813f131
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 29 ++++++++++++++++++-----------
1 file changed, 18 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 396c075..3016e535 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6390,8 +6390,6 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
/* sync PFP to ME, otherwise we might get invalid PFP reads */
amdgpu_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
amdgpu_ring_write(ring, 0x0);
- /* GFX8 emits 128 dw nop to prevent CE access VM before vm_flush finish */
- amdgpu_ring_insert_nop(ring, 128);
}
}
@@ -6791,15 +6789,24 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
.get_rptr = gfx_v8_0_ring_get_rptr,
.get_wptr = gfx_v8_0_ring_get_wptr_gfx,
.set_wptr = gfx_v8_0_ring_set_wptr_gfx,
- .emit_frame_size =
- 20 + /* gfx_v8_0_ring_emit_gds_switch */
- 7 + /* gfx_v8_0_ring_emit_hdp_flush */
- 5 + /* gfx_v8_0_ring_emit_hdp_invalidate */
- 6 + 6 + 6 +/* gfx_v8_0_ring_emit_fence_gfx x3 for user fence, vm fence */
- 7 + /* gfx_v8_0_ring_emit_pipeline_sync */
- 128 + 19 + /* gfx_v8_0_ring_emit_vm_flush */
- 2 + /* gfx_v8_ring_emit_sb */
- 3 + 4 + 29, /* gfx_v8_ring_emit_cntxcntl including vgt flush/meta-data */
+ .emit_frame_size = /* maximum 215dw if count 16 IBs in */
+ 5 + /* COND_EXEC */
+ 7 + /* PIPELINE_SYNC */
+ 19 + /* VM_FLUSH */
+ 8 + /* FENCE for VM_FLUSH */
+ 20 + /* GDS switch */
+ 4 + /* double SWITCH_BUFFER,
+ the first COND_EXEC jump to the place just
+ prior to this double SWITCH_BUFFER */
+ 5 + /* COND_EXEC */
+ 7 + /* HDP_flush */
+ 4 + /* VGT_flush */
+ 14 + /* CE_META */
+ 31 + /* DE_META */
+ 3 + /* CNTX_CTRL */
+ 5 + /* HDP_INVL */
+ 8 + 8 + /* FENCE x2 */
+ 2, /* SWITCH_BUFFER */
.emit_ib_size = 4, /* gfx_v8_0_ring_emit_ib_gfx */
.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
.emit_fence = gfx_v8_0_ring_emit_fence_gfx,
--
2.7.4
