Skip to contentSkip to conversation

Add support for high priority scheduling in amdgpu v8

PATCH In review Andres Rodriguez 4 participants 44 messages Apr 6, 2017 – Apr 12, 2017 15 messages not in the archive Page 1 of 2

Subsystems (4)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-1-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#2 lore raw

PATCH 1/26 drm/amdgpu: refactor MQD/HQD initialization v2

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +241 -206
index 185cb31..f67ef58 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +68 -42

374 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-2-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#4 lore raw

Re: [PATCH 01/26] drm/amdgpu: refactor MQD/HQD initialization v2

Quoted 27 lines · Andres Rodriguez

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
index 185cb31..f67ef58 100644
@@ -42,20 +42,22 @@
 #include "gca/gfx_7_2_sh_mask.h"
 

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c line 53

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +2 -0
 #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
+

Might want to split out that the rename of this define into a separate patch so it can be applied early. Could probably also split the gfx7 and gfx8 changes into two patches so they can be applied separately separately so gfx7 doesn't have to be beholden to the flux in gfx8 at the moment.

Quoted 604 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +239 -206
 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +2 -0
index 4e63e52..88b85f7 100644
@@ -46,20 +46,22 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
+
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -1406,38 +1408,38 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 
        return r;

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev, · line 1418

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq)
 {
        amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
        amdgpu_ring_fini(ring);
 }
 
-#define MEC_HPD_SIZE 2048
+#define GFX8_MEC_HPD_SIZE 2048

Same comment about the rename of this.

Quoted 208 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +43 -12
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
 
        /*
         * 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_queue * MEC_HPD_SIZE,
+                                    adev->gfx.mec.num_queue * GFX8_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);
@@ -1452,50 +1454,50 @@ 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 * MEC_HPD_SIZE);
+       memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_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;
 
        amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
 }
 
 static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
        struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-       r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+       r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
                                    &kiq->eop_gpu_addr, (void **)&hpd);
        if (r) {
                dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
                return r;
        }
 
-       memset(hpd, 0, MEC_HPD_SIZE);
+       memset(hpd, 0, GFX8_MEC_HPD_SIZE);
 
        r = amdgpu_bo_reserve(kiq->eop_obj, false);
        if (unlikely(r != 0))
                dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
        amdgpu_bo_kunmap(kiq->eop_obj);
        amdgpu_bo_unreserve(kiq->eop_obj);
 
        return 0;
 }
 
@@ -2148,21 +2150,21 @@ static int gfx_v8_0_sw_init(void *handle)
                        DRM_ERROR("Too many (%d) compute rings!\n", i);
                        break;
                }
                ring = &adev->gfx.compute_ring[i];
                ring->ring_obj = NULL;
                ring->use_doorbell = true;
                ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
                ring->me = 1; /* first MEC */
                ring->pipe = i / 8;
                ring->queue = i % 8;
-               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
                sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
                irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
                /* type-2 packets are deprecated on MEC, use type-3 instead */
                r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
                                     irq_type);
                if (r)
                        return r;
        }
 
        r = gfx_v8_0_kiq_init(adev);
@@ -4747,52 +4749,50 @@ static int gfx_v8_0_kiq_kcq_disable(struct amdgpu_device *adev)
        return r;
 }
 
 static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
        uint32_t tmp;
 
+       /* init the mqd struct */
+       memset(mqd, 0, sizeof(struct vi_mqd));
+
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
 
        eop_base_addr = ring->eop_gpu_addr >> 8;
        mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
        mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
        /* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
        tmp = RREG32(mmCP_HQD_EOP_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-                       (order_base_2(MEC_HPD_SIZE / 4) - 1));
+                       (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
 
        mqd->cp_hqd_eop_control = tmp;
 
        /* enable doorbell? */
        tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
                            CP_HQD_PQ_DOORBELL_CONTROL,
                            DOORBELL_EN,
                            ring->use_doorbell ? 1 : 0);
 
        mqd->cp_hqd_pq_doorbell_control = tmp;
 
-       /* disable the queue if it's active */
-       mqd->cp_hqd_dequeue_request = 0;
-       mqd->cp_hqd_pq_rptr = 0;
-       mqd->cp_hqd_pq_wptr = 0;
-
        /* set the pointer to the MQD */
        mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
        mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
        /* set MQD vmid to 0 */
        tmp = RREG32(mmCP_MQD_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
        mqd->cp_mqd_control = tmp;
 
        /* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
@@ -4854,50 +4854,86 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
        tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
 
        return 0;
 }
 
-static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
+static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)
+{
+       int i;
+
+       /* 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);
+               }
+
+               if (i == adev->usec_timeout)
+                       return -ETIMEDOUT;
+
+               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+               WREG32(mmCP_HQD_PQ_RPTR, 0);
+               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)
+               return;
+
+       if ((adev->asic_type == CHIP_CARRIZO) ||
+                       (adev->asic_type == CHIP_FIJI) ||
+                       (adev->asic_type == CHIP_STONEY) ||

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4907

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+                       (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);
+}

This can be dropped since we've already split out the doorbell range setting and with KIQ enabled, these registers are only set once anyway. No need to split it out.

Quoted 101 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +6 -26
+
+static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
-       int j;
 
        /* 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);
 
-       /* disable the queue if it's active */
-       if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-               for (j = 0; j < adev->usec_timeout; j++) {
-                       if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
-                               break;
-                       udelay(1);
-               }
-               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);
-       }
+       /* 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);
 
        /* 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);
@@ -4910,46 +4946,33 @@ static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
        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 */
-       if (ring->use_doorbell) {
-               if ((adev->asic_type == CHIP_CARRIZO) ||
-                               (adev->asic_type == CHIP_FIJI) ||
-                               (adev->asic_type == CHIP_STONEY)) {
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
-                                               AMDGPU_DOORBELL_KIQ << 2);
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-                                               AMDGPU_DOORBELL_MEC_RING7 << 2);
-               }
-       }
        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);
 
        /* set the vmid for the queue */
        WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
 
        WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
        /* activate the queue */
        WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
-       if (ring->use_doorbell)
-               WREG32_FIELD(CP_PQ_STATUS, DOORBELL_ENABLE, 1);
-
        return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
        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);
@@ -4958,29 +4981,32 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
                /* 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;
                amdgpu_ring_clear_ring(ring);
 

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring) · line 4972

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -2
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
        } else {
-               memset((void *)mqd, 0, sizeof(*mqd));

Since you memset the mpq in gfx_v8_0_mqd_init(), you can also drop the memset in gfx_v8_0_kcq_init_queue().

Quoted 20 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -2
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return 0;
 }
 
--

2.9.3

Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): CADnq5_PAth5UD1zq2dYvmFXgqE4s_OKY_VtHuKj467JDuyCHhA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org

#6 lore raw

Re: [PATCH 01/26] drm/amdgpu: refactor MQD/HQD initialization v2

Quoted 34 lines · Alex Deucher
Quoted 33 lines · Andres Rodriguez

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
index 185cb31..f67ef58 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"
 
Quoted 11 lines

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c line 53

Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +2 -0
 #define GFX7_NUM_GFX_RINGS     1
 #define GFX7_NUM_COMPUTE_RINGS 8
+#define GFX7_MEC_HPD_SIZE      2048
+

Might want to split out that the rename of this define into a separate patch so it can be applied early. Could probably also split the gfx7 and gfx8 changes into two patches so they can be applied separately separately so gfx7 doesn't have to be beholden to the flux in gfx8 at the moment.

Done

Quoted 612 lines
Quoted 612 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +239 -206
 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +2 -0
index 4e63e52..88b85f7 100644
@@ -46,20 +46,22 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
+
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -1406,38 +1408,38 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 
        return r;
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq)
 {
        amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
        amdgpu_ring_fini(ring);
 }
 
Quoted 5 lines

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev, · line 1418

Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
-#define MEC_HPD_SIZE 2048
+#define GFX8_MEC_HPD_SIZE 2048

Same comment about the rename of this.

Done

Quoted 214 lines
Quoted 214 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +49 -12
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
 
        /*
         * 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_queue * MEC_HPD_SIZE,
+                                    adev->gfx.mec.num_queue * GFX8_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);
@@ -1452,50 +1454,50 @@ 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 * MEC_HPD_SIZE);
+       memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_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;
 
        amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
 }
 
 static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
        struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-       r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+       r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
                                    &kiq->eop_gpu_addr, (void **)&hpd);
        if (r) {
                dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
                return r;
        }
 
-       memset(hpd, 0, MEC_HPD_SIZE);
+       memset(hpd, 0, GFX8_MEC_HPD_SIZE);
 
        r = amdgpu_bo_reserve(kiq->eop_obj, false);
        if (unlikely(r != 0))
                dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
        amdgpu_bo_kunmap(kiq->eop_obj);
        amdgpu_bo_unreserve(kiq->eop_obj);
 
        return 0;
 }
 
@@ -2148,21 +2150,21 @@ static int gfx_v8_0_sw_init(void *handle)
                        DRM_ERROR("Too many (%d) compute rings!\n", i);
                        break;
                }
                ring = &adev->gfx.compute_ring[i];
                ring->ring_obj = NULL;
                ring->use_doorbell = true;
                ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
                ring->me = 1; /* first MEC */
                ring->pipe = i / 8;
                ring->queue = i % 8;
-               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
                sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
                irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
                /* type-2 packets are deprecated on MEC, use type-3 instead */
                r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
                                     irq_type);
                if (r)
                        return r;
        }
 
        r = gfx_v8_0_kiq_init(adev);
@@ -4747,52 +4749,50 @@ static int gfx_v8_0_kiq_kcq_disable(struct amdgpu_device *adev)
        return r;
 }
 
 static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
        uint32_t tmp;
 
+       /* init the mqd struct */
+       memset(mqd, 0, sizeof(struct vi_mqd));
+
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
 
        eop_base_addr = ring->eop_gpu_addr >> 8;
        mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
        mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
        /* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
        tmp = RREG32(mmCP_HQD_EOP_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-                       (order_base_2(MEC_HPD_SIZE / 4) - 1));
+                       (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
 
        mqd->cp_hqd_eop_control = tmp;
 
        /* enable doorbell? */
        tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
                            CP_HQD_PQ_DOORBELL_CONTROL,
                            DOORBELL_EN,
                            ring->use_doorbell ? 1 : 0);
 
        mqd->cp_hqd_pq_doorbell_control = tmp;
 
-       /* disable the queue if it's active */
-       mqd->cp_hqd_dequeue_request = 0;
-       mqd->cp_hqd_pq_rptr = 0;
-       mqd->cp_hqd_pq_wptr = 0;
-
        /* set the pointer to the MQD */
        mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
        mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
        /* set MQD vmid to 0 */
        tmp = RREG32(mmCP_MQD_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
        mqd->cp_mqd_control = tmp;
 
        /* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
@@ -4854,50 +4854,86 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
        tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
 
        return 0;
 }
 
-static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
+static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)
+{
+       int i;
+
+       /* 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);
+               }
+
+               if (i == adev->usec_timeout)
+                       return -ETIMEDOUT;
+
+               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+               WREG32(mmCP_HQD_PQ_RPTR, 0);
+               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)
+               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);
+       }
+
Quoted 9 lines

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4907

Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +4 -0
+       tmp = RREG32(mmCP_PQ_STATUS);
+       tmp = REG_SET_FIELD(tmp, CP_PQ_STATUS, DOORBELL_ENABLE, 1);
+       WREG32(mmCP_PQ_STATUS, tmp);
+}

This can be dropped since we've already split out the doorbell range setting and with KIQ enabled, these registers are only set once anyway. No need to split it out.

Done. From my understanding of your comment + the code, this just needs to be removed.

Quoted 101 lines
Quoted 101 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +6 -26
+
+static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
-       int j;
 
        /* 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);
 
-       /* disable the queue if it's active */
-       if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-               for (j = 0; j < adev->usec_timeout; j++) {
-                       if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
-                               break;
-                       udelay(1);
-               }
-               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);
-       }
+       /* 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);
 
        /* 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);
@@ -4910,46 +4946,33 @@ static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
        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 */
-       if (ring->use_doorbell) {
-               if ((adev->asic_type == CHIP_CARRIZO) ||
-                               (adev->asic_type == CHIP_FIJI) ||
-                               (adev->asic_type == CHIP_STONEY)) {
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
-                                               AMDGPU_DOORBELL_KIQ << 2);
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-                                               AMDGPU_DOORBELL_MEC_RING7 << 2);
-               }
-       }
        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);
 
        /* set the vmid for the queue */
        WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
 
        WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
        /* activate the queue */
        WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
-       if (ring->use_doorbell)
-               WREG32_FIELD(CP_PQ_STATUS, DOORBELL_ENABLE, 1);
-
        return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
        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);
@@ -4958,29 +4981,32 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
                /* 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;
                amdgpu_ring_clear_ring(ring);
 
Quoted 14 lines

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring) · line 4972

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -2
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
        } else {
-               memset((void *)mqd, 0, sizeof(*mqd));

Since you memset the mpq in gfx_v8_0_mqd_init(), you can also drop the memset in gfx_v8_0_kcq_init_queue().

Done

Quoted 17 lines
Quoted 17 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -1
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return 0;
 }
 
Quoted 7 lines
Quoted 7 lines

--
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#7 lore raw

Re: [PATCH 01/26] drm/amdgpu: refactor MQD/HQD initialization v2

In reply to a message not in the archive
Quoted 816 lines · Andres Rodriguez

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +241 -206
index 185cb31..f67ef58 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +12 -12
index 4e63e52..88b85f7 100644
@@ -46,20 +46,22 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
+
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -1406,38 +1408,38 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 
        return r;
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq)
 {
        amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
        amdgpu_ring_fini(ring);
 }
 
-#define MEC_HPD_SIZE 2048
+#define GFX8_MEC_HPD_SIZE 2048
 
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
 
        /*
         * 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_queue * MEC_HPD_SIZE,
+                                    adev->gfx.mec.num_queue * GFX8_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);
@@ -1452,50 +1454,50 @@ 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 * MEC_HPD_SIZE);
+       memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_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;
 
        amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
 }
 
 static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
        struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-       r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+       r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
                                    &kiq->eop_gpu_addr, (void **)&hpd);
        if (r) {
                dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
                return r;
        }
 
-       memset(hpd, 0, MEC_HPD_SIZE);
+       memset(hpd, 0, GFX8_MEC_HPD_SIZE);
 
        r = amdgpu_bo_reserve(kiq->eop_obj, false);
        if (unlikely(r != 0))
                dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
        amdgpu_bo_kunmap(kiq->eop_obj);
        amdgpu_bo_unreserve(kiq->eop_obj);
 
        return 0;
 }
 
@@ -2148,21 +2150,21 @@ static int gfx_v8_0_sw_init(void *handle)
                        DRM_ERROR("Too many (%d) compute rings!\n", i);
                        break;
                }
                ring = &adev->gfx.compute_ring[i];
                ring->ring_obj = NULL;
                ring->use_doorbell = true;
                ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
                ring->me = 1; /* first MEC */
                ring->pipe = i / 8;
                ring->queue = i % 8;
-               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
                sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
                irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
                /* type-2 packets are deprecated on MEC, use type-3 instead */
                r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
                                     irq_type);
                if (r)
                        return r;
        }
 
        r = gfx_v8_0_kiq_init(adev);
@@ -4747,52 +4749,50 @@ static int gfx_v8_0_kiq_kcq_disable(struct amdgpu_device *adev)
        return r;
 }
 
 static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
        uint32_t tmp;
 
+       /* init the mqd struct */
+       memset(mqd, 0, sizeof(struct vi_mqd));
+
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
 
        eop_base_addr = ring->eop_gpu_addr >> 8;
        mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
        mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
        /* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
        tmp = RREG32(mmCP_HQD_EOP_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-                       (order_base_2(MEC_HPD_SIZE / 4) - 1));
+                       (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
 
        mqd->cp_hqd_eop_control = tmp;
 
        /* enable doorbell? */
        tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
                            CP_HQD_PQ_DOORBELL_CONTROL,
                            DOORBELL_EN,
                            ring->use_doorbell ? 1 : 0);
 
        mqd->cp_hqd_pq_doorbell_control = tmp;
 
-       /* disable the queue if it's active */
-       mqd->cp_hqd_dequeue_request = 0;
-       mqd->cp_hqd_pq_rptr = 0;
-       mqd->cp_hqd_pq_wptr = 0;
-
        /* set the pointer to the MQD */
        mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
        mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
        /* set MQD vmid to 0 */
        tmp = RREG32(mmCP_MQD_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
        mqd->cp_mqd_control = tmp;
 
        /* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
@@ -4854,50 +4854,86 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
        tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4864

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
 
        return 0;
 }
 
-static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
+static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)

I'd prefer to call this gfx_v8_0_deactivate_hqd() since it's operating on an HQD rather than an MQD and generally we use the verb first in the naming.

Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +8 -0
+{
+       int i;
+
+       /* 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))

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4882

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+                               break;
+                       udelay(1);
+               }
+
+               if (i == adev->usec_timeout)
+                       return -ETIMEDOUT;
+
+               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+               WREG32(mmCP_HQD_PQ_RPTR, 0);
+               WREG32(mmCP_HQD_PQ_WPTR, 0);

Maybe move this hunk outside of the loop? Then I think this function could also replace gfx_v8_0_init_hqd() and gfx_v8_0_inactive_hqd(). Also, maybe the request type should be selectable? How about the attached patch?

Alex

Quoted 156 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +37 -30
+       }
+
+       return 0;
+}
+
+static void gfx_v8_0_enable_doorbell(struct amdgpu_device *adev, bool enable)
+{
+       uint32_t tmp;
+
+       if (!enable)
+               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);
+}
+
+static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
-       int j;
 
        /* 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);
 
-       /* disable the queue if it's active */
-       if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-               for (j = 0; j < adev->usec_timeout; j++) {
-                       if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
-                               break;
-                       udelay(1);
-               }
-               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);
-       }
+       /* 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);
 
        /* 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);
@@ -4910,46 +4946,33 @@ static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
        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 */
-       if (ring->use_doorbell) {
-               if ((adev->asic_type == CHIP_CARRIZO) ||
-                               (adev->asic_type == CHIP_FIJI) ||
-                               (adev->asic_type == CHIP_STONEY)) {
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
-                                               AMDGPU_DOORBELL_KIQ << 2);
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-                                               AMDGPU_DOORBELL_MEC_RING7 << 2);
-               }
-       }
        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);
 
        /* set the vmid for the queue */
        WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
 
        WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
        /* activate the queue */
        WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
-       if (ring->use_doorbell)
-               WREG32_FIELD(CP_PQ_STATUS, DOORBELL_ENABLE, 1);
-
        return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
        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);
@@ -4958,29 +4981,32 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
                /* 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;
                amdgpu_ring_clear_ring(ring);
 
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
        } else {
-               memset((void *)mqd, 0, sizeof(*mqd));
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return 0;
 }
 
--

2.9.3

Quoted 4 lines

_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

From 5041d4e1beb65998f660a989db9e23a662a59408 Mon Sep 17 00:00:00 2001
From: Alex Deucher <[email protected]>
Date: Tue, 11 Apr 2017 17:37:01 -0400
Subject: [PATCH] drm/amdgpu/gfx8: unify the HQD deactivation code

This could be used in Andres' priority scheduling patch as well.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 42 +++++++++++++++++------------------
 1 file changed, 20 insertions(+), 22 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +20 -22
index 5cfcb1a..461ad23 100644
@@ -5297,23 +5297,25 @@ static bool gfx_v8_0_check_soft_reset(void *handle)
 	}
 }
 
-static void gfx_v8_0_inactive_hqd(struct amdgpu_device *adev,
-				  struct amdgpu_ring *ring)
+static int gfx_v8_0_deactivate_hqd(struct amdgpu_device *adev, u32 req)
 {
-	int i;
+	int i, r = 0;
 
-	mutex_lock(&adev->srbm_mutex);
-	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 	if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-		WREG32_FIELD(CP_HQD_DEQUEUE_REQUEST, DEQUEUE_REQ, 2);
+		WREG32_FIELD(CP_HQD_DEQUEUE_REQUEST, DEQUEUE_REQ, req);
 		for (i = 0; i < adev->usec_timeout; i++) {
 			if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
 				break;
 			udelay(1);
 		}
+		if (i == adev->usec_timeout)
+			r = -ETIMEDOUT;
 	}
-	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+	WREG32(mmCP_HQD_PQ_RPTR, 0);
+	WREG32(mmCP_HQD_PQ_WPTR, 0);
+
+	return r;
 }
 
 static int gfx_v8_0_pre_soft_reset(void *handle)
@@ -5345,7 +5347,11 @@ static int gfx_v8_0_pre_soft_reset(void *handle)
 		for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 			struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-			gfx_v8_0_inactive_hqd(adev, ring);
+			mutex_lock(&adev->srbm_mutex);
+			vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
+			gfx_v8_0_deactivate_hqd(adev, 2);
+			vi_srbm_select(adev, 0, 0, 0, 0);
+			mutex_unlock(&adev->srbm_mutex);
 		}
 		/* Disable MEC parsing/prefetching */
 		gfx_v8_0_cp_compute_enable(adev, false);
@@ -5416,18 +5422,6 @@ static int gfx_v8_0_soft_reset(void *handle)
 	return 0;
 }
 
-static void gfx_v8_0_init_hqd(struct amdgpu_device *adev,
-			      struct amdgpu_ring *ring)
-{
-	mutex_lock(&adev->srbm_mutex);
-	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-	WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
-	WREG32(mmCP_HQD_PQ_RPTR, 0);
-	WREG32(mmCP_HQD_PQ_WPTR, 0);
-	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
-}
-
 static int gfx_v8_0_post_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -5453,7 +5447,11 @@ static int gfx_v8_0_post_soft_reset(void *handle)
 		for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 			struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-			gfx_v8_0_init_hqd(adev, ring);
+			mutex_lock(&adev->srbm_mutex);
+			vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
+			gfx_v8_0_deactivate_hqd(adev, 2);
+			vi_srbm_select(adev, 0, 0, 0, 0);
+			mutex_unlock(&adev->srbm_mutex);
 		}
 		gfx_v8_0_kiq_resume(adev);
 	}
Signature · 1 line
2.5.5

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): CADnq5_OdNy8hW8=WZouJBTtGjd261E9Boz6zL2L1o-GYegqP8Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org

author Reviewed-by
#9 lore raw

Re: [PATCH 01/26] drm/amdgpu: refactor MQD/HQD initialization v2

Your proposed patch looks good to me. You can add a:

