drm/amdgpu: Use instance lookup table for GC 9.4.3

Register accesses need to be based on physical instance on bare metal.
Pass the right instance using logical to physical instance lookup
table before accessing registers. Add a macro GET_INST to get the right
physical instance of an IP corresponding to a logical instance.

v2: fix gfx_v9_4_3_check_rlcg_range() (Alex)
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c

@@ -279,8 +279,8 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd,
 
 	/* HQD registers extend to CP_HQD_AQL_DISPATCH_ID_HI */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
-	hqd_base = SOC15_REG_OFFSET(GC, inst, regCP_MQD_BASE_ADDR);
-	hqd_end = SOC15_REG_OFFSET(GC, inst, regCP_HQD_AQL_DISPATCH_ID_HI);
+	hqd_base = SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_MQD_BASE_ADDR);
+	hqd_end = SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_AQL_DISPATCH_ID_HI);
 
 	for (reg = hqd_base; reg <= hqd_end; reg++)
 		WREG32_RLC(reg, mqd_hqd[reg - hqd_base]);
@@ -289,7 +289,7 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd,
 	/* Activate doorbell logic before triggering WPTR poll. */
 	data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_PQ_DOORBELL_CONTROL),
+	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL),
 				data);
 
 	if (wptr) {
@@ -319,27 +319,27 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd,
 		guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1);
 		guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32;
 
-		WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_PQ_WPTR_LO),
+		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_LO),
 		       lower_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_PQ_WPTR_HI),
+		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_HI),
 		       upper_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_PQ_WPTR_POLL_ADDR),
+		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR),
 		       lower_32_bits((uintptr_t)wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, inst,
+		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
 			regCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 			upper_32_bits((uintptr_t)wptr));
-		WREG32(SOC15_REG_OFFSET(GC, inst, regCP_PQ_WPTR_POLL_CNTL1),
+		WREG32(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_PQ_WPTR_POLL_CNTL1),
 		       (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id,
 			       queue_id));
 	}
 
 	/* Start the EOP fetcher */
-	WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_EOP_RPTR),
+	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_EOP_RPTR),
 	       REG_SET_FIELD(m->cp_hqd_eop_rptr,
 			     CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
 
 	data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, inst, regCP_HQD_ACTIVE), data);
+	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_ACTIVE), data);
 
 	kgd_gfx_v9_release_queue(adev, inst);
 

drivers/gpu/drm/amd/amdgpu/soc15_common.h

@@ -24,6 +24,9 @@
 #ifndef __SOC15_COMMON_H__
 #define __SOC15_COMMON_H__
 
+/* GET_INST returns the physical instance corresponding to a logical instance */
+#define GET_INST(ip, inst) (adev->ip_map.logical_to_dev_inst? adev->ip_map.logical_to_dev_inst(adev, ip##_HWIP, inst): inst)
+
 /* Register Access Macros */
 #define SOC15_REG_OFFSET(ip, inst, reg)	(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
 #define SOC15_REG_OFFSET1(ip, inst, reg, offset) \