[PATCH 1/6] drm/amdgpu: condense mqd programming sequence

Andres Rodriguez andresx7 at gmail.com
Thu Apr 13 22:04:31 UTC 2017


The MQD structure matches the reg layout. Take advantage of this to
simplify HQD programming.

Note that the ACTIVE field still needs to be programmed last.

Suggested-by: Felix Kuehling <Felix.Kuehling at amd.com>
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 44 +++++-------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 84 +++++------------------------------
 2 files changed, 23 insertions(+), 105 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index c0844a5..85321d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3118,81 +3118,59 @@ static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
 	mqd->cp_hqd_ib_rptr = RREG32(mmCP_HQD_IB_RPTR);
 	mqd->cp_hqd_persistent_state = RREG32(mmCP_HQD_PERSISTENT_STATE);
 	mqd->cp_hqd_sema_cmd = RREG32(mmCP_HQD_SEMA_CMD);
 	mqd->cp_hqd_msg_type = RREG32(mmCP_HQD_MSG_TYPE);
 	mqd->cp_hqd_atomic0_preop_lo = RREG32(mmCP_HQD_ATOMIC0_PREOP_LO);
 	mqd->cp_hqd_atomic0_preop_hi = RREG32(mmCP_HQD_ATOMIC0_PREOP_HI);
 	mqd->cp_hqd_atomic1_preop_lo = RREG32(mmCP_HQD_ATOMIC1_PREOP_LO);
 	mqd->cp_hqd_atomic1_preop_hi = RREG32(mmCP_HQD_ATOMIC1_PREOP_HI);
 	mqd->cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
 	mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM);
 	mqd->cp_hqd_pipe_priority = RREG32(mmCP_HQD_PIPE_PRIORITY);
 	mqd->cp_hqd_queue_priority = RREG32(mmCP_HQD_QUEUE_PRIORITY);
 	mqd->cp_hqd_iq_rptr = RREG32(mmCP_HQD_IQ_RPTR);
 
 	/* activate the queue */
 	mqd->cp_hqd_active = 1;
 }
 
 int gfx_v7_0_mqd_commit(struct amdgpu_device *adev, struct cik_mqd *mqd)
 {
-	u32 tmp;
+	uint32_t tmp;
+	uint32_t mqd_reg;
+	uint32_t *mqd_data;
+
+	/* HQD registers extend from mmCP_MQD_BASE_ADDR to mmCP_MQD_CONTROL */
+	mqd_data = &mqd->cp_mqd_base_addr_lo;
 
 	/* disable wptr polling */
 	tmp = RREG32(mmCP_PQ_WPTR_POLL_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PQ_WPTR_POLL_CNTL, EN, 0);
 	WREG32(mmCP_PQ_WPTR_POLL_CNTL, tmp);
 
-	/* program MQD field to HW */
-	WREG32(mmCP_MQD_BASE_ADDR, mqd->cp_mqd_base_addr_lo);
-	WREG32(mmCP_MQD_BASE_ADDR_HI, mqd->cp_mqd_base_addr_hi);
-	WREG32(mmCP_MQD_CONTROL, mqd->cp_mqd_control);
-	WREG32(mmCP_HQD_PQ_BASE, mqd->cp_hqd_pq_base_lo);
-	WREG32(mmCP_HQD_PQ_BASE_HI, mqd->cp_hqd_pq_base_hi);
-	WREG32(mmCP_HQD_PQ_CONTROL, mqd->cp_hqd_pq_control);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, mqd->cp_hqd_pq_wptr_poll_addr_lo);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, mqd->cp_hqd_pq_wptr_poll_addr_hi);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR, mqd->cp_hqd_pq_rptr_report_addr_lo);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI, mqd->cp_hqd_pq_rptr_report_addr_hi);
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, mqd->cp_hqd_pq_doorbell_control);
-	WREG32(mmCP_HQD_PQ_WPTR, mqd->cp_hqd_pq_wptr);
-	WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
-
-	WREG32(mmCP_HQD_IB_CONTROL, mqd->cp_hqd_ib_control);
-	WREG32(mmCP_HQD_IB_BASE_ADDR, mqd->cp_hqd_ib_base_addr_lo);
-	WREG32(mmCP_HQD_IB_BASE_ADDR_HI, mqd->cp_hqd_ib_base_addr_hi);
-	WREG32(mmCP_HQD_IB_RPTR, mqd->cp_hqd_ib_rptr);
-	WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
-	WREG32(mmCP_HQD_SEMA_CMD, mqd->cp_hqd_sema_cmd);
-	WREG32(mmCP_HQD_MSG_TYPE, mqd->cp_hqd_msg_type);
-	WREG32(mmCP_HQD_ATOMIC0_PREOP_LO, mqd->cp_hqd_atomic0_preop_lo);
-	WREG32(mmCP_HQD_ATOMIC0_PREOP_HI, mqd->cp_hqd_atomic0_preop_hi);
-	WREG32(mmCP_HQD_ATOMIC1_PREOP_LO, mqd->cp_hqd_atomic1_preop_lo);
-	WREG32(mmCP_HQD_ATOMIC1_PREOP_HI, mqd->cp_hqd_atomic1_preop_hi);
-	WREG32(mmCP_HQD_PQ_RPTR, mqd->cp_hqd_pq_rptr);
-	WREG32(mmCP_HQD_QUANTUM, mqd->cp_hqd_quantum);
-	WREG32(mmCP_HQD_PIPE_PRIORITY, mqd->cp_hqd_pipe_priority);
-	WREG32(mmCP_HQD_QUEUE_PRIORITY, mqd->cp_hqd_queue_priority);
-	WREG32(mmCP_HQD_IQ_RPTR, mqd->cp_hqd_iq_rptr);
+	/* program all HQD registers */
+	for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_MQD_CONTROL; mqd_reg++)
+		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
 