Quoted 1,013 lines · Alex Deucher
Quoted 816 lines · Andres Rodriguez

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +241 -206
index 185cb31..f67ef58 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +12 -12
index 4e63e52..88b85f7 100644
@@ -46,20 +46,22 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
+
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -1406,38 +1408,38 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 
        return r;
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq)
 {
        amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
        amdgpu_ring_fini(ring);
 }
 
-#define MEC_HPD_SIZE 2048
+#define GFX8_MEC_HPD_SIZE 2048
 
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
 
        /*
         * 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_queue * MEC_HPD_SIZE,
+                                    adev->gfx.mec.num_queue * GFX8_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);
@@ -1452,50 +1454,50 @@ 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 * MEC_HPD_SIZE);
+       memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_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;
 
        amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
 }
 
 static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
        struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-       r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+       r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
                                    &kiq->eop_gpu_addr, (void **)&hpd);
        if (r) {
                dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
                return r;
        }
 
-       memset(hpd, 0, MEC_HPD_SIZE);
+       memset(hpd, 0, GFX8_MEC_HPD_SIZE);
 
        r = amdgpu_bo_reserve(kiq->eop_obj, false);
        if (unlikely(r != 0))
                dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
        amdgpu_bo_kunmap(kiq->eop_obj);
        amdgpu_bo_unreserve(kiq->eop_obj);
 
        return 0;
 }
 
@@ -2148,21 +2150,21 @@ static int gfx_v8_0_sw_init(void *handle)
                        DRM_ERROR("Too many (%d) compute rings!\n", i);
                        break;
                }
                ring = &adev->gfx.compute_ring[i];
                ring->ring_obj = NULL;
                ring->use_doorbell = true;
                ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
                ring->me = 1; /* first MEC */
                ring->pipe = i / 8;
                ring->queue = i % 8;
-               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
                sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
                irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
                /* type-2 packets are deprecated on MEC, use type-3 instead */
                r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
                                     irq_type);
                if (r)
                        return r;
        }
 
        r = gfx_v8_0_kiq_init(adev);
@@ -4747,52 +4749,50 @@ static int gfx_v8_0_kiq_kcq_disable(struct amdgpu_device *adev)
        return r;
 }
 
 static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
        uint32_t tmp;
 
+       /* init the mqd struct */
+       memset(mqd, 0, sizeof(struct vi_mqd));
+
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
 
        eop_base_addr = ring->eop_gpu_addr >> 8;
        mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
        mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
        /* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
        tmp = RREG32(mmCP_HQD_EOP_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-                       (order_base_2(MEC_HPD_SIZE / 4) - 1));
+                       (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
 
        mqd->cp_hqd_eop_control = tmp;
 
        /* enable doorbell? */
        tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
                            CP_HQD_PQ_DOORBELL_CONTROL,
                            DOORBELL_EN,
                            ring->use_doorbell ? 1 : 0);
 
        mqd->cp_hqd_pq_doorbell_control = tmp;
 
-       /* disable the queue if it's active */
-       mqd->cp_hqd_dequeue_request = 0;
-       mqd->cp_hqd_pq_rptr = 0;
-       mqd->cp_hqd_pq_wptr = 0;
-
        /* set the pointer to the MQD */
        mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
        mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
        /* set MQD vmid to 0 */
        tmp = RREG32(mmCP_MQD_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
        mqd->cp_mqd_control = tmp;
 
        /* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
@@ -4854,50 +4854,86 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
        tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4864

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
 
        return 0;
 }
 
-static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
+static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)

I'd prefer to call this gfx_v8_0_deactivate_hqd() since it's operating on an HQD rather than an MQD and generally we use the verb first in the naming.

Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +8 -0
+{
+       int i;
+
+       /* 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))

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4882

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+                               break;
+                       udelay(1);
+               }
+
+               if (i == adev->usec_timeout)
+                       return -ETIMEDOUT;
+
+               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+               WREG32(mmCP_HQD_PQ_RPTR, 0);
+               WREG32(mmCP_HQD_PQ_WPTR, 0);

Maybe move this hunk outside of the loop? Then I think this function could also replace gfx_v8_0_init_hqd() and gfx_v8_0_inactive_hqd(). Also, maybe the request type should be selectable? How about the attached patch?

Alex

Quoted 153 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +37 -29
+       }
+
+       return 0;
+}
+
+static void gfx_v8_0_enable_doorbell(struct amdgpu_device *adev, bool enable)
+{
+       uint32_t tmp;
+
+       if (!enable)
+               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);
+}
+
+static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
-       int j;
 
        /* 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);
 
-       /* disable the queue if it's active */
-       if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-               for (j = 0; j < adev->usec_timeout; j++) {
-                       if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
-                               break;
-                       udelay(1);
-               }
-               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);
-       }
+       /* 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);
 
        /* 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);
@@ -4910,46 +4946,33 @@ static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
        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 */
-       if (ring->use_doorbell) {
-               if ((adev->asic_type == CHIP_CARRIZO) ||
-                               (adev->asic_type == CHIP_FIJI) ||
-                               (adev->asic_type == CHIP_STONEY)) {
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
-                                               AMDGPU_DOORBELL_KIQ << 2);
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-                                               AMDGPU_DOORBELL_MEC_RING7 << 2);
-               }
-       }
        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);
 
        /* set the vmid for the queue */
        WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
 
        WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
        /* activate the queue */
        WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
-       if (ring->use_doorbell)
-               WREG32_FIELD(CP_PQ_STATUS, DOORBELL_ENABLE, 1);
-
        return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
        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);
@@ -4958,29 +4981,32 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
                /* 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;
                amdgpu_ring_clear_ring(ring);
 
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
        } else {
-               memset((void *)mqd, 0, sizeof(*mqd));
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return 0;
 }
 
Quoted 7 lines
Quoted 7 lines

--
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#10 lore raw

Re: [PATCH 01/26] drm/amdgpu: refactor MQD/HQD initialization v2

In reply to a message not in the archive
Quoted 857 lines · Alex Deucher
Quoted 816 lines · Andres Rodriguez

The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates.

The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled.

The error handling paths have been updated to deal with the new code structure.

v2: the non-kiq path for gfxv8 was dropped in the rebase

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 447 ++++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 110 +++++----
 2 files changed, 309 insertions(+), 248 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +241 -206
index 185cb31..f67ef58 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");
@@ -2814,40 +2816,38 @@ 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);
@@ -2863,21 +2863,21 @@ 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;
@@ -2938,261 +2938,296 @@ 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 = lower_32_bits(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 = lower_32_bits(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)
 {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +12 -12
index 4e63e52..88b85f7 100644
@@ -46,20 +46,22 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
+
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -1406,38 +1408,38 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 
        return r;
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
                                   struct amdgpu_irq_src *irq)
 {
        amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
        amdgpu_ring_fini(ring);
 }
 
-#define MEC_HPD_SIZE 2048
+#define GFX8_MEC_HPD_SIZE 2048
 
 static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
 
        /*
         * 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_queue * MEC_HPD_SIZE,
+                                    adev->gfx.mec.num_queue * GFX8_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);
@@ -1452,50 +1454,50 @@ 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 * MEC_HPD_SIZE);
+       memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_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;
 
        amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
 }
 
 static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
 {
        int r;
        u32 *hpd;
        struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
-       r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+       r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
                                    &kiq->eop_gpu_addr, (void **)&hpd);
        if (r) {
                dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
                return r;
        }
 
-       memset(hpd, 0, MEC_HPD_SIZE);
+       memset(hpd, 0, GFX8_MEC_HPD_SIZE);
 
        r = amdgpu_bo_reserve(kiq->eop_obj, false);
        if (unlikely(r != 0))
                dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
        amdgpu_bo_kunmap(kiq->eop_obj);
        amdgpu_bo_unreserve(kiq->eop_obj);
 
        return 0;
 }
 
@@ -2148,21 +2150,21 @@ static int gfx_v8_0_sw_init(void *handle)
                        DRM_ERROR("Too many (%d) compute rings!\n", i);
                        break;
                }
                ring = &adev->gfx.compute_ring[i];
                ring->ring_obj = NULL;
                ring->use_doorbell = true;
                ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
                ring->me = 1; /* first MEC */
                ring->pipe = i / 8;
                ring->queue = i % 8;
-               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+               ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
                sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
                irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
                /* type-2 packets are deprecated on MEC, use type-3 instead */
                r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
                                     irq_type);
                if (r)
                        return r;
        }
 
        r = gfx_v8_0_kiq_init(adev);
@@ -4747,52 +4749,50 @@ static int gfx_v8_0_kiq_kcq_disable(struct amdgpu_device *adev)
        return r;
 }
 
 static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
        uint32_t tmp;
 
+       /* init the mqd struct */
+       memset(mqd, 0, sizeof(struct vi_mqd));
+
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
 
        eop_base_addr = ring->eop_gpu_addr >> 8;
        mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
        mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
        /* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
        tmp = RREG32(mmCP_HQD_EOP_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-                       (order_base_2(MEC_HPD_SIZE / 4) - 1));
+                       (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
 
        mqd->cp_hqd_eop_control = tmp;
 
        /* enable doorbell? */
        tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
                            CP_HQD_PQ_DOORBELL_CONTROL,
                            DOORBELL_EN,
                            ring->use_doorbell ? 1 : 0);
 
        mqd->cp_hqd_pq_doorbell_control = tmp;
 
-       /* disable the queue if it's active */
-       mqd->cp_hqd_dequeue_request = 0;
-       mqd->cp_hqd_pq_rptr = 0;
-       mqd->cp_hqd_pq_wptr = 0;
-
        /* set the pointer to the MQD */
        mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
        mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
        /* set MQD vmid to 0 */
        tmp = RREG32(mmCP_MQD_CONTROL);
        tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
        mqd->cp_mqd_control = tmp;
 
        /* set the pointer to the HQD, this is similar CP_RB0_BASE/_HI */
@@ -4854,50 +4854,86 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
        tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4864

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
 
        return 0;
 }
 
-static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
+static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)

I'd prefer to call this gfx_v8_0_deactivate_hqd() since it's operating on an HQD rather than an MQD and generally we use the verb first in the naming.

Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +8 -0
+{
+       int i;
+
+       /* 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))

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) · line 4882

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+                               break;
+                       udelay(1);
+               }
+
+               if (i == adev->usec_timeout)
+                       return -ETIMEDOUT;
+
+               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
+               WREG32(mmCP_HQD_PQ_RPTR, 0);
+               WREG32(mmCP_HQD_PQ_WPTR, 0);

Maybe move this hunk outside of the loop? Then I think this function could also replace gfx_v8_0_init_hqd() and gfx_v8_0_inactive_hqd(). Also, maybe the request type should be selectable? How about the attached patch?

Quoted 3 lines

Alex

Done. Rebased on top of 4.12-wip which includes your patch.

Quoted 153 lines
Quoted 153 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +37 -29
+       }
+
+       return 0;
+}
+
+static void gfx_v8_0_enable_doorbell(struct amdgpu_device *adev, bool enable)
+{
+       uint32_t tmp;
+
+       if (!enable)
+               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);
+}
+
+static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
-       int j;
 
        /* 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);
 
-       /* disable the queue if it's active */
-       if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
-               WREG32(mmCP_HQD_DEQUEUE_REQUEST, 1);
-               for (j = 0; j < adev->usec_timeout; j++) {
-                       if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
-                               break;
-                       udelay(1);
-               }
-               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);
-       }
+       /* 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);
 
        /* 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);
@@ -4910,46 +4946,33 @@ static int gfx_v8_0_kiq_init_register(struct amdgpu_ring *ring)
        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 */
-       if (ring->use_doorbell) {
-               if ((adev->asic_type == CHIP_CARRIZO) ||
-                               (adev->asic_type == CHIP_FIJI) ||
-                               (adev->asic_type == CHIP_STONEY)) {
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
-                                               AMDGPU_DOORBELL_KIQ << 2);
-                       WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-                                               AMDGPU_DOORBELL_MEC_RING7 << 2);
-               }
-       }
        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);
 
        /* set the vmid for the queue */
        WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
 
        WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
        /* activate the queue */
        WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
-       if (ring->use_doorbell)
-               WREG32_FIELD(CP_PQ_STATUS, DOORBELL_ENABLE, 1);
-
        return 0;
 }
 
 static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 {
        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);
@@ -4958,29 +4981,32 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
                /* 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;
                amdgpu_ring_clear_ring(ring);
 
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
        } else {
-               memset((void *)mqd, 0, sizeof(*mqd));
                mutex_lock(&adev->srbm_mutex);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
-               gfx_v8_0_kiq_init_register(ring);
+               gfx_v8_0_mqd_deactivate(adev);
+               gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
+               gfx_v8_0_mqd_commit(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
                mutex_unlock(&adev->srbm_mutex);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return 0;
 }
 
Quoted 7 lines
Quoted 7 lines

--
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#11 lore raw

PATCH 2/26 drm/amdgpu: doorbell registers need only be set once v2

In reply to a message not in the archive

The CP_MEC_DOORBELL_RANGE_* and CP_PQ_STATUS.DOORBELL_ENABLE registers are not HQD specific.

They only need to be set once if at least 1 pipe requested doorbell support.

v2: move doorbell_enable to amdgpu_gfx instead of amdgpu_device

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   | 3 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 +++++-
 2 files changed, 8 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -0
index 15b9675..f8a08d8 100644
@@ -1054,20 +1054,23 @@ struct amdgpu_gfx {
 	const struct amdgpu_gfx_funcs	*funcs;
 
 	/* reset mask */
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
 	bool                            in_reset;
 	/* s3/s4 mask */
 	bool                            in_suspend;
 	/* NGG */
 	struct amdgpu_ngg		ngg;
+
+	/* 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);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +5 -1
index 88b85f7..4c79fb0 100644
@@ -4882,35 +4882,37 @@ 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_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct vi_mqd *mqd = ring->mqd_ptr;
 
 	/* disable wptr polling */
 	WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
@@ -5102,20 +5104,22 @@ static int gfx_v8_0_kiq_resume(struct amdgpu_device *adev)
 	}
 
 done:
 	return r;
 }
 
 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.load_type != AMDGPU_FW_LOAD_SMU) {
 			/* legacy firmware loading */
 			r = gfx_v8_0_cp_gfx_load_microcode(adev);
 			if (r)
 				return r;
 
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-3-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#13 lore raw

Re: [PATCH 02/26] drm/amdgpu: doorbell registers need only be set once v2

Quoted 7 lines · Andres Rodriguez

The CP_MEC_DOORBELL_RANGE_* and CP_PQ_STATUS.DOORBELL_ENABLE registers are not HQD specific.

They only need to be set once if at least 1 pipe requested doorbell support.

v2: move doorbell_enable to amdgpu_gfx instead of amdgpu_device

This patch is no longer necessary with KIQ as we only set the doorbell range and enable bit once.

Alex

Quoted 106 lines
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   | 3 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 +++++-
 2 files changed, 8 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -0
index 15b9675..f8a08d8 100644
@@ -1054,20 +1054,23 @@ struct amdgpu_gfx {
        const struct amdgpu_gfx_funcs   *funcs;
 
        /* reset mask */
        uint32_t                        grbm_soft_reset;
        uint32_t                        srbm_soft_reset;
        bool                            in_reset;
        /* s3/s4 mask */
        bool                            in_suspend;
        /* NGG */
        struct amdgpu_ngg               ngg;
+
+       /* 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);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +5 -2
index 88b85f7..4c79fb0 100644
@@ -4882,35 +4882,37 @@ 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_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
 
        /* disable wptr polling */
        WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
@@ -5102,20 +5104,22 @@ static int gfx_v8_0_kiq_resume(struct amdgpu_device *adev)
        }
 
 done:
        return r;
 }
 
 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.load_type != AMDGPU_FW_LOAD_SMU) {
                        /* legacy firmware loading */
                        r = gfx_v8_0_cp_gfx_load_microcode(adev);
                        if (r)
                                return r;
 
--

2.9.3

Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#14 lore raw

PATCH 3/26 drm/amdgpu: detect timeout error when deactivating hqd

In reply to a message not in the archive

Handle HQD deactivation timeouts instead of ignoring them.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +17 -3
index 4c79fb0..5fb4100 100644
@@ -4966,57 +4966,71 @@ static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 	WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
 	/* activate the queue */
 	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	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;
 		amdgpu_ring_clear_ring(ring);
 
 		mutex_lock(&adev->srbm_mutex);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-		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(ring);
 		vi_srbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 	} else {
 		mutex_lock(&adev->srbm_mutex);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		gfx_v8_0_mqd_init(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(ring);
 		vi_srbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	}
 
-	return 0;
+	return r;
+
+out_unlock:
+	vi_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+	return r;
 }
 
 static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
 	if (!adev->gfx.in_reset && !adev->gfx.in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#15 lore raw

PATCH 4/26 drm/amdgpu: remove duplicate definition of cik_mqd

In reply to a message not in the archive

The gfxv7 contains a slightly different version of cik_mqd called bonaire_mqd. This can introduce subtle bugs if fixes are not applied in both places.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 135 ++++++++++++++--------------------
 1 file changed, 54 insertions(+), 81 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +54 -81
index f67ef58..c5041ab 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"
 
@@ -2910,48 +2911,20 @@ 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);
@@ -2991,162 +2964,162 @@ 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 = lower_32_bits(ring->wptr);
-	mqd->queue_state.cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_wptr = lower_32_bits(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);
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#16 lore raw

PATCH 5/26 drm/amdgpu: unify MQD programming sequence for kfd and amdgpu

In reply to a message not in the archive

Use the same gfx_*_mqd_commit function for kfd and amdgpu codepaths.

This removes the last duplicates of this programming sequence.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 51 ++---------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 49 ++--------------------
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c             | 38 ++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h             |  5 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c             | 51 ++++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h             |  5 +++
 6 files changed, 99 insertions(+), 100 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +4 -47
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;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +4 -45

91 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +36 -2
index c5041ab..4c89ac2 100644
@@ -3061,26 +3061,43 @@ 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 = lower_32_bits(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);
@@ -3090,20 +3107,37 @@ 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;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h +5 -0
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
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +45 -6

144 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h +5 -0
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
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-6-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#18 lore raw

Re: [PATCH 05/26] drm/amdgpu: unify MQD programming sequence for kfd and amdgpu

The amdgpu_amdkfd code you're modifying has changed a lot on the KFD branch. I'm not sure it's worth fixing on the amdgpu branch. We'll largely replace it when we upstream KFD changes.

I spotted an obvious bug in your patch, but it was also broken before.

See inline [FK].

Quoted 160 lines · Andres Rodriguez

Use the same gfx_*_mqd_commit function for kfd and amdgpu codepaths.

This removes the last duplicates of this programming sequence.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 51 ++---------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 49 ++--------------------
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c             | 38 ++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h             |  5 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c             | 51 ++++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h             |  5 +++
 6 files changed, 99 insertions(+), 100 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +4 -47
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;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +1 -8
index 6697612..2ecef3d 100644
@@ -21,20 +21,21 @@
  */
 
 #include <linux/module.h>
 #include <linux/fdtable.h>
 #include <linux/uaccess.h>
 #include <linux/firmware.h>
 #include <drm/drmP.h>
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_ucode.h"
+#include "gfx_v8_0.h"
 #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"
 
@@ -244,67 +245,25 @@ 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 vi_mqd *m;
 	uint32_t shadow_wptr, valid_wptr;
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
 	m = get_mqd(mqd);
 
 	valid_wptr = copy_from_user(&shadow_wptr, wptr, sizeof(shadow_wptr));
-	acquire_queue(kgd, pipe_id, queue_id);
-
-	WREG32(mmCP_MQD_CONTROL, m->cp_mqd_control);
-	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_HQD_VMID, m->cp_hqd_vmid);
-	WREG32(mmCP_HQD_PERSISTENT_STATE, m->cp_hqd_persistent_state);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd) · line 255

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +0 -9
-	WREG32(mmCP_HQD_PIPE_PRIORITY, m->cp_hqd_pipe_priority);
-	WREG32(mmCP_HQD_QUEUE_PRIORITY, m->cp_hqd_queue_priority);
-	WREG32(mmCP_HQD_QUANTUM, m->cp_hqd_quantum);
-	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_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);
-
 	if (valid_wptr > 0)

[FK] I think copy_from_user returns 0 for success. So this condition looks incorrect.

Quoted 19 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +0 -19
-		WREG32(mmCP_HQD_PQ_WPTR, shadow_wptr);
-
-	WREG32(mmCP_HQD_PQ_CONTROL, m->cp_hqd_pq_control);
-	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, m->cp_hqd_pq_doorbell_control);
-
-	WREG32(mmCP_HQD_EOP_BASE_ADDR, m->cp_hqd_eop_base_addr_lo);
-	WREG32(mmCP_HQD_EOP_BASE_ADDR_HI, m->cp_hqd_eop_base_addr_hi);
-	WREG32(mmCP_HQD_EOP_CONTROL, m->cp_hqd_eop_control);
-	WREG32(mmCP_HQD_EOP_RPTR, m->cp_hqd_eop_rptr);
-	WREG32(mmCP_HQD_EOP_WPTR, m->cp_hqd_eop_wptr);
-	WREG32(mmCP_HQD_EOP_EVENTS, m->cp_hqd_eop_done_events);
-
-	WREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_LO, m->cp_hqd_ctx_save_base_addr_lo);
-	WREG32(mmCP_HQD_CTX_SAVE_BASE_ADDR_HI, m->cp_hqd_ctx_save_base_addr_hi);
-	WREG32(mmCP_HQD_CTX_SAVE_CONTROL, m->cp_hqd_ctx_save_control);
-	WREG32(mmCP_HQD_CNTL_STACK_OFFSET, m->cp_hqd_cntl_stack_offset);
-	WREG32(mmCP_HQD_CNTL_STACK_SIZE, m->cp_hqd_cntl_stack_size);
-	WREG32(mmCP_HQD_WG_STATE_OFFSET, m->cp_hqd_wg_state_offset);
-	WREG32(mmCP_HQD_CTX_SAVE_SIZE, m->cp_hqd_ctx_save_size);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd) · line 256

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +1 -9
-
-	WREG32(mmCP_HQD_IB_CONTROL, m->cp_hqd_ib_control);
-
-	WREG32(mmCP_HQD_DEQUEUE_REQUEST, m->cp_hqd_dequeue_request);
-	WREG32(mmCP_HQD_ERROR, m->cp_hqd_error);
-	WREG32(mmCP_HQD_EOP_WPTR_MEM, m->cp_hqd_eop_wptr_mem);
-	WREG32(mmCP_HQD_EOP_DONES, m->cp_hqd_eop_dones);
-
-	WREG32(mmCP_HQD_ACTIVE, m->cp_hqd_active);
+		m->cp_hqd_pq_wptr = valid_wptr;

[FK] This should be shadow_wptr. valid_wptr is the return value from copy_from_user.

