1 files changed, 72 insertions, 64 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 41c6b3aacd37..239e71174855 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -125,6 +125,7 @@ const char *amdgpu_asic_name[] = {
 	"DIMGREY_CAVEFISH",
 	"BEIGE_GOBY",
 	"YELLOW_CARP",
+	"IP DISCOVERY",
 	"LAST",
 };
 
@@ -305,7 +306,7 @@ void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
 	uint64_t last;
 	int idx;
 
-	if (!drm_dev_enter(&adev->ddev, &idx))
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
 		return;
 
 	BUG_ON(!IS_ALIGNED(pos, 4) || !IS_ALIGNED(size, 4));
@@ -2126,46 +2127,11 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 		break;
-	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	case CHIP_RAVEN:
-	case CHIP_ARCTURUS:
-	case CHIP_RENOIR:
-	case CHIP_ALDEBARAN:
-		if (adev->flags & AMD_IS_APU)
-			adev->family = AMDGPU_FAMILY_RV;
-		else
-			adev->family = AMDGPU_FAMILY_AI;
-
-		r = soc15_set_ip_blocks(adev);
-		if (r)
-			return r;
-		break;
-	case  CHIP_NAVI10:
-	case  CHIP_NAVI14:
-	case  CHIP_NAVI12:
-	case  CHIP_SIENNA_CICHLID:
-	case  CHIP_NAVY_FLOUNDER:
-	case  CHIP_DIMGREY_CAVEFISH:
-	case  CHIP_BEIGE_GOBY:
-	case CHIP_VANGOGH:
-	case CHIP_YELLOW_CARP:
-	case CHIP_CYAN_SKILLFISH:
-		if (adev->asic_type == CHIP_VANGOGH)
-			adev->family = AMDGPU_FAMILY_VGH;
-		else if (adev->asic_type == CHIP_YELLOW_CARP)
-			adev->family = AMDGPU_FAMILY_YC;
-		else
-			adev->family = AMDGPU_FAMILY_NV;
-
-		r = nv_set_ip_blocks(adev);
+	default:
+		r = amdgpu_discovery_set_ip_blocks(adev);
 		if (r)
 			return r;
 		break;
-	default:
-		/* FIXME: not supported yet */
-		return -EINVAL;
 	}
 
 	amdgpu_amdkfd_device_probe(adev);
@@ -2432,6 +2398,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -2741,6 +2711,11 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
+	if (amdgpu_sriov_vf(adev)) {
+		if (amdgpu_virt_release_full_gpu(adev, false))
+			DRM_ERROR("failed to release exclusive mode on fini\n");
+	}
+
 	return 0;
 }
 
@@ -2801,10 +2776,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 
 	amdgpu_ras_fini(adev);
 
-	if (amdgpu_sriov_vf(adev))
-		if (amdgpu_virt_release_full_gpu(adev, false))
-			DRM_ERROR("failed to release exclusive mode on fini\n");
-
 	return 0;
 }
 
@@ -3148,6 +3119,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -3232,6 +3207,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_RENOIR:
+	case CHIP_CYAN_SKILLFISH:
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
 	case CHIP_DIMGREY_CAVEFISH:
@@ -3239,13 +3215,15 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
 #endif
+	default:
 		return amdgpu_dc != 0;
-#endif
+#else
 	default:
 		if (amdgpu_dc > 0)
 			DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
 					 "but isn't supported by ASIC, ignoring\n");
 		return false;
+#endif
 	}
 }
 
@@ -3346,6 +3324,8 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 				continue;
 			} else if (timeout < 0) {
 				timeout = MAX_SCHEDULE_TIMEOUT;
+				dev_warn(adev->dev, "lockup timeout disabled");
+				add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 			} else {
 				timeout = msecs_to_jiffies(timeout);
 			}
@@ -3530,17 +3510,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	DRM_INFO("register mmio base: 0x%08X\n", (uint32_t)adev->rmmio_base);
 	DRM_INFO("register mmio size: %u\n", (unsigned)adev->rmmio_size);
 