 	/* activate the HQD */
-	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
+	for (mqd_reg = mmCP_MQD_BASE_ADDR; mqd_reg <= mmCP_HQD_ACTIVE; mqd_reg++)
+		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
 
 	return 0;
 }
 
 static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
 {
 	int r;
 	u64 mqd_gpu_addr;
 	struct cik_mqd *mqd;
 	struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id];
 
 	if (ring->mqd_obj == NULL) {
 		r = amdgpu_bo_create(adev,
 				sizeof(struct cik_mqd),
 				PAGE_SIZE, true,
 				AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				&ring->mqd_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index a5ba48b..0f1b62d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5023,116 +5023,56 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_ctx_save_base_addr_lo = RREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_LO);
 	mqd->cp_hqd_ctx_save_base_addr_hi = RREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_HI);
 	mqd->cp_hqd_cntl_stack_offset = RREG32(mmCP_HQD_CNTL_STACK_OFFSET);
 	mqd->cp_hqd_cntl_stack_size = RREG32(mmCP_HQD_CNTL_STACK_SIZE);
 	mqd->cp_hqd_wg_state_offset = RREG32(mmCP_HQD_WG_STATE_OFFSET);
 	mqd->cp_hqd_ctx_save_size = RREG32(mmCP_HQD_CTX_SAVE_SIZE);
 	mqd->cp_hqd_eop_done_events = RREG32(mmCP_HQD_EOP_EVENTS);
 	mqd->cp_hqd_error = RREG32(mmCP_HQD_ERROR);
 	mqd->cp_hqd_eop_wptr_mem = RREG32(mmCP_HQD_EOP_WPTR_MEM);
 	mqd->cp_hqd_eop_dones = RREG32(mmCP_HQD_EOP_DONES);
 
 	/* activate the queue */
 	mqd->cp_hqd_active = 1;
 
 	return 0;
 }
 
 int gfx_v8_0_mqd_commit(struct amdgpu_device *adev,
 			struct vi_mqd *mqd)
 {
-	/* disable wptr polling */
-	WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0);
-
-	WREG32(mmCP_HQD_EOP_BASE_ADDR, mqd->cp_hqd_eop_base_addr_lo);
-	WREG32(mmCP_HQD_EOP_BASE_ADDR_HI, mqd->cp_hqd_eop_base_addr_hi);
-
-	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	WREG32(mmCP_HQD_EOP_CONTROL, mqd->cp_hqd_eop_control);
-
-	/* enable doorbell? */
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, mqd->cp_hqd_pq_doorbell_control);
+	uint32_t mqd_reg;
+	uint32_t *mqd_data;
 
-	/* set pq read/write pointers */
-	WREG32(mmCP_HQD_DEQUEUE_REQUEST, mqd->cp_hqd_dequeue_request);
-	WREG32(mmCP_HQD_PQ_RPTR, mqd->cp_hqd_pq_rptr);
-	WREG32(mmCP_HQD_PQ_WPTR, mqd->cp_hqd_pq_wptr);
+	/* HQD registers extend from mmCP_MQD_BASE_ADDR to mmCP_HQD_ERROR */
+	mqd_data = &mqd->cp_mqd_base_addr_lo;
 