Quoted 285 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +2 -0
+	acquire_queue(kgd, pipe_id, queue_id);
+	gfx_v8_0_mqd_commit(adev, mqd);
 	release_queue(kgd);
 
 	return 0;
 }
 
 static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
 {
 	return 0;
 }
 
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +36 -2
index c5041ab..4c89ac2 100644
@@ -3061,26 +3061,43 @@ 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 = lower_32_bits(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);
@@ -3090,20 +3107,37 @@ 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;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h +5 -0
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
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +45 -6
index 5fb4100..35690e1 100644
@@ -4848,20 +4848,40 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 	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;
 
 	tmp = RREG32(mmCP_HQD_PERSISTENT_STATE);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
 	mqd->cp_hqd_persistent_state = tmp;
 
+	/* defaults */
+	mqd->cp_hqd_eop_rptr = RREG32(mmCP_HQD_EOP_RPTR);
+	mqd->cp_hqd_eop_wptr = RREG32(mmCP_HQD_EOP_WPTR);
+	mqd->cp_hqd_pipe_priority = RREG32(mmCP_HQD_PIPE_PRIORITY);
+	mqd->cp_hqd_queue_priority = RREG32(mmCP_HQD_QUEUE_PRIORITY);
+	mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM);
+	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_ctx_save_control = RREG32(mmCP_HQD_CTX_SAVE_CONTROL);
+	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_ib_control = RREG32(mmCP_HQD_IB_CONTROL);
+	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;
 }
 
 static int gfx_v8_0_mqd_deactivate(struct amdgpu_device *adev)
 {
 	int i;
 
@@ -4901,25 +4921,22 @@ static void gfx_v8_0_enable_doorbell(struct amdgpu_device *adev, bool enable)
 		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_ring *ring)
+int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd)
 {
-	struct amdgpu_device *adev = ring->adev;
-	struct vi_mqd *mqd = ring->mqd_ptr;
-
 	/* 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? */
@@ -4952,20 +4969,42 @@ static int gfx_v8_0_mqd_commit(struct amdgpu_ring *ring)
 
 	/* 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);
 
 	WREG32(mmCP_HQD_PERSISTENT_STATE, mqd->cp_hqd_persistent_state);
 
 	/* activate the queue */
 	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	return 0;
@@ -4990,34 +5029,34 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
 		amdgpu_ring_clear_ring(ring);
 
 		mutex_lock(&adev->srbm_mutex);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		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(ring);
+		gfx_v8_0_mqd_commit(adev, mqd);
 		vi_srbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 	} else {
 		mutex_lock(&adev->srbm_mutex);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		gfx_v8_0_mqd_init(ring);
 		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(ring);
+		gfx_v8_0_mqd_commit(adev, mqd);
 		vi_srbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	}
 
 	return r;
 
 out_unlock:
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h +0 -0
index 788cc3a..ec3f11f 100644
@@ -20,11 +20,16 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
 
 #ifndef __GFX_V8_0_H__
 #define __GFX_V8_0_H__

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h line 35

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h +5 -0
 
 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

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#19 lore raw

PATCH 6/26 drm/amdgpu: rename rdev to adev

In reply to a message not in the archive

Rename straggler instances of r(adeon)dev to a(mdgpu)dev

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 70 +++++++++++++++---------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 14 +++---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c      |  2 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      |  2 +-
 4 files changed, 44 insertions(+), 44 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +35 -35
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;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +7 -7
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);
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1 -1
index 4c89ac2..629e3fb 100644
@@ -1833,21 +1833,21 @@ 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;
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
index 35690e1..ad08291 100644
@@ -3802,21 +3802,21 @@ 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;
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#20 lore raw

PATCH 7/26 drm/amdgpu: take ownership of per-pipe configuration v2

In reply to a message not in the archive

Make amdgpu the owner of all per-pipe state of the HQDs.

This change will allow us to split the queues between kfd and amdgpu with a queue granularity instead of pipe granularity.

This patch fixes kfd allocating an HDP_EOP region for its 3 pipes which goes unused.

v2: support for gfx9

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h                |  4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c  | 13 +------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c  |  1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c              | 28 ++++++++++----
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c              | 33 +++++++++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c              | 24 ++++++++----
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 45 ----------------------
 7 files changed, 65 insertions(+), 83 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -2
index f8a08d8..8187587 100644
@@ -890,23 +890,23 @@ struct amdgpu_rlc {
 
 	u32 *register_list_format;
 	u32 *register_restore;
 };
 
 struct amdgpu_mec {
 	struct amdgpu_bo	*hpd_eop_obj;
 	u64			hpd_eop_gpu_addr;
 	struct amdgpu_bo	*mec_fw_obj;
 	u64			mec_fw_gpu_addr;
-	u32 num_pipe;
 	u32 num_mec;
-	u32 num_queue;
+	u32 num_pipe_per_mec;
+	u32 num_queue_per_pipe;
 	void			*mqd_backup[AMDGPU_MAX_COMPUTE_RINGS + 1];
 };
 
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
 
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +1 -12
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;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +1 -0
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;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +21 -7
index 629e3fb..3340012 100644
@@ -2821,34 +2821,48 @@ 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);
@@ -2864,21 +2878,21 @@ 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;
@@ -3202,23 +3216,23 @@ 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;
 		}
 	}
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +24 -9
index ad08291..b34e597 100644
@@ -1414,32 +1414,47 @@ static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
 	amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
 	amdgpu_ring_fini(ring);
 }
 
 #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);
@@ -1454,21 +1469,21 @@ 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;
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +16 -8
index a447b70..5dcc1b0 100644
@@ -476,34 +476,42 @@ static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 
 #define MEC_HPD_SIZE 2048
 
 static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
 {
 	int r;
 	u32 *hpd;
 	const __le32 *fw_data;
 	unsigned fw_size;
 	u32 *fw;
+	size_t mec_hpd_size;
 
 	const struct gfx_firmware_header_v1_0 *mec_hdr;
 
-	/*
-	 * 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_VEGA10:
+		adev->gfx.mec.num_mec = 2;
+		break;
+	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 * MEC_HPD_SIZE;
 
 	if (adev->gfx.mec.hpd_eop_obj == NULL) {
 		r = amdgpu_bo_create(adev,
-				     adev->gfx.mec.num_queue * 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);
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +0 -45

69 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#21 lore raw

PATCH 8/26 drm/radeon: take ownership of pipe initialization

In reply to a message not in the archive

Take ownership of pipe initialization away from KFD.

Note that hpd_eop_gpu_addr was already large enough to accomodate all pipes.

---
 drivers/gpu/drm/radeon/cik.c        | 27 ++++++++++++++-------------
 drivers/gpu/drm/radeon/radeon_kfd.c | 13 +------------
 2 files changed, 15 insertions(+), 25 deletions(-)
drivers/gpu/drm/radeon/cik.c +14 -13
index 53710dd..3d084c2 100644
@@ -4573,37 +4573,38 @@ 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) {
drivers/gpu/drm/radeon/radeon_kfd.c +1 -12
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);
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#22 lore raw

PATCH 9/26 drm/amdgpu: allow split of queues with kfd at queue granularity v3

In reply to a message not in the archive

Previously the queue/pipe split with kfd operated with pipe granularity. This patch allows amdgpu to take ownership of an arbitrary set of queues.

It also consolidates the last few magic numbers in the compute initialization process into mec_init.

v2: support for gfx9
v3: renamed AMDGPU_MAX_QUEUES to AMDGPU_MAX_COMPUTE_QUEUES

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h             |  7 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c           | 83 +++++++++++++++++-------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c           | 81 +++++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c           | 84 +++++++++++++++++++++++--
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h |  1 +
 5 files changed, 212 insertions(+), 44 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +7 -0
index 8187587..b765aca 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_psp.h"
 #include "amdgpu_gds.h"
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
@@ -885,29 +887,34 @@ 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_COMPUTE_QUEUES KGD_MAX_QUEUES
+
 struct amdgpu_mec {
 	struct amdgpu_bo	*hpd_eop_obj;
 	u64			hpd_eop_gpu_addr;
 	struct amdgpu_bo	*mec_fw_obj;
 	u64			mec_fw_gpu_addr;
 	u32 num_mec;
 	u32 num_pipe_per_mec;
 	u32 num_queue_per_pipe;
 	void			*mqd_backup[AMDGPU_MAX_COMPUTE_RINGS + 1];
+
+	/* These are the resources for which amdgpu takes ownership */
+	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
 };
 
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
 
 /*
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +62 -21

214 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +64 -17

217 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +78 -6

207 lines not on this page · raw message

drivers/gpu/drm/amd/include/kgd_kfd_interface.h +1 -0
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,
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-10-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#24 lore raw

Re: [PATCH 09/26] drm/amdgpu: allow split of queues with kfd at queue granularity v3

Comments inline.

Quoted 25 lines · Andres Rodriguez

Previously the queue/pipe split with kfd operated with pipe granularity. This patch allows amdgpu to take ownership of an arbitrary set of queues.

It also consolidates the last few magic numbers in the compute initialization process into mec_init.

v2: support for gfx9
v3: renamed AMDGPU_MAX_QUEUES to AMDGPU_MAX_COMPUTE_QUEUES

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h             |  7 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c           | 83 +++++++++++++++++-------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c           | 81 +++++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c           | 84 +++++++++++++++++++++++--
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h |  1 +
 5 files changed, 212 insertions(+), 44 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +0 -0
index 8187587..b765aca 100644

[snip]

Quoted 41 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +4 -1
index 3340012..55e61a9 100644
@@ -42,21 +42,20 @@
 #include "gca/gfx_7_2_enum.h"
 #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");
@@ -2817,47 +2816,79 @@ 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;
 	}
 }
 
+static void gfx_v7_0_compute_queue_acquire(struct amdgpu_device *adev)
+{
+	int i, queue, pipe, mec;
+

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static void gfx_v7_0_mec_fini(struct amdgpu_device *adev) · line 2839

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +10 -0
+	/* policy for amdgpu compute queue ownership */
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		queue = i % adev->gfx.mec.num_queue_per_pipe;
+		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)

[FK] Shouldn't this be >=?

Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +5 -0
+			break;
+
+		/* policy: amdgpu owns all queues in the first pipe */
+		if (mec == 0 && pipe == 0)
+			set_bit(i, adev->gfx.mec.queue_bitmap);

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static void gfx_v7_0_mec_fini(struct amdgpu_device *adev) · line 2854

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +10 -0
+	}
+
+	/* update the number of active compute rings */
+	adev->gfx.num_compute_rings =
+		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_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);
+	if (adev->gfx.num_compute_rings > AMDGPU_MAX_COMPUTE_RINGS)

[FK] You can write this shorter:

    if (WARN_ON(condition))
        statement;
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +3 -0
+		adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+}
+

[snip]

Quoted 45 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +17 -12
@@ -4769,42 +4800,52 @@ static int gfx_v7_0_sw_init(void *handle)
 		ring = &adev->gfx.gfx_ring[i];
 		ring->ring_obj = NULL;
 		sprintf(ring->name, "gfx");
 		r = amdgpu_ring_init(adev, ring, 1024,
 				     &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_EOP);
 		if (r)
 			return r;
 	}
 
 	/* set up the compute queues */
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+	for (i = 0, ring_id = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; i++) {
 		unsigned irq_type;
 
-		/* max 32 queues per MEC */
-		if ((i >= 32) || (i >= AMDGPU_MAX_COMPUTE_RINGS)) {
-			DRM_ERROR("Too many (%d) compute rings!\n", i);
-			break;
-		}
-		ring = &adev->gfx.compute_ring[i];
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		ring = &adev->gfx.compute_ring[ring_id];
+
+		/* mec0 is me1 */
+		ring->me = ((i / adev->gfx.mec.num_queue_per_pipe)
+				/ adev->gfx.mec.num_pipe_per_mec)
+				+ 1;
+		ring->pipe = (i / adev->gfx.mec.num_queue_per_pipe)
+				% adev->gfx.mec.num_pipe_per_mec;
+		ring->queue = i % adev->gfx.mec.num_queue_per_pipe;
+
 		ring->ring_obj = NULL;
 		ring->use_doorbell = true;
-		ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
-		ring->me = 1; /* first MEC */
-		ring->pipe = i / 8;
-		ring->queue = i % 8;
+		ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + ring_id;
 		sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
-		irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
+
+		irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static int gfx_v7_0_sw_init(void *handle) · line 4841

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +5 -0
+			+ ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
+			+ ring->pipe;
+
 		/* type-2 packets are deprecated on MEC, use type-3 instead */
 		r = amdgpu_ring_init(adev, ring, 1024,
 				     &adev->gfx.eop_irq, irq_type);
 		if (r)
 			return r;
+
+		ring_id++;

[FK] Is there any case where ring_id != i? I'm just wondering what's the purpose of a separate variable for this. I'm guessing it's for a later change in the queue allocation policy ...

Quoted 51 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
 	}
 
 	/* reserve GDS, GWS and OA resource for gfx */
 	r = amdgpu_bo_create_kernel(adev, adev->gds.mem.gfx_partition_size,
 				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GDS,
 				    &adev->gds.gds_gfx_bo, NULL, NULL);
 	if (r)
 		return r;
 
 	r = amdgpu_bo_create_kernel(adev, adev->gds.gws.gfx_partition_size,
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +4 -1
index b34e597..c010b5d 100644
@@ -45,21 +45,20 @@
 #include "gca/gfx_8_0_enum.h"
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
-#define GFX8_NUM_COMPUTE_RINGS 8
 #define GFX8_MEC_HPD_SIZE 2048
 
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)					((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)					((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
@@ -1410,47 +1409,82 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
 }
 static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq)
 {
 	amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
 	amdgpu_ring_fini(ring);
 }
 
 #define GFX8_MEC_HPD_SIZE 2048
 
+static void gfx_v8_0_compute_queue_acquire(struct amdgpu_device *adev)
+{
+	int i, queue, pipe, mec;
+

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev, · line 1432

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+	/* policy for amdgpu compute queue ownership */
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		queue = i % adev->gfx.mec.num_queue_per_pipe;
+		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)

[FK] >=

Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +6 -0
+			break;
+
+		/* policy: amdgpu owns all queues in the first pipe */
+		if (mec == 0 && pipe == 0)
+			set_bit(i, adev->gfx.mec.queue_bitmap);
+	}

[snip]

Quoted 42 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +5 -1
index 5dcc1b0..72eeda3 100644
@@ -31,21 +31,20 @@
 #include "vega10/GC/gc_9_0_offset.h"
 #include "vega10/GC/gc_9_0_sh_mask.h"
 #include "vega10/vega10_enum.h"
 #include "vega10/HDP/hdp_4_0_offset.h"
 
 #include "soc15_common.h"
 #include "clearstate_gfx9.h"
 #include "v9_structs.h"
 
 #define GFX9_NUM_GFX_RINGS     1
-#define GFX9_NUM_COMPUTE_RINGS 8
 #define GFX9_NUM_SE		4
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x2000
 
 MODULE_FIRMWARE("amdgpu/vega10_ce.bin");
 MODULE_FIRMWARE("amdgpu/vega10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/vega10_me.bin");
 MODULE_FIRMWARE("amdgpu/vega10_mec.bin");
 MODULE_FIRMWARE("amdgpu/vega10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/vega10_rlc.bin");
 
@@ -469,45 +468,79 @@ static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 		amdgpu_bo_unpin(adev->gfx.mec.mec_fw_obj);
 		amdgpu_bo_unreserve(adev->gfx.mec.mec_fw_obj);
 
 		amdgpu_bo_unref(&adev->gfx.mec.mec_fw_obj);
 		adev->gfx.mec.mec_fw_obj = NULL;
 	}
 }
 
 #define MEC_HPD_SIZE 2048
 
+static void gfx_v9_0_compute_queue_acquire(struct amdgpu_device *adev)
+{
+	int i, queue, pipe, mec;
+
+	/* policy for amdgpu compute queue ownership */

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c static void gfx_v9_0_mec_fini(struct amdgpu_device *adev) · line 492

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +10 -0
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		queue = i % adev->gfx.mec.num_queue_per_pipe;
+		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;

[FK] >=

Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +6 -0
+
+		/* policy: amdgpu owns all queues in the first pipe */
+		if (mec == 0 && pipe == 0)
+			set_bit(i, adev->gfx.mec.queue_bitmap);
+	}
+

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c static void gfx_v9_0_mec_fini(struct amdgpu_device *adev) · line 508

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +10 -0
+	/* update the number of active compute rings */
+	adev->gfx.num_compute_rings =
+		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_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))
+		adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+}
+

[snip]

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#25 lore raw

PATCH 10/26 drm/amdgpu: teach amdgpu how to enable interrupts for any pipe v3

In reply to a message not in the archive

The current implementation is hardcoded to enable ME1/PIPE0 interrupts only.

This patch allows amdgpu to enable interrupts for any pipe of ME1.

v2: added gfx9 support
v3: use soc15_grbm_select for gfx9

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 48 ++++++++++++---------------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 33 +++++++++++------------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 50 +++++++++++------------------------
 3 files changed, 49 insertions(+), 82 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +17 -31
index 55e61a9..c1c7d52 100644
@@ -5059,56 +5059,42 @@ 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) {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +16 -17
index c010b5d..a1da772 100644
@@ -6806,41 +6806,40 @@ 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 reserved for graphics */
+	if (me < 1 || me > adev->gfx.mec.num_mec) {
+		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);
 
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +16 -34

74 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#26 lore raw

PATCH 11/26 drm/amdkfd: allow split HQD on per-queue granularity v4

In reply to a message not in the archive

Update the KGD to KFD interface to allow sharing pipes with queue granularity instead of pipe granularity.

This allows for more interesting pipe/queue splits.

v2: fix overflow check for res.queue_mask
v3: fix shift overflow when setting res.queue_mask
v4: fix comment in is_pipeline_enabled()

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c         |  22 ++++-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c            |   4 +
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 100 ++++++++++++++-------
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h  |  10 +--
 .../drm/amd/amdkfd/kfd_device_queue_manager_cik.c  |   2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c    |   3 +-
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c |   2 +-
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h    |  17 ++--
 drivers/gpu/drm/radeon/radeon_kfd.c                |  21 ++++-
 9 files changed, 126 insertions(+), 55 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +19 -3
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)
drivers/gpu/drm/amd/amdkfd/kfd_device.c +4 -0
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 *
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +66 -34

270 lines not on this page · raw message

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +4 -6
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;
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c +1 -1
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;
 }
drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +1 -2
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) +
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +1 -1
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;
drivers/gpu/drm/amd/include/kgd_kfd_interface.h +12 -5
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;
 };
drivers/gpu/drm/radeon/radeon_kfd.c +18 -3
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)
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#27 lore raw

PATCH 12/26 drm/amdgpu: remove duplicate magic constants from amdgpu_amdkfd_gfx*.c

In reply to a message not in the archive

This information is already available in adev.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 12 ++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +6 -6
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;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +6 -6
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;
 }
 
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#28 lore raw

PATCH 13/26 drm/amdgpu: allocate queues horizontally across pipes

In reply to a message not in the archive

Pipes provide better concurrency than queues, therefore we want to make sure that apps use queues from different pipes whenever possible.

Optimize for the trivial case where an app will consume rings in order, therefore we don't want adjacent rings to belong to the same pipe.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   | 13 ++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 83 +++++++++++++++++++--------------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 86 +++++++++++++++++++++--------------
 3 files changed, 113 insertions(+), 69 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +13 -0
index b765aca..22c775d 100644
@@ -1778,20 +1778,33 @@ 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))
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +49 -34

127 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +51 -35

131 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#29 lore raw

PATCH 14/26 drm/amdgpu: remove hardcoded queue_mask in PACKET3_SET_RESOURCES v2

In reply to a message not in the archive

The assumption that we are only using the first pipe no longer holds. Instead, calculate the queue_mask from the queue_bitmap.

v2: rename AMDGPU_MAX_QUEUES to AMDGPU_MAX_COMPUTE_QUEUES

---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 20 ++++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 23 +++++++++++++++++++++--
 2 files changed, 39 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +18 -2
index 4827954..8fd1068 100644
@@ -4704,40 +4704,56 @@ static void gfx_v8_0_kiq_setting(struct amdgpu_ring *ring)
 	tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue);
 	WREG32(mmRLC_CP_SCHEDULERS, tmp);
 	tmp |= 0x80;
 	WREG32(mmRLC_CP_SCHEDULERS, tmp);
 }
 
 static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
 	uint32_t scratch, tmp = 0;
+	uint64_t queue_mask = 0;
 	int r, i;
 
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << i);
+	}
+
 	r = amdgpu_gfx_scratch_get(adev, &scratch);
 	if (r) {
 		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
 
 	r = amdgpu_ring_alloc(kiq_ring, (8 * adev->gfx.num_compute_rings) + 11);
 	if (r) {
 		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
 		amdgpu_gfx_scratch_free(adev, scratch);
 		return r;
 	}
 	/* set resources */
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
 	amdgpu_ring_write(kiq_ring, 0);	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(kiq_ring, 0x000000FF);	/* queue mask lo */
-	amdgpu_ring_write(kiq_ring, 0);	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
 	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 		uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
 		uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
 
 		/* map queues */
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +21 -2
index 2061710..772311c 100644
@@ -1906,26 +1906,45 @@ static void gfx_v9_0_kiq_setting(struct amdgpu_ring *ring)
 	tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
 	tmp &= 0xffffff00;
 	tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue);
 	WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), tmp);
 	tmp |= 0x80;
 	WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), tmp);
 }
 
 static void gfx_v9_0_kiq_enable(struct amdgpu_ring *ring)
 {
+	int i;
+	struct amdgpu_device *adev = ring->adev;
+	uint64_t queue_mask = 0;
+
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << i);
+	}
+
 	amdgpu_ring_alloc(ring, 8);
 	/* set resources */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_RESOURCES, 6));
 	amdgpu_ring_write(ring, 0);	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(ring, 0x000000FF);	/* queue mask lo */
-	amdgpu_ring_write(ring, 0);	/* queue mask hi */
+	amdgpu_ring_write(ring, lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(ring, upper_32_bits(queue_mask));	/* queue mask hi */
 	amdgpu_ring_write(ring, 0);	/* gws mask lo */
 	amdgpu_ring_write(ring, 0);	/* gws mask hi */
 	amdgpu_ring_write(ring, 0);	/* oac mask */
 	amdgpu_ring_write(ring, 0);	/* gds heap base:0, gds heap size:0 */
 	amdgpu_ring_commit(ring);
 	udelay(50);
 }
 
 static void gfx_v9_0_map_queue_enable(struct amdgpu_ring *kiq_ring,
 				   struct amdgpu_ring *ring)
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#30 lore raw

PATCH 15/26 drm/amdgpu: avoid KIQ clashing with compute or KFD queues

In reply to a message not in the archive

Instead of picking an arbitrary queue for KIQ, search for one according to policy. The queue must be unused.

