[PATCH 7/9] drm/amdgpu/gfx7: Use COND_EXEC

COND_EXEC tells the CP to discard the dwords following it
when its condition is zero (false).

This is useful for GPU recovery because it can help reduce
collateral damage during GFX IP block soft reset, meaning
that it reduces the likelyhood that we fail some jobs which
are not guilty of the hang as the IP block soft reset
mechanism clears the condition before doing the reset.

Signed-off-by: Timur Kristóf <[email protected]>
Reviewed-by: Tvrtko Ursulin <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 67dfda7c0a45..dbd4667100b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3160,6 +3160,22 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	}
 }
 
+static unsigned int gfx_v7_0_ring_emit_init_cond_exec(struct amdgpu_ring *ring,
+						      uint64_t gpu_addr)
+{
+	unsigned int ret;
+
+	/* Discard following DWs after this packet when gpu_addr==0 */
+	amdgpu_ring_write(ring, PACKET3(PACKET3_COND_EXEC, 3));
+	amdgpu_ring_write(ring, lower_32_bits(gpu_addr));
+	amdgpu_ring_write(ring, upper_32_bits(gpu_addr));
+	amdgpu_ring_write(ring, 0);
+	ret = ring->wptr & ring->buf_mask;
+	/* patch dummy value later */
+	amdgpu_ring_write(ring, 0);
+	return ret;
+}
+
 static void gfx_v7_0_ring_emit_wreg(struct amdgpu_ring *ring,
 				    uint32_t reg, uint32_t val)
 {
@@ -4941,6 +4957,8 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = {
 	.get_wptr = gfx_v7_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v7_0_ring_set_wptr_gfx,
 	.emit_frame_size =
+		5 + /* gfx_v7_0_ring_emit_init_cond_exec (from amdgpu_ib_schedule) */
+		5 + /* gfx_v7_0_ring_emit_init_cond_exec (from amdgpu_vm_flush) */
 		20 + /* gfx_v7_0_ring_emit_gds_switch */
 		7 + /* gfx_v7_0_ring_emit_hdp_flush */
 		5 + /* hdp invalidate */
@@ -4963,6 +4981,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_switch_buffer = gfx_v7_0_ring_emit_sb,
 	.emit_cntxcntl = gfx_v7_ring_emit_cntxcntl,
+	.init_cond_exec = gfx_v7_0_ring_emit_init_cond_exec,
 	.emit_wreg = gfx_v7_0_ring_emit_wreg,
 	.soft_recovery = gfx_v7_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v7_0_emit_mem_sync,
@@ -4977,6 +4996,8 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_compute = {
 	.get_wptr = gfx_v7_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v7_0_ring_set_wptr_compute,
 	.emit_frame_size =
+		5 + /* gfx_v7_0_ring_emit_init_cond_exec (from amdgpu_ib_schedule) */
+		5 + /* gfx_v7_0_ring_emit_init_cond_exec (from amdgpu_vm_flush) */
 		20 + /* gfx_v7_0_ring_emit_gds_switch */
 		7 + /* gfx_v7_0_ring_emit_hdp_flush */
 		5 + /* hdp invalidate */
@@ -4995,6 +5016,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_compute = {
 	.test_ib = gfx_v7_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.init_cond_exec = gfx_v7_0_ring_emit_init_cond_exec,
 	.emit_wreg = gfx_v7_0_ring_emit_wreg,
 	.soft_recovery = gfx_v7_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v7_0_emit_mem_sync_compute,
-- 
2.55.0