Add support for high priority scheduling in amdgpu v5

index 1f93545..8e1e601 100644
@@ -42,20 +42,22 @@
 #include "gca/gfx_7_2_sh_mask.h"
 
 #include "gmc/gmc_7_0_d.h"
 #include "gmc/gmc_7_0_sh_mask.h"
 
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 
 #define GFX7_NUM_GFX_RINGS     1
 #define GFX7_NUM_COMPUTE_RINGS 8
+#define GFX7_MEC_HPD_SIZE      2048
+
 
 static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
 
 MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
 MODULE_FIRMWARE("radeon/bonaire_me.bin");
 MODULE_FIRMWARE("radeon/bonaire_ce.bin");
 MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
 MODULE_FIRMWARE("radeon/bonaire_mec.bin");

@@ -2792,40 +2794,38 @@ static void gfx_v7_0_mec_fini(struct amdgpu_device *adev)
 		if (unlikely(r != 0))
 			dev_warn(adev->dev, "(%d) reserve HPD EOP bo failed\n", r);
 		amdgpu_bo_unpin(adev->gfx.mec.hpd_eop_obj);
 		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
 
 		amdgpu_bo_unref(&adev->gfx.mec.hpd_eop_obj);
 		adev->gfx.mec.hpd_eop_obj = NULL;
 	}
 }
 
-#define MEC_HPD_SIZE 2048
-
 static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 {
 	int r;
 	u32 *hpd;
 
 	/*
 	 * KV:    2 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 64 Queues total
 	 * CI/KB: 1 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 32 Queues total
 	 * Nonetheless, we assign only 1 pipe because all other pipes will
 	 * be handled by KFD
 	 */
 	adev->gfx.mec.num_mec = 1;
 	adev->gfx.mec.num_pipe = 1;
 	adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
 
 	if (adev->gfx.mec.hpd_eop_obj == NULL) {
 		r = amdgpu_bo_create(adev,
-				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
+				     adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
 			return r;
 		}
 	}
 
 	r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);

@@ -2841,21 +2841,21 @@ static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 	r = amdgpu_bo_kmap(adev->gfx.mec.hpd_eop_obj, (void **)&hpd);
 	if (r) {
 		dev_warn(adev->dev, "(%d) map HDP EOP bo failed\n", r);
 		gfx_v7_0_mec_fini(adev);
 		return r;
 	}
 
 	/* clear memory.  Not sure if this is required or not */
-	memset(hpd, 0, adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2);
+	memset(hpd, 0, adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
 
 	return 0;
 }
 
 struct hqd_registers
 {
 	u32 cp_mqd_base_addr;

@@ -2916,261 +2916,296 @@ struct bonaire_mqd
 	u32 restart[3];
 	u32 thread_trace_enable;
 	u32 reserved1;
 	u32 user_data[16];
 	u32 vgtcs_invoke_count[2];
 	struct hqd_registers queue_state;
 	u32 dequeue_cntr;
 	u32 interrupt_queue[64];
 };
 
-/**
- * gfx_v7_0_cp_compute_resume - setup the compute queue registers
- *
- * @adev: amdgpu_device pointer
- *
- * Program the compute queues and test them to make sure they
- * are working.
- * Returns 0 for success, error for failure.
- */
-static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
+static void gfx_v7_0_compute_pipe_init(struct amdgpu_device *adev, int me, int pipe)
 {
-	int r, i, j;
-	u32 tmp;
-	bool use_doorbell = true;
-	u64 hqd_gpu_addr;
-	u64 mqd_gpu_addr;
 	u64 eop_gpu_addr;
-	u64 wb_gpu_addr;
-	u32 *buf;
-	struct bonaire_mqd *mqd;
-	struct amdgpu_ring *ring;
-
-	/* fix up chicken bits */
-	tmp = RREG32(mmCP_CPF_DEBUG);
-	tmp |= (1 << 23);
-	WREG32(mmCP_CPF_DEBUG, tmp);
+	u32 tmp;
+	size_t eop_offset = me * pipe * GFX7_MEC_HPD_SIZE * 2;
 
-	/* init the pipes */
 	mutex_lock(&adev->srbm_mutex);
-	for (i = 0; i < (adev->gfx.mec.num_pipe * adev->gfx.mec.num_mec); i++) {
-		int me = (i < 4) ? 1 : 2;
-		int pipe = (i < 4) ? i : (i - 4);
+	eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + eop_offset;
 
-		eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE * 2);
+	cik_srbm_select(adev, me, pipe, 0, 0);
 
-		cik_srbm_select(adev, me, pipe, 0, 0);
+	/* write the EOP addr */
+	WREG32(mmCP_HPD_EOP_BASE_ADDR, eop_gpu_addr >> 8);
+	WREG32(mmCP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr) >> 8);
 
-		/* write the EOP addr */
-		WREG32(mmCP_HPD_EOP_BASE_ADDR, eop_gpu_addr >> 8);
-		WREG32(mmCP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr) >> 8);
+	/* set the VMID assigned */
+	WREG32(mmCP_HPD_EOP_VMID, 0);
 
-		/* set the VMID assigned */
-		WREG32(mmCP_HPD_EOP_VMID, 0);
+	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
+	tmp = RREG32(mmCP_HPD_EOP_CONTROL);
+	tmp &= ~CP_HPD_EOP_CONTROL__EOP_SIZE_MASK;
+	tmp |= order_base_2(GFX7_MEC_HPD_SIZE / 8);
+	WREG32(mmCP_HPD_EOP_CONTROL, tmp);
 
-		/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-		tmp = RREG32(mmCP_HPD_EOP_CONTROL);
-		tmp &= ~CP_HPD_EOP_CONTROL__EOP_SIZE_MASK;
-		tmp |= order_base_2(MEC_HPD_SIZE / 8);
-		WREG32(mmCP_HPD_EOP_CONTROL, tmp);
-	}
 	cik_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+}
 
-	/* init the queues.  Just two for now. */
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		ring = &adev->gfx.compute_ring[i];
+static int gfx_v7_0_mqd_deactivate(struct amdgpu_device *adev)
+{
+	int i;
 
-		if (ring->mqd_obj == NULL) {
-			r = amdgpu_bo_create(adev,
-					     sizeof(struct bonaire_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;
-			}
+	/* disable the queue if it's active */
+	if (RREG32(mmCP_HQD_ACTIVE) & 1) {
+		WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32(mmCP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
 		}
 
-		r = amdgpu_bo_reserve(ring->mqd_obj, false);
-		if (unlikely(r != 0)) {
-			gfx_v7_0_cp_compute_fini(adev);
-			return r;
-		}
-		r = amdgpu_bo_pin(ring->mqd_obj, AMDGPU_GEM_DOMAIN_GTT,
-				  &mqd_gpu_addr);
-		if (r) {
-			dev_warn(adev->dev, "(%d) pin MQD bo failed\n", r);
-			gfx_v7_0_cp_compute_fini(adev);
-			return r;
-		}
-		r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&buf);
-		if (r) {
-			dev_warn(adev->dev, "(%d) map MQD bo failed\n", r);
-			gfx_v7_0_cp_compute_fini(adev);
-			return r;
-		}
+		if (i == adev->usec_timeout)
+			return -ETIMEDOUT;
 
-		/* init the mqd struct */
-		memset(buf, 0, sizeof(struct bonaire_mqd));
+		WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+		WREG32(mmCP_HQD_PQ_RPTR, 0);
+		WREG32(mmCP_HQD_PQ_WPTR, 0);
+	}
 
-		mqd = (struct bonaire_mqd *)buf;
-		mqd->header = 0xC0310800;
-		mqd->static_thread_mgmt01[0] = 0xffffffff;
-		mqd->static_thread_mgmt01[1] = 0xffffffff;
-		mqd->static_thread_mgmt23[0] = 0xffffffff;
-		mqd->static_thread_mgmt23[1] = 0xffffffff;
+	return 0;
+}
 
-		mutex_lock(&adev->srbm_mutex);
-		cik_srbm_select(adev, ring->me,
-				ring->pipe,
-				ring->queue, 0);
+static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
+			     struct bonaire_mqd *mqd,
+			     uint64_t mqd_gpu_addr,
+			     struct amdgpu_ring *ring)
+{
+	u64 hqd_gpu_addr;
+	u64 wb_gpu_addr;
 
-		/* disable wptr polling */
-		tmp = RREG32(mmCP_PQ_WPTR_POLL_CNTL);
-		tmp &= ~CP_PQ_WPTR_POLL_CNTL__EN_MASK;
-		WREG32(mmCP_PQ_WPTR_POLL_CNTL, tmp);
+	/* init the mqd struct */
+	memset(mqd, 0, sizeof(struct bonaire_mqd));
 
-		/* enable doorbell? */
-		mqd->queue_state.cp_hqd_pq_doorbell_control =
-			RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
-		if (use_doorbell)
-			mqd->queue_state.cp_hqd_pq_doorbell_control |= CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
-		else
-			mqd->queue_state.cp_hqd_pq_doorbell_control &= ~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
-		WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL,
-		       mqd->queue_state.cp_hqd_pq_doorbell_control);
-
-		/* disable the queue if it's active */
-		mqd->queue_state.cp_hqd_dequeue_request = 0;
-		mqd->queue_state.cp_hqd_pq_rptr = 0;
-		mqd->queue_state.cp_hqd_pq_wptr= 0;
-		if (RREG32(mmCP_HQD_ACTIVE) & 1) {
-			WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-			for (j = 0; j < adev->usec_timeout; j++) {
-				if (!(RREG32(mmCP_HQD_ACTIVE) & 1))
-					break;
-				udelay(1);
-			}
-			WREG32(mmCP_HQD_DEQUEUE_REQUEST, mqd->queue_state.cp_hqd_dequeue_request);
-			WREG32(mmCP_HQD_PQ_RPTR, mqd->queue_state.cp_hqd_pq_rptr);
-			WREG32(mmCP_HQD_PQ_WPTR, mqd->queue_state.cp_hqd_pq_wptr);
-		}
+	mqd->header = 0xC0310800;
+	mqd->static_thread_mgmt01[0] = 0xffffffff;
+	mqd->static_thread_mgmt01[1] = 0xffffffff;
+	mqd->static_thread_mgmt23[0] = 0xffffffff;
+	mqd->static_thread_mgmt23[1] = 0xffffffff;
 