Also report the KIQ as an unavailable resource to KFD.

In testing I ran into KCQ initialization issues when using pipes 2/3 of MEC2 for the KIQ. Therefore the policy disallows grabbing one of these.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 23 +++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c |  8 ++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      | 43 ++++++++++++++++++++++++------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c      | 42 ++++++++++++++++++++++++-----
 4 files changed, 98 insertions(+), 18 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +20 -3
index 22c775d..6fc0e70 100644
@@ -1778,31 +1778,48 @@ 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)
+static inline int amdgpu_queue_to_bit(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);
+	return bit;
+}
+
+static inline void amdgpu_bit_to_queue(struct amdgpu_device *adev, int bit,
+				       int *mec, int *pipe, int *queue)
+{
+	*queue = bit % adev->gfx.mec.num_queue_per_pipe;
+	*pipe = (bit / adev->gfx.mec.num_queue_per_pipe)
+		% adev->gfx.mec.num_pipe_per_mec;
+	*mec = (bit / adev->gfx.mec.num_queue_per_pipe)
+	       / adev->gfx.mec.num_pipe_per_mec;
+
+}
+static inline bool amdgpu_is_mec_queue_enabled(struct amdgpu_device *adev,
+					       int mec, int pipe, int queue)
+{
+	return test_bit(amdgpu_queue_to_bit(adev, mec, pipe, queue),
+			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))
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +8 -0
index 8fc5aa3..fe214b5 100644
@@ -104,20 +104,28 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.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);
 
+		/* remove the KIQ bit as well */
+		if (adev->gfx.kiq.ring.ready)
+			clear_bit(amdgpu_queue_to_bit(adev,
+						      adev->gfx.kiq.ring.me + 1,
+						      adev->gfx.kiq.ring.pipe,
+						      adev->gfx.kiq.ring.queue),
+				  gpu_resources.queue_bitmap);
+
 		/* 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,
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +35 -8

79 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +35 -7

77 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-16-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#32 lore raw

Re: [PATCH 15/26] drm/amdgpu: avoid KIQ clashing with compute or KFD queues

See comment inline [FK].

Quoted 15 lines · Andres Rodriguez

Instead of picking an arbitrary queue for KIQ, search for one according to policy. The queue must be unused.

Also report the KIQ as an unavailable resource to KFD.

In testing I ran into KCQ initialization issues when using pipes 2/3 of MEC2 for the KIQ. Therefore the policy disallows grabbing one of these.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 23 +++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c |  8 ++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      | 43 ++++++++++++++++++++++++------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c      | 42 ++++++++++++++++++++++++-----
 4 files changed, 98 insertions(+), 18 deletions(-)

[snip]

Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +0 -0
@@ -104,20 +104,28 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
 			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
 		};
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) · line 117

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +4 -0
 		/* 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);
 
+		/* remove the KIQ bit as well */
+		if (adev->gfx.kiq.ring.ready)
+			clear_bit(amdgpu_queue_to_bit(adev,
+						      adev->gfx.kiq.ring.me + 1,

[FK] Shouldn't this be adev->gfx.kiq.ring.me - 1?

Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +4 -0
+						      adev->gfx.kiq.ring.pipe,
+						      adev->gfx.kiq.ring.queue),
+				  gpu_resources.queue_bitmap);
+

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) · line 131

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +0 -0
 		/* 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,

[snip]

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#33 lore raw

PATCH 16/26 drm/amdgpu: new queue policy, take first 2 queues of each pipe

In reply to a message not in the archive

Instead of taking the first pipe and giving the rest to kfd, take the first 2 queues of each pipe.

Effectively, amdgpu and amdkfd own the same number of queues. But because the queues are spread over multiple pipes the hardware will be able to better handle concurrent compute workloads.

amdgpu goes from 1 pipe to 4 pipes, i.e. from 1 compute threads to 4 amdkfd goes from 3 pipe to 4 pipes, i.e. from 3 compute threads to 4

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1 -1
index 5a8ebae..c0cfcb9 100644
@@ -2833,21 +2833,21 @@ 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_COMPUTE_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);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
index 70119c5..f0c1a3f 100644
@@ -1453,21 +1453,21 @@ 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_COMPUTE_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))
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-17-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#35 lore raw

Re: [PATCH 16/26] drm/amdgpu: new queue policy, take first 2 queues of each pipe

What about GFX9?

See one more comment inline [FK].

Quoted 23 lines · Andres Rodriguez

Instead of taking the first pipe and giving the rest to kfd, take the first 2 queues of each pipe.

Effectively, amdgpu and amdkfd own the same number of queues. But because the queues are spread over multiple pipes the hardware will be able to better handle concurrent compute workloads.

amdgpu goes from 1 pipe to 4 pipes, i.e. from 1 compute threads to 4 amdkfd goes from 3 pipe to 4 pipes, i.e. from 3 compute threads to 4

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
index 5a8ebae..c0cfcb9 100644

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static void gfx_v7_0_compute_queue_acquire(struct amdgpu_device *adev) · line 2842

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
@@ -2833,21 +2833,21 @@ 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 */

[FK] The comments needs to be updated (same for GFX8 below).

Quoted 29 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1 -1
-		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_COMPUTE_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);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
index 70119c5..f0c1a3f 100644
@@ -1453,21 +1453,21 @@ 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)

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static void gfx_v8_0_compute_queue_acquire(struct amdgpu_device *adev) · line 1473

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0 -0
 			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_COMPUTE_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))

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): de2e972f-df8c-f3d2-1bc0-7336be3e67a8-5C7GfCeVMHo@public.gmane.org

#37 lore raw

Re: [PATCH 16/26] drm/amdgpu: new queue policy, take first 2 queues of each pipe

Quoted 1 line · Felix Kuehling

What about GFX9?

I don't have a gfx9 card to test with yet.

When changing the queue policy for gfx7/8 I found a lot of places in the code that had the assumption that amdgpu would only be using the same pipe. I'm pretty sure there is probably something on the gfx9 code that I've missed and will blow up with the queue policy change. So I don't really want to send out this change without testing it.

If someone wants to create a similar patch for gfx9 and test it that should be simple.

Or... if you could send me a vega board... ;)

Regards,
Andres

Quoted 73 lines

See one more comment inline [FK].

Quoted 23 lines · Andres Rodriguez

Instead of taking the first pipe and giving the rest to kfd, take the first 2 queues of each pipe.

Effectively, amdgpu and amdkfd own the same number of queues. But because the queues are spread over multiple pipes the hardware will be able to better handle concurrent compute workloads.

amdgpu goes from 1 pipe to 4 pipes, i.e. from 1 compute threads to 4 amdkfd goes from 3 pipe to 4 pipes, i.e. from 3 compute threads to 4

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
index 5a8ebae..c0cfcb9 100644

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static void gfx_v7_0_compute_queue_acquire(struct amdgpu_device *adev) · line 2842

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0 -0
@@ -2833,21 +2833,21 @@ 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 */

[FK] The comments needs to be updated (same for GFX8 below).

Quoted 32 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1 -1
-		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_COMPUTE_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);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
index 70119c5..f0c1a3f 100644
@@ -1453,21 +1453,21 @@ 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);
 	}
 
Quoted 8 lines

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static void gfx_v8_0_compute_queue_acquire(struct amdgpu_device *adev) · line 1473

Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0 -0
 	/* update the number of active compute rings */
 	adev->gfx.num_compute_rings =
 		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_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))

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#38 lore raw

PATCH 17/26 drm/amdgpu: untie user ring ids from kernel ring ids v5

In reply to a message not in the archive

Add amdgpu_queue_mgr, a mechanism that allows disjointing usermode's ring ids from the kernel's ring ids.

The queue manager maintains a per-file descriptor map of user ring ids to amdgpu_ring pointers. Once a map is created it is permanent (this is required to maintain FIFO execution guarantees for a context's ring).

Different queue map policies can be configured for each HW IP. Currently all HW IPs use the identity mapper, i.e. kernel ring id is equal to the user ring id.

The purpose of this mechanism is to distribute the load across multiple queues more effectively for HW IPs that support multiple rings. Userspace clients are unable to check whether a specific resource is in use by a different client. Therefore, it is up to the kernel driver to make the optimal choice.

v2: remove amdgpu_queue_mapper_funcs
v3: made amdgpu_queue_mgr per context instead of per-fd
v4: add context_put on error paths
v5: moved prototypes to amdgpu_queue_mgr.h

---
 drivers/gpu/drm/amd/amdgpu/Makefile           |   3 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu.h           |   8 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c        | 117 +++----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c       |   6 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_defs.h      |  29 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c | 231 ++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.h |  51 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c      |  45 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h      |   2 +
 9 files changed, 395 insertions(+), 97 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_defs.h
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.h
drivers/gpu/drm/amd/amdgpu/Makefile +2 -1
index 660786a..dd48eb2 100644
@@ -17,21 +17,22 @@ amdgpu-y := amdgpu_drv.o
 amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_atombios.o atombios_crtc.o amdgpu_connectors.o \
 	atom.o amdgpu_fence.o amdgpu_ttm.o amdgpu_object.o amdgpu_gart.o \
 	amdgpu_encoders.o amdgpu_display.o amdgpu_i2c.o \
 	amdgpu_fb.o amdgpu_gem.o amdgpu_ring.o \
 	amdgpu_cs.o amdgpu_bios.o amdgpu_benchmark.o amdgpu_test.o \
 	amdgpu_pm.o atombios_dp.o amdgpu_afmt.o amdgpu_trace_points.o \
 	atombios_encoders.o amdgpu_sa.o atombios_i2c.o \
 	amdgpu_prime.o amdgpu_vm.o amdgpu_ib.o amdgpu_pll.o \
 	amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
-	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o
+	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
+	amdgpu_queue_mgr.o
 
 # add asic specific block
 amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
 	ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o \
 	amdgpu_amdkfd_gfx_v7.o
 
 amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o si_dpm.o si_smc.o
 
 amdgpu-y += \
 	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o mxgpu_ai.o
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -5
index 6fc0e70..ca96ab3 100644
@@ -42,29 +42,31 @@
 #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_defs.h"
 #include "amdgpu_mode.h"
 #include "amdgpu_ih.h"
 #include "amdgpu_irq.h"
 #include "amdgpu_ucode.h"
 #include "amdgpu_ttm.h"
 #include "amdgpu_psp.h"
 #include "amdgpu_gds.h"
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
+#include "amdgpu_queue_mgr.h"
 #include "amdgpu_vm.h"
 #include "amd_powerplay.h"
 #include "amdgpu_dpm.h"
 #include "amdgpu_acp.h"
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
 
 #include "gpu_scheduler.h"
 #include "amdgpu_virt.h"
 
@@ -200,22 +202,20 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
 				  enum amd_clockgating_state state);
 int amdgpu_set_powergating_state(struct amdgpu_device *adev,
 				  enum amd_ip_block_type block_type,
 				  enum amd_powergating_state state);
 void amdgpu_get_clockgating_state(struct amdgpu_device *adev, u32 *flags);
 int amdgpu_wait_for_idle(struct amdgpu_device *adev,
 			 enum amd_ip_block_type block_type);
 bool amdgpu_is_idle(struct amdgpu_device *adev,
 		    enum amd_ip_block_type block_type);
 
-#define AMDGPU_MAX_IP_NUM 16
-
 struct amdgpu_ip_block_status {
 	bool valid;
 	bool sw;
 	bool hw;
 	bool late_initialized;
 	bool hang;
 };
 
 struct amdgpu_ip_block_version {
 	const enum amd_ip_block_type type;
@@ -778,20 +778,21 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 
 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;
@@ -1882,23 +1883,20 @@ static inline bool amdgpu_is_mec_queue_enabled(struct amdgpu_device *adev,
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
 /* 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);
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +26 -91

229 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +6 -0
index cf05006..b38edaa 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;
 
drivers/gpu/drm/amd/amdgpu/amdgpu_defs.h new file +29 -0
new file mode 100644
index 0000000..f5ffe10
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2017 Valve Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_DEFS_H__
+#define __AMDGPU_DEFS_H__
+
+#define AMDGPU_MAX_IP_NUM 16
+
+#endif
drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c new file +231 -0

231 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.h new file +51 -0

51 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +45 -0

65 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +2 -0
index 63e5639..cf411f7 100644
@@ -176,20 +176,22 @@ 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);
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#39 lore raw

PATCH 18/26 drm/amdgpu: implement lru amdgpu_queue_mgr policy for compute v4

In reply to a message not in the archive

Use an LRU policy to map usermode rings to HW compute queues.

Most compute clients use one queue, and usually the first queue available. This results in poor pipe/queue work distribution when multiple compute apps are running. In most cases pipe 0 queue 0 is the only queue that gets used.

In order to better distribute work across multiple HW queues, we adopt a policy to map the usermode ring ids to the LRU HW queue.

This fixes a large majority of multi-app compute workloads sharing the same HW queue, even though 7 other queues are available.

v2: use ring->funcs->type instead of ring->hw_ip
v3: remove amdgpu_queue_mapper_funcs
v4: change ring_lru_list_lock to spinlock, grab only once in lru_get()

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h           |  3 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    |  3 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c | 38 +++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c      | 63 +++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h      |  4 ++
 5 files changed, 110 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -0
index ca96ab3..4f54846 100644
@@ -1607,20 +1607,23 @@ struct amdgpu_device {
 	struct kfd_dev          *kfd;
 
 	struct amdgpu_virt	virt;
 
 	/* link all shadow bo */
 	struct list_head                shadow_list;
 	struct mutex                    shadow_list_lock;
 	/* link all gtt */
 	spinlock_t			gtt_list_lock;
 	struct list_head                gtt_list;
+	/* keep an lru list of rings by HW IP */
+	struct list_head		ring_lru_list;
+	spinlock_t			ring_lru_list_lock;
 
 	/* record hw reset is performed */
 	bool has_hw_reset;
 
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
 {
 	return container_of(bdev, struct amdgpu_device, mman.bdev);
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3 -0
index 82f863a..0bfc6c6 100644
@@ -1881,20 +1881,23 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->gc_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 	spin_lock_init(&adev->mm_stats.lock);
 
 	INIT_LIST_HEAD(&adev->shadow_list);
 	mutex_init(&adev->shadow_list_lock);
 
 	INIT_LIST_HEAD(&adev->gtt_list);
 	spin_lock_init(&adev->gtt_list_lock);
 
+	INIT_LIST_HEAD(&adev->ring_lru_list);
+	spin_lock_init(&adev->ring_lru_list_lock);
+
 	if (adev->asic_type >= CHIP_BONAIRE) {
 		adev->rmmio_base = pci_resource_start(adev->pdev, 5);
 		adev->rmmio_size = pci_resource_len(adev->pdev, 5);
 	} else {
 		adev->rmmio_base = pci_resource_start(adev->pdev, 2);
 		adev->rmmio_size = pci_resource_len(adev->pdev, 2);
 	}
 
 	adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
 	if (adev->rmmio == NULL) {
drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c +37 -1
index 33ad810..926da09 100644
@@ -85,20 +85,54 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 		break;
 	default:
 		*out_ring = NULL;
 		DRM_ERROR("unknown HW IP type: %d\n", mapper->hw_ip);
 		return -EINVAL;
 	}
 
 	return amdgpu_update_cached_map(mapper, ring, *out_ring);
 }
 
+static enum amdgpu_ring_type amdgpu_hw_ip_to_ring_type(int hw_ip)
+{
+	switch (hw_ip) {
+	case AMDGPU_HW_IP_GFX:
+		return AMDGPU_RING_TYPE_GFX;
+	case AMDGPU_HW_IP_COMPUTE:
+		return AMDGPU_RING_TYPE_COMPUTE;
+	case AMDGPU_HW_IP_DMA:
+		return AMDGPU_RING_TYPE_SDMA;
+	case AMDGPU_HW_IP_UVD:
+		return AMDGPU_RING_TYPE_UVD;
+	case AMDGPU_HW_IP_VCE:
+		return AMDGPU_RING_TYPE_VCE;
+	default:
+		DRM_ERROR("Invalid HW IP specified %d\n", hw_ip);
+		return -1;
+	}
+}
+
+static int amdgpu_lru_map(struct amdgpu_device *adev,
+			  struct amdgpu_queue_mapper *mapper,
+			  int user_ring,
+			  struct amdgpu_ring **out_ring)
+{
+	int r;
+	int ring_type = amdgpu_hw_ip_to_ring_type(mapper->hw_ip);
+
+	r = amdgpu_ring_lru_get(adev, ring_type, out_ring);
+	if (r)
+		return r;
+
+	return amdgpu_update_cached_map(mapper, user_ring, *out_ring);
+}
+
 /**
  * amdgpu_queue_mgr_init - init an amdgpu_queue_mgr struct
  *
  * @adev: amdgpu_device pointer
  * @mgr: amdgpu_queue_mgr structure holding queue information
  *
  * Initialize the the selected @mgr (all asics).
  *
  * Returns 0 on success, error on failure.
  */
@@ -206,26 +240,28 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 
 	*out_ring = amdgpu_get_cached_map(mapper, ring);
 	if (*out_ring) {
 		/* cache hit */
 		r = 0;
 		goto out_unlock;
 	}
 
 	switch (mapper->hw_ip) {
 	case AMDGPU_HW_IP_GFX:
-	case AMDGPU_HW_IP_COMPUTE:
 	case AMDGPU_HW_IP_DMA:
 	case AMDGPU_HW_IP_UVD:
 	case AMDGPU_HW_IP_VCE:
 		r = amdgpu_identity_map(adev, mapper, ring, out_ring);
 		break;
+	case AMDGPU_HW_IP_COMPUTE:
+		r = amdgpu_lru_map(adev, mapper, ring, out_ring);
+		break;
 	default:
 		*out_ring = NULL;
 		r = -EINVAL;
 		DRM_ERROR("unknown HW IP type: %d\n", mapper->hw_ip);
 	}
 
 out_unlock:
 	mutex_unlock(&mapper->lock);
 	return r;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +63 -0

123 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +4 -0
index cf411f7..41ab767 100644
@@ -141,20 +141,21 @@ struct amdgpu_ring_funcs {
 	void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
 	void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg);
 	void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
 };
 
 struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
 	struct amd_gpu_scheduler	sched;
+	struct list_head		lru_list;
 
 	struct amdgpu_bo	*ring_obj;
 	volatile uint32_t	*ring;
 	unsigned		rptr_offs;
 	u64			wptr;
 	u64			wptr_old;
 	unsigned		ring_size;
 	unsigned		max_dw;
 	int			count_dw;
 	uint64_t		gpu_addr;
@@ -187,19 +188,22 @@ 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);
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int hw_ip,
+			struct amdgpu_ring **ring);
+void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {
 	int i = 0;
 	while (i <= ring->buf_mask)
 		ring->ring[i++] = ring->funcs->nop;
 
 }
 
 #endif
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#40 lore raw

PATCH 19/26 drm/amdgpu: add parameter to allocate high priority contexts v7

In reply to a message not in the archive

Add a new context creation parameter to express a global context priority.

