1 files changed, 26 insertions, 16 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index b66c5f7e1c56..2ac5820e9c92 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -817,7 +817,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 					uint32_t vmhub, uint32_t flush_type)
 {
 	bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub);
-	u32 j, inv_req, tmp, sem, req, ack;
+	u32 j, inv_req, tmp, sem, req, ack, inst;
 	const unsigned int eng = 17;
 	struct amdgpu_vmhub *hub;
 
@@ -832,13 +832,17 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	/* This is necessary for a HW workaround under SRIOV as well
 	 * as GFXOFF under bare metal
 	 */
-	if (adev->gfx.kiq[0].ring.sched.ready &&
+	if (vmhub >= AMDGPU_MMHUB0(0))
+		inst = GET_INST(GC, 0);
+	else
+		inst = vmhub;
+	if (adev->gfx.kiq[inst].ring.sched.ready &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		uint32_t req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 		uint32_t ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-						   1 << vmid);
+						   1 << vmid, inst);
 		return;
 	}
 
@@ -856,9 +860,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		for (j = 0; j < adev->usec_timeout; j++) {
 			/* a read return value of 1 means semaphore acquire */
 			if (vmhub >= AMDGPU_MMHUB0(0))
-				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem, inst);
 			else
-				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem, inst);
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -869,9 +873,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	if (vmhub >= AMDGPU_MMHUB0(0))
-		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req, inst);
 	else
-		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req, inst);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to
@@ -884,9 +888,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	for (j = 0; j < adev->usec_timeout; j++) {
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack, inst);
 		else
-			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack, inst);
 		if (tmp & (1 << vmid))
 			break;
 		udelay(1);
@@ -899,9 +903,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		 * write with 0 means semaphore release
 		 */
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0, inst);
 		else
-			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0, inst);
 	}
 
 	spin_unlock(&adev->gmc.invalidate_lock);
@@ -1176,7 +1180,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 		if (uncached) {
 			mtype = MTYPE_UC;
 		} else if (ext_coherent) {
-			mtype = is_local ? MTYPE_CC : MTYPE_UC;
+			if (adev->rev_id)
+				mtype = is_local ? MTYPE_CC : MTYPE_UC;
+			else
+				mtype = MTYPE_UC;
 		} else if (adev->flags & AMD_IS_APU) {
 			mtype = is_local ? mtype_local : MTYPE_NC;
 		} else {
@@ -1297,7 +1304,7 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 
 			*flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) |
 				 AMDGPU_PTE_MTYPE_VG10(mtype_local);
-		} else {
+		} else if (adev->rev_id) {
 			/* MTYPE_UC case */
 			*flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) |
 				 AMDGPU_PTE_MTYPE_VG10(MTYPE_CC);
@@ -1614,6 +1621,8 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 {
 	u64 base = adev->mmhub.funcs->get_fb_location(adev);
 
+	amdgpu_gmc_set_agp_default(adev, mc);
+
 	/* add the xgmi offset of the physical node */
 	base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
 	if (adev->gmc.xgmi.connected_to_cpu) {
@@ -1621,7 +1630,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	} else {
 		amdgpu_gmc_vram_location(adev, mc, base);
 		amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
-		if (!amdgpu_sriov_vf(adev))
+		if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1))
 			amdgpu_gmc_agp_location(adev, mc);
 	}
 	/* base offset of vram pages */
@@ -2161,8 +2170,6 @@ static int gmc_v9_0_sw_fini(void *handle)
 
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3))
 		amdgpu_gmc_sysfs_fini(adev);
-	adev->gmc.num_mem_partitions = 0;
-	kfree(adev->gmc.mem_partitions);
 
 	amdgpu_gmc_ras_fini(adev);
 	amdgpu_gem_force_release(adev);
@@ -2176,6 +2183,9 @@ static int gmc_v9_0_sw_fini(void *handle)
 	amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0);
 	amdgpu_bo_fini(adev);
 
+	adev->gmc.num_mem_partitions = 0;
+	kfree(adev->gmc.mem_partitions);
+
 	return 0;
 }