-		/* set the pointer to the MQD */
-		mqd->queue_state.cp_mqd_base_addr = mqd_gpu_addr & 0xfffffffc;
-		mqd->queue_state.cp_mqd_base_addr_hi = upper_32_bits(mqd_gpu_addr);
-		WREG32(mmCP_MQD_BASE_ADDR, mqd->queue_state.cp_mqd_base_addr);
-		WREG32(mmCP_MQD_BASE_ADDR_HI, mqd->queue_state.cp_mqd_base_addr_hi);
-		/* set MQD vmid to 0 */
-		mqd->queue_state.cp_mqd_control = RREG32(mmCP_MQD_CONTROL);
-		mqd->queue_state.cp_mqd_control &= ~CP_MQD_CONTROL__VMID_MASK;
-		WREG32(mmCP_MQD_CONTROL, mqd->queue_state.cp_mqd_control);
-
-		/* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
-		hqd_gpu_addr = ring->gpu_addr >> 8;
-		mqd->queue_state.cp_hqd_pq_base = hqd_gpu_addr;
-		mqd->queue_state.cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
-		WREG32(mmCP_HQD_PQ_BASE, mqd->queue_state.cp_hqd_pq_base);
-		WREG32(mmCP_HQD_PQ_BASE_HI, mqd->queue_state.cp_hqd_pq_base_hi);
-
-		/* set up the HQD, this is similar to CP_RB0_CNTL */
-		mqd->queue_state.cp_hqd_pq_control = RREG32(mmCP_HQD_PQ_CONTROL);
-		mqd->queue_state.cp_hqd_pq_control &=
-			~(CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK |
-					CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE_MASK);
-
-		mqd->queue_state.cp_hqd_pq_control |=
-			order_base_2(ring->ring_size / 8);
-		mqd->queue_state.cp_hqd_pq_control |=
-			(order_base_2(AMDGPU_GPU_PAGE_SIZE/8) << 8);
+	/* enable doorbell? */
+	mqd->queue_state.cp_hqd_pq_doorbell_control =
+		RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
+	if (ring->use_doorbell)
+		mqd->queue_state.cp_hqd_pq_doorbell_control |= CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
+	else
+		mqd->queue_state.cp_hqd_pq_doorbell_control &= ~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
+
+	/* set the pointer to the MQD */
+	mqd->queue_state.cp_mqd_base_addr = mqd_gpu_addr & 0xfffffffc;
+	mqd->queue_state.cp_mqd_base_addr_hi = upper_32_bits(mqd_gpu_addr);
+
+	/* set MQD vmid to 0 */
+	mqd->queue_state.cp_mqd_control = RREG32(mmCP_MQD_CONTROL);
+	mqd->queue_state.cp_mqd_control &= ~CP_MQD_CONTROL__VMID_MASK;
+
+	/* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
+	hqd_gpu_addr = ring->gpu_addr >> 8;
+	mqd->queue_state.cp_hqd_pq_base = hqd_gpu_addr;
+	mqd->queue_state.cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
+
+	/* set up the HQD, this is similar to CP_RB0_CNTL */
+	mqd->queue_state.cp_hqd_pq_control = RREG32(mmCP_HQD_PQ_CONTROL);
+	mqd->queue_state.cp_hqd_pq_control &=
+		~(CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK |
+				CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE_MASK);
+
+	mqd->queue_state.cp_hqd_pq_control |=
+		order_base_2(ring->ring_size / 8);
+	mqd->queue_state.cp_hqd_pq_control |=
+		(order_base_2(AMDGPU_GPU_PAGE_SIZE/8) << 8);
 #ifdef __BIG_ENDIAN
-		mqd->queue_state.cp_hqd_pq_control |=
-			2 << CP_HQD_PQ_CONTROL__ENDIAN_SWAP__SHIFT;
+	mqd->queue_state.cp_hqd_pq_control |=
+		2 << CP_HQD_PQ_CONTROL__ENDIAN_SWAP__SHIFT;
 #endif
-		mqd->queue_state.cp_hqd_pq_control &=
-			~(CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK |
+	mqd->queue_state.cp_hqd_pq_control &=
+		~(CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK |
 				CP_HQD_PQ_CONTROL__ROQ_PQ_IB_FLIP_MASK |
 				CP_HQD_PQ_CONTROL__PQ_VOLATILE_MASK);
-		mqd->queue_state.cp_hqd_pq_control |=
-			CP_HQD_PQ_CONTROL__PRIV_STATE_MASK |
-			CP_HQD_PQ_CONTROL__KMD_QUEUE_MASK; /* assuming kernel queue control */
-		WREG32(mmCP_HQD_PQ_CONTROL, mqd->queue_state.cp_hqd_pq_control);
-
-		/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-		wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-		mqd->queue_state.cp_hqd_pq_wptr_poll_addr = wb_gpu_addr & 0xfffffffc;
-		mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
-		WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, mqd->queue_state.cp_hqd_pq_wptr_poll_addr);
-		WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI,
-		       mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi);
-
-		/* set the wb address wether it's enabled or not */
-		wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
-		mqd->queue_state.cp_hqd_pq_rptr_report_addr = wb_gpu_addr & 0xfffffffc;
-		mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi =
-			upper_32_bits(wb_gpu_addr) & 0xffff;
-		WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR,
-		       mqd->queue_state.cp_hqd_pq_rptr_report_addr);
-		WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI,
-		       mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi);
-
-		/* enable the doorbell if requested */
-		if (use_doorbell) {
-			mqd->queue_state.cp_hqd_pq_doorbell_control =
-				RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
-			mqd->queue_state.cp_hqd_pq_doorbell_control &=
-				~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK;
-			mqd->queue_state.cp_hqd_pq_doorbell_control |=
-				(ring->doorbell_index <<
-				 CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT);
-			mqd->queue_state.cp_hqd_pq_doorbell_control |=
-				CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
-			mqd->queue_state.cp_hqd_pq_doorbell_control &=
-				~(CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_SOURCE_MASK |
-				CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_HIT_MASK);
+	mqd->queue_state.cp_hqd_pq_control |=
+		CP_HQD_PQ_CONTROL__PRIV_STATE_MASK |
+		CP_HQD_PQ_CONTROL__KMD_QUEUE_MASK; /* assuming kernel queue control */
 
-		} else {
-			mqd->queue_state.cp_hqd_pq_doorbell_control = 0;
+	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
+	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	mqd->queue_state.cp_hqd_pq_wptr_poll_addr = wb_gpu_addr & 0xfffffffc;
+	mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
+
+	/* set the wb address wether it's enabled or not */
+	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	mqd->queue_state.cp_hqd_pq_rptr_report_addr = wb_gpu_addr & 0xfffffffc;
+	mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi =
+		upper_32_bits(wb_gpu_addr) & 0xffff;
+
+	/* enable the doorbell if requested */
+	if (ring->use_doorbell) {
+		mqd->queue_state.cp_hqd_pq_doorbell_control =
+			RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
+		mqd->queue_state.cp_hqd_pq_doorbell_control &=
+			~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK;
+		mqd->queue_state.cp_hqd_pq_doorbell_control |=
+			(ring->doorbell_index <<
+			 CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT);
+		mqd->queue_state.cp_hqd_pq_doorbell_control |=
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
+		mqd->queue_state.cp_hqd_pq_doorbell_control &=
+			~(CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_SOURCE_MASK |
+					CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_HIT_MASK);
+
+	} else {
+		mqd->queue_state.cp_hqd_pq_doorbell_control = 0;
+	}
+
+	/* read and write pointers, similar to CP_RB0_WPTR/_RPTR */
+	ring->wptr = 0;
+	mqd->queue_state.cp_hqd_pq_wptr = ring->wptr;
+	mqd->queue_state.cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
+
+	/* set the vmid for the queue */
+	mqd->queue_state.cp_hqd_vmid = 0;
+
+	/* activate the queue */
+	mqd->queue_state.cp_hqd_active = 1;
+}
+
+static int gfx_v7_0_mqd_commit(struct amdgpu_device *adev,
+			       struct bonaire_mqd *mqd)
+{
+	u32 tmp;
+
+	/* 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->queue_state.cp_mqd_base_addr);
+	WREG32(mmCP_MQD_BASE_ADDR_HI, mqd->queue_state.cp_mqd_base_addr_hi);
+	WREG32(mmCP_MQD_CONTROL, mqd->queue_state.cp_mqd_control);
+	WREG32(mmCP_HQD_PQ_BASE, mqd->queue_state.cp_hqd_pq_base);
+	WREG32(mmCP_HQD_PQ_BASE_HI, mqd->queue_state.cp_hqd_pq_base_hi);
+	WREG32(mmCP_HQD_PQ_CONTROL, mqd->queue_state.cp_hqd_pq_control);
+	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, mqd->queue_state.cp_hqd_pq_wptr_poll_addr);
+	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi);
+	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR, mqd->queue_state.cp_hqd_pq_rptr_report_addr);
+	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI, mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi);
+	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, mqd->queue_state.cp_hqd_pq_doorbell_control);
+	WREG32(mmCP_HQD_PQ_WPTR, mqd->queue_state.cp_hqd_pq_wptr);
+	WREG32(mmCP_HQD_VMID, mqd->queue_state.cp_hqd_vmid);
+
+	/* activate the HQD */
+	WREG32(mmCP_HQD_ACTIVE, mqd->queue_state.cp_hqd_active);
+
+	return 0;
+}
+
+static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
+{
+	int r;
+	u64 mqd_gpu_addr;
+	struct bonaire_mqd *mqd;
+	struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id];
+
+	if (ring->mqd_obj == NULL) {
+		r = amdgpu_bo_create(adev,
+				sizeof(struct bonaire_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;
 		}
-		WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL,
-		       mqd->queue_state.cp_hqd_pq_doorbell_control);
+	}
+
+	r = amdgpu_bo_reserve(ring->mqd_obj, false);
+	if (unlikely(r != 0))
+		goto out;
+
+	r = amdgpu_bo_pin(ring->mqd_obj, AMDGPU_GEM_DOMAIN_GTT,
+			&mqd_gpu_addr);
+	if (r) {
+		dev_warn(adev->dev, "(%d) pin MQD bo failed\n", r);
+		goto out_unreserve;
+	}
+	r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd);
+	if (r) {
+		dev_warn(adev->dev, "(%d) map MQD bo failed\n", r);
+		goto out_unreserve;
+	}
+
+	mutex_lock(&adev->srbm_mutex);
+	cik_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
-		/* read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-		ring->wptr = 0;
-		mqd->queue_state.cp_hqd_pq_wptr = ring->wptr;
-		WREG32(mmCP_HQD_PQ_WPTR, mqd->queue_state.cp_hqd_pq_wptr);
-		mqd->queue_state.cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
+	gfx_v7_0_mqd_init(adev, mqd, mqd_gpu_addr, ring);
+	gfx_v7_0_mqd_deactivate(adev);
+	gfx_v7_0_mqd_commit(adev, mqd);
 
-		/* set the vmid for the queue */
-		mqd->queue_state.cp_hqd_vmid = 0;
-		WREG32(mmCP_HQD_VMID, mqd->queue_state.cp_hqd_vmid);
+	cik_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
 
-		/* activate the queue */
-		mqd->queue_state.cp_hqd_active = 1;
-		WREG32(mmCP_HQD_ACTIVE, mqd->queue_state.cp_hqd_active);
+	amdgpu_bo_kunmap(ring->mqd_obj);
+out_unreserve:
+	amdgpu_bo_unreserve(ring->mqd_obj);
+out:
+	return 0;
+}
+
+/**
+ * gfx_v7_0_cp_compute_resume - setup the compute queue registers
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Program the compute queues and test them to make sure they
+ * are working.
+ * Returns 0 for success, error for failure.
+ */
+static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
+{
+	int r, i, j;
+	u32 tmp;
+	struct amdgpu_ring *ring;
 
-		cik_srbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+	/* fix up chicken bits */
+	tmp = RREG32(mmCP_CPF_DEBUG);
+	tmp |= (1 << 23);
+	WREG32(mmCP_CPF_DEBUG, tmp);
 
-		amdgpu_bo_kunmap(ring->mqd_obj);
-		amdgpu_bo_unreserve(ring->mqd_obj);
+	/* init the pipes */
+	for (i = 0; i < adev->gfx.mec.num_mec; i++)
+		for (j = 0; j < adev->gfx.mec.num_pipe; j++)
+			gfx_v7_0_compute_pipe_init(adev, i, j);
 
-		ring->ready = true;
+	/* init the queues */
+	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+		r = gfx_v7_0_compute_queue_init(adev, i);
+		if (r) {
+			gfx_v7_0_cp_compute_fini(adev);
+			return r;
+		}
 	}
 
 	gfx_v7_0_cp_compute_enable(adev, true);
 
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
-
+		ring->ready = true;
 		r = amdgpu_ring_test_ring(ring);
 		if (r)
 			ring->ready = false;
 	}
 
 	return 0;
 }
 
 static void gfx_v7_0_cp_enable(struct amdgpu_device *adev, bool enable)
 {

734 lines not on this page · raw message

index c1b9135..b577ec1 100644
@@ -892,20 +892,23 @@ struct amdgpu_gfx {
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
 	unsigned			ce_ram_size;
 	struct amdgpu_cu_info		cu_info;
 	const struct amdgpu_gfx_funcs	*funcs;
 