Contexts allocated with AMDGPU_CTX_PRIORITY_HIGH will receive higher priority to schedule their work than AMDGPU_CTX_PRIORITY_NORMAL (default) contexts.

v2: Instead of using flags, repurpose __pad
v3: Swap enum values of _NORMAL _HIGH for backwards compatibility
v4: Validate usermode priority and store it
v5: Move priority validation into amdgpu_ctx_ioctl(), headline reword
v6: add UAPI note regarding priorities requiring CAP_SYS_ADMIN
v7: remove ctx->priority

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c       | 36 ++++++++++++++++++++++++---
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.h |  1 +
 include/uapi/drm/amdgpu_drm.h                 |  8 +++++-
 3 files changed, 40 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +32 -4
index b38edaa..9edcf7f 100644
@@ -18,25 +18,33 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: monk liu <[email protected]>
  */
 
 #include <drm/drmP.h>
 #include "amdgpu.h"
 
-static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
+static int amdgpu_ctx_init(struct amdgpu_device *adev,
+			   enum amd_sched_priority priority,
+			   struct amdgpu_ctx *ctx)
 {
 	unsigned i, j;
 	int r;
 
+	if (priority < 0 || priority >= AMD_SCHED_MAX_PRIORITY)
+		return -EINVAL;
+
+	if (priority == AMD_SCHED_PRIORITY_HIGH && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->adev = adev;
 	kref_init(&ctx->refcount);
 	spin_lock_init(&ctx->ring_lock);
 	ctx->fences = kcalloc(amdgpu_sched_jobs * AMDGPU_MAX_RINGS,
 			      sizeof(struct dma_fence*), GFP_KERNEL);
 	if (!ctx->fences)
 		return -ENOMEM;
 
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -44,21 +52,21 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
 		ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
 	}
 
 	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
 
 	/* create context entity for each ring */
 	for (i = 0; i < adev->num_rings; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 		struct amd_sched_rq *rq;
 
-		rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
+		rq = &ring->sched.sched_rq[priority];
 		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;
 
@@ -89,39 +97,41 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 
 	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,
+			    enum amd_sched_priority priority,
 			    uint32_t *id)
 {
 	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
 	struct amdgpu_ctx *ctx;
 	int r;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
 	mutex_lock(&mgr->lock);
 	r = idr_alloc(&mgr->ctx_handles, ctx, 1, 0, GFP_KERNEL);
 	if (r < 0) {
 		mutex_unlock(&mgr->lock);
 		kfree(ctx);
 		return r;
 	}
+
 	*id = (uint32_t)r;
-	r = amdgpu_ctx_init(adev, ctx);
+	r = amdgpu_ctx_init(adev, priority, ctx);
 	if (r) {
 		idr_remove(&mgr->ctx_handles, *id);
 		*id = 0;
 		kfree(ctx);
 	}
 	mutex_unlock(&mgr->lock);
 	return r;
 }
 
 static void amdgpu_ctx_do_release(struct kref *ref)
@@ -177,36 +187,54 @@ static int amdgpu_ctx_query(struct amdgpu_device *adev,
 	if (ctx->reset_counter == reset_counter)
 		out->state.reset_status = AMDGPU_CTX_NO_RESET;
 	else
 		out->state.reset_status = AMDGPU_CTX_UNKNOWN_RESET;
 	ctx->reset_counter = reset_counter;
 
 	mutex_unlock(&mgr->lock);
 	return 0;
 }
 
+static enum amd_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+{
+	switch (amdgpu_priority) {
+	case AMDGPU_CTX_PRIORITY_HIGH:
+		return AMD_SCHED_PRIORITY_HIGH;
+	case AMDGPU_CTX_PRIORITY_NORMAL:
+		return AMD_SCHED_PRIORITY_NORMAL;
+	default:
+		WARN(1, "Invalid context priority %d\n", amdgpu_priority);
+		return AMD_SCHED_PRIORITY_NORMAL;
+	}
+}
+
 int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *filp)
 {
 	int r;
 	uint32_t id;
+	enum amd_sched_priority priority;
 
 	union drm_amdgpu_ctx *args = data;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 
 	r = 0;
 	id = args->in.ctx_id;
+	priority = amdgpu_to_sched_priority(args->in.priority);
+
+	if (priority >= AMD_SCHED_MAX_PRIORITY)
+		return -EINVAL;
 
 	switch (args->in.op) {
 	case AMDGPU_CTX_OP_ALLOC_CTX:
-		r = amdgpu_ctx_alloc(adev, fpriv, &id);
+		r = amdgpu_ctx_alloc(adev, fpriv, priority, &id);
 		args->out.alloc.ctx_id = id;
 		break;
 	case AMDGPU_CTX_OP_FREE_CTX:
 		r = amdgpu_ctx_free(fpriv, id);
 		break;
 	case AMDGPU_CTX_OP_QUERY_STATE:
 		r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
 		break;
 	default:
 		return -EINVAL;
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +1 -0
index 0255c7f..e266e1e 100644
@@ -103,20 +103,21 @@ static inline struct amd_sched_fence *to_amd_sched_fence(struct dma_fence *f)
 struct amd_sched_backend_ops {
 	struct dma_fence *(*dependency)(struct amd_sched_job *sched_job);
 	struct dma_fence *(*run_job)(struct amd_sched_job *sched_job);
 	void (*timedout_job)(struct amd_sched_job *sched_job);
 	void (*free_job)(struct amd_sched_job *sched_job);
 };
 
 enum amd_sched_priority {
 	AMD_SCHED_PRIORITY_MIN,
 	AMD_SCHED_PRIORITY_NORMAL = AMD_SCHED_PRIORITY_MIN,
+	AMD_SCHED_PRIORITY_HIGH,
 	AMD_SCHED_PRIORITY_KERNEL,
 	AMD_SCHED_PRIORITY_MAX
 };
 
 /**
  * One scheduler is implemented for each hardware ring
 */
 struct amd_gpu_scheduler {
 	const struct amd_sched_backend_ops	*ops;
 	uint32_t			hw_submission_limit;
include/uapi/drm/amdgpu_drm.h +7 -1
index 516a9f2..bacdd73 100644
@@ -153,27 +153,33 @@ union drm_amdgpu_bo_list {
 
 /* GPU reset status */
 #define AMDGPU_CTX_NO_RESET		0
 /* this the context caused it */
 #define AMDGPU_CTX_GUILTY_RESET		1
 /* some other context caused it */
 #define AMDGPU_CTX_INNOCENT_RESET	2
 /* unknown cause */
 #define AMDGPU_CTX_UNKNOWN_RESET	3
 
+/* Context priority level */
+#define AMDGPU_CTX_PRIORITY_NORMAL	0
+/* Selecting a priority above NORMAL requires CAP_SYS_ADMIN */
+#define AMDGPU_CTX_PRIORITY_HIGH	1
+#define AMDGPU_CTX_PRIORITY_NUM		2
+
 struct drm_amdgpu_ctx_in {
 	/** AMDGPU_CTX_OP_* */
 	__u32	op;
 	/** For future use, no flags defined so far */
 	__u32	flags;
 	__u32	ctx_id;
-	__u32	_pad;
+	__u32	priority;
 };
 
 union drm_amdgpu_ctx_out {
 		struct {
 			__u32	ctx_id;
 			__u32	_pad;
 		} alloc;
 
 		struct {
 			/** For future use, no flags defined so far */
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#41 lore raw

PATCH 20/26 drm/amdgpu: add framework for HW specific priority settings v6

In reply to a message not in the archive

Add an initial framework for changing the HW priorities of rings. The framework allows requesting priority changes for the lifetime of an amdgpu_job. After the job completes the priority will decay to the next lowest priority for which a request is still valid.

A new ring function set_priority() can now be populated to take care of the HW specific programming sequence for priority changes.

v2: set priority before emitting IB, and take a ref on amdgpu_job
v3: use AMD_SCHED_PRIORITY_* instead of AMDGPU_CTX_PRIORITY_*
v4: plug amdgpu_ring_restore_priority_cb into amdgpu_job_free_cb
v5: use atomic for tracking job priorities instead of last_job
v6: rename amdgpu_ring_priority_[get/put]() and align parameters

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c       |  4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c       |  7 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c      | 78 ++++++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h      | 15 ++++++
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.h |  7 +++
 5 files changed, 108 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +2 -2
index 9edcf7f..56a2d27 100644
@@ -25,21 +25,21 @@
 #include <drm/drmP.h>
 #include "amdgpu.h"
 
 static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			   enum amd_sched_priority priority,
 			   struct amdgpu_ctx *ctx)
 {
 	unsigned i, j;
 	int r;
 
-	if (priority < 0 || priority >= AMD_SCHED_MAX_PRIORITY)
+	if (priority < 0 || priority >= AMD_SCHED_PRIORITY_MAX)
 		return -EINVAL;
 
 	if (priority == AMD_SCHED_PRIORITY_HIGH && !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->adev = adev;
 	kref_init(&ctx->refcount);
 	spin_lock_init(&ctx->ring_lock);
 	ctx->fences = kcalloc(amdgpu_sched_jobs * AMDGPU_MAX_RINGS,
@@ -215,21 +215,21 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 	enum amd_sched_priority priority;
 
 	union drm_amdgpu_ctx *args = data;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 
 	r = 0;
 	id = args->in.ctx_id;
 	priority = amdgpu_to_sched_priority(args->in.priority);
 
-	if (priority >= AMD_SCHED_MAX_PRIORITY)
+	if (priority >= AMD_SCHED_PRIORITY_MAX)
 		return -EINVAL;
 
 	switch (args->in.op) {
 	case AMDGPU_CTX_OP_ALLOC_CTX:
 		r = amdgpu_ctx_alloc(adev, fpriv, priority, &id);
 		args->out.alloc.ctx_id = id;
 		break;
 	case AMDGPU_CTX_OP_FREE_CTX:
 		r = amdgpu_ctx_free(fpriv, id);
 		break;
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +7 -0
index 86a1242..ac90dfc 100644
@@ -88,20 +88,21 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
 
 	for (i = 0; i < job->num_ibs; ++i)
 		amdgpu_ib_free(job->adev, &job->ibs[i], f);
 }
 
 static void amdgpu_job_free_cb(struct amd_sched_job *s_job)
 {
 	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
+	amdgpu_ring_priority_put(job->ring, amd_sched_get_job_priority(s_job));
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	kfree(job);
 }
 
 void amdgpu_job_free(struct amdgpu_job *job)
 {
 	amdgpu_job_free_resources(job);
 
 	dma_fence_put(job->fence);
@@ -162,28 +163,34 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 	int r;
 
 	if (!sched_job) {
 		DRM_ERROR("job is null\n");
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
+	r = amdgpu_ring_priority_get(job->ring,
+				     amd_sched_get_job_priority(&job->base));
+	if (r)
+		DRM_ERROR("Failed to set job priority (%d)\n", r);
+
 	trace_amdgpu_sched_run_job(job);
 	r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job, &fence);
 	if (r)
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 
 	/* if gpu reset, hw fence will be replaced here */
 	dma_fence_put(job->fence);
 	job->fence = dma_fence_get(fence);
+
 	amdgpu_job_free_resources(job);
 	return fence;
 }
 
 const struct amd_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_job_dependency,
 	.run_job = amdgpu_job_run,
 	.timedout_job = amdgpu_job_timedout,
 	.free_job = amdgpu_job_free_cb
 };
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +77 -1

135 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +15 -0
index 41ab767..e8ba708 100644
@@ -17,20 +17,21 @@
  * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: Christian König
  */
 #ifndef __AMDGPU_RING_H__
 #define __AMDGPU_RING_H__
 
+#include <drm/amdgpu_drm.h>
 #include "gpu_scheduler.h"
 
 /* max number of rings */
 #define AMDGPU_MAX_RINGS		18
 #define AMDGPU_MAX_GFX_RINGS		1
 #define AMDGPU_MAX_COMPUTE_RINGS	8
 #define AMDGPU_MAX_VCE_RINGS		3
 #define AMDGPU_MAX_UVD_ENC_RINGS	2
 
 /* some special values for the owner field */
@@ -47,20 +48,21 @@ enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_UVD,
 	AMDGPU_RING_TYPE_VCE,
 	AMDGPU_RING_TYPE_KIQ,
 	AMDGPU_RING_TYPE_UVD_ENC
 };
 
 struct amdgpu_device;
 struct amdgpu_ring;
 struct amdgpu_ib;
 struct amdgpu_cs_parser;
+struct amdgpu_job;
 
 /*
  * Fences.
  */
 struct amdgpu_fence_driver {
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
 	/* sync_seq is protected by ring emission lock */
 	uint32_t			sync_seq;
 	atomic_t			last_seq;
@@ -134,20 +136,23 @@ struct amdgpu_ring_funcs {
 	void (*pad_ib)(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
 	unsigned (*init_cond_exec)(struct amdgpu_ring *ring);
 	void (*patch_cond_exec)(struct amdgpu_ring *ring, unsigned offset);
 	/* note usage for clock and power gating */
 	void (*begin_use)(struct amdgpu_ring *ring);
 	void (*end_use)(struct amdgpu_ring *ring);
 	void (*emit_switch_buffer) (struct amdgpu_ring *ring);
 	void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
 	void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg);
 	void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+	/* priority functions */
+	void (*set_priority) (struct amdgpu_ring *ring,
+			      enum amd_sched_priority priority);
 };
 
 struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
 	struct amd_gpu_scheduler	sched;
 	struct list_head		lru_list;
 
 	struct amdgpu_bo	*ring_obj;
@@ -172,32 +177,42 @@ struct amdgpu_ring {
 	uint64_t                eop_gpu_addr;
 	u32			doorbell_index;
 	bool			use_doorbell;
 	unsigned		wptr_offs;
 	unsigned		fence_offs;
 	uint64_t		current_ctx;
 	char			name[16];
 	unsigned		cond_exe_offs;
 	u64			cond_exe_gpu_addr;
 	volatile u32		*cond_exe_cpu_addr;
+
+	atomic_t		num_jobs[AMD_SCHED_PRIORITY_MAX];
+	spinlock_t		priority_lock;
+	/* protected by priority_lock */
+	int			priority;
+
 #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_priority_get(struct amdgpu_ring *ring,
+			     enum amd_sched_priority priority);
+void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
+			      enum amd_sched_priority priority);
 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);
 int amdgpu_ring_lru_get(struct amdgpu_device *adev, int hw_ip,
 			struct amdgpu_ring **ring);
 void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {
 	int i = 0;
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +7 -0
index e266e1e..a33f6ec 100644
@@ -152,11 +152,18 @@ void amd_sched_fence_slab_fini(void);
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
 void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
 void amd_sched_fence_finished(struct amd_sched_fence *fence);
 int amd_sched_job_init(struct amd_sched_job *job,
 		       struct amd_gpu_scheduler *sched,
 		       struct amd_sched_entity *entity,
 		       void *owner);
 void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched);
 void amd_sched_job_recovery(struct amd_gpu_scheduler *sched);
+
+static inline enum amd_sched_priority
+amd_sched_get_job_priority(struct amd_sched_job *job)
+{
+	return (job->s_entity->rq - job->sched->sched_rq);
+}
+
 #endif
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#42 lore raw

PATCH 21/26 drm/amdgpu: convert srbm lock to a spinlock v2

In reply to a message not in the archive

Replace adev->srbm_mutex with a spinlock adev->srbm_lock

v2: rebased on 4.12 and included gfx9

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h               |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c             |  4 +--
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c             | 20 ++++++-------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c             | 34 +++++++++++------------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c             | 24 ++++++++--------
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c            |  4 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c            |  4 +--
 10 files changed, 51 insertions(+), 51 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -1
index 4f54846..b9a4161 100644
@@ -1455,21 +1455,21 @@ struct amdgpu_device {
 	struct work_struct		reset_work;
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
 	struct amdgpu_debugfs		debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 	unsigned			debugfs_count;
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
 	struct amdgpu_atif		atif;
 	struct amdgpu_atcs		atcs;
-	struct mutex			srbm_mutex;
+	spinlock_t			srbm_lock;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
 	struct mutex                    grbm_idx_mutex;
 	struct dev_pm_domain		vga_pm_domain;
 	bool				have_disp_power_ref;
 
 	/* BIOS */
 	bool				is_atom_fw;
 	uint8_t				*bios;
 	uint32_t			bios_size;
 	struct amdgpu_bo		*stollen_vga_memory;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +2 -2
index 5254562..a009990 100644
@@ -162,30 +162,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
 	return (struct amdgpu_device *)kgd;
 }
 
 static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
 			uint32_t queue, uint32_t vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	WREG32(mmSRBM_GFX_CNTL, value);
 }
 
 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);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t queue_id)
 {
 	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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +2 -2
index db7410a..6b93a5c 100644
@@ -123,30 +123,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
 	return (struct amdgpu_device *)kgd;
 }
 
 static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
 			uint32_t queue, uint32_t vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	WREG32(mmSRBM_GFX_CNTL, value);
 }
 
 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);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t queue_id)
 {
 	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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
index 0bfc6c6..07f16b4 100644
@@ -1857,21 +1857,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		 amdgpu_asic_name[adev->asic_type], pdev->vendor, pdev->device,
 		 pdev->subsystem_vendor, pdev->subsystem_device, pdev->revision);
 
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */
 	mutex_init(&adev->vm_manager.lock);
 	atomic_set(&adev->irq.ih.lock, 0);
 	mutex_init(&adev->firmware.mutex);
 	mutex_init(&adev->pm.mutex);
 	mutex_init(&adev->gfx.gpu_clock_mutex);
-	mutex_init(&adev->srbm_mutex);
+	spin_lock_init(&adev->srbm_lock);
 	mutex_init(&adev->grbm_idx_mutex);
 	mutex_init(&adev->mn_lock);
 	hash_init(adev->mn_hash);
 
 	amdgpu_check_arguments(adev);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
 	spin_lock_init(&adev->mmio_idx_lock);
 	spin_lock_init(&adev->smc_idx_lock);
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +2 -2
index c216e16..fe462ec 100644
@@ -382,30 +382,30 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
 	u32 wb_offset;
 	int i, j, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		wb_offset = (ring->rptr_offs * 4);
 
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		for (j = 0; j < 16; j++) {
 			cik_srbm_select(adev, 0, 0, 0, j);
 			/* SDMA GFX */
 			WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
 			WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
 			/* XXX SDMA RLC - todo */
 		}
 		cik_srbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+		spin_unlock(&adev->srbm_lock);
 
 		WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
 		       adev->gfx.config.gb_addr_config & 0x70);
 
 		WREG32(mmSDMA0_SEM_INCOMPLETE_TIMER_CNTL + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
 		rb_cntl = rb_bufsz << 1;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +10 -10
index c0cfcb9..83391d5 100644
@@ -1856,31 +1856,31 @@ static void gmc_v7_0_init_compute_vmid(struct amdgpu_device *adev)
 	/*
 	 * Configure apertures:
 	 * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
 	 * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
 	 * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
 	*/
 	sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 	sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 			SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
 	sh_mem_config |= MTYPE_NONCACHED << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT;
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
 		cik_srbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		WREG32(mmSH_MEM_CONFIG, sh_mem_config);
 		WREG32(mmSH_MEM_APE1_BASE, 1);
 		WREG32(mmSH_MEM_APE1_LIMIT, 0);
 		WREG32(mmSH_MEM_BASES, sh_mem_bases);
 	}
 	cik_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v7_0_config_init(struct amdgpu_device *adev)
 {
 	adev->gfx.config.double_offchip_lds_buf = 1;
 }
 
 /**
  * gfx_v7_0_gpu_init - setup the 3D engine
  *
@@ -1929,36 +1929,36 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
 				   MTYPE_UC);
 	sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, PRIVATE_ATC, 0);
 
 	sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
 				   SWIZZLE_ENABLE, 1);
 	sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
 				   ELEMENT_SIZE, 1);
 	sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
 				   INDEX_STRIDE, 3);
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = 0; i < adev->vm_manager.num_ids; i++) {
 		if (i == 0)
 			sh_mem_base = 0;
 		else
 			sh_mem_base = adev->mc.shared_aperture_start >> 48;
 		cik_srbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		WREG32(mmSH_MEM_CONFIG, sh_mem_cfg);
 		WREG32(mmSH_MEM_APE1_BASE, 1);
 		WREG32(mmSH_MEM_APE1_LIMIT, 0);
 		WREG32(mmSH_MEM_BASES, sh_mem_base);
 		WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
 	}
 	cik_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 
 	gmc_v7_0_init_compute_vmid(adev);
 
 	WREG32(mmSX_DEBUG_1, 0x20);
 
 	WREG32(mmTA_CNTL_AUX, 0x00010000);
 
 	tmp = RREG32(mmSPI_CONFIG_CNTL);
 	tmp |= 0x03000000;
 	WREG32(mmSPI_CONFIG_CNTL, tmp);
@@ -2962,40 +2962,40 @@ struct hqd_registers
 	u32 cp_hqd_hq_scheduler1;
 	u32 cp_mqd_control;
 };
 
 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);
+	spin_lock(&adev->srbm_lock);
 	eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + eop_offset;
 
 	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);
 
 	/* 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);
 
 	cik_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v7_0_mqd_deactivate(struct amdgpu_device *adev)
 {
 	int i;
 
 	/* 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++) {
@@ -3210,29 +3210,29 @@ static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
 	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);
+	spin_lock(&adev->srbm_lock);
 	cik_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
 	gfx_v7_0_mqd_init(adev, mqd, mqd_gpu_addr, ring);
 	gfx_v7_0_mqd_deactivate(adev);
 	gfx_v7_0_mqd_commit(adev, mqd);
 
 	cik_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 
 	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
@@ -5088,28 +5088,28 @@ static void gfx_v7_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 		DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
 		return;
 	}
 
 	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);
+	spin_lock(&adev->srbm_lock);
 	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);
+	spin_unlock(&adev->srbm_lock);
 }
 
 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) {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +17 -17
index f0c1a3f..3cfe3c0 100644
@@ -3936,31 +3936,31 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev)
 	 */
 	sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
 	sh_mem_config = SH_MEM_ADDRESS_MODE_HSA64 <<
 			SH_MEM_CONFIG__ADDRESS_MODE__SHIFT |
 			SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 			SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT |
 			MTYPE_CC << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
 			SH_MEM_CONFIG__PRIVATE_ATC_MASK;
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
 		vi_srbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		WREG32(mmSH_MEM_CONFIG, sh_mem_config);
 		WREG32(mmSH_MEM_APE1_BASE, 1);
 		WREG32(mmSH_MEM_APE1_LIMIT, 0);
 		WREG32(mmSH_MEM_BASES, sh_mem_bases);
 	}
 	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v8_0_config_init(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	default:
 		adev->gfx.config.double_offchip_lds_buf = 1;
 		break;
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
@@ -3985,21 +3985,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 	gfx_v8_0_config_init(adev);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
 	sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
 				   SWIZZLE_ENABLE, 1);
 	sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
 				   ELEMENT_SIZE, 1);
 	sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
 				   INDEX_STRIDE, 3);
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = 0; i < adev->vm_manager.num_ids; i++) {
 		vi_srbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		if (i == 0) {
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_UC);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			WREG32(mmSH_MEM_CONFIG, tmp);
 			WREG32(mmSH_MEM_BASES, 0);
@@ -4011,21 +4011,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 			WREG32(mmSH_MEM_CONFIG, tmp);
 			tmp = adev->mc.shared_aperture_start >> 48;
 			WREG32(mmSH_MEM_BASES, tmp);
 		}
 
 		WREG32(mmSH_MEM_APE1_BASE, 1);
 		WREG32(mmSH_MEM_APE1_LIMIT, 0);
 		WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
 	}
 	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 
 	gfx_v8_0_init_compute_vmid(adev);
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	/*
 	 * making sure that the following register writes will be broadcasted
 	 * to all the shaders
 	 */
 	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -5142,70 +5142,70 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *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;
 		amdgpu_ring_clear_ring(ring);
 
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		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);
+		spin_unlock(&adev->srbm_lock);
 	} else {
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		gfx_v8_0_mqd_init(ring);
 		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);
+		spin_unlock(&adev->srbm_lock);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	}
 
 	return r;
 
 out_unlock:
 	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 	return r;
 }
 
 static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
 	if (!adev->gfx.in_reset && !adev->gfx.in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		gfx_v8_0_mqd_init(ring);
 		vi_srbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+		spin_unlock(&adev->srbm_lock);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
 			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else 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;
@@ -5486,32 +5486,32 @@ static bool gfx_v8_0_check_soft_reset(void *handle)
 		adev->gfx.srbm_soft_reset = 0;
 		return false;
 	}
 }
 
 static void gfx_v8_0_inactive_hqd(struct amdgpu_device *adev,
 				  struct amdgpu_ring *ring)
 {
 	int i;
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 	if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
 		WREG32_FIELD(CP_HQD_DEQUEUE_REQUEST, DEQUEUE_REQ, 2);
 		for (i = 0; i < adev->usec_timeout; i++) {
 			if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
 				break;
 			udelay(1);
 		}
 	}
 	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 }
 
 static int gfx_v8_0_pre_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
 	if ((!adev->gfx.grbm_soft_reset) &&
 	    (!adev->gfx.srbm_soft_reset))
 		return 0;
@@ -5603,27 +5603,27 @@ static int gfx_v8_0_soft_reset(void *handle)
 