-	/* set the pointer to the MQD */
-	WREG32(mmCP_MQD_BASE_ADDR, mqd->cp_mqd_base_addr_lo);
-	WREG32(mmCP_MQD_BASE_ADDR_HI, mqd->cp_mqd_base_addr_hi);
-
-	/* set MQD vmid to 0 */
-	WREG32(mmCP_MQD_CONTROL, mqd->cp_mqd_control);
-
-	/* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
-	WREG32(mmCP_HQD_PQ_BASE, mqd->cp_hqd_pq_base_lo);
-	WREG32(mmCP_HQD_PQ_BASE_HI, mqd->cp_hqd_pq_base_hi);
-
-	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	WREG32(mmCP_HQD_PQ_CONTROL, mqd->cp_hqd_pq_control);
-
-	/* set the wb address whether it's enabled or not */
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR,
-				mqd->cp_hqd_pq_rptr_report_addr_lo);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI,
-				mqd->cp_hqd_pq_rptr_report_addr_hi);
-
-	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, mqd->cp_hqd_pq_wptr_poll_addr_lo);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, mqd->cp_hqd_pq_wptr_poll_addr_hi);
-
-	/* enable the doorbell if requested */
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, mqd->cp_hqd_pq_doorbell_control);
-
-	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	WREG32(mmCP_HQD_PQ_WPTR, mqd->cp_hqd_pq_wptr);
-	WREG32(mmCP_HQD_EOP_RPTR, mqd->cp_hqd_eop_rptr);
-	WREG32(mmCP_HQD_EOP_WPTR, mqd->cp_hqd_eop_wptr);
-
-	/* set the HQD priority */
-	WREG32(mmCP_HQD_PIPE_PRIORITY, mqd->cp_hqd_pipe_priority);
-	WREG32(mmCP_HQD_QUEUE_PRIORITY, mqd->cp_hqd_queue_priority);
-	WREG32(mmCP_HQD_QUANTUM, mqd->cp_hqd_quantum);
-
-	/* set cwsr save area */
-	WREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_LO, mqd->cp_hqd_ctx_save_base_addr_lo);
-	WREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_HI, mqd->cp_hqd_ctx_save_base_addr_hi);
-	WREG32(mmCP_HQD_CTX_SAVE_CONTROL, mqd->cp_hqd_ctx_save_control);
-	WREG32(mmCP_HQD_CNTL_STACK_OFFSET, mqd->cp_hqd_cntl_stack_offset);
-	WREG32(mmCP_HQD_CNTL_STACK_SIZE, mqd->cp_hqd_cntl_stack_size);
-	WREG32(mmCP_HQD_WG_STATE_OFFSET, mqd->cp_hqd_wg_state_offset);
-	WREG32(mmCP_HQD_CTX_SAVE_SIZE, mqd->cp_hqd_ctx_save_size);
-
-	WREG32(mmCP_HQD_IB_CONTROL, mqd->cp_hqd_ib_control);
-	WREG32(mmCP_HQD_EOP_EVENTS, mqd->cp_hqd_eop_done_events);
-	WREG32(mmCP_HQD_ERROR, mqd->cp_hqd_error);
-	WREG32(mmCP_HQD_EOP_WPTR_MEM, mqd->cp_hqd_eop_wptr_mem);
-	WREG32(mmCP_HQD_EOP_DONES, mqd->cp_hqd_eop_dones);
-
-	/* set the vmid for the queue */
-	WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
+	/* disable wptr polling */
+	WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
-	WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
+	/* program all HQD registers */
+	for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_HQD_ERROR; mqd_reg++)
+		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
 
-	/* activate the queue */
-	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
+	/* activate the HQD */
+	for (mqd_reg = mmCP_MQD_BASE_ADDR; mqd_reg <= mmCP_HQD_ACTIVE; mqd_reg++)
+		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
 
 	return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
 	int r = 0;
 	struct amdgpu_device *adev = ring->adev;
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
 
 	gfx_v8_0_kiq_setting(ring);
 
 	if (adev->gfx.in_reset) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
 
 		/* reset ring buffer */
 		ring->wptr = 0;
-- 
2.9.3



More information about the amd-gfx mailing list