 	/* reset mask */
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
+
+	/* doorbell */
+	bool				doorbell_enabled;
 };
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		  unsigned size, struct amdgpu_ib *ib);
 void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
 		    struct dma_fence *f);
 int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		       struct amdgpu_ib *ibs, struct amdgpu_job *job,
 		       struct dma_fence **f);
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);

index 1c8589a..044449a 100644
@@ -4797,35 +4797,37 @@ static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)
 		WREG32(mmCP_HQD_PQ_WPTR, 0);
 	}
 
 	return 0;
 }
 
 static void gfx_v8_0_enable_doorbell(struct amdgpu_device *adev, bool enable)
 {
 	uint32_t tmp;
 
-	if (!enable)
+	if (!enable || adev->gfx.doorbell_enabled)
 		return;
 
 	if ((adev->asic_type == CHIP_CARRIZO) ||
 			(adev->asic_type == CHIP_FIJI) ||
 			(adev->asic_type == CHIP_STONEY) ||
 			(adev->asic_type == CHIP_POLARIS11) ||
 			(adev->asic_type == CHIP_POLARIS10)) {
 		WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER, AMDGPU_DOORBELL_KIQ << 2);
 		WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER, AMDGPU_DOORBELL_MEC_RING7 << 2);
 	}
 
 	tmp = RREG32(mmCP_PQ_STATUS);
 	tmp = REG_SET_FIELD(tmp, CP_PQ_STATUS, DOORBELL_ENABLE, 1);
 	WREG32(mmCP_PQ_STATUS, tmp);
+
+	adev->gfx.doorbell_enabled = true;
 }
 
 static int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd)
 {
 	uint32_t tmp;
 
 	/* 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);

@@ -5109,20 +5111,22 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
 			ring->ready = false;
 	}
 
 	return 0;
 }
 
 static int gfx_v8_0_cp_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	adev->gfx.doorbell_enabled = false;
+
 	if (!(adev->flags & AMD_IS_APU))
 		gfx_v8_0_enable_gui_idle_interrupt(adev, false);
 
 	if (!adev->pp_enabled) {
 		if (!adev->firmware.smu_load) {
 			/* legacy firmware loading */
 			r = gfx_v8_0_cp_gfx_load_microcode(adev);
 			if (r)
 				return r;
 

index 044449a..af4b505 100644
@@ -4884,20 +4884,21 @@ static int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd)
 	/* activate the queue */
 	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	return 0;
 }
 
 static int gfx_v8_0_kiq_queue_init(struct amdgpu_ring *ring,
 				   struct vi_mqd *mqd,
 				   u64 mqd_gpu_addr)
 {
+	int r = 0;
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	uint64_t eop_gpu_addr;
 	bool is_kiq = false;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
 		is_kiq = true;
 
 	if (is_kiq) {
 		eop_gpu_addr = kiq->eop_gpu_addr;

@@ -4905,34 +4906,45 @@ static int gfx_v8_0_kiq_queue_init(struct amdgpu_ring *ring,
 	} else
 		eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr +
 					ring->queue * GFX8_MEC_HPD_SIZE;
 
 	mutex_lock(&adev->srbm_mutex);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
 	gfx_v8_0_mqd_init(adev, mqd, mqd_gpu_addr, eop_gpu_addr, ring);
 
 	if (is_kiq) {
-		gfx_v8_0_mqd_deactivate(adev);
+		r = gfx_v8_0_mqd_deactivate(adev);
+		if (r) {
+			dev_err(adev->dev, "failed to deactivate ring %s\n", ring->name);
+			goto out_unlock;
+		}
+
 		gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
 		gfx_v8_0_mqd_commit(adev, mqd);
 	}
 
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
 	if (is_kiq)
 		gfx_v8_0_kiq_enable(ring);
 	else
 		gfx_v8_0_map_queue_enable(&kiq->ring, ring);
 
 	return 0;
+
+out_unlock:
+	vi_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+
+	return r;
 }
 
 static void gfx_v8_0_kiq_free_queue(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring = NULL;
 	int i;
 
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
 		amdgpu_bo_free_kernel(&ring->mqd_obj, NULL, NULL);

@@ -5052,24 +5064,30 @@ static int gfx_v8_0_compute_queue_init(struct amdgpu_device *adev,
 	eop_gpu_addr >>= 8;
 
 	/* init the mqd struct */
 	memset(mqd, 0, sizeof(struct vi_mqd));
 
 	mutex_lock(&adev->srbm_mutex);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
 	gfx_v8_0_mqd_init(adev, mqd, mqd_gpu_addr, eop_gpu_addr, ring);
 
-	gfx_v8_0_mqd_deactivate(adev);
+	r = gfx_v8_0_mqd_deactivate(adev);
+	if (r) {
+		dev_err(adev->dev, "failed to deactivate ring %s\n", ring->name);
+		goto out_unlock;
+	}
+
 	gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
 	gfx_v8_0_mqd_commit(adev, mqd);
 
+out_unlock:
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
 	amdgpu_bo_kunmap(ring->mqd_obj);
 out_unreserve:
 	amdgpu_bo_unreserve(ring->mqd_obj);
 out:
 	return r;
 }
 

index 8e1e601..c606e0b 100644
@@ -20,20 +20,21 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
 #include <linux/firmware.h>
 #include "drmP.h"
 #include "amdgpu.h"
 #include "amdgpu_ih.h"
 #include "amdgpu_gfx.h"
 #include "cikd.h"
 #include "cik.h"
+#include "cik_structs.h"
 #include "atom.h"
 #include "amdgpu_ucode.h"
 #include "clearstate_ci.h"
 
 #include "dce/dce_8_0_d.h"
 #include "dce/dce_8_0_sh_mask.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
 

@@ -2888,48 +2889,20 @@ struct hqd_registers
 	u32 cp_hqd_msg_type;
 	u32 cp_hqd_atomic0_preop_lo;
 	u32 cp_hqd_atomic0_preop_hi;
 	u32 cp_hqd_atomic1_preop_lo;
 	u32 cp_hqd_atomic1_preop_hi;
 	u32 cp_hqd_hq_scheduler0;
 	u32 cp_hqd_hq_scheduler1;
 	u32 cp_mqd_control;
 };
 
-struct bonaire_mqd
-{
-	u32 header;
-	u32 dispatch_initiator;
-	u32 dimensions[3];
-	u32 start_idx[3];
-	u32 num_threads[3];
-	u32 pipeline_stat_enable;
-	u32 perf_counter_enable;
-	u32 pgm[2];
-	u32 tba[2];
-	u32 tma[2];
-	u32 pgm_rsrc[2];
-	u32 vmid;
-	u32 resource_limits;
-	u32 static_thread_mgmt01[2];
-	u32 tmp_ring_size;
-	u32 static_thread_mgmt23[2];
-	u32 restart[3];
-	u32 thread_trace_enable;
-	u32 reserved1;
-	u32 user_data[16];
-	u32 vgtcs_invoke_count[2];
-	struct hqd_registers queue_state;
-	u32 dequeue_cntr;
-	u32 interrupt_queue[64];
-};
-
 static void gfx_v7_0_compute_pipe_init(struct amdgpu_device *adev, int me, int pipe)
 {
 	u64 eop_gpu_addr;
 	u32 tmp;
 	size_t eop_offset = me * pipe * GFX7_MEC_HPD_SIZE * 2;
 
 	mutex_lock(&adev->srbm_mutex);
 	eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + eop_offset;
 
 	cik_srbm_select(adev, me, pipe, 0, 0);

@@ -2969,162 +2942,162 @@ static int gfx_v7_0_mqd_deactivate(struct amdgpu_device *adev)
 
 		WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
 		WREG32(mmCP_HQD_PQ_RPTR, 0);
 		WREG32(mmCP_HQD_PQ_WPTR, 0);
 	}
 
 	return 0;
 }
 
 static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
-			     struct bonaire_mqd *mqd,
+			     struct cik_mqd *mqd,
 			     uint64_t mqd_gpu_addr,
 			     struct amdgpu_ring *ring)
 {
 	u64 hqd_gpu_addr;
 	u64 wb_gpu_addr;
 
 	/* init the mqd struct */
-	memset(mqd, 0, sizeof(struct bonaire_mqd));
+	memset(mqd, 0, sizeof(struct cik_mqd));
 
 	mqd->header = 0xC0310800;
-	mqd->static_thread_mgmt01[0] = 0xffffffff;
-	mqd->static_thread_mgmt01[1] = 0xffffffff;
-	mqd->static_thread_mgmt23[0] = 0xffffffff;
-	mqd->static_thread_mgmt23[1] = 0xffffffff;
+	mqd->compute_static_thread_mgmt_se0 = 0xffffffff;
+	mqd->compute_static_thread_mgmt_se1 = 0xffffffff;
+	mqd->compute_static_thread_mgmt_se2 = 0xffffffff;
+	mqd->compute_static_thread_mgmt_se3 = 0xffffffff;
 
 	/* enable doorbell? */
-	mqd->queue_state.cp_hqd_pq_doorbell_control =
+	mqd->cp_hqd_pq_doorbell_control =
 		RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
 	if (ring->use_doorbell)
-		mqd->queue_state.cp_hqd_pq_doorbell_control |= CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
+		mqd->cp_hqd_pq_doorbell_control |= CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
 	else
-		mqd->queue_state.cp_hqd_pq_doorbell_control &= ~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
+		mqd->cp_hqd_pq_doorbell_control &= ~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
 
 	/* set the pointer to the MQD */
-	mqd->queue_state.cp_mqd_base_addr = mqd_gpu_addr & 0xfffffffc;
-	mqd->queue_state.cp_mqd_base_addr_hi = upper_32_bits(mqd_gpu_addr);
+	mqd->cp_mqd_base_addr_lo = mqd_gpu_addr & 0xfffffffc;
+	mqd->cp_mqd_base_addr_hi = upper_32_bits(mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	mqd->queue_state.cp_mqd_control = RREG32(mmCP_MQD_CONTROL);
-	mqd->queue_state.cp_mqd_control &= ~CP_MQD_CONTROL__VMID_MASK;
+	mqd->cp_mqd_control = RREG32(mmCP_MQD_CONTROL);
+	mqd->cp_mqd_control &= ~CP_MQD_CONTROL__VMID_MASK;
 
 	/* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
 	hqd_gpu_addr = ring->gpu_addr >> 8;
-	mqd->queue_state.cp_hqd_pq_base = hqd_gpu_addr;
-	mqd->queue_state.cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
+	mqd->cp_hqd_pq_base_lo = hqd_gpu_addr;
+	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	mqd->queue_state.cp_hqd_pq_control = RREG32(mmCP_HQD_PQ_CONTROL);
-	mqd->queue_state.cp_hqd_pq_control &=
+	mqd->cp_hqd_pq_control = RREG32(mmCP_HQD_PQ_CONTROL);
+	mqd->cp_hqd_pq_control &=
 		~(CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK |
 				CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE_MASK);
 
-	mqd->queue_state.cp_hqd_pq_control |=
+	mqd->cp_hqd_pq_control |=
 		order_base_2(ring->ring_size / 8);
-	mqd->queue_state.cp_hqd_pq_control |=
+	mqd->cp_hqd_pq_control |=
 		(order_base_2(AMDGPU_GPU_PAGE_SIZE/8) << 8);
 #ifdef __BIG_ENDIAN
-	mqd->queue_state.cp_hqd_pq_control |=
+	mqd->cp_hqd_pq_control |=
 		2 << CP_HQD_PQ_CONTROL__ENDIAN_SWAP__SHIFT;
 #endif
-	mqd->queue_state.cp_hqd_pq_control &=
+	mqd->cp_hqd_pq_control &=
 		~(CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK |
 				CP_HQD_PQ_CONTROL__ROQ_PQ_IB_FLIP_MASK |
 				CP_HQD_PQ_CONTROL__PQ_VOLATILE_MASK);
-	mqd->queue_state.cp_hqd_pq_control |=
+	mqd->cp_hqd_pq_control |=
 		CP_HQD_PQ_CONTROL__PRIV_STATE_MASK |
 		CP_HQD_PQ_CONTROL__KMD_QUEUE_MASK; /* assuming kernel queue control */
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
 	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-	mqd->queue_state.cp_hqd_pq_wptr_poll_addr = wb_gpu_addr & 0xfffffffc;
-	mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
+	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
+	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* set the wb address wether it's enabled or not */
 	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
-	mqd->queue_state.cp_hqd_pq_rptr_report_addr = wb_gpu_addr & 0xfffffffc;
-	mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi =
+	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
+	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* enable the doorbell if requested */
 	if (ring->use_doorbell) {
-		mqd->queue_state.cp_hqd_pq_doorbell_control =
+		mqd->cp_hqd_pq_doorbell_control =
 			RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
-		mqd->queue_state.cp_hqd_pq_doorbell_control &=
+		mqd->cp_hqd_pq_doorbell_control &=
 			~CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK;
-		mqd->queue_state.cp_hqd_pq_doorbell_control |=
+		mqd->cp_hqd_pq_doorbell_control |=
 			(ring->doorbell_index <<
 			 CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT);
-		mqd->queue_state.cp_hqd_pq_doorbell_control |=
+		mqd->cp_hqd_pq_doorbell_control |=
 			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_EN_MASK;
-		mqd->queue_state.cp_hqd_pq_doorbell_control &=
+		mqd->cp_hqd_pq_doorbell_control &=
 			~(CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_SOURCE_MASK |
 					CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_HIT_MASK);
 