 	/* Wait a little for things to settle down */
 	udelay(50);
 
 	return 0;
 }
 
 static void gfx_v8_0_init_hqd(struct amdgpu_device *adev,
 			      struct amdgpu_ring *ring)
 {
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 	WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
 	WREG32(mmCP_HQD_PQ_RPTR, 0);
 	WREG32(mmCP_HQD_PQ_WPTR, 0);
 	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v8_0_post_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
 	if ((!adev->gfx.grbm_soft_reset) &&
 	    (!adev->gfx.srbm_soft_reset))
 		return 0;
@@ -6877,28 +6877,28 @@ static void gfx_v8_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 		DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
 		return;
 	}
 
 	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);
+	spin_lock(&adev->srbm_lock);
 	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);
+	spin_unlock(&adev->srbm_lock);
 }
 
 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);
 
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +12 -12
index 388a6bb..a16cee7 100644
@@ -1373,58 +1373,58 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev)
 	 * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
 	 * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
 	 * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
 	 */
 	sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
 	sh_mem_config = SH_MEM_ADDRESS_MODE_64 |
 			SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 			SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; 
 
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
 		soc15_grbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config);
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases);
 	}
 	soc15_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
 {
 	u32 tmp;
 	int i;
 
 	WREG32_FIELD15(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
 
 	gfx_v9_0_tiling_mode_table_init(adev);
 
 	gfx_v9_0_setup_rb(adev);
 	gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	for (i = 0; i < 16; i++) {
 		soc15_grbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		tmp = 0;
 		tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
 				    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), tmp);
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), 0);
 	}
 	soc15_grbm_select(adev, 0, 0, 0, 0);
 
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 
 	gfx_v9_0_init_compute_vmid(adev);
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	/*
 	 * making sure that the following register writes will be broadcasted
 	 * to all the shaders
 	 */
 	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -2245,40 +2245,40 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)
 	int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
 
 	if (is_kiq) {
 		gfx_v9_0_kiq_setting(&kiq->ring);
 	} else {
 		mqd_idx = ring - &adev->gfx.compute_ring[0];
 	}
 
 	if (!adev->gfx.in_reset) {
 		memset((void *)mqd, 0, sizeof(*mqd));
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		gfx_v9_0_mqd_init(ring);
 		if (is_kiq)
 			gfx_v9_0_kiq_init_register(ring);
 		soc15_grbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+		spin_unlock(&adev->srbm_lock);
 
 	} else { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 
 		/* reset ring buffer */
 		ring->wptr = 0;
 
 		if (is_kiq) {
-		    mutex_lock(&adev->srbm_mutex);
+		    spin_lock(&adev->srbm_lock);
 		    soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 		    gfx_v9_0_kiq_init_register(ring);
 		    soc15_grbm_select(adev, 0, 0, 0, 0);
-		    mutex_unlock(&adev->srbm_mutex);
+		    spin_unlock(&adev->srbm_lock);
 		}
 	}
 
 	if (is_kiq)
 		gfx_v9_0_kiq_enable(ring);
 	else
 		gfx_v9_0_map_queue_enable(&kiq->ring, ring);
 
 	return 0;
 }
@@ -3333,28 +3333,28 @@ static void gfx_v9_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 		DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
 		return;
 	}
 
 	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);
+	spin_lock(&adev->srbm_lock);
 	soc15_grbm_select(adev, me, pipe, 0, 0);
 
 	WREG32_FIELD(CPC_INT_CNTL, TIME_STAMP_INT_ENABLE,
 			state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
 
 	soc15_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v9_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
 					     struct amdgpu_irq_src *source,
 					     unsigned type,
 					     enum amdgpu_interrupt_state state)
 {
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
 	case AMDGPU_IRQ_STATE_ENABLE:
@@ -3853,21 +3853,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
 	memset(buf, 0, sizeof(struct v9_mqd));
 
 	mqd = (struct v9_mqd *)buf;
 	mqd->header = 0xC0310800;
 	mqd->compute_pipelinestat_enable = 0x00000001;
 	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;
 	mqd->compute_misc_reserved = 0x00000003;
-	mutex_lock(&adev->srbm_mutex);
+	spin_lock(&adev->srbm_lock);
 	soc15_grbm_select(adev, ring->me,
 			       ring->pipe,
 			       ring->queue, 0);
 	/* disable wptr polling */
 	WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
 	/* write the EOP addr */
 	BUG_ON(ring->me != 1 || ring->pipe != 0); /* can't handle other cases eop address */
 	eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (ring->queue * MEC_HPD_SIZE);
 	eop_gpu_addr >>= 8;
@@ -3997,21 +3997,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
 	tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
 	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE), tmp);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* activate the queue */
 	mqd->cp_hqd_active = 1;
 	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), mqd->cp_hqd_active);
 
 	soc15_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+	spin_unlock(&adev->srbm_lock);
 
 	amdgpu_bo_kunmap(ring->mqd_obj);
 	amdgpu_bo_unreserve(ring->mqd_obj);
 
 	if (use_doorbell)
 		WREG32_FIELD15(GC, 0, CP_PQ_STATUS, DOORBELL_ENABLE, 1);
 
 	return 0;
 }
 
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +2 -2
index f2d0710..0e0e344 100644
@@ -415,29 +415,29 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
 	u32 wb_offset;
 	int i, j, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		wb_offset = (ring->rptr_offs * 4);
 
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		for (j = 0; j < 16; j++) {
 			vi_srbm_select(adev, 0, 0, 0, j);
 			/* SDMA GFX */
 			WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
 			WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
 		}
 		vi_srbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+		spin_unlock(&adev->srbm_lock);
 
 		WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
 		       adev->gfx.config.gb_addr_config & 0x70);
 
 		WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
 		rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +2 -2
index a69e5d4..f8a5da3 100644
@@ -609,29 +609,29 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 	u32 rb_bufsz;
 	u32 wb_offset;
 	u32 doorbell;
 	int i, j, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		amdgpu_ring_clear_ring(ring);
 		wb_offset = (ring->rptr_offs * 4);
 
-		mutex_lock(&adev->srbm_mutex);
+		spin_lock(&adev->srbm_lock);
 		for (j = 0; j < 16; j++) {
 			vi_srbm_select(adev, 0, 0, 0, j);
 			/* SDMA GFX */
 			WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
 			WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
 		}
 		vi_srbm_select(adev, 0, 0, 0, 0);
-		mutex_unlock(&adev->srbm_mutex);
+		spin_unlock(&adev->srbm_lock);
 
 		WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
 		       adev->gfx.config.gb_addr_config & 0x70);
 
 		WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
 		rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-22-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#44 lore raw

Re: [PATCH 21/26] drm/amdgpu: convert srbm lock to a spinlock v2

Quoted 4 lines · Andres Rodriguez

Replace adev->srbm_mutex with a spinlock adev->srbm_lock

v2: rebased on 4.12 and included gfx9

Maybe move this one up to the front of the series so it can be applied now?

Alex

Quoted 883 lines
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h               |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c             |  4 +--
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c             | 20 ++++++-------
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c             | 34 +++++++++++------------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c             | 24 ++++++++--------
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c            |  4 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c            |  4 +--
 10 files changed, 51 insertions(+), 51 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -1
index 4f54846..b9a4161 100644
@@ -1455,21 +1455,21 @@ struct amdgpu_device {
        struct work_struct              reset_work;
        struct notifier_block           acpi_nb;
        struct amdgpu_i2c_chan          *i2c_bus[AMDGPU_MAX_I2C_BUS];
        struct amdgpu_debugfs           debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
        unsigned                        debugfs_count;
 #if defined(CONFIG_DEBUG_FS)
        struct dentry                   *debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
        struct amdgpu_atif              atif;
        struct amdgpu_atcs              atcs;
-       struct mutex                    srbm_mutex;
+       spinlock_t                      srbm_lock;
        /* GRBM index mutex. Protects concurrent access to GRBM index */
        struct mutex                    grbm_idx_mutex;
        struct dev_pm_domain            vga_pm_domain;
        bool                            have_disp_power_ref;
 
        /* BIOS */
        bool                            is_atom_fw;
        uint8_t                         *bios;
        uint32_t                        bios_size;
        struct amdgpu_bo                *stollen_vga_memory;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +2 -2
index 5254562..a009990 100644
@@ -162,30 +162,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
        return (struct amdgpu_device *)kgd;
 }
 
 static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
                        uint32_t queue, uint32_t vmid)
 {
        struct amdgpu_device *adev = get_amdgpu_device(kgd);
        uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        WREG32(mmSRBM_GFX_CNTL, value);
 }
 
 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);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
                                uint32_t queue_id)
 {
        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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +2 -2
index db7410a..6b93a5c 100644
@@ -123,30 +123,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
        return (struct amdgpu_device *)kgd;
 }
 
 static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
                        uint32_t queue, uint32_t vmid)
 {
        struct amdgpu_device *adev = get_amdgpu_device(kgd);
        uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        WREG32(mmSRBM_GFX_CNTL, value);
 }
 
 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);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
                                uint32_t queue_id)
 {
        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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
index 0bfc6c6..07f16b4 100644
@@ -1857,21 +1857,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
                 amdgpu_asic_name[adev->asic_type], pdev->vendor, pdev->device,
                 pdev->subsystem_vendor, pdev->subsystem_device, pdev->revision);
 
        /* mutex initialization are all done here so we
         * can recall function without having locking issues */
        mutex_init(&adev->vm_manager.lock);
        atomic_set(&adev->irq.ih.lock, 0);
        mutex_init(&adev->firmware.mutex);
        mutex_init(&adev->pm.mutex);
        mutex_init(&adev->gfx.gpu_clock_mutex);
-       mutex_init(&adev->srbm_mutex);
+       spin_lock_init(&adev->srbm_lock);
        mutex_init(&adev->grbm_idx_mutex);
        mutex_init(&adev->mn_lock);
        hash_init(adev->mn_hash);
 
        amdgpu_check_arguments(adev);
 
        /* Registers mapping */
        /* TODO: block userspace mapping of io register */
        spin_lock_init(&adev->mmio_idx_lock);
        spin_lock_init(&adev->smc_idx_lock);
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +2 -2
index c216e16..fe462ec 100644
@@ -382,30 +382,30 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
        struct amdgpu_ring *ring;
        u32 rb_cntl, ib_cntl;
        u32 rb_bufsz;
        u32 wb_offset;
        int i, j, r;
 
        for (i = 0; i < adev->sdma.num_instances; i++) {
                ring = &adev->sdma.instance[i].ring;
                wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                for (j = 0; j < 16; j++) {
                        cik_srbm_select(adev, 0, 0, 0, j);
                        /* SDMA GFX */
                        WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                        WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                        /* XXX SDMA RLC - todo */
                }
                cik_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                       adev->gfx.config.gb_addr_config & 0x70);
 
                WREG32(mmSDMA0_SEM_INCOMPLETE_TIMER_CNTL + sdma_offsets[i], 0);
                WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                /* Set ring buffer size in dwords */
                rb_bufsz = order_base_2(ring->ring_size / 4);
                rb_cntl = rb_bufsz << 1;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +10 -10
index c0cfcb9..83391d5 100644
@@ -1856,31 +1856,31 @@ static void gmc_v7_0_init_compute_vmid(struct amdgpu_device *adev)
        /*
         * Configure apertures:
         * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
         * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
         * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
        */
        sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
        sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                        SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
        sh_mem_config |= MTYPE_NONCACHED << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT;
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                cik_srbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                WREG32(mmSH_MEM_CONFIG, sh_mem_config);
                WREG32(mmSH_MEM_APE1_BASE, 1);
                WREG32(mmSH_MEM_APE1_LIMIT, 0);
                WREG32(mmSH_MEM_BASES, sh_mem_bases);
        }
        cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v7_0_config_init(struct amdgpu_device *adev)
 {
        adev->gfx.config.double_offchip_lds_buf = 1;
 }
 
 /**
  * gfx_v7_0_gpu_init - setup the 3D engine
  *
@@ -1929,36 +1929,36 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
                                   MTYPE_UC);
        sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, PRIVATE_ATC, 0);
 
        sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
                                   SWIZZLE_ENABLE, 1);
        sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                   ELEMENT_SIZE, 1);
        sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                   INDEX_STRIDE, 3);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = 0; i < adev->vm_manager.num_ids; i++) {
                if (i == 0)
                        sh_mem_base = 0;
                else
                        sh_mem_base = adev->mc.shared_aperture_start >> 48;
                cik_srbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                WREG32(mmSH_MEM_CONFIG, sh_mem_cfg);
                WREG32(mmSH_MEM_APE1_BASE, 1);
                WREG32(mmSH_MEM_APE1_LIMIT, 0);
                WREG32(mmSH_MEM_BASES, sh_mem_base);
                WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
        }
        cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
        gmc_v7_0_init_compute_vmid(adev);
 
        WREG32(mmSX_DEBUG_1, 0x20);
 
        WREG32(mmTA_CNTL_AUX, 0x00010000);
 
        tmp = RREG32(mmSPI_CONFIG_CNTL);
        tmp |= 0x03000000;
        WREG32(mmSPI_CONFIG_CNTL, tmp);
@@ -2962,40 +2962,40 @@ struct hqd_registers
        u32 cp_hqd_hq_scheduler1;
        u32 cp_mqd_control;
 };
 
 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);
+       spin_lock(&adev->srbm_lock);
        eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + eop_offset;
 
        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);
 
        /* 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);
 
        cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v7_0_mqd_deactivate(struct amdgpu_device *adev)
 {
        int i;
 
        /* 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++) {
@@ -3210,29 +3210,29 @@ static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
        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);
+       spin_lock(&adev->srbm_lock);
        cik_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
        gfx_v7_0_mqd_init(adev, mqd, mqd_gpu_addr, ring);
        gfx_v7_0_mqd_deactivate(adev);
        gfx_v7_0_mqd_commit(adev, mqd);
 
        cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
        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
@@ -5088,28 +5088,28 @@ static void gfx_v7_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                return;
        }
 
        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);
+       spin_lock(&adev->srbm_lock);
        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);
+       spin_unlock(&adev->srbm_lock);
 }
 
 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) {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +17 -17
index f0c1a3f..3cfe3c0 100644
@@ -3936,31 +3936,31 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev)
         */
        sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
        sh_mem_config = SH_MEM_ADDRESS_MODE_HSA64 <<
                        SH_MEM_CONFIG__ADDRESS_MODE__SHIFT |
                        SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                        SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT |
                        MTYPE_CC << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
                        SH_MEM_CONFIG__PRIVATE_ATC_MASK;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                vi_srbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                WREG32(mmSH_MEM_CONFIG, sh_mem_config);
                WREG32(mmSH_MEM_APE1_BASE, 1);
                WREG32(mmSH_MEM_APE1_LIMIT, 0);
                WREG32(mmSH_MEM_BASES, sh_mem_bases);
        }
        vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v8_0_config_init(struct amdgpu_device *adev)
 {
        switch (adev->asic_type) {
        default:
                adev->gfx.config.double_offchip_lds_buf = 1;
                break;
        case CHIP_CARRIZO:
        case CHIP_STONEY:
@@ -3985,21 +3985,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
        gfx_v8_0_config_init(adev);
 
        /* XXX SH_MEM regs */
        /* where to put LDS, scratch, GPUVM in FSA64 space */
        sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
                                   SWIZZLE_ENABLE, 1);
        sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                   ELEMENT_SIZE, 1);
        sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                   INDEX_STRIDE, 3);
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = 0; i < adev->vm_manager.num_ids; i++) {
                vi_srbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                if (i == 0) {
                        tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_UC);
                        tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC);
                        tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
                                            SH_MEM_ALIGNMENT_MODE_UNALIGNED);
                        WREG32(mmSH_MEM_CONFIG, tmp);
                        WREG32(mmSH_MEM_BASES, 0);
@@ -4011,21 +4011,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
                        WREG32(mmSH_MEM_CONFIG, tmp);
                        tmp = adev->mc.shared_aperture_start >> 48;
                        WREG32(mmSH_MEM_BASES, tmp);
                }
 
                WREG32(mmSH_MEM_APE1_BASE, 1);
                WREG32(mmSH_MEM_APE1_LIMIT, 0);
                WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
        }
        vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
        gfx_v8_0_init_compute_vmid(adev);
 
        mutex_lock(&adev->grbm_idx_mutex);
        /*
         * making sure that the following register writes will be broadcasted
         * to all the shaders
         */
        gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -5142,70 +5142,70 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *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;
                amdgpu_ring_clear_ring(ring);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                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);
+               spin_unlock(&adev->srbm_lock);
        } else {
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
                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);
+               spin_unlock(&adev->srbm_lock);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        }
 
        return r;
 
 out_unlock:
        vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
        return r;
 }
 
 static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
        struct vi_mqd *mqd = ring->mqd_ptr;
        int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
        if (!adev->gfx.in_reset && !adev->gfx.in_suspend) {
                memset((void *)mqd, 0, sizeof(*mqd));
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v8_0_mqd_init(ring);
                vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                if (adev->gfx.mec.mqd_backup[mqd_idx])
                        memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
        } else 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;
@@ -5486,32 +5486,32 @@ static bool gfx_v8_0_check_soft_reset(void *handle)
                adev->gfx.srbm_soft_reset = 0;
                return false;
        }
 }
 
 static void gfx_v8_0_inactive_hqd(struct amdgpu_device *adev,
                                  struct amdgpu_ring *ring)
 {
        int i;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
        if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
                WREG32_FIELD(CP_HQD_DEQUEUE_REQUEST, DEQUEUE_REQ, 2);
                for (i = 0; i < adev->usec_timeout; i++) {
                        if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
                                break;
                        udelay(1);
                }
        }
        vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
 }
 
 static int gfx_v8_0_pre_soft_reset(void *handle)
 {
        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
        u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
        if ((!adev->gfx.grbm_soft_reset) &&
            (!adev->gfx.srbm_soft_reset))
                return 0;
@@ -5603,27 +5603,27 @@ static int gfx_v8_0_soft_reset(void *handle)
 
        /* Wait a little for things to settle down */
        udelay(50);
 
        return 0;
 }
 
 static void gfx_v8_0_init_hqd(struct amdgpu_device *adev,
                              struct amdgpu_ring *ring)
 {
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
        WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
        WREG32(mmCP_HQD_PQ_RPTR, 0);
        WREG32(mmCP_HQD_PQ_WPTR, 0);
        vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v8_0_post_soft_reset(void *handle)
 {
        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
        u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
        if ((!adev->gfx.grbm_soft_reset) &&
            (!adev->gfx.srbm_soft_reset))
                return 0;
@@ -6877,28 +6877,28 @@ static void gfx_v8_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                return;
        }
 
        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);
+       spin_lock(&adev->srbm_lock);
        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);
+       spin_unlock(&adev->srbm_lock);
 }
 
 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);
 
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +12 -12
index 388a6bb..a16cee7 100644
@@ -1373,58 +1373,58 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev)
         * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
         * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
         * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
         */
        sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
        sh_mem_config = SH_MEM_ADDRESS_MODE_64 |
                        SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                        SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                soc15_grbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config);
                WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases);
        }
        soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
 {
        u32 tmp;
        int i;
 
        WREG32_FIELD15(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
 
        gfx_v9_0_tiling_mode_table_init(adev);
 
        gfx_v9_0_setup_rb(adev);
        gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 
        /* XXX SH_MEM regs */
        /* where to put LDS, scratch, GPUVM in FSA64 space */
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        for (i = 0; i < 16; i++) {
                soc15_grbm_select(adev, 0, 0, 0, i);
                /* CP and shaders */
                tmp = 0;
                tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
                                    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
                WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), tmp);
                WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), 0);
        }
        soc15_grbm_select(adev, 0, 0, 0, 0);
 
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
        gfx_v9_0_init_compute_vmid(adev);
 
        mutex_lock(&adev->grbm_idx_mutex);
        /*
         * making sure that the following register writes will be broadcasted
         * to all the shaders
         */
        gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -2245,40 +2245,40 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)
        int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
 
        if (is_kiq) {
                gfx_v9_0_kiq_setting(&kiq->ring);
        } else {
                mqd_idx = ring - &adev->gfx.compute_ring[0];
        }
 
        if (!adev->gfx.in_reset) {
                memset((void *)mqd, 0, sizeof(*mqd));
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                gfx_v9_0_mqd_init(ring);
                if (is_kiq)
                        gfx_v9_0_kiq_init_register(ring);
                soc15_grbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
        } else { /* for GPU_RESET case */
                /* reset MQD to a clean status */
 
                /* reset ring buffer */
                ring->wptr = 0;
 
                if (is_kiq) {
-                   mutex_lock(&adev->srbm_mutex);
+                   spin_lock(&adev->srbm_lock);
                    soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                    gfx_v9_0_kiq_init_register(ring);
                    soc15_grbm_select(adev, 0, 0, 0, 0);
-                   mutex_unlock(&adev->srbm_mutex);
+                   spin_unlock(&adev->srbm_lock);
                }
        }
 
        if (is_kiq)
                gfx_v9_0_kiq_enable(ring);
        else
                gfx_v9_0_map_queue_enable(&kiq->ring, ring);
 
        return 0;
 }
@@ -3333,28 +3333,28 @@ static void gfx_v9_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                return;
        }
 
        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);
+       spin_lock(&adev->srbm_lock);
        soc15_grbm_select(adev, me, pipe, 0, 0);
 
