drm/amdgpu/vcn: move more instanced data to vcn_instance

Move more per instance data into the per instance structure.

v2: index instances directly on vcn1.0 and 2.0 to make
it clear that they only support a single instance (Lijo)
v3: fix typo on vcn 2.5

Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com> (v2)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 36 insertions, 31 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index acfe85b0c062..282a186cb0c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -127,11 +127,13 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i;
 
 	if (amdgpu_sriov_vf(adev)) {
 		adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
 		adev->vcn.harvest_config = 0;
-		adev->vcn.num_enc_rings = 1;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++)
+			adev->vcn.inst[i].num_enc_rings = 1;
 
 	} else {
 		if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 |
@@ -139,11 +141,13 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
 			/* both instances are harvested, disable the block */
 			return -ENOENT;
 
-		if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
-		    IP_VERSION(3, 0, 33))
-			adev->vcn.num_enc_rings = 0;
-		else
-			adev->vcn.num_enc_rings = 2;
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+			if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
+			    IP_VERSION(3, 0, 33))
+				adev->vcn.inst[i].num_enc_rings = 0;
+			else
+				adev->vcn.inst[i].num_enc_rings = 2;
+		}
 	}
 
 	vcn_v3_0_set_dec_ring_funcs(adev);
@@ -198,22 +202,22 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
-		adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
 
-		adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.scratch9 = SOC15_REG_OFFSET(VCN, i, mmUVD_SCRATCH9);
-		adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.data0 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA0);
-		adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.data1 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA1);
-		adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.cmd = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_CMD);
-		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
+		adev->vcn.inst[i].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 		adev->vcn.inst[i].external.nop = SOC15_REG_OFFSET(VCN, i, mmUVD_NO_OP);
 
 		/* VCN DEC TRAP */
@@ -227,7 +231,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		ring = &adev->vcn.inst[i].ring_dec;
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev)) {
-			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1);
+			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1);
 		} else {
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i;
 		}
@@ -239,7 +243,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j);
 
 			/* VCN ENC TRAP */
@@ -251,7 +255,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->use_doorbell = true;
 			if (amdgpu_sriov_vf(adev)) {
-				ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1 + j;
+				ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1 + j;
 			} else {
 				ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i;
 			}
@@ -277,6 +281,9 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			adev->vcn.inst[i].pause_dpg_mode = vcn_v3_0_pause_dpg_mode;
 	}
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -284,8 +291,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 	}
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		adev->vcn.pause_dpg_mode = vcn_v3_0_pause_dpg_mode;
 
 	/* Allocate memory for VCN IP Dump buffer */
 	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
@@ -373,7 +378,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
 				ring->sched.ready = true;
 			}
 
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 				ring = &adev->vcn.inst[i].ring_enc[j];
 				if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) {
 					ring->sched.ready = false;
@@ -401,7 +406,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block)
 			if (r)
 				return r;
 
-			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 				ring = &adev->vcn.inst[i].ring_enc[j];
 				r = amdgpu_ring_test_helper(ring);
 				if (r)
@@ -1153,7 +1158,7 @@ static int vcn_v3_0_start(struct amdgpu_device *adev, int i)
 		amdgpu_dpm_enable_vcn(adev, true, i);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
-		return vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
+		return vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.inst[i].indirect_sram);
 
 	/* disable VCN power gating */
 	vcn_v3_0_disable_static_power_gating(adev, i);
@@ -1433,7 +1438,7 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 			mmUVD_VCPU_CACHE_SIZE2),
 			AMDGPU_VCN_CONTEXT_SIZE);
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->wptr = 0;
 			rb_addr = ring->gpu_addr;
@@ -1924,11 +1929,11 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 		uint32_t reg = amdgpu_ib_get_value(ib, i);
 		uint32_t val = amdgpu_ib_get_value(ib, i + 1);
 
-		if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) {
+		if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data0, 0)) {
 			msg_lo = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) {
+		} else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data1, 0)) {
 			msg_hi = val;
-		} else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) &&
+		} else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.cmd, 0) &&
 			   val == 0) {
 			r = vcn_v3_0_dec_msg(p, job,
 					     ((u64)msg_hi) << 32 | msg_lo);
@@ -2092,7 +2097,7 @@ static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) {
 			adev->vcn.inst[i].ring_enc[j].funcs = &vcn_v3_0_enc_ring_vm_funcs;
 			adev->vcn.inst[i].ring_enc[j].me = i;
 		}
@@ -2258,7 +2263,7 @@ static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v3_0_irq_funcs;
 	}
 }