 	} else {
-		mqd->queue_state.cp_hqd_pq_doorbell_control = 0;
+		mqd->cp_hqd_pq_doorbell_control = 0;
 	}
 
 	/* read and write pointers, similar to CP_RB0_WPTR/_RPTR */
 	ring->wptr = 0;
-	mqd->queue_state.cp_hqd_pq_wptr = ring->wptr;
-	mqd->queue_state.cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_wptr = ring->wptr;
+	mqd->cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
 
 	/* set the vmid for the queue */
-	mqd->queue_state.cp_hqd_vmid = 0;
+	mqd->cp_hqd_vmid = 0;
 
 	/* activate the queue */
-	mqd->queue_state.cp_hqd_active = 1;
+	mqd->cp_hqd_active = 1;
 }
 
 static int gfx_v7_0_mqd_commit(struct amdgpu_device *adev,
-			       struct bonaire_mqd *mqd)
+			       struct cik_mqd *mqd)
 {
 	u32 tmp;
 
 	/* 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->queue_state.cp_mqd_base_addr);
-	WREG32(mmCP_MQD_BASE_ADDR_HI, mqd->queue_state.cp_mqd_base_addr_hi);
-	WREG32(mmCP_MQD_CONTROL, mqd->queue_state.cp_mqd_control);
-	WREG32(mmCP_HQD_PQ_BASE, mqd->queue_state.cp_hqd_pq_base);
-	WREG32(mmCP_HQD_PQ_BASE_HI, mqd->queue_state.cp_hqd_pq_base_hi);
-	WREG32(mmCP_HQD_PQ_CONTROL, mqd->queue_state.cp_hqd_pq_control);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, mqd->queue_state.cp_hqd_pq_wptr_poll_addr);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, mqd->queue_state.cp_hqd_pq_wptr_poll_addr_hi);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR, mqd->queue_state.cp_hqd_pq_rptr_report_addr);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI, mqd->queue_state.cp_hqd_pq_rptr_report_addr_hi);
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, mqd->queue_state.cp_hqd_pq_doorbell_control);
-	WREG32(mmCP_HQD_PQ_WPTR, mqd->queue_state.cp_hqd_pq_wptr);
-	WREG32(mmCP_HQD_VMID, mqd->queue_state.cp_hqd_vmid);
+	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);
 
 	/* activate the HQD */
-	WREG32(mmCP_HQD_ACTIVE, mqd->queue_state.cp_hqd_active);
+	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	return 0;
 }
 
 static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
 {
 	int r;
 	u64 mqd_gpu_addr;
-	struct bonaire_mqd *mqd;
+	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 bonaire_mqd),
+				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;
 		}
 	}
 
 	r = amdgpu_bo_reserve(ring->mqd_obj, false);

index 1a0a5f7..038b7ea 100644
@@ -22,20 +22,21 @@
 
 #include <linux/fdtable.h>
 #include <linux/uaccess.h>
 #include <linux/firmware.h>
 #include <drm/drmP.h>
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
 #include "cikd.h"
 #include "cik_sdma.h"
 #include "amdgpu_ucode.h"
+#include "gfx_v7_0.h"
 #include "gca/gfx_7_2_d.h"
 #include "gca/gfx_7_2_enum.h"
 #include "gca/gfx_7_2_sh_mask.h"
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 #include "gmc/gmc_7_1_d.h"
 #include "gmc/gmc_7_1_sh_mask.h"
 #include "cik_structs.h"
 
 #define CIK_PIPE_PER_MEC	(4)

@@ -302,69 +303,25 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t wptr_shadow, is_wptr_shadow_valid;
 	struct cik_mqd *m;
 
 	m = get_mqd(mqd);
 
 	is_wptr_shadow_valid = !get_user(wptr_shadow, wptr);
-
-	acquire_queue(kgd, pipe_id, queue_id);
-	WREG32(mmCP_MQD_BASE_ADDR, m->cp_mqd_base_addr_lo);
-	WREG32(mmCP_MQD_BASE_ADDR_HI, m->cp_mqd_base_addr_hi);
-	WREG32(mmCP_MQD_CONTROL, m->cp_mqd_control);
-
-	WREG32(mmCP_HQD_PQ_BASE, m->cp_hqd_pq_base_lo);
-	WREG32(mmCP_HQD_PQ_BASE_HI, m->cp_hqd_pq_base_hi);
-	WREG32(mmCP_HQD_PQ_CONTROL, m->cp_hqd_pq_control);
-
-	WREG32(mmCP_HQD_IB_CONTROL, m->cp_hqd_ib_control);
-	WREG32(mmCP_HQD_IB_BASE_ADDR, m->cp_hqd_ib_base_addr_lo);
-	WREG32(mmCP_HQD_IB_BASE_ADDR_HI, m->cp_hqd_ib_base_addr_hi);
-
-	WREG32(mmCP_HQD_IB_RPTR, m->cp_hqd_ib_rptr);
-
-	WREG32(mmCP_HQD_PERSISTENT_STATE, m->cp_hqd_persistent_state);
-	WREG32(mmCP_HQD_SEMA_CMD, m->cp_hqd_sema_cmd);
-	WREG32(mmCP_HQD_MSG_TYPE, m->cp_hqd_msg_type);
-
-	WREG32(mmCP_HQD_ATOMIC0_PREOP_LO, m->cp_hqd_atomic0_preop_lo);
-	WREG32(mmCP_HQD_ATOMIC0_PREOP_HI, m->cp_hqd_atomic0_preop_hi);
-	WREG32(mmCP_HQD_ATOMIC1_PREOP_LO, m->cp_hqd_atomic1_preop_lo);
-	WREG32(mmCP_HQD_ATOMIC1_PREOP_HI, m->cp_hqd_atomic1_preop_hi);
-
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR, m->cp_hqd_pq_rptr_report_addr_lo);
-	WREG32(mmCP_HQD_PQ_RPTR_REPORT_ADDR_HI,
-			m->cp_hqd_pq_rptr_report_addr_hi);
-
-	WREG32(mmCP_HQD_PQ_RPTR, m->cp_hqd_pq_rptr);
-
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR, m->cp_hqd_pq_wptr_poll_addr_lo);
-	WREG32(mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, m->cp_hqd_pq_wptr_poll_addr_hi);
-
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, m->cp_hqd_pq_doorbell_control);
-
-	WREG32(mmCP_HQD_VMID, m->cp_hqd_vmid);
-
-	WREG32(mmCP_HQD_QUANTUM, m->cp_hqd_quantum);
-
-	WREG32(mmCP_HQD_PIPE_PRIORITY, m->cp_hqd_pipe_priority);
-	WREG32(mmCP_HQD_QUEUE_PRIORITY, m->cp_hqd_queue_priority);
-
-	WREG32(mmCP_HQD_IQ_RPTR, m->cp_hqd_iq_rptr);
-
 	if (is_wptr_shadow_valid)
-		WREG32(mmCP_HQD_PQ_WPTR, wptr_shadow);
+		m->cp_hqd_pq_wptr = wptr_shadow;
 
-	WREG32(mmCP_HQD_ACTIVE, m->cp_hqd_active);
+	acquire_queue(kgd, pipe_id, queue_id);
+	gfx_v7_0_mqd_commit(adev, m);
 	release_queue(kgd);
 
 	return 0;
 }
 
 static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
 	uint32_t sdma_base_addr;

91 lines not on this page · raw message

index c606e0b..7e5b426 100644
@@ -3039,26 +3039,43 @@ static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
 	}
 
 	/* read and write pointers, similar to CP_RB0_WPTR/_RPTR */
 	ring->wptr = 0;
 	mqd->cp_hqd_pq_wptr = ring->wptr;
 	mqd->cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
+	/* defaults */
+	mqd->cp_hqd_ib_control = RREG32(mmCP_HQD_IB_CONTROL);
+	mqd->cp_hqd_ib_base_addr_lo = RREG32(mmCP_HQD_IB_BASE_ADDR);
+	mqd->cp_hqd_ib_base_addr_hi = RREG32(mmCP_HQD_IB_BASE_ADDR_HI);
+	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;
 }
 
-static int gfx_v7_0_mqd_commit(struct amdgpu_device *adev,
-			       struct cik_mqd *mqd)
+int gfx_v7_0_mqd_commit(struct amdgpu_device *adev, struct cik_mqd *mqd)
 {
 	u32 tmp;
 
 	/* 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);

@@ -3068,20 +3085,37 @@ static int gfx_v7_0_mqd_commit(struct amdgpu_device *adev,
 	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);
+
 	/* activate the HQD */
 	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	return 0;
 }
 
 static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
 {
 	int r;
 	u64 mqd_gpu_addr;

index 2f5164c..6fb9c15 100644
@@ -22,11 +22,16 @@
  */
 
 #ifndef __GFX_V7_0_H__
 #define __GFX_V7_0_H__
 
 extern const struct amdgpu_ip_block_version gfx_v7_0_ip_block;
 extern const struct amdgpu_ip_block_version gfx_v7_1_ip_block;
 extern const struct amdgpu_ip_block_version gfx_v7_2_ip_block;
 extern const struct amdgpu_ip_block_version gfx_v7_3_ip_block;
 
+struct amdgpu_device;
+struct cik_mqd;
+
+int gfx_v7_0_mqd_commit(struct amdgpu_device *adev, struct cik_mqd *mqd);
+
 #endif

104 lines not on this page · raw message

index 788cc3a..ec3f11f 100644
@@ -20,11 +20,16 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
 
 #ifndef __GFX_V8_0_H__
 #define __GFX_V8_0_H__
 
 extern const struct amdgpu_ip_block_version gfx_v8_0_ip_block;
 extern const struct amdgpu_ip_block_version gfx_v8_1_ip_block;
 
+struct amdgpu_device;
+struct vi_mqd;
+
+int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd);
+
 #endif

index dba8a5b..3200ff9 100644
@@ -53,23 +53,23 @@ int amdgpu_amdkfd_init(void)
 	if (ret)
 		kgd2kfd = NULL;
 
 #else
 	ret = -ENOENT;
 #endif
 
 	return ret;
 }
 
-bool amdgpu_amdkfd_load_interface(struct amdgpu_device *rdev)
+bool amdgpu_amdkfd_load_interface(struct amdgpu_device *adev)
 {
-	switch (rdev->asic_type) {
+	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	case CHIP_KAVERI:
 		kfd2kgd = amdgpu_amdkfd_gfx_7_get_functions();
 		break;
 #endif
 	case CHIP_CARRIZO:
 		kfd2kgd = amdgpu_amdkfd_gfx_8_0_get_functions();
 		break;
 	default:
 		return false;

@@ -79,119 +79,119 @@ bool amdgpu_amdkfd_load_interface(struct amdgpu_device *rdev)
 }
 
 void amdgpu_amdkfd_fini(void)
 {
 	if (kgd2kfd) {
 		kgd2kfd->exit();
 		symbol_put(kgd2kfd_init);
 	}
 }
 