        WREG32_FIELD(CPC_INT_CNTL, TIME_STAMP_INT_ENABLE,
                        state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
 
        soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 }
 
 static int gfx_v9_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
                                             struct amdgpu_irq_src *source,
                                             unsigned type,
                                             enum amdgpu_interrupt_state state)
 {
        switch (state) {
        case AMDGPU_IRQ_STATE_DISABLE:
        case AMDGPU_IRQ_STATE_ENABLE:
@@ -3853,21 +3853,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
        memset(buf, 0, sizeof(struct v9_mqd));
 
        mqd = (struct v9_mqd *)buf;
        mqd->header = 0xC0310800;
        mqd->compute_pipelinestat_enable = 0x00000001;
        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;
        mqd->compute_misc_reserved = 0x00000003;
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
        soc15_grbm_select(adev, ring->me,
                               ring->pipe,
                               ring->queue, 0);
        /* disable wptr polling */
        WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
        /* write the EOP addr */
        BUG_ON(ring->me != 1 || ring->pipe != 0); /* can't handle other cases eop address */
        eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (ring->queue * MEC_HPD_SIZE);
        eop_gpu_addr >>= 8;
@@ -3997,21 +3997,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
        tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE));
        tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
        WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE), tmp);
        mqd->cp_hqd_persistent_state = tmp;
 
        /* activate the queue */
        mqd->cp_hqd_active = 1;
        WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), mqd->cp_hqd_active);
 
        soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
        amdgpu_bo_kunmap(ring->mqd_obj);
        amdgpu_bo_unreserve(ring->mqd_obj);
 
        if (use_doorbell)
                WREG32_FIELD15(GC, 0, CP_PQ_STATUS, DOORBELL_ENABLE, 1);
 
        return 0;
 }
 
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +2 -2
index f2d0710..0e0e344 100644
@@ -415,29 +415,29 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
        struct amdgpu_ring *ring;
        u32 rb_cntl, ib_cntl;
        u32 rb_bufsz;
        u32 wb_offset;
        int i, j, r;
 
        for (i = 0; i < adev->sdma.num_instances; i++) {
                ring = &adev->sdma.instance[i].ring;
                wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                for (j = 0; j < 16; j++) {
                        vi_srbm_select(adev, 0, 0, 0, j);
                        /* SDMA GFX */
                        WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                        WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                }
                vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                       adev->gfx.config.gb_addr_config & 0x70);
 
                WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                /* Set ring buffer size in dwords */
                rb_bufsz = order_base_2(ring->ring_size / 4);
                rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
                rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +2 -3
index a69e5d4..f8a5da3 100644
@@ -609,29 +609,29 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
        u32 rb_bufsz;
        u32 wb_offset;
        u32 doorbell;
        int i, j, r;
 
        for (i = 0; i < adev->sdma.num_instances; i++) {
                ring = &adev->sdma.instance[i].ring;
                amdgpu_ring_clear_ring(ring);
                wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                for (j = 0; j < 16; j++) {
                        vi_srbm_select(adev, 0, 0, 0, j);
                        /* SDMA GFX */
                        WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                        WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                }
                vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                       adev->gfx.config.gb_addr_config & 0x70);
 
                WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                /* Set ring buffer size in dwords */
                rb_bufsz = order_base_2(ring->ring_size / 4);
                rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
                rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
--

2.9.3

Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): CADnq5_OLYK+NzN9CZC4SDMnTKDxQpqH9MnT6jvNih3hVbOFBQw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org

#46 lore raw

Re: [PATCH 21/26] drm/amdgpu: convert srbm lock to a spinlock v2

Am 12.04.2017 um 00:19 schrieb Alex Deucher:

Quoted 6 lines · Andres Rodriguez
Quoted 4 lines

Replace adev->srbm_mutex with a spinlock adev->srbm_lock

v2: rebased on 4.12 and included gfx9

Maybe move this one up to the front of the series so it can be applied now?

Actually I'm not sure if that patch is still a good idea.

It turned out we need to sleep way more often when the KIQ is in use.

Christian.

Quoted 887 lines

Alex

Quoted 883 lines
---
  drivers/gpu/drm/amd/amdgpu/amdgpu.h               |  2 +-
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c |  4 +--
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c |  4 +--
  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c        |  2 +-
  drivers/gpu/drm/amd/amdgpu/cik_sdma.c             |  4 +--
  drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c             | 20 ++++++-------
  drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c             | 34 +++++++++++------------
  drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c             | 24 ++++++++--------
  drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c            |  4 +--
  drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c            |  4 +--
  10 files changed, 51 insertions(+), 51 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -1
index 4f54846..b9a4161 100644
@@ -1455,21 +1455,21 @@ struct amdgpu_device {
         struct work_struct              reset_work;
         struct notifier_block           acpi_nb;
         struct amdgpu_i2c_chan          *i2c_bus[AMDGPU_MAX_I2C_BUS];
         struct amdgpu_debugfs           debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
         unsigned                        debugfs_count;
  #if defined(CONFIG_DEBUG_FS)
         struct dentry                   *debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
  #endif
         struct amdgpu_atif              atif;
         struct amdgpu_atcs              atcs;
-       struct mutex                    srbm_mutex;
+       spinlock_t                      srbm_lock;
         /* GRBM index mutex. Protects concurrent access to GRBM index */
         struct mutex                    grbm_idx_mutex;
         struct dev_pm_domain            vga_pm_domain;
         bool                            have_disp_power_ref;
 
         /* BIOS */
         bool                            is_atom_fw;
         uint8_t                         *bios;
         uint32_t                        bios_size;
         struct amdgpu_bo                *stollen_vga_memory;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +2 -2
index 5254562..a009990 100644
@@ -162,30 +162,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
  {
         return (struct amdgpu_device *)kgd;
  }
 
  static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
                         uint32_t queue, uint32_t vmid)
  {
         struct amdgpu_device *adev = get_amdgpu_device(kgd);
         uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         WREG32(mmSRBM_GFX_CNTL, value);
  }
 
  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);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
                                 uint32_t queue_id)
  {
         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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +2 -2
index db7410a..6b93a5c 100644
@@ -123,30 +123,30 @@ static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
  {
         return (struct amdgpu_device *)kgd;
  }
 
  static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
                         uint32_t queue, uint32_t vmid)
  {
         struct amdgpu_device *adev = get_amdgpu_device(kgd);
         uint32_t value = PIPEID(pipe) | MEID(mec) | VMID(vmid) | QUEUEID(queue);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         WREG32(mmSRBM_GFX_CNTL, value);
  }
 
  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);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
                                 uint32_t queue_id)
  {
         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);
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
index 0bfc6c6..07f16b4 100644
@@ -1857,21 +1857,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
                  amdgpu_asic_name[adev->asic_type], pdev->vendor, pdev->device,
                  pdev->subsystem_vendor, pdev->subsystem_device, pdev->revision);
 
         /* mutex initialization are all done here so we
          * can recall function without having locking issues */
         mutex_init(&adev->vm_manager.lock);
         atomic_set(&adev->irq.ih.lock, 0);
         mutex_init(&adev->firmware.mutex);
         mutex_init(&adev->pm.mutex);
         mutex_init(&adev->gfx.gpu_clock_mutex);
-       mutex_init(&adev->srbm_mutex);
+       spin_lock_init(&adev->srbm_lock);
         mutex_init(&adev->grbm_idx_mutex);
         mutex_init(&adev->mn_lock);
         hash_init(adev->mn_hash);
 
         amdgpu_check_arguments(adev);
 
         /* Registers mapping */
         /* TODO: block userspace mapping of io register */
         spin_lock_init(&adev->mmio_idx_lock);
         spin_lock_init(&adev->smc_idx_lock);
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +2 -2
index c216e16..fe462ec 100644
@@ -382,30 +382,30 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
         struct amdgpu_ring *ring;
         u32 rb_cntl, ib_cntl;
         u32 rb_bufsz;
         u32 wb_offset;
         int i, j, r;
 
         for (i = 0; i < adev->sdma.num_instances; i++) {
                 ring = &adev->sdma.instance[i].ring;
                 wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 for (j = 0; j < 16; j++) {
                         cik_srbm_select(adev, 0, 0, 0, j);
                         /* SDMA GFX */
                         WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                         WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                         /* XXX SDMA RLC - todo */
                 }
                 cik_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                 WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                        adev->gfx.config.gb_addr_config & 0x70);
 
                 WREG32(mmSDMA0_SEM_INCOMPLETE_TIMER_CNTL + sdma_offsets[i], 0);
                 WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                 /* Set ring buffer size in dwords */
                 rb_bufsz = order_base_2(ring->ring_size / 4);
                 rb_cntl = rb_bufsz << 1;
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +10 -10
index c0cfcb9..83391d5 100644
@@ -1856,31 +1856,31 @@ static void gmc_v7_0_init_compute_vmid(struct amdgpu_device *adev)
         /*
          * Configure apertures:
          * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
          * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
          * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
         */
         sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
         sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                         SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
         sh_mem_config |= MTYPE_NONCACHED << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT;
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                 cik_srbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 WREG32(mmSH_MEM_CONFIG, sh_mem_config);
                 WREG32(mmSH_MEM_APE1_BASE, 1);
                 WREG32(mmSH_MEM_APE1_LIMIT, 0);
                 WREG32(mmSH_MEM_BASES, sh_mem_bases);
         }
         cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static void gfx_v7_0_config_init(struct amdgpu_device *adev)
  {
         adev->gfx.config.double_offchip_lds_buf = 1;
  }
 
  /**
   * gfx_v7_0_gpu_init - setup the 3D engine
   *
@@ -1929,36 +1929,36 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
                                    MTYPE_UC);
         sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, PRIVATE_ATC, 0);
 
         sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
                                    SWIZZLE_ENABLE, 1);
         sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                    ELEMENT_SIZE, 1);
         sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                    INDEX_STRIDE, 3);
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = 0; i < adev->vm_manager.num_ids; i++) {
                 if (i == 0)
                         sh_mem_base = 0;
                 else
                         sh_mem_base = adev->mc.shared_aperture_start >> 48;
                 cik_srbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 WREG32(mmSH_MEM_CONFIG, sh_mem_cfg);
                 WREG32(mmSH_MEM_APE1_BASE, 1);
                 WREG32(mmSH_MEM_APE1_LIMIT, 0);
                 WREG32(mmSH_MEM_BASES, sh_mem_base);
                 WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
         }
         cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
         gmc_v7_0_init_compute_vmid(adev);
 
         WREG32(mmSX_DEBUG_1, 0x20);
 
         WREG32(mmTA_CNTL_AUX, 0x00010000);
 
         tmp = RREG32(mmSPI_CONFIG_CNTL);
         tmp |= 0x03000000;
         WREG32(mmSPI_CONFIG_CNTL, tmp);
@@ -2962,40 +2962,40 @@ struct hqd_registers
         u32 cp_hqd_hq_scheduler1;
         u32 cp_mqd_control;
  };
 
  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);
+       spin_lock(&adev->srbm_lock);
         eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + eop_offset;
 
         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);
 
         /* 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);
 
         cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static int gfx_v7_0_mqd_deactivate(struct amdgpu_device *adev)
  {
         int i;
 
         /* 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++) {
@@ -3210,29 +3210,29 @@ static int gfx_v7_0_compute_queue_init(struct amdgpu_device *adev, int ring_id)
         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);
+       spin_lock(&adev->srbm_lock);
         cik_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
         gfx_v7_0_mqd_init(adev, mqd, mqd_gpu_addr, ring);
         gfx_v7_0_mqd_deactivate(adev);
         gfx_v7_0_mqd_commit(adev, mqd);
 
         cik_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
         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
@@ -5088,28 +5088,28 @@ static void gfx_v7_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                 DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                 return;
         }
 
         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);
+       spin_lock(&adev->srbm_lock);
         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);
+       spin_unlock(&adev->srbm_lock);
  }
 
  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) {
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +17 -17
index f0c1a3f..3cfe3c0 100644
@@ -3936,31 +3936,31 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev)
          */
         sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
         sh_mem_config = SH_MEM_ADDRESS_MODE_HSA64 <<
                         SH_MEM_CONFIG__ADDRESS_MODE__SHIFT |
                         SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                         SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT |
                         MTYPE_CC << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
                         SH_MEM_CONFIG__PRIVATE_ATC_MASK;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                 vi_srbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 WREG32(mmSH_MEM_CONFIG, sh_mem_config);
                 WREG32(mmSH_MEM_APE1_BASE, 1);
                 WREG32(mmSH_MEM_APE1_LIMIT, 0);
                 WREG32(mmSH_MEM_BASES, sh_mem_bases);
         }
         vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static void gfx_v8_0_config_init(struct amdgpu_device *adev)
  {
         switch (adev->asic_type) {
         default:
                 adev->gfx.config.double_offchip_lds_buf = 1;
                 break;
         case CHIP_CARRIZO:
         case CHIP_STONEY:
@@ -3985,21 +3985,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
         gfx_v8_0_config_init(adev);
 
         /* XXX SH_MEM regs */
         /* where to put LDS, scratch, GPUVM in FSA64 space */
         sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
                                    SWIZZLE_ENABLE, 1);
         sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                    ELEMENT_SIZE, 1);
         sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
                                    INDEX_STRIDE, 3);
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = 0; i < adev->vm_manager.num_ids; i++) {
                 vi_srbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 if (i == 0) {
                         tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_UC);
                         tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC);
                         tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
                                             SH_MEM_ALIGNMENT_MODE_UNALIGNED);
                         WREG32(mmSH_MEM_CONFIG, tmp);
                         WREG32(mmSH_MEM_BASES, 0);
@@ -4011,21 +4011,21 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
                         WREG32(mmSH_MEM_CONFIG, tmp);
                         tmp = adev->mc.shared_aperture_start >> 48;
                         WREG32(mmSH_MEM_BASES, tmp);
                 }
 
                 WREG32(mmSH_MEM_APE1_BASE, 1);
                 WREG32(mmSH_MEM_APE1_LIMIT, 0);
                 WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
         }
         vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
         gfx_v8_0_init_compute_vmid(adev);
 
         mutex_lock(&adev->grbm_idx_mutex);
         /*
          * making sure that the following register writes will be broadcasted
          * to all the shaders
          */
         gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -5142,70 +5142,70 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *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;
                 amdgpu_ring_clear_ring(ring);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                 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);
+               spin_unlock(&adev->srbm_lock);
         } else {
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                 gfx_v8_0_mqd_init(ring);
                 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);
+               spin_unlock(&adev->srbm_lock);
 
                 if (adev->gfx.mec.mqd_backup[mqd_idx])
                         memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
         }
 
         return r;
 
  out_unlock:
         vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
         return r;
  }
 
  static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
  {
         struct amdgpu_device *adev = ring->adev;
         struct vi_mqd *mqd = ring->mqd_ptr;
         int mqd_idx = ring - &adev->gfx.compute_ring[0];
 
         if (!adev->gfx.in_reset && !adev->gfx.in_suspend) {
                 memset((void *)mqd, 0, sizeof(*mqd));
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                 gfx_v8_0_mqd_init(ring);
                 vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                 if (adev->gfx.mec.mqd_backup[mqd_idx])
                         memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
         } else 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;
@@ -5486,32 +5486,32 @@ static bool gfx_v8_0_check_soft_reset(void *handle)
                 adev->gfx.srbm_soft_reset = 0;
                 return false;
         }
  }
 
  static void gfx_v8_0_inactive_hqd(struct amdgpu_device *adev,
                                   struct amdgpu_ring *ring)
  {
         int i;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
         if (RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK) {
                 WREG32_FIELD(CP_HQD_DEQUEUE_REQUEST, DEQUEUE_REQ, 2);
                 for (i = 0; i < adev->usec_timeout; i++) {
                         if (!(RREG32(mmCP_HQD_ACTIVE) & CP_HQD_ACTIVE__ACTIVE_MASK))
                                 break;
                         udelay(1);
                 }
         }
         vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
  }
 
  static int gfx_v8_0_pre_soft_reset(void *handle)
  {
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
         if ((!adev->gfx.grbm_soft_reset) &&
             (!adev->gfx.srbm_soft_reset))
                 return 0;
@@ -5603,27 +5603,27 @@ static int gfx_v8_0_soft_reset(void *handle)
 
         /* Wait a little for things to settle down */
         udelay(50);
 
         return 0;
  }
 
  static void gfx_v8_0_init_hqd(struct amdgpu_device *adev,
                               struct amdgpu_ring *ring)
  {
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
         WREG32(mmCP_HQD_DEQUEUE_REQUEST, 0);
         WREG32(mmCP_HQD_PQ_RPTR, 0);
         WREG32(mmCP_HQD_PQ_WPTR, 0);
         vi_srbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static int gfx_v8_0_post_soft_reset(void *handle)
  {
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
 
         if ((!adev->gfx.grbm_soft_reset) &&
             (!adev->gfx.srbm_soft_reset))
                 return 0;
@@ -6877,28 +6877,28 @@ static void gfx_v8_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                 DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                 return;
         }
 
         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);
+       spin_lock(&adev->srbm_lock);
         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);
+       spin_unlock(&adev->srbm_lock);
  }
 
  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);
 
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +12 -12
index 388a6bb..a16cee7 100644
@@ -1373,58 +1373,58 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev)
          * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
          * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
          * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
          */
         sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
 
         sh_mem_config = SH_MEM_ADDRESS_MODE_64 |
                         SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
                         SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
 
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
                 soc15_grbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config);
                 WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases);
         }
         soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
  {
         u32 tmp;
         int i;
 
         WREG32_FIELD15(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
 
         gfx_v9_0_tiling_mode_table_init(adev);
 
         gfx_v9_0_setup_rb(adev);
         gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 
         /* XXX SH_MEM regs */
         /* where to put LDS, scratch, GPUVM in FSA64 space */
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         for (i = 0; i < 16; i++) {
                 soc15_grbm_select(adev, 0, 0, 0, i);
                 /* CP and shaders */
                 tmp = 0;
                 tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
                                     SH_MEM_ALIGNMENT_MODE_UNALIGNED);
                 WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), tmp);
                 WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), 0);
         }
         soc15_grbm_select(adev, 0, 0, 0, 0);
 
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
         gfx_v9_0_init_compute_vmid(adev);
 
         mutex_lock(&adev->grbm_idx_mutex);
         /*
          * making sure that the following register writes will be broadcasted
          * to all the shaders
          */
         gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
@@ -2245,40 +2245,40 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)
         int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
 
         if (is_kiq) {
                 gfx_v9_0_kiq_setting(&kiq->ring);
         } else {
                 mqd_idx = ring - &adev->gfx.compute_ring[0];
         }
 
         if (!adev->gfx.in_reset) {
                 memset((void *)mqd, 0, sizeof(*mqd));
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                 gfx_v9_0_mqd_init(ring);
                 if (is_kiq)
                         gfx_v9_0_kiq_init_register(ring);
                 soc15_grbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
         } else { /* for GPU_RESET case */
                 /* reset MQD to a clean status */
 
                 /* reset ring buffer */
                 ring->wptr = 0;
 
                 if (is_kiq) {
-                   mutex_lock(&adev->srbm_mutex);
+                   spin_lock(&adev->srbm_lock);
                     soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
                     gfx_v9_0_kiq_init_register(ring);
                     soc15_grbm_select(adev, 0, 0, 0, 0);
-                   mutex_unlock(&adev->srbm_mutex);
+                   spin_unlock(&adev->srbm_lock);
                 }
         }
 
         if (is_kiq)
                 gfx_v9_0_kiq_enable(ring);
         else
                 gfx_v9_0_map_queue_enable(&kiq->ring, ring);
 
         return 0;
  }
@@ -3333,28 +3333,28 @@ static void gfx_v9_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
                 DRM_ERROR("Ignoring request to enable interrupts for invalid me:%d\n", me);
                 return;
         }
 
         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);
+       spin_lock(&adev->srbm_lock);
         soc15_grbm_select(adev, me, pipe, 0, 0);
 
         WREG32_FIELD(CPC_INT_CNTL, TIME_STAMP_INT_ENABLE,
                         state == AMDGPU_IRQ_STATE_DISABLE ? 0 : 1);
 
         soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
  }
 
  static int gfx_v9_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
                                              struct amdgpu_irq_src *source,
                                              unsigned type,
                                              enum amdgpu_interrupt_state state)
  {
         switch (state) {
         case AMDGPU_IRQ_STATE_DISABLE:
         case AMDGPU_IRQ_STATE_ENABLE:
@@ -3853,21 +3853,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
         memset(buf, 0, sizeof(struct v9_mqd));
 
         mqd = (struct v9_mqd *)buf;
         mqd->header = 0xC0310800;
         mqd->compute_pipelinestat_enable = 0x00000001;
         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;
         mqd->compute_misc_reserved = 0x00000003;
-       mutex_lock(&adev->srbm_mutex);
+       spin_lock(&adev->srbm_lock);
         soc15_grbm_select(adev, ring->me,
                                ring->pipe,
                                ring->queue, 0);
         /* disable wptr polling */
         WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
         /* write the EOP addr */
         BUG_ON(ring->me != 1 || ring->pipe != 0); /* can't handle other cases eop address */
         eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (ring->queue * MEC_HPD_SIZE);
         eop_gpu_addr >>= 8;
@@ -3997,21 +3997,21 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
         tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE));
         tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
         WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PERSISTENT_STATE), tmp);
         mqd->cp_hqd_persistent_state = tmp;
 
         /* activate the queue */
         mqd->cp_hqd_active = 1;
         WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), mqd->cp_hqd_active);
 
         soc15_grbm_select(adev, 0, 0, 0, 0);
-       mutex_unlock(&adev->srbm_mutex);
+       spin_unlock(&adev->srbm_lock);
 
         amdgpu_bo_kunmap(ring->mqd_obj);
         amdgpu_bo_unreserve(ring->mqd_obj);
 
         if (use_doorbell)
                 WREG32_FIELD15(GC, 0, CP_PQ_STATUS, DOORBELL_ENABLE, 1);
 
         return 0;
  }
 
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +2 -2
index f2d0710..0e0e344 100644
@@ -415,29 +415,29 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
         struct amdgpu_ring *ring;
         u32 rb_cntl, ib_cntl;
         u32 rb_bufsz;
         u32 wb_offset;
         int i, j, r;
 
         for (i = 0; i < adev->sdma.num_instances; i++) {
                 ring = &adev->sdma.instance[i].ring;
                 wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 for (j = 0; j < 16; j++) {
                         vi_srbm_select(adev, 0, 0, 0, j);
                         /* SDMA GFX */
                         WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                         WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                 }
                 vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                 WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                        adev->gfx.config.gb_addr_config & 0x70);
 
                 WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                 /* Set ring buffer size in dwords */
                 rb_bufsz = order_base_2(ring->ring_size / 4);
                 rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
                 rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +2 -3
index a69e5d4..f8a5da3 100644
@@ -609,29 +609,29 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
         u32 rb_bufsz;
         u32 wb_offset;
         u32 doorbell;
         int i, j, r;
 
         for (i = 0; i < adev->sdma.num_instances; i++) {
                 ring = &adev->sdma.instance[i].ring;
                 amdgpu_ring_clear_ring(ring);
                 wb_offset = (ring->rptr_offs * 4);
 
-               mutex_lock(&adev->srbm_mutex);
+               spin_lock(&adev->srbm_lock);
                 for (j = 0; j < 16; j++) {
                         vi_srbm_select(adev, 0, 0, 0, j);
                         /* SDMA GFX */
                         WREG32(mmSDMA0_GFX_VIRTUAL_ADDR + sdma_offsets[i], 0);
                         WREG32(mmSDMA0_GFX_APE1_CNTL + sdma_offsets[i], 0);
                 }
                 vi_srbm_select(adev, 0, 0, 0, 0);
-               mutex_unlock(&adev->srbm_mutex);
+               spin_unlock(&adev->srbm_lock);
 
                 WREG32(mmSDMA0_TILING_CONFIG + sdma_offsets[i],
                        adev->gfx.config.gb_addr_config & 0x70);
 
                 WREG32(mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL + sdma_offsets[i], 0);
 
                 /* Set ring buffer size in dwords */
                 rb_bufsz = order_base_2(ring->ring_size / 4);
                 rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
                 rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
--

2.9.3

Quoted 8 lines
Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#47 lore raw

PATCH 22/26 drm/amdgpu: implement ring set_priority for gfx_v8 compute v5

In reply to a message not in the archive

Programming CP_HQD_QUEUE_PRIORITY enables a queue to take priority over other queues on the same pipe. Multiple queues on a pipe are timesliced so this gives us full precedence over other queues.

