[PATCH 13/27] drm/amdgpu/gfx12: re-emit unprocessed state on ring reset

[Alex Deucher]

Re-emit the unprocessed state after resetting the queue.

Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 39 +++++++++++++-------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index d2ee4543ce222..693a3f0aa58b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -4690,21 +4690,6 @@ static void gfx_v12_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
 			       ref, mask, 0x20);
 }
 
-static void gfx_v12_0_ring_soft_recovery(struct amdgpu_ring *ring,
-					 unsigned vmid)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t value = 0;
-
-	value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03);
-	value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
-	value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
-	value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid);
-	amdgpu_gfx_rlc_enter_safe_mode(adev, 0);
-	WREG32_SOC15(GC, 0, regSQ_CMD, value);
-	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
-}
-
 static void
 gfx_v12_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5317,6 +5302,8 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	amdgpu_ring_backup_unprocessed_commands(ring, guilty_fence);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false);
 	if (r) {
 		dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r);
@@ -5340,8 +5327,15 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 	r = amdgpu_ring_test_ring(ring);
 	if (r)
 		return r;
-	amdgpu_fence_driver_force_completion(ring);
+
+	/* signal the fence of the bad job */
+	amdgpu_fence_driver_guilty_force_completion(guilty_fence);
 	atomic_inc(&ring->adev->gpu_reset_counter);
+	r = amdgpu_ring_reemit_unprocessed_commands(ring);
+	if (r)
+		/* if we fail to reemit, force complete all fences */
+		amdgpu_fence_driver_force_completion(ring);
+
 	return 0;
 }
 
@@ -5438,6 +5432,8 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	amdgpu_ring_backup_unprocessed_commands(ring, guilty_fence);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, true);
 	if (r) {
 		dev_warn(adev->dev, "fail(%d) to reset kcq  and try pipe reset\n", r);
@@ -5460,8 +5456,15 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
 	r = amdgpu_ring_test_ring(ring);
 	if (r)
 		return r;
-	amdgpu_fence_driver_force_completion(ring);
+
+	/* signal the fence of the bad job */
+	amdgpu_fence_driver_guilty_force_completion(guilty_fence);
 	atomic_inc(&ring->adev->gpu_reset_counter);
+	r = amdgpu_ring_reemit_unprocessed_commands(ring);
+	if (r)
+		/* if we fail to reemit, force complete all fences */
+		amdgpu_fence_driver_force_completion(ring);
+
 	return 0;
 }
 
@@ -5540,7 +5543,6 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = {
 	.emit_wreg = gfx_v12_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v12_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v12_0_ring_emit_reg_write_reg_wait,
-	.soft_recovery = gfx_v12_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v12_0_emit_mem_sync,
 	.reset = gfx_v12_0_reset_kgq,
 	.emit_cleaner_shader = gfx_v12_0_ring_emit_cleaner_shader,
@@ -5579,7 +5581,6 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_compute = {
 	.emit_wreg = gfx_v12_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v12_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v12_0_ring_emit_reg_write_reg_wait,
-	.soft_recovery = gfx_v12_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v12_0_emit_mem_sync,
 	.reset = gfx_v12_0_reset_kcq,
 	.emit_cleaner_shader = gfx_v12_0_ring_emit_cleaner_shader,
-- 
2.49.0