-void amdgpu_amdkfd_device_probe(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	if (kgd2kfd)
-		rdev->kfd = kgd2kfd->probe((struct kgd_dev *)rdev,
-					rdev->pdev, kfd2kgd);
+		adev->kfd = kgd2kfd->probe((struct kgd_dev *)adev,
+					adev->pdev, kfd2kgd);
 }
 
-void amdgpu_amdkfd_device_init(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
-	if (rdev->kfd) {
+	if (adev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = 0xFF00,
 
 			.first_compute_pipe = 1,
 			.compute_pipe_count = 4 - 1,
 		};
 
-		amdgpu_doorbell_get_kfd_info(rdev,
+		amdgpu_doorbell_get_kfd_info(adev,
 				&gpu_resources.doorbell_physical_address,
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
 
-		kgd2kfd->device_init(rdev->kfd, &gpu_resources);
+		kgd2kfd->device_init(adev->kfd, &gpu_resources);
 	}
 }
 
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)
 {
-	if (rdev->kfd) {
-		kgd2kfd->device_exit(rdev->kfd);
-		rdev->kfd = NULL;
+	if (adev->kfd) {
+		kgd2kfd->device_exit(adev->kfd);
+		adev->kfd = NULL;
 	}
 }
 
-void amdgpu_amdkfd_interrupt(struct amdgpu_device *rdev,
+void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 		const void *ih_ring_entry)
 {
-	if (rdev->kfd)
-		kgd2kfd->interrupt(rdev->kfd, ih_ring_entry);
+	if (adev->kfd)
+		kgd2kfd->interrupt(adev->kfd, ih_ring_entry);
 }
 
-void amdgpu_amdkfd_suspend(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_suspend(struct amdgpu_device *adev)
 {
-	if (rdev->kfd)
-		kgd2kfd->suspend(rdev->kfd);
+	if (adev->kfd)
+		kgd2kfd->suspend(adev->kfd);
 }
 
-int amdgpu_amdkfd_resume(struct amdgpu_device *rdev)
+int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 {
 	int r = 0;
 
-	if (rdev->kfd)
-		r = kgd2kfd->resume(rdev->kfd);
+	if (adev->kfd)
+		r = kgd2kfd->resume(adev->kfd);
 
 	return r;
 }
 
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	struct kgd_mem **mem = (struct kgd_mem **) mem_obj;
 	int r;
 
 	BUG_ON(kgd == NULL);
 	BUG_ON(gpu_addr == NULL);
 	BUG_ON(cpu_ptr == NULL);
 
 	*mem = kmalloc(sizeof(struct kgd_mem), GFP_KERNEL);
 	if ((*mem) == NULL)
 		return -ENOMEM;
 
-	r = amdgpu_bo_create(rdev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
 			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, NULL, &(*mem)->bo);
 	if (r) {
-		dev_err(rdev->dev,
+		dev_err(adev->dev,
 			"failed to allocate BO for amdkfd (%d)\n", r);
 		return r;
 	}
 
 	/* map the buffer */
 	r = amdgpu_bo_reserve((*mem)->bo, true);
 	if (r) {
-		dev_err(rdev->dev, "(%d) failed to reserve bo for amdkfd\n", r);
+		dev_err(adev->dev, "(%d) failed to reserve bo for amdkfd\n", r);
 		goto allocate_mem_reserve_bo_failed;
 	}
 
 	r = amdgpu_bo_pin((*mem)->bo, AMDGPU_GEM_DOMAIN_GTT,
 				&(*mem)->gpu_addr);
 	if (r) {
-		dev_err(rdev->dev, "(%d) failed to pin bo for amdkfd\n", r);
+		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
 		goto allocate_mem_pin_bo_failed;
 	}
 	*gpu_addr = (*mem)->gpu_addr;
 
 	r = amdgpu_bo_kmap((*mem)->bo, &(*mem)->cpu_ptr);
 	if (r) {
-		dev_err(rdev->dev,
+		dev_err(adev->dev,
 			"(%d) failed to map bo to kernel for amdkfd\n", r);
 		goto allocate_mem_kmap_bo_failed;
 	}
 	*cpu_ptr = (*mem)->cpu_ptr;
 
 	amdgpu_bo_unreserve((*mem)->bo);
 
 	return 0;
 
 allocate_mem_kmap_bo_failed:

@@ -213,34 +213,34 @@ void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj)
 	amdgpu_bo_reserve(mem->bo, true);
 	amdgpu_bo_kunmap(mem->bo);
 	amdgpu_bo_unpin(mem->bo);
 	amdgpu_bo_unreserve(mem->bo);
 	amdgpu_bo_unref(&(mem->bo));
 	kfree(mem);
 }
 
 uint64_t get_vmem_size(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev =
+	struct amdgpu_device *adev =
 		(struct amdgpu_device *)kgd;
 
 	BUG_ON(kgd == NULL);
 
-	return rdev->mc.real_vram_size;
+	return adev->mc.real_vram_size;
 }
 
 uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	if (rdev->gfx.funcs->get_gpu_clock_counter)
-		return rdev->gfx.funcs->get_gpu_clock_counter(rdev);
+	if (adev->gfx.funcs->get_gpu_clock_counter)
+		return adev->gfx.funcs->get_gpu_clock_counter(adev);
 	return 0;
 }
 
 uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
 	/* The sclk is in quantas of 10kHz */
-	return rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
+	return adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
 }

index de530f68d..73f83a1 100644
@@ -32,29 +32,29 @@ struct amdgpu_device;
 
 struct kgd_mem {
 	struct amdgpu_bo *bo;
 	uint64_t gpu_addr;
 	void *cpu_ptr;
 };
 
 int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
-bool amdgpu_amdkfd_load_interface(struct amdgpu_device *rdev);
+bool amdgpu_amdkfd_load_interface(struct amdgpu_device *adev);
 
-void amdgpu_amdkfd_suspend(struct amdgpu_device *rdev);
-int amdgpu_amdkfd_resume(struct amdgpu_device *rdev);
-void amdgpu_amdkfd_interrupt(struct amdgpu_device *rdev,
+void amdgpu_amdkfd_suspend(struct amdgpu_device *adev);
+int amdgpu_amdkfd_resume(struct amdgpu_device *adev);
+void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
-void amdgpu_amdkfd_device_probe(struct amdgpu_device *rdev);
-void amdgpu_amdkfd_device_init(struct amdgpu_device *rdev);
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *rdev);
+void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
+void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
+void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
 
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr);
 void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
 uint64_t get_vmem_size(struct kgd_dev *kgd);

index 7e5b426..03a4cee 100644
@@ -1835,21 +1835,21 @@ static void gfx_v7_0_setup_rb(struct amdgpu_device *adev)
 		gfx_v7_0_write_harvested_raster_configs(adev, raster_config, raster_config_1,
 							adev->gfx.config.backend_enable_mask,
 							num_rb_pipes);
 	}
 	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
 /**
  * gmc_v7_0_init_compute_vmid - gart enable
  *
- * @rdev: amdgpu_device pointer
+ * @adev: amdgpu_device pointer
  *
  * Initialize compute vmid sh_mem registers
  *
  */
 #define DEFAULT_SH_MEM_BASES	(0x6000)
 #define FIRST_COMPUTE_VMID	(8)
 #define LAST_COMPUTE_VMID	(16)
 static void gmc_v7_0_init_compute_vmid(struct amdgpu_device *adev)
 {
 	int i;

index f862bc0..3cb39d4 100644
@@ -3792,21 +3792,21 @@ static void gfx_v8_0_setup_rb(struct amdgpu_device *adev)
 				RREG32(mmPA_SC_RASTER_CONFIG_1);
 		}
 	}
 	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
 /**
  * gfx_v8_0_init_compute_vmid - gart enable
  *
- * @rdev: amdgpu_device pointer
+ * @adev: amdgpu_device pointer
  *
  * Initialize compute vmid sh_mem registers
  *
  */
 #define DEFAULT_SH_MEM_BASES	(0x6000)
 #define FIRST_COMPUTE_VMID	(8)
 #define LAST_COMPUTE_VMID	(16)
 static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev)
 {
 	int i;

index b577ec1..15e048c 100644
@@ -769,23 +769,23 @@ struct amdgpu_rlc {
 	u32 reg_list_format_size_bytes;
 	u32 reg_list_size_bytes;
 
 	u32 *register_list_format;
 	u32 *register_restore;
 };
 
 struct amdgpu_mec {
 	struct amdgpu_bo	*hpd_eop_obj;
 	u64			hpd_eop_gpu_addr;
-	u32 num_pipe;
 	u32 num_mec;
-	u32 num_queue;
+	u32 num_pipe_per_mec;
+	u32 num_queue_per_pipe;
 };
 
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
 
 /*

index 038b7ea..910f9d3 100644
@@ -237,32 +237,21 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 
 	/* Mapping vmid to pasid also for IH block */
 	WREG32(mmIH_VMID_0_LUT + vmid, pasid_mapping);
 
 	return 0;
 }
 
 static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t hpd_size, uint64_t hpd_gpu_addr)
 {
-	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-
-	uint32_t mec = (++pipe_id / CIK_PIPE_PER_MEC) + 1;
-	uint32_t pipe = (pipe_id % CIK_PIPE_PER_MEC);
-
-	lock_srbm(kgd, mec, pipe, 0, 0);
-	WREG32(mmCP_HPD_EOP_BASE_ADDR, lower_32_bits(hpd_gpu_addr >> 8));
-	WREG32(mmCP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(hpd_gpu_addr >> 8));
-	WREG32(mmCP_HPD_EOP_VMID, 0);
-	WREG32(mmCP_HPD_EOP_CONTROL, hpd_size);
-	unlock_srbm(kgd);
-
+	/* amdgpu owns the per-pipe state */
 	return 0;
 }
 
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t mec;
 	uint32_t pipe;
 
 	mec = (pipe_id / CIK_PIPE_PER_MEC) + 1;

index 2ecef3d..5843368 100644
@@ -199,20 +199,21 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 
 	/* Mapping vmid to pasid also for IH block */
 	WREG32(mmIH_VMID_0_LUT + vmid, pasid_mapping);
 
 	return 0;
 }
 
 static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t hpd_size, uint64_t hpd_gpu_addr)
 {
+	/* amdgpu owns the per-pipe state */
 	return 0;
 }
 
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t mec;
 	uint32_t pipe;
 
 	mec = (++pipe_id / VI_PIPE_PER_MEC) + 1;

index 03a4cee..2f1faa4 100644
@@ -2799,34 +2799,48 @@ static void gfx_v7_0_mec_fini(struct amdgpu_device *adev)
 
 		amdgpu_bo_unref(&adev->gfx.mec.hpd_eop_obj);
 		adev->gfx.mec.hpd_eop_obj = NULL;
 	}
 }
 
 static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 {
 	int r;
 	u32 *hpd;
+	size_t mec_hpd_size;
 
 	/*
 	 * KV:    2 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 64 Queues total
 	 * CI/KB: 1 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 32 Queues total
 	 * Nonetheless, we assign only 1 pipe because all other pipes will
 	 * be handled by KFD
 	 */
-	adev->gfx.mec.num_mec = 1;
-	adev->gfx.mec.num_pipe = 1;
-	adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
+	switch (adev->asic_type) {
+	case CHIP_KAVERI:
+		adev->gfx.mec.num_mec = 2;
+		break;
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+	case CHIP_KABINI:
+	case CHIP_MULLINS:
+	default:
+		adev->gfx.mec.num_mec = 1;
+		break;
+	}
+	adev->gfx.mec.num_pipe_per_mec = 4;
+	adev->gfx.mec.num_queue_per_pipe = 8;
 
+	mec_hpd_size = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe_per_mec
+		* GFX7_MEC_HPD_SIZE * 2;
 	if (adev->gfx.mec.hpd_eop_obj == NULL) {
 		r = amdgpu_bo_create(adev,
-				     adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2,
+				     mec_hpd_size,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
 			return r;
 		}
 	}
 
 	r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);