Programming CP_HQD_PIPE_PRIORITY changes the SPI_ARB_PRIORITY of the wave as follows:

        0x2: CS_H
        0x1: CS_M
        0x0: CS_L

The SPI block will then dispatch work according to the policy set by SPI_ARB_PRIORITY. In the current policy CS_H is higher priority than gfx.

In order to prevent getting stuck in loops of CUs bouncing between GFX and high priority compute and introducing further latency, we reserve CUs 2+ for high priority compute on-demand.

v2: fix srbm_select to ring->queue and use ring->funcs->type
v3: use AMD_SCHED_PRIORITY_* instead of AMDGPU_CTX_PRIORITY_*
v4: switch int to enum amd_sched_priority
v5: corresponding changes for srbm_lock

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      | 96 +++++++++++++++++++++++++++++-
 3 files changed, 99 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -0
index b9a4161..c56a884 100644
@@ -1044,20 +1044,23 @@ struct amdgpu_gfx {
 	uint32_t			me_feature_version;
 	uint32_t			ce_feature_version;
 	uint32_t			pfp_feature_version;
 	uint32_t			rlc_feature_version;
 	uint32_t			mec_feature_version;
 	uint32_t			mec2_feature_version;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
 	unsigned			num_compute_rings;
+	spinlock_t			cu_reserve_lock;
+	uint32_t			cu_reserve_pipe_mask;
+	uint32_t			cu_reserve_queue_mask[AMDGPU_MAX_COMPUTE_RINGS];
 	struct amdgpu_irq_src		eop_irq;
 	struct amdgpu_irq_src		priv_reg_irq;
 	struct amdgpu_irq_src		priv_inst_irq;
 	/* 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;
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -0
index 07f16b4..29b45bb 100644
@@ -1874,20 +1874,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
 	spin_lock_init(&adev->mmio_idx_lock);
 	spin_lock_init(&adev->smc_idx_lock);
 	spin_lock_init(&adev->pcie_idx_lock);
 	spin_lock_init(&adev->uvd_ctx_idx_lock);
 	spin_lock_init(&adev->didt_idx_lock);
 	spin_lock_init(&adev->gc_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 	spin_lock_init(&adev->mm_stats.lock);
+	spin_lock_init(&adev->gfx.cu_reserve_lock);
 
 	INIT_LIST_HEAD(&adev->shadow_list);
 	mutex_init(&adev->shadow_list_lock);
 
 	INIT_LIST_HEAD(&adev->gtt_list);
 	spin_lock_init(&adev->gtt_list_lock);
 
 	INIT_LIST_HEAD(&adev->ring_lru_list);
 	spin_lock_init(&adev->ring_lru_list_lock);
 
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +95 -1

156 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-23-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org

#49 lore raw

Re: [PATCH 22/26] drm/amdgpu: implement ring set_priority for gfx_v8 compute v5

Quoted 165 lines · Andres Rodriguez

Programming CP_HQD_QUEUE_PRIORITY enables a queue to take priority over other queues on the same pipe. Multiple queues on a pipe are timesliced so this gives us full precedence over other queues.

Programming CP_HQD_PIPE_PRIORITY changes the SPI_ARB_PRIORITY of the wave as follows:

        0x2: CS_H
        0x1: CS_M
        0x0: CS_L

The SPI block will then dispatch work according to the policy set by SPI_ARB_PRIORITY. In the current policy CS_H is higher priority than gfx.

In order to prevent getting stuck in loops of CUs bouncing between GFX and high priority compute and introducing further latency, we reserve CUs 2+ for high priority compute on-demand.

v2: fix srbm_select to ring->queue and use ring->funcs->type
v3: use AMD_SCHED_PRIORITY_* instead of AMDGPU_CTX_PRIORITY_*
v4: switch int to enum amd_sched_priority
v5: corresponding changes for srbm_lock

---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      | 96 +++++++++++++++++++++++++++++-
 3 files changed, 99 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +3 -0
index b9a4161..c56a884 100644
@@ -1044,20 +1044,23 @@ struct amdgpu_gfx {
        uint32_t                        me_feature_version;
        uint32_t                        ce_feature_version;
        uint32_t                        pfp_feature_version;
        uint32_t                        rlc_feature_version;
        uint32_t                        mec_feature_version;
        uint32_t                        mec2_feature_version;
        struct amdgpu_ring              gfx_ring[AMDGPU_MAX_GFX_RINGS];
        unsigned                        num_gfx_rings;
        struct amdgpu_ring              compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
        unsigned                        num_compute_rings;
+       spinlock_t                      cu_reserve_lock;
+       uint32_t                        cu_reserve_pipe_mask;
+       uint32_t                        cu_reserve_queue_mask[AMDGPU_MAX_COMPUTE_RINGS];
        struct amdgpu_irq_src           eop_irq;
        struct amdgpu_irq_src           priv_reg_irq;
        struct amdgpu_irq_src           priv_inst_irq;
        /* 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;
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -0
index 07f16b4..29b45bb 100644
@@ -1874,20 +1874,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
        /* Registers mapping */
        /* TODO: block userspace mapping of io register */
        spin_lock_init(&adev->mmio_idx_lock);
        spin_lock_init(&adev->smc_idx_lock);
        spin_lock_init(&adev->pcie_idx_lock);
        spin_lock_init(&adev->uvd_ctx_idx_lock);
        spin_lock_init(&adev->didt_idx_lock);
        spin_lock_init(&adev->gc_cac_idx_lock);
        spin_lock_init(&adev->audio_endpt_idx_lock);
        spin_lock_init(&adev->mm_stats.lock);
+       spin_lock_init(&adev->gfx.cu_reserve_lock);
 
        INIT_LIST_HEAD(&adev->shadow_list);
        mutex_init(&adev->shadow_list_lock);
 
        INIT_LIST_HEAD(&adev->gtt_list);
        spin_lock_init(&adev->gtt_list_lock);
 
        INIT_LIST_HEAD(&adev->ring_lru_list);
        spin_lock_init(&adev->ring_lru_list_lock);
 
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +43 -1
index 3cfe3c0..f94d532 100644
@@ -46,21 +46,24 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "gca/gfx_8_0_enum.h"
 
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "smu/smu_7_1_3_d.h"
 
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_MEC_HPD_SIZE 2048
-
+#define GFX8_CU_RESERVE_RESOURCES 0x45888
+#define GFX8_CU_NUM 8
+#define GFX8_UNRESERVED_CU_NUM 2
+#define GFX8_CU_RESERVE_PIPE_SHIFT 7
 
 #define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
 #define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
 #define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
 
 #define ARRAY_MODE(x)                                  ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
 #define PIPE_CONFIG(x)                                 ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
 #define TILE_SPLIT(x)                                  ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
 #define MICRO_TILE_MODE_NEW(x)                         ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
@@ -6710,20 +6713,110 @@ static u64 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 
 static void gfx_v8_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 {
        struct amdgpu_device *adev = ring->adev;
 
        /* XXX check if swapping is necessary on BE */
        adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
        WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 }
 
+static void gfx_v8_0_cu_reserve(struct amdgpu_device *adev,
+                               struct amdgpu_ring *ring, bool acquire)
+{
+       int i, resources;
+       int tmp = 0, queue_mask = 0, type_mask = 0;
+       int reserve_res_reg, reserve_en_reg;
+
+       /* gfx_v8_0_cu_reserve only supports compute path */
+       if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
+               return;
+
+       spin_lock(&adev->gfx.cu_reserve_lock);
+       if (acquire) {
+               adev->gfx.cu_reserve_pipe_mask |= (1 << ring->pipe);
+               adev->gfx.cu_reserve_queue_mask[ring->pipe] |= (1 << ring->queue);
+       } else {
+               adev->gfx.cu_reserve_pipe_mask &= ~(1 << ring->pipe);
+               adev->gfx.cu_reserve_queue_mask[ring->pipe] &= ~(1 << ring->queue);
+       }
+
+       /* compute pipe 0 starts at GFX8_CU_RESERVE_PIPE_SHIFT */
+       type_mask = (adev->gfx.cu_reserve_pipe_mask << GFX8_CU_RESERVE_PIPE_SHIFT);
+
+       /* HW only has one register for queue mask, so we collaspse them */
+       for (i = 0; i < AMDGPU_MAX_COMPUTE_RINGS; i++)
+               queue_mask |= adev->gfx.cu_reserve_queue_mask[i];
+
+       /* leave the first CUs for general processing */
+       for (i = GFX8_UNRESERVED_CU_NUM; i < GFX8_CU_NUM; i++) {
+               reserve_res_reg = mmSPI_RESOURCE_RESERVE_CU_0 + i;
+               reserve_en_reg = mmSPI_RESOURCE_RESERVE_EN_CU_0 + i;
+
+               tmp = REG_SET_FIELD(tmp, SPI_RESOURCE_RESERVE_EN_CU_0,
+                                   TYPE_MASK, type_mask);
+               tmp = REG_SET_FIELD(tmp, SPI_RESOURCE_RESERVE_EN_CU_0,
+                                   QUEUE_MASK, queue_mask);
+               if (queue_mask) {
+                       resources = GFX8_CU_RESERVE_RESOURCES;
+                       tmp = REG_SET_FIELD(tmp, SPI_RESOURCE_RESERVE_EN_CU_0,

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static u64 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring) · line 6771

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+                                           EN, 1);
+               } else {
+                       resources = 0;
+                       tmp = REG_SET_FIELD(tmp, SPI_RESOURCE_RESERVE_EN_CU_0,
+                                           EN, 0);
+               }
+               /* Commit */
+               WREG32(reserve_res_reg, resources);
+               WREG32(reserve_en_reg, tmp);
+       }

Should these be programmed via the KIQ rather than MMIO? I think there may even be a special packet for this. John? Felix?

Quoted 15 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +15 -0
+
+       spin_unlock(&adev->gfx.cu_reserve_lock);
+}
+
+static void gfx_v8_0_set_spi_priority(struct amdgpu_device *adev,
+                                     struct amdgpu_ring *ring,
+                                     enum amd_sched_priority priority)
+{
+       spin_lock(&adev->srbm_lock);
+       vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
+
+       switch (priority) {
+       case AMD_SCHED_PRIORITY_NORMAL:
+               WREG32(mmCP_HQD_PIPE_PRIORITY, 0x0);
+               WREG32(mmCP_HQD_QUEUE_PRIORITY, 0x0);

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static u64 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring) · line 6796

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +10 -0
+               break;
+       case AMD_SCHED_PRIORITY_HIGH:
+               WREG32(mmCP_HQD_PIPE_PRIORITY, 0x2);
+               WREG32(mmCP_HQD_QUEUE_PRIORITY, 0xf);
+               break;
+       default:
+               WARN(1, "Attempt to set invalid SPI priority:%d for ring:%d\n",
+                               priority, ring->idx);
+               break;
+       }

I wonder if it would be better to program these via the KIQ rather than MMIO.

Quoted 51 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +17 -1
+
+       vi_srbm_select(adev, 0, 0, 0, 0);
+       spin_unlock(&adev->srbm_lock);
+}
+static void gfx_v8_0_ring_set_priority_compute(struct amdgpu_ring *ring,
+                                              enum amd_sched_priority priority)
+{
+       struct amdgpu_device *adev = ring->adev;
+
+       if (ring->funcs->type != AMDGPU_RING_TYPE_COMPUTE)
+               return;
+
+       gfx_v8_0_set_spi_priority(adev, ring, priority);
+       gfx_v8_0_cu_reserve(adev, ring, priority == AMD_SCHED_PRIORITY_HIGH);
+}
+
 static void gfx_v8_0_ring_emit_fence_compute(struct amdgpu_ring *ring,
                                             u64 addr, u64 seq,
                                             unsigned flags)
 {
        bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
        bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
 
        /* RELEASE_MEM - flush caches, send int */
        amdgpu_ring_write(ring, PACKET3(PACKET3_RELEASE_MEM, 5));
        amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
@@ -7140,20 +7233,21 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
        .emit_fence = gfx_v8_0_ring_emit_fence_compute,
        .emit_pipeline_sync = gfx_v8_0_ring_emit_pipeline_sync,
        .emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
        .emit_gds_switch = gfx_v8_0_ring_emit_gds_switch,
        .emit_hdp_flush = gfx_v8_0_ring_emit_hdp_flush,
        .emit_hdp_invalidate = gfx_v8_0_ring_emit_hdp_invalidate,
        .test_ring = gfx_v8_0_ring_test_ring,
        .test_ib = gfx_v8_0_ring_test_ib,
        .insert_nop = amdgpu_ring_insert_nop,
        .pad_ib = amdgpu_ring_generic_pad_ib,
+       .set_priority = gfx_v8_0_ring_set_priority_compute,
 };
 
 static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_kiq = {
        .type = AMDGPU_RING_TYPE_KIQ,
        .align_mask = 0xff,
        .nop = PACKET3(PACKET3_NOP, 0x3FFF),
        .support_64bit_ptrs = false,
        .get_rptr = gfx_v8_0_ring_get_rptr,
        .get_wptr = gfx_v8_0_ring_get_wptr_compute,
        .set_wptr = gfx_v8_0_ring_set_wptr_compute,
--

2.9.3

Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

#50 lore raw

PATCH 23/26 drm/amdgpu: condense mqd programming sequence

In reply to a message not in the archive

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.

---
 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(-)
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +11 -33
index 83391d5..1d178d9 100644
@@ -3130,61 +3130,39 @@ static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
 	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];
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +12 -72

108 lines not on this page · raw message

Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#51 lore raw

PATCH 24/26 drm/amdgpu: workaround tonga HW bug in HQD programming sequence

In reply to a message not in the archive

Tonga based asics may experience hangs when an HQD's EOP parameters are modified.

Workaround this HW issue by avoiding writes to these registers for tonga asics.

Based on the following ROCm commit:
2a0fb8 - drm/amdgpu: Synchronize KFD HQD load protocol with CP scheduler

From the ROCm git repository:
https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver.git

---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +15 -1
index 9bc706f..9408ae8 100644
@@ -5057,21 +5057,35 @@ int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd)
 	uint32_t mqd_reg;
 	uint32_t *mqd_data;
 
 	/* HQD registers extend from mmCP_MQD_BASE_ADDR to mmCP_HQD_ERROR */
 	mqd_data = &mqd->cp_mqd_base_addr_lo;
 
 	/* disable wptr polling */
 	WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0);
 
 	/* program all HQD registers */
-	for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_HQD_ERROR; mqd_reg++)
+	for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_HQD_EOP_CONTROL; mqd_reg++)
+		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
+
+	/* Tonga errata: EOP RPTR/WPTR should be left unmodified.
+	 * This is safe since EOP RPTR==WPTR for any inactive HQD
+	 * on ASICs that do not support context-save.
+	 * EOP writes/reads can start anywhere in the ring.
+	 */
+	if (adev->asic_type != CHIP_TONGA) {
+		WREG32(mmCP_HQD_EOP_RPTR, mqd->cp_hqd_eop_rptr);
+		WREG32(mmCP_HQD_EOP_WPTR, mqd->cp_hqd_eop_wptr);
+		WREG32(mmCP_HQD_EOP_WPTR_MEM, mqd->cp_hqd_eop_wptr_mem);
+	}
+
+	for (mqd_reg = mmCP_HQD_EOP_EVENTS; mqd_reg <= mmCP_HQD_ERROR; mqd_reg++)
 		WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]);
 
 	/* 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)
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#52 lore raw

PATCH 25/26 drm/amdgpu: guarantee bijective mapping of ring ids for LRU v3

In reply to a message not in the archive

Depending on usage patterns, the current LRU policy may create a non-injective mapping between userspace ring ids and kernel rings.

This behaviour is undesired as apps that attempt to fill all HW blocks would be unable to reach some of them.

This change forces the LRU policy to create bijective mappings only.

v2: compress ring_blacklist
v3: simplify amdgpu_ring_is_blacklisted() logic

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c | 16 +++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c      | 33 +++++++++++++++++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h      |  4 ++--
 3 files changed, 42 insertions(+), 11 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c +14 -2
index 926da09..adf59ef 100644
@@ -109,24 +109,36 @@ static enum amdgpu_ring_type amdgpu_hw_ip_to_ring_type(int hw_ip)
 		DRM_ERROR("Invalid HW IP specified %d\n", hw_ip);
 		return -1;
 	}
 }
 
 static int amdgpu_lru_map(struct amdgpu_device *adev,
 			  struct amdgpu_queue_mapper *mapper,
 			  int user_ring,
 			  struct amdgpu_ring **out_ring)
 {
-	int r;
+	int r, i, j;
 	int ring_type = amdgpu_hw_ip_to_ring_type(mapper->hw_ip);
+	int ring_blacklist[AMDGPU_MAX_RINGS];
+	struct amdgpu_ring *ring;
 
-	r = amdgpu_ring_lru_get(adev, ring_type, out_ring);
+	/* 0 is a valid ring index, so initialize to -1 */
+	memset(ring_blacklist, 0xff, sizeof(ring_blacklist));
+
+	for (i = 0, j = 0; i < AMDGPU_MAX_RINGS; i++) {
+		ring = mapper->queue_map[i];
+		if (ring)
+			ring_blacklist[j++] = ring->idx;
+	}
+
+	r = amdgpu_ring_lru_get(adev, ring_type, ring_blacklist,
+				j, out_ring);
 	if (r)
 		return r;
 
 	return amdgpu_update_cached_map(mapper, user_ring, *out_ring);
 }
 
 /**
  * amdgpu_queue_mgr_init - init an amdgpu_queue_mgr struct
  *
  * @adev: amdgpu_device pointer
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +26 -7
index b1af952..09fa8f7 100644
@@ -419,46 +419,65 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 	ring->adev->rings[ring->idx] = NULL;
 }
 
 static void amdgpu_ring_lru_touch_locked(struct amdgpu_device *adev,
 					 struct amdgpu_ring *ring)
 {
 	/* list_move_tail handles the case where ring isn't part of the list */
 	list_move_tail(&ring->lru_list, &adev->ring_lru_list);
 }
 
+static bool amdgpu_ring_is_blacklisted(struct amdgpu_ring *ring,
+				       int *blacklist, int num_blacklist)
+{
+	int i;
+
+	for (i = 0; i < num_blacklist; i++) {
+		if (ring->idx == blacklist[i])
+			return true;
+	}
+
+	return false;
+}
+
 /**
  * amdgpu_ring_lru_get - get the least recently used ring for a HW IP block
  *
  * @adev: amdgpu_device pointer
  * @type: amdgpu_ring_type enum
+ * @blacklist: blacklisted ring ids array
+ * @num_blacklist: number of entries in @blacklist
  * @ring: output ring
  *
  * Retrieve the amdgpu_ring structure for the least recently used ring of
  * a specific IP block (all asics).
  * Returns 0 on success, error on failure.
  */
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
-			struct amdgpu_ring **ring)
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
+			int num_blacklist, struct amdgpu_ring **ring)
 {
 	struct amdgpu_ring *entry;
 
 	/* List is sorted in LRU order, find first entry corresponding
 	 * to the desired HW IP */
 	*ring = NULL;
 	spin_lock(&adev->ring_lru_list_lock);
 	list_for_each_entry(entry, &adev->ring_lru_list, lru_list) {
-		if (entry->funcs->type == type) {
-			*ring = entry;
-			amdgpu_ring_lru_touch_locked(adev, *ring);
-			break;
-		}
+		if (entry->funcs->type != type)
+			continue;
+
+		if (amdgpu_ring_is_blacklisted(entry, blacklist, num_blacklist))
+			continue;
+
+		*ring = entry;
+		amdgpu_ring_lru_touch_locked(adev, *ring);
+		break;
 	}
 	spin_unlock(&adev->ring_lru_list_lock);
 
 	if (!*ring) {
 		DRM_ERROR("Ring LRU contains no entries for ring type:%d\n", type);
 		return -EINVAL;
 	}
 
 	return 0;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +2 -2
index e8ba708..2de56f8 100644
@@ -203,22 +203,22 @@ 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_priority_get(struct amdgpu_ring *ring,
 			     enum amd_sched_priority priority);
 void amdgpu_ring_priority_put(struct amdgpu_ring *ring,
 			      enum amd_sched_priority priority);
 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);
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int hw_ip,
-			struct amdgpu_ring **ring);
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
+			int num_blacklist, struct amdgpu_ring **ring);
 void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {
 	int i = 0;
 	while (i <= ring->buf_mask)
 		ring->ring[i++] = ring->funcs->nop;
 
 }
 
 #endif
Signature · 6 lines
2.9.3

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 20170406062139.3335-26-andresx7-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org