-	/* enable PCIE atomic ops */
-	r = pci_enable_atomic_ops_to_root(adev->pdev,
-					  PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
-					  PCI_EXP_DEVCAP2_ATOMIC_COMP64);
-	if (r) {
-		adev->have_atomics_support = false;
-		DRM_INFO("PCIE atomic ops is not supported\n");
-	} else {
-		adev->have_atomics_support = true;
-	}
-
 	amdgpu_device_get_pcie_info(adev);
 
 	if (amdgpu_mcbp)
@@ -3563,6 +3532,19 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* enable PCIE atomic ops */
+	if (amdgpu_sriov_vf(adev))
+		adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *)
+			adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_enabled_flags ==
+			(PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	else
+		adev->have_atomics_support =
+			!pci_enable_atomic_ops_to_root(adev->pdev,
+					  PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
+					  PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	if (!adev->have_atomics_support)
+		dev_info(adev->dev, "PCIE atomic ops is not supported\n");
+
 	/* doorbell bar mapping and doorbell index init*/
 	amdgpu_device_doorbell_init(adev);
 
@@ -3861,6 +3843,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_device_ip_fini_early(adev);
 
+	ttm_device_clear_dma_mappings(&adev->mman.bdev);
+
 	amdgpu_gart_dummy_page_fini(adev);
 
 	amdgpu_device_unmap_mmio(adev);
@@ -3901,6 +3885,25 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 }
 
+/**
+ * amdgpu_device_evict_resources - evict device resources
+ * @adev: amdgpu device object
+ *
+ * Evicts all ttm device resources(vram BOs, gart table) from the lru list
+ * of the vram memory type. Mainly used for evicting device resources
+ * at suspend time.
+ *
+ */
+static void amdgpu_device_evict_resources(struct amdgpu_device *adev)
+{
+	/* No need to evict vram on APUs for suspend to ram */
+	if (adev->in_s3 && (adev->flags & AMD_IS_APU))
+		return;
+
+	if (amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM))
+		DRM_WARN("evicting device resources failed\n");
+
+}
 
 /*
  * Suspend & resume.
@@ -3941,17 +3944,16 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (!adev->in_s0ix)
 		amdgpu_amdkfd_suspend(adev, adev->in_runpm);
 
-	/* evict vram memory */
-	amdgpu_bo_evict_vram(adev);
+	/* First evict vram memory */
+	amdgpu_device_evict_resources(adev);
 
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
-	/* evict remaining vram memory
-	 * This second call to evict vram is to evict the gart page table
-	 * using the CPU.
+	/* This second call to evict device resources is to evict
+	 * the gart page table using the CPU.
 	 */
-	amdgpu_bo_evict_vram(adev);
+	amdgpu_device_evict_resources(adev);
 
 	return 0;
 }
@@ -4458,10 +4460,6 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	if (reset_context->reset_req_dev == adev)
 		job = reset_context->job;
 
-	/* no need to dump if device is not in good state during probe period */
-	if (!adev->gmc.xgmi.pending_reset)
-		amdgpu_debugfs_wait_dump(adev);
-
 	if (amdgpu_sriov_vf(adev)) {
 		/* stop the data exchange thread */
 		amdgpu_virt_fini_data_exchange(adev);
@@ -4601,6 +4599,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
+				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
+				if (r)
+					goto out;
+
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)
 					goto out;
@@ -5387,6 +5389,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	adev->pci_channel_state = state;
+
 	switch (state) {
 	case pci_channel_io_normal:
 		return PCI_ERS_RESULT_CAN_RECOVER;
@@ -5529,6 +5533,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 	DRM_INFO("PCI error: resume callback!!\n");
 
+	/* Only continue execution for the case of pci_channel_io_frozen */
+	if (adev->pci_channel_state != pci_channel_io_frozen)
+		return;
+
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];