@@ -2842,21 +2856,21 @@ static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 	r = amdgpu_bo_kmap(adev->gfx.mec.hpd_eop_obj, (void **)&hpd);
 	if (r) {
 		dev_warn(adev->dev, "(%d) map HDP EOP bo failed\n", r);
 		gfx_v7_0_mec_fini(adev);
 		return r;
 	}
 
 	/* clear memory.  Not sure if this is required or not */
-	memset(hpd, 0, adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2);
+	memset(hpd, 0, mec_hpd_size);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
 
 	return 0;
 }
 
 struct hqd_registers
 {
 	u32 cp_mqd_base_addr;

@@ -3180,23 +3194,23 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 {
 	int r, i, j;
 	u32 tmp;
 	struct amdgpu_ring *ring;
 
 	/* fix up chicken bits */
 	tmp = RREG32(mmCP_CPF_DEBUG);
 	tmp |= (1 << 23);
 	WREG32(mmCP_CPF_DEBUG, tmp);
 
-	/* init the pipes */
+	/* init all pipes (even the ones we don't own) */
 	for (i = 0; i < adev->gfx.mec.num_mec; i++)
-		for (j = 0; j < adev->gfx.mec.num_pipe; j++)
+		for (j = 0; j < adev->gfx.mec.num_pipe_per_mec; j++)
 			gfx_v7_0_compute_pipe_init(adev, i, j);
 
 	/* init the queues */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		r = gfx_v7_0_compute_queue_init(adev, i);
 		if (r) {
 			gfx_v7_0_cp_compute_fini(adev);
 			return r;
 		}
 	}

index 3cb39d4..1bd4759 100644
@@ -1417,32 +1417,47 @@ static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
 	amdgpu_ring_fini(ring);
 	irq->data = NULL;
 }
 
 #define GFX8_MEC_HPD_SIZE 2048
 
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
 	int r;
 	u32 *hpd;
+	size_t mec_hpd_size;
 
-	/*
-	 * we assign only 1 pipe because all other pipes will
-	 * be handled by KFD
-	 */
-	adev->gfx.mec.num_mec = 1;
-	adev->gfx.mec.num_pipe = 1;
-	adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
+	switch (adev->asic_type) {
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_POLARIS10:
+	case CHIP_CARRIZO:
+		adev->gfx.mec.num_mec = 2;
+		break;
+	case CHIP_TOPAZ:
+	case CHIP_STONEY:
+	default:
+		adev->gfx.mec.num_mec = 1;
+		break;
+	}
+
+	adev->gfx.mec.num_pipe_per_mec = 4;
+	adev->gfx.mec.num_queue_per_pipe = 8;
+
+	/* only 1 pipe of the first MEC is owned by amdgpu */
+	mec_hpd_size = 1 * 1 * adev->gfx.mec.num_queue_per_pipe * GFX8_MEC_HPD_SIZE;
 
 	if (adev->gfx.mec.hpd_eop_obj == NULL) {
 		r = amdgpu_bo_create(adev,
-				     adev->gfx.mec.num_queue * GFX8_MEC_HPD_SIZE,
+				     mec_hpd_size,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
 			return r;
 		}
 	}
 
 	r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);

@@ -1457,21 +1472,21 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 		gfx_v8_0_mec_fini(adev);
 		return r;
 	}
 	r = amdgpu_bo_kmap(adev->gfx.mec.hpd_eop_obj, (void **)&hpd);
 	if (r) {
 		dev_warn(adev->dev, "(%d) map HDP EOP bo failed\n", r);
 		gfx_v8_0_mec_fini(adev);
 		return r;
 	}
 
-	memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_MEC_HPD_SIZE);
+	memset(hpd, 0, mec_hpd_size);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
 
 	return 0;
 }
 
 static void gfx_v8_0_kiq_fini(struct amdgpu_device *adev)
 {
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;

69 lines not on this page · raw message

index f6ff41a..82b57ef 100644
@@ -4588,37 +4588,38 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		return r;
 
 	/* fix up chicken bits */
 	tmp = RREG32(CP_CPF_DEBUG);
 	tmp |= (1 << 23);
 	WREG32(CP_CPF_DEBUG, tmp);
 
 	/* init the pipes */
 	mutex_lock(&rdev->srbm_mutex);
 
-	eop_gpu_addr = rdev->mec.hpd_eop_gpu_addr;
+	for (i = 0; i < rdev->mec.num_pipe; ++i) {
+		cik_srbm_select(rdev, 0, i, 0, 0);
 
-	cik_srbm_select(rdev, 0, 0, 0, 0);
-
-	/* write the EOP addr */
-	WREG32(CP_HPD_EOP_BASE_ADDR, eop_gpu_addr >> 8);
-	WREG32(CP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr) >> 8);
+		eop_gpu_addr = rdev->mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE * 2) ;
+		/* write the EOP addr */
+		WREG32(CP_HPD_EOP_BASE_ADDR, eop_gpu_addr >> 8);
+		WREG32(CP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr) >> 8);
 
-	/* set the VMID assigned */
-	WREG32(CP_HPD_EOP_VMID, 0);
+		/* set the VMID assigned */
+		WREG32(CP_HPD_EOP_VMID, 0);
 
-	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32(CP_HPD_EOP_CONTROL);
-	tmp &= ~EOP_SIZE_MASK;
-	tmp |= order_base_2(MEC_HPD_SIZE / 8);
-	WREG32(CP_HPD_EOP_CONTROL, tmp);
+		/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
+		tmp = RREG32(CP_HPD_EOP_CONTROL);
+		tmp &= ~EOP_SIZE_MASK;
+		tmp |= order_base_2(MEC_HPD_SIZE / 8);
+		WREG32(CP_HPD_EOP_CONTROL, tmp);
 
+	}
 	mutex_unlock(&rdev->srbm_mutex);
 
 	/* init the queues.  Just two for now. */
 	for (i = 0; i < 2; i++) {
 		if (i == 0)
 			idx = CAYMAN_RING_TYPE_CP1_INDEX;
 		else
 			idx = CAYMAN_RING_TYPE_CP2_INDEX;
 
 		if (rdev->ring[idx].mqd_obj == NULL) {

index 87a9ebb..a06e3b1 100644
@@ -416,32 +416,21 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 	/* Mapping vmid to pasid also for IH block */
 	write_register(kgd, IH_VMID_0_LUT + vmid * sizeof(uint32_t),
 			pasid_mapping);
 
 	return 0;
 }
 
 static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t hpd_size, uint64_t hpd_gpu_addr)
 {
-	uint32_t mec = (pipe_id / CIK_PIPE_PER_MEC) + 1;
-	uint32_t pipe = (pipe_id % CIK_PIPE_PER_MEC);
-
-	lock_srbm(kgd, mec, pipe, 0, 0);
-	write_register(kgd, CP_HPD_EOP_BASE_ADDR,
-			lower_32_bits(hpd_gpu_addr >> 8));
-	write_register(kgd, CP_HPD_EOP_BASE_ADDR_HI,
-			upper_32_bits(hpd_gpu_addr >> 8));
-	write_register(kgd, CP_HPD_EOP_VMID, 0);
-	write_register(kgd, CP_HPD_EOP_CONTROL, hpd_size);
-	unlock_srbm(kgd);
-
+	/* nothing to do here */
 	return 0;
 }
 
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	uint32_t mec;
 	uint32_t pipe;
 
 	mec = (pipe_id / CIK_PIPE_PER_MEC) + 1;
 	pipe = (pipe_id % CIK_PIPE_PER_MEC);

index 15e048c..f9df217 100644
@@ -39,20 +39,22 @@
 #include <ttm/ttm_bo_api.h>
 #include <ttm/ttm_bo_driver.h>
 #include <ttm/ttm_placement.h>
 #include <ttm/ttm_module.h>
 #include <ttm/ttm_execbuf_util.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_gem.h>
 #include <drm/amdgpu_drm.h>
 
+#include <kgd_kfd_interface.h>
+
 #include "amd_shared.h"
 #include "amdgpu_mode.h"
 #include "amdgpu_ih.h"
 #include "amdgpu_irq.h"
 #include "amdgpu_ucode.h"
 #include "amdgpu_ttm.h"
 #include "amdgpu_gds.h"
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
 #include "amdgpu_vm.h"

@@ -766,26 +768,31 @@ struct amdgpu_rlc {
 	u32 reg_list_format_start;
 	u32 reg_list_format_separate_start;
 	u32 starting_offsets_start;
 	u32 reg_list_format_size_bytes;
 	u32 reg_list_size_bytes;
 
 	u32 *register_list_format;
 	u32 *register_restore;
 };
 
+#define AMDGPU_MAX_QUEUES KGD_MAX_QUEUES
+
 struct amdgpu_mec {
 	struct amdgpu_bo	*hpd_eop_obj;
 	u64			hpd_eop_gpu_addr;
 	u32 num_mec;
 	u32 num_pipe_per_mec;
 	u32 num_queue_per_pipe;
+
+	/* These are the resources for which amdgpu takes ownership */
+	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_QUEUES);
 };
 
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
 
 /*

214 lines not on this page · raw message

215 lines not on this page · raw message

index a09d9f3..67f6d19 100644
@@ -26,20 +26,21 @@
  */
 
 #ifndef KGD_KFD_INTERFACE_H_INCLUDED
 #define KGD_KFD_INTERFACE_H_INCLUDED
 
 #include <linux/types.h>
 
 struct pci_dev;
 
 #define KFD_INTERFACE_VERSION 1
+#define KGD_MAX_QUEUES 128
 
 struct kfd_dev;
 struct kgd_dev;
 
 struct kgd_mem;
 
 enum kgd_memory_pool {
 	KGD_POOL_SYSTEM_CACHEABLE = 1,
 	KGD_POOL_SYSTEM_WRITECOMBINE = 2,
 	KGD_POOL_FRAMEBUFFER = 3,

index fe46765..68265b7 100644
@@ -5032,56 +5032,42 @@ static void gfx_v7_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 		break;
 	default:
 		break;
 	}
 }
 
 static void gfx_v7_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 						     int me, int pipe,
 						     enum amdgpu_interrupt_state state)
 {
-	u32 mec_int_cntl, mec_int_cntl_reg;
-
-	/*
-	 * amdgpu controls only pipe 0 of MEC1. That's why this function only
-	 * handles the setting of interrupts for this specific pipe. All other
-	 * pipes' interrupts are set by amdkfd.
+	/* Me 0 is for graphics and Me 2 is reserved for HW scheduling
+	 * So we should only really be configuring ME 1 i.e. MEC0
 	 */
-
-	if (me == 1) {
-		switch (pipe) {
-		case 0:
-			mec_int_cntl_reg = mmCP_ME1_PIPE0_INT_CNTL;
-			break;
-		default:
-			DRM_DEBUG("invalid pipe %d\n", pipe);
-			return;
-		}
-	} else {
-		DRM_DEBUG("invalid me %d\n", me);
+	if (me != 1) {
+		DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
 		return;
 	}
 
-	switch (state) {
-	case AMDGPU_IRQ_STATE_DISABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
-		mec_int_cntl &= ~CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK;
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
-		break;
-	case AMDGPU_IRQ_STATE_ENABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
-		mec_int_cntl |= CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK;
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
-		break;
-	default:
-		break;
+	if (pipe >= adev->gfx.mec.num_pipe_per_mec) {
+		DRM_ERROR("Ignoring request to enable interrupts for invalid "
+				"me:%d pipe:%d\n", pipe, me);
+		return;
 	}
+
+	mutex_lock(&adev->srbm_mutex);
+	cik_srbm_select(adev, me, pipe, 0, 0);
+
+	WREG32_FIELD(CPC_INT_CNTL, TIME_STAMP_INT_ENABLE,
+			state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
+
+	cik_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
 }
 
 static int gfx_v7_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
 					     struct amdgpu_irq_src *src,
 					     unsigned type,
 					     enum amdgpu_interrupt_state state)
 {
 	u32 cp_int_cntl;
 
 	switch (state) {

index 1238b3d..861334b 100644
@@ -6779,41 +6779,42 @@ static void gfx_v8_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 						 enum amdgpu_interrupt_state state)
 {
 	WREG32_FIELD(CP_INT_CNTL_RING0, TIME_STAMP_INT_ENABLE,
 		     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
 }
 
 static void gfx_v8_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 						     int me, int pipe,
 						     enum amdgpu_interrupt_state state)
 {
-	/*
-	 * amdgpu controls only pipe 0 of MEC1. That's why this function only
-	 * handles the setting of interrupts for this specific pipe. All other
-	 * pipes' interrupts are set by amdkfd.
+	/* Me 0 is for graphics and Me 2 is reserved for HW scheduling
+	 * So we should only really be configuring ME 1 i.e. MEC0
 	 */
+	if (me != 1) {
+		DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
+		return;
+	}
 
-	if (me == 1) {
-		switch (pipe) {
-		case 0:
-			break;
-		default:
-			DRM_DEBUG("invalid pipe %d\n", pipe);
-			return;
-		}
-	} else {
-		DRM_DEBUG("invalid me %d\n", me);
+	if (pipe >= adev->gfx.mec.num_pipe_per_mec) {
+		DRM_ERROR("Ignoring request to enable interrupts for invalid "
+				"me:%d pipe:%d\n", pipe, me);
 		return;
 	}
 
-	WREG32_FIELD(CP_ME1_PIPE0_INT_CNTL, TIME_STAMP_INT_ENABLE,
-		     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
+	mutex_lock(&adev->srbm_mutex);
+	vi_srbm_select(adev, me, pipe, 0, 0);
+
+	WREG32_FIELD(CPC_INT_CNTL, TIME_STAMP_INT_ENABLE,
+			state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
+
+	vi_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
 }
 
 static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
 					     struct amdgpu_irq_src *source,
 					     unsigned type,
 					     enum amdgpu_interrupt_state state)
 {
 	WREG32_FIELD(CP_INT_CNTL_RING0, PRIV_REG_INT_ENABLE,
 		     state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
 

index 3200ff9..8fc5aa3 100644
@@ -88,28 +88,44 @@ void amdgpu_amdkfd_fini(void)
 
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	if (kgd2kfd)
 		adev->kfd = kgd2kfd->probe((struct kgd_dev *)adev,
 					adev->pdev, kfd2kgd);
 }
 
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
+	int i;
+	int last_valid_bit;
 	if (adev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = 0xFF00,
-
-			.first_compute_pipe = 1,
-			.compute_pipe_count = 4 - 1,
+			.num_mec = adev->gfx.mec.num_mec,
+			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
+			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
 		};
 
+		/* this is going to have a few of the MSBs set that we need to
+		 * clear */
+		bitmap_complement(gpu_resources.queue_bitmap,
+				  adev->gfx.mec.queue_bitmap,
+				  KGD_MAX_QUEUES);
+
+		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
+		 * nbits is not compile time constant */
+		last_valid_bit = adev->gfx.mec.num_mec
+				* adev->gfx.mec.num_pipe_per_mec
+				* adev->gfx.mec.num_queue_per_pipe;
+		for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
+			clear_bit(i, gpu_resources.queue_bitmap);
+
 		amdgpu_doorbell_get_kfd_info(adev,
 				&gpu_resources.doorbell_physical_address,
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
 
 		kgd2kfd->device_init(adev->kfd, &gpu_resources);
 	}
 }
 
 void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)

index 3f95f7c..88187bf 100644
@@ -219,20 +219,24 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 	return AMD_IOMMU_INV_PRI_RSP_INVALID;
 }
 
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources)
 {
 	unsigned int size;
 
 	kfd->shared_resources = *gpu_resources;
 
+	/* We only use the first MEC */
+	if (kfd->shared_resources.num_mec > 1)
+		kfd->shared_resources.num_mec = 1;
+
 	/* calculate max size of mqds needed for queues */
 	size = max_num_of_queues_per_device *
 			kfd->device_info->mqd_size_aligned;
 
 	/*
 	 * calculate max size of runlist packet.
 	 * There can be only 2 packets at once
 	 */
 	size += (KFD_MAX_NUM_OF_PROCESSES * sizeof(struct pm4_map_process) +
 		max_num_of_queues_per_device *

270 lines not on this page · raw message

index a625b91..66b9615 100644
@@ -23,22 +23,20 @@
 
 #ifndef KFD_DEVICE_QUEUE_MANAGER_H_
 #define KFD_DEVICE_QUEUE_MANAGER_H_
 
 #include <linux/rwsem.h>
 #include <linux/list.h>
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS	(500)
-#define QUEUES_PER_PIPE				(8)
-#define PIPE_PER_ME_CP_SCHEDULING		(3)
 #define CIK_VMID_NUM				(8)
 #define KFD_VMID_START_OFFSET			(8)
 #define VMID_PER_DEVICE				CIK_VMID_NUM
 #define KFD_DQM_FIRST_PIPE			(0)
 #define CIK_SDMA_QUEUES				(4)
 #define CIK_SDMA_QUEUES_PER_ENGINE		(2)
 #define CIK_SDMA_ENGINE_NUM			(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;

@@ -175,24 +173,24 @@ struct device_queue_manager {
 	uint64_t		fence_gpu_addr;
 	unsigned int		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 };
 
 void device_queue_manager_init_cik(struct device_queue_manager_asic_ops *ops);
 void device_queue_manager_init_vi(struct device_queue_manager_asic_ops *ops);
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd);
-int init_pipelines(struct device_queue_manager *dqm,
-		unsigned int pipes_num, unsigned int first_pipe);
-unsigned int get_first_pipe(struct device_queue_manager *dqm);
-unsigned int get_pipes_num(struct device_queue_manager *dqm);
+unsigned int get_mec_num(struct device_queue_manager *dqm);
+unsigned int get_queues_num(struct device_queue_manager *dqm);
+unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
+unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
 	return (pdd->lds_base >> 16) & 0xFF;
 }
 
 static inline unsigned int
 get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 {
 	return (pdd->lds_base >> 60) & 0x0E;

index c6f435a..48dc056 100644
@@ -144,12 +144,12 @@ static void init_sdma_vm(struct device_queue_manager *dqm, struct queue *q,
 	else
 		value |= ((get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd))) <<
 				SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE__SHIFT) &
 				SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE_MASK;
 
 	q->properties.sdma_vm_addr = value;
 }
 
 static int initialize_cpsch_cik(struct device_queue_manager *dqm)
 {
-	return init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
+	return 0;
 }

index ca8c093..7131998 100644
@@ -58,22 +58,21 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
 	unsigned int process_count, queue_count;
 	unsigned int map_queue_size;
 
 	BUG_ON(!pm || !rlib_size || !over_subscription);
 
 	process_count = pm->dqm->processes_count;
 	queue_count = pm->dqm->queue_count;
 
 	/* check if there is over subscription*/
 	*over_subscription = false;
-	if ((process_count > 1) ||
-		queue_count > PIPE_PER_ME_CP_SCHEDULING * QUEUES_PER_PIPE) {
+	if ((process_count > 1) || queue_count > get_queues_num(pm->dqm)) {
 		*over_subscription = true;
 		pr_debug("kfd: over subscribed runlist\n");
 	}
 
 	map_queue_size =
 		(pm->dqm->dev->device_info->asic_family == CHIP_CARRIZO) ?
 		sizeof(struct pm4_mes_map_queues) :
 		sizeof(struct pm4_map_queues);
 	/* calculate run list ib allocation size */
 	*rlib_size = process_count * sizeof(struct pm4_map_process) +

index e1fb40b..32cdf2b 100644
@@ -202,21 +202,21 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		retval = -ENOMEM;
 		goto err_allocate_pqn;
 	}
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
 	case KFD_QUEUE_TYPE_COMPUTE:
 		/* check if there is over subscription */
 		if ((sched_policy == KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
 		((dev->dqm->processes_count >= VMID_PER_DEVICE) ||
-		(dev->dqm->queue_count >= PIPE_PER_ME_CP_SCHEDULING * QUEUES_PER_PIPE))) {
+		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
 			pr_err("kfd: over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
 
 		retval = create_cp_queue(pqm, dev, &q, &q_properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;

index 67f6d19..91ef148 100644
@@ -22,24 +22,25 @@
 
 /*
  * This file defines the private interface between the
  * AMD kernel graphics drivers and the AMD KFD.
  */
 
 #ifndef KGD_KFD_INTERFACE_H_INCLUDED
 #define KGD_KFD_INTERFACE_H_INCLUDED
 
 #include <linux/types.h>
+#include <linux/bitmap.h>
 
 struct pci_dev;
 
-#define KFD_INTERFACE_VERSION 1
+#define KFD_INTERFACE_VERSION 2
 #define KGD_MAX_QUEUES 128
 
 struct kfd_dev;
 struct kgd_dev;
 
 struct kgd_mem;
 
 enum kgd_memory_pool {
 	KGD_POOL_SYSTEM_CACHEABLE = 1,
 	KGD_POOL_SYSTEM_WRITECOMBINE = 2,

@@ -55,25 +56,31 @@ enum kgd_engine_type {
 	KGD_ENGINE_RLC,
 	KGD_ENGINE_SDMA1,
 	KGD_ENGINE_SDMA2,
 	KGD_ENGINE_MAX
 };
 
 struct kgd2kfd_shared_resources {
 	/* Bit n == 1 means VMID n is available for KFD. */
 	unsigned int compute_vmid_bitmap;
 
-	/* Compute pipes are counted starting from MEC0/pipe0 as 0. */
-	unsigned int first_compute_pipe;
+	/* number of mec available from the hardware */
+	uint32_t num_mec;
 
-	/* Number of MEC pipes available for KFD. */
-	unsigned int compute_pipe_count;
+	/* number of pipes per mec */
+	uint32_t num_pipe_per_mec;
+
+	/* number of queues per pipe */
+	uint32_t num_queue_per_pipe;
+
+	/* Bit n == 1 means Queue n is available for KFD */
+	DECLARE_BITMAP(queue_bitmap, KGD_MAX_QUEUES);
 
 	/* Base address of doorbell aperture. */
 	phys_addr_t doorbell_physical_address;
 
 	/* Size in bytes of doorbell aperture. */
 	size_t doorbell_aperture_size;
 
 	/* Number of bytes at start of aperture reserved for KGD. */
 	size_t doorbell_start_offset;
 };

index a06e3b1..699fe7f 100644
@@ -172,28 +172,43 @@ void radeon_kfd_fini(void)
 
 void radeon_kfd_device_probe(struct radeon_device *rdev)
 {
 	if (kgd2kfd)
 		rdev->kfd = kgd2kfd->probe((struct kgd_dev *)rdev,
 			rdev->pdev, &kfd2kgd);
 }
 
 void radeon_kfd_device_init(struct radeon_device *rdev)
 {
+	int i, queue, pipe, mec;
+
 	if (rdev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = 0xFF00,
-
-			.first_compute_pipe = 1,
-			.compute_pipe_count = 4 - 1,
+			.num_mec = 1,
+			.num_pipe_per_mec = 4,
+			.num_queue_per_pipe = 8
 		};
 
+		bitmap_zero(gpu_resources.queue_bitmap, KGD_MAX_QUEUES);
+
+		for (i = 0; i < KGD_MAX_QUEUES; ++i) {
+			queue = i % gpu_resources.num_queue_per_pipe;
+			pipe = (i / gpu_resources.num_queue_per_pipe)
+				% gpu_resources.num_pipe_per_mec;
+			mec = (i / gpu_resources.num_queue_per_pipe)
+				/ gpu_resources.num_pipe_per_mec;
+
+			if (mec == 0 && pipe > 0)
+				set_bit(i, gpu_resources.queue_bitmap);
+		}
+
 		radeon_doorbell_get_kfd_info(rdev,
 				&gpu_resources.doorbell_physical_address,
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
 
 		kgd2kfd->device_init(rdev->kfd, &gpu_resources);
 	}
 }
 
 void radeon_kfd_device_fini(struct radeon_device *rdev)

index 910f9d3..5254562 100644
@@ -32,22 +32,20 @@
 #include "gfx_v7_0.h"
 #include "gca/gfx_7_2_d.h"
 #include "gca/gfx_7_2_enum.h"
 #include "gca/gfx_7_2_sh_mask.h"
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 #include "gmc/gmc_7_1_d.h"
 #include "gmc/gmc_7_1_sh_mask.h"
 #include "cik_structs.h"
 
-#define CIK_PIPE_PER_MEC	(4)
-
 enum {
 	MAX_TRAPID = 8,		/* 3 bits in the bitfield. */
 	MAX_WATCH_ADDRESSES = 4
 };
 
 enum {
 	ADDRESS_WATCH_REG_ADDR_HI = 0,
 	ADDRESS_WATCH_REG_ADDR_LO,
 	ADDRESS_WATCH_REG_CNTL,
 	ADDRESS_WATCH_REG_MAX

@@ -179,22 +177,24 @@ static void unlock_srbm(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
 	WREG32(mmSRBM_GFX_CNTL, 0);
 	mutex_unlock(&adev->srbm_mutex);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t queue_id)
 {
-	uint32_t mec = (++pipe_id / CIK_PIPE_PER_MEC) + 1;
-	uint32_t pipe = (pipe_id % CIK_PIPE_PER_MEC);
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t mec = (++pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	uint32_t pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
 
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
 static void release_queue(struct kgd_dev *kgd)
 {
 	unlock_srbm(kgd);
 }
 
 static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,

@@ -247,22 +247,22 @@ static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 	/* amdgpu owns the per-pipe state */
 	return 0;
 }
 
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t mec;
 	uint32_t pipe;
 
-	mec = (pipe_id / CIK_PIPE_PER_MEC) + 1;
-	pipe = (pipe_id % CIK_PIPE_PER_MEC);
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
 
 	lock_srbm(kgd, mec, pipe, 0, 0);
 
 	WREG32(mmCPC_INT_CNTL, CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
 			CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
 
 	unlock_srbm(kgd);
 
 	return 0;
 }

index 5843368..db7410a 100644
@@ -32,22 +32,20 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
 #include "gca/gfx_8_0_enum.h"
 #include "oss/oss_3_0_sh_mask.h"
 #include "oss/oss_3_0_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 #include "gmc/gmc_8_1_d.h"
 #include "vi_structs.h"
 #include "vid.h"
 
-#define VI_PIPE_PER_MEC	(4)
-
 struct cik_sdma_rlc_registers;
 
 /*
  * Register access functions
  */
 
 static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t sh_mem_config,
 		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
 		uint32_t sh_mem_bases);

@@ -140,22 +138,24 @@ static void unlock_srbm(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
 	WREG32(mmSRBM_GFX_CNTL, 0);
 	mutex_unlock(&adev->srbm_mutex);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t queue_id)
 {
-	uint32_t mec = (++pipe_id / VI_PIPE_PER_MEC) + 1;
-	uint32_t pipe = (pipe_id % VI_PIPE_PER_MEC);
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t mec = (++pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	uint32_t pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
 
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
 static void release_queue(struct kgd_dev *kgd)
 {
 	unlock_srbm(kgd);
 }
 
 static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,

@@ -209,22 +209,22 @@ static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 	/* amdgpu owns the per-pipe state */
 	return 0;
 }
 
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t mec;
 	uint32_t pipe;
 
-	mec = (++pipe_id / VI_PIPE_PER_MEC) + 1;
-	pipe = (pipe_id % VI_PIPE_PER_MEC);
+	mec = (++pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
 
 	lock_srbm(kgd, mec, pipe, 0, 0);
 
 	WREG32(mmCPC_INT_CNTL, CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK);
 
 	unlock_srbm(kgd);
 
 	return 0;
 }
 

index f9df217..377f58a 100644
@@ -1639,20 +1639,33 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		if (&adev->sdma.instance[i].ring == ring)
 			break;
 
 	if (i < AMDGPU_MAX_SDMA_INSTANCES)
 		return &adev->sdma.instance[i];
 	else
 		return NULL;
 }
 
+static inline bool amdgpu_is_mec_queue_enabled(struct amdgpu_device *adev,
+						int mec, int pipe, int queue)
+{
+	int bit = 0;
+
+	bit += mec * adev->gfx.mec.num_pipe_per_mec
+		* adev->gfx.mec.num_queue_per_pipe;
+	bit += pipe * adev->gfx.mec.num_queue_per_pipe;
+	bit += queue;
+
+	return test_bit(bit, adev->gfx.mec.queue_bitmap);
+}
+
 /*
  * ASICs macro.
  */
 #define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
 #define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
 #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
 #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
 #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
 #define amdgpu_get_pcie_lanes(adev) (adev)->asic_funcs->get_pcie_lanes((adev))
 #define amdgpu_set_pcie_lanes(adev, l) (adev)->asic_funcs->set_pcie_lanes((adev), (l))

125 lines not on this page · raw message

128 lines not on this page · raw message

index 3ca5519..b0b0c89 100644
@@ -2811,21 +2811,21 @@ static void gfx_v7_0_compute_queue_acquire(struct amdgpu_device *adev)
 		pipe = (i / adev->gfx.mec.num_queue_per_pipe)
 			% adev->gfx.mec.num_pipe_per_mec;
 		mec = (i / adev->gfx.mec.num_queue_per_pipe)
 			/ adev->gfx.mec.num_pipe_per_mec;
 
 		/* we've run out of HW */
 		if (mec > adev->gfx.mec.num_mec)
 			break;
 
 		/* policy: amdgpu owns all queues in the first pipe */
-		if (mec == 0 && pipe == 0)
+		if (mec == 0 && queue < 2)
 			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
 	/* update the number of active compute rings */
 	adev->gfx.num_compute_rings =
 		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_QUEUES);
 
 	/* If you hit this case and edited the policy, you probably just
 	 * need to increase AMDGPU_MAX_COMPUTE_RINGS */
 	WARN_ON(adev->gfx.num_compute_rings > AMDGPU_MAX_COMPUTE_RINGS);

index edddd86..5db5bac 100644
@@ -1429,21 +1429,21 @@ static void gfx_v8_0_compute_queue_acquire(struct amdgpu_device *adev)
 		pipe = (i / adev->gfx.mec.num_queue_per_pipe)
 			% adev->gfx.mec.num_pipe_per_mec;
 		mec = (i / adev->gfx.mec.num_queue_per_pipe)
 			/ adev->gfx.mec.num_pipe_per_mec;
 
 		/* we've run out of HW */
 		if (mec > adev->gfx.mec.num_mec)
 			break;
 
 		/* policy: amdgpu owns all queues in the first pipe */
-		if (mec == 0 && pipe == 0)
+		if (mec == 0 && queue < 2)
 			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
 	/* update the number of active compute rings */
 	adev->gfx.num_compute_rings =
 		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_QUEUES);
 
 	/* If you hit this case and edited the policy, you probably just
 	 * need to increase AMDGPU_MAX_COMPUTE_RINGS */
 	if (WARN_ON(adev->gfx.num_compute_rings > AMDGPU_MAX_COMPUTE_RINGS))

index 377f58a..734d941 100644
@@ -648,32 +648,56 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 			     struct amdgpu_job **job);
 
 void amdgpu_job_free_resources(struct amdgpu_job *job);
 void amdgpu_job_free(struct amdgpu_job *job);
 int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		      struct amd_sched_entity *entity, void *owner,
 		      struct dma_fence **f);
 
 /*
+ * Queue manager
+ */
+struct amdgpu_queue_mapper {
+	int 		hw_ip;
+	struct mutex	lock;
+	/* protected by lock */
+	struct amdgpu_ring *queue_map[AMDGPU_MAX_RINGS];
+};
+
+struct amdgpu_queue_mgr {
+	struct amdgpu_queue_mapper mapper[AMDGPU_MAX_IP_NUM];
+};
+
+int amdgpu_queue_mgr_init(struct amdgpu_device *adev,
+			  struct amdgpu_queue_mgr *mgr);
+int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
+			  struct amdgpu_queue_mgr *mgr);
+int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
+			 struct amdgpu_queue_mgr *mgr,
+			 int hw_ip, int instance, int ring,
+			 struct amdgpu_ring **out_ring);
+
+/*
  * context related structures
  */
 
 struct amdgpu_ctx_ring {
 	uint64_t		sequence;
 	struct dma_fence	**fences;
 	struct amd_sched_entity	entity;
 };
 
 struct amdgpu_ctx {
 	struct kref		refcount;
 	struct amdgpu_device    *adev;
+	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
 	struct amdgpu_ctx_ring	rings[AMDGPU_MAX_RINGS];
 	bool preamble_presented;
 };
 
 struct amdgpu_ctx_mgr {
 	struct amdgpu_device	*adev;
 	struct mutex		lock;

@@ -1723,23 +1747,20 @@ static inline bool amdgpu_is_mec_queue_enabled(struct amdgpu_device *adev,
 #define amdgpu_gds_switch(adev, r, v, d, w, a) (adev)->gds.funcs->patch_gds_switch((r), (v), (d), (w), (a))
 
 /* Common functions */
 int amdgpu_gpu_reset(struct amdgpu_device *adev);
 bool amdgpu_need_backup(struct amdgpu_device *adev);
 void amdgpu_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_need_post(struct amdgpu_device *adev);
 void amdgpu_update_display_priority(struct amdgpu_device *adev);
 
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data);
-int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
-		       u32 ip_instance, u32 ring,
-		       struct amdgpu_ring **out_ring);
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes);
 void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
 bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages);
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 				     uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
 struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm);
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 				  unsigned long end);

207 lines not on this page · raw message

index 400c66b..3ddc8db 100644
@@ -51,20 +51,24 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
 		struct amdgpu_ring *ring = adev->rings[i];
 		struct amd_sched_rq *rq;
 
 		rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
 		r = amd_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
 					  rq, amdgpu_sched_jobs);
 		if (r)
 			goto failed;
 	}
 
+	r = amdgpu_queue_mgr_init(adev, &ctx->queue_mgr);
+	if (r)
+		goto failed;
+
 	return 0;
 
 failed:
 	for (j = 0; j < i; j++)
 		amd_sched_entity_fini(&adev->rings[j]->sched,
 				      &ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 	return r;
 }

@@ -79,20 +83,22 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
 		for (j = 0; j < amdgpu_sched_jobs; ++j)
 			dma_fence_put(ctx->rings[i].fences[j]);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 
 	for (i = 0; i < adev->num_rings; i++)
 		amd_sched_entity_fini(&adev->rings[i]->sched,
 				      &ctx->rings[i].entity);
+
+	amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
 }
 
 static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 			    struct amdgpu_fpriv *fpriv,
 			    uint32_t *id)
 {
 	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
 	struct amdgpu_ctx *ctx;
 	int r;
 

230 lines not on this page · raw message

65 lines not on this page · raw message

index 2345b398..35da5c5 100644
@@ -168,20 +168,22 @@ struct amdgpu_ring {
 	uint64_t		current_ctx;
 	char			name[16];
 	unsigned		cond_exe_offs;
 	u64			cond_exe_gpu_addr;
 	volatile u32		*cond_exe_cpu_addr;
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry *ent;
 #endif
 };
 
+int amdgpu_ring_is_valid_index(struct amdgpu_device *adev,
+			       int hw_ip, int ring);
 int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw);
 void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
 void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
 void amdgpu_ring_commit(struct amdgpu_ring *ring);
 void amdgpu_ring_undo(struct amdgpu_ring *ring);
 int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     unsigned ring_size, struct amdgpu_irq_src *irq_src,
 		     unsigned irq_type);
 void amdgpu_ring_fini(struct amdgpu_ring *ring);