1 files changed, 97 insertions, 81 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 41c6b3aacd37..90d22a376632 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);
@@ -2741,6 +2707,11 @@ 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 +2772,6 @@ 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 +3115,10 @@ 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;
@@ -3196,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
-#if defined(CONFIG_DRM_AMD_DC_SI)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
+		/*
+		 * We have systems in the wild with these ASICs that require
+		 * LVDS and VGA support which is not supported with DC.
+		 *
+		 * Fallback to the non-DC driver here by default so as not to
+		 * cause regressions.
+		 */
+#if defined(CONFIG_DRM_AMD_DC_SI)
+		return amdgpu_dc > 0;
+#else
+		return false;
 #endif
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
@@ -3232,6 +3213,7 @@ 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 +3221,15 @@ 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 +3330,8 @@ 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);
 			}
@@ -3523,6 +3509,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		adev->rmmio_size = pci_resource_len(adev->pdev, 2);
 	}
 
+	for (i = 0; i < AMD_IP_BLOCK_TYPE_NUM; i++)
+		atomic_set(&adev->pm.pwr_state[i], POWER_STATE_UNKNOWN);
+
 	adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
 	if (adev->rmmio == NULL) {
 		return -ENOMEM;
@@ -3530,17 +3519,6 @@ 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 +3541,19 @@ 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);
 
@@ -3696,8 +3687,6 @@ fence_driver_init:
 	/* Get a log2 for easy divisions. */
 	adev->mm_stats.log2_max_MBps = ilog2(max(1u, max_MBps));
 
-	amdgpu_fbdev_init(adev);
-
 	r = amdgpu_pm_sysfs_init(adev);
 	if (r) {
 		adev->pm_sysfs_en = false;
@@ -3842,7 +3831,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	/* disable all interrupts */
 	amdgpu_irq_disable_all(adev);
 	if (adev->mode_info.mode_config_initialized){
-		if (!amdgpu_device_has_dc_support(adev))
+		if (!drm_drv_uses_atomic_modeset(adev_to_drm(adev)))
 			drm_helper_force_disable_all(adev_to_drm(adev));
 		else
 			drm_atomic_helper_shutdown(adev_to_drm(adev));
@@ -3855,11 +3844,11 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		amdgpu_ucode_sysfs_fini(adev);
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 
-	amdgpu_fbdev_fini(adev);
+	amdgpu_device_ip_fini_early(adev);
 
 	amdgpu_irq_fini_hw(adev);
 
-	amdgpu_device_ip_fini_early(adev);
+	ttm_device_clear_dma_mappings(&adev->mman.bdev);
 
 	amdgpu_gart_dummy_page_fini(adev);
 
@@ -3868,8 +3857,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 {
-	amdgpu_device_ip_fini(adev);
 	amdgpu_fence_driver_sw_fini(adev);
+	amdgpu_device_ip_fini(adev);
 	release_firmware(adev->firmware.gpu_info_fw);
 	adev->firmware.gpu_info_fw = NULL;
 	adev->accel_working = false;
@@ -3901,6 +3890,25 @@ 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.
@@ -3930,7 +3938,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	drm_kms_helper_poll_disable(dev);
 
 	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 1);
+		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
@@ -3941,17 +3949,16 @@ 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;
 }
@@ -4008,7 +4015,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	flush_delayed_work(&adev->delayed_init_work);
 
 	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 0);
+		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false);
 
 	drm_kms_helper_poll_enable(dev);
 
@@ -4278,6 +4285,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 {
 	int r;
 
+	amdgpu_amdkfd_pre_reset(adev);
+
 	if (from_hypervisor)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 	else
@@ -4285,8 +4294,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
@@ -4307,7 +4314,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 
 	amdgpu_irq_gpu_reset_resume_helper(adev);
 	r = amdgpu_ib_ring_tests(adev);
-	amdgpu_amdkfd_post_reset(adev);
 
 error:
 	if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
@@ -4458,10 +4464,6 @@ 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 +4603,10 @@ 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;
@@ -4640,7 +4646,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				if (r)
 					goto out;
 
-				amdgpu_fbdev_set_suspend(tmp_adev, 0);
+				drm_fb_helper_set_suspend_unlocked(adev_to_drm(tmp_adev)->fb_helper, false);
 
 				/*
 				 * The GPU enters bad state once faulty pages
@@ -4848,6 +4854,9 @@ static void amdgpu_device_recheck_guilty_jobs(
 
 		/* clear job's guilty and depend the folowing step to decide the real one */
 		drm_sched_reset_karma(s_job);
+		/* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+		 * to make sure fence is balanced */
+		dma_fence_get(s_job->s_fence->parent);
 		drm_sched_resubmit_jobs_ext(&ring->sched, 1);
 
 		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@@ -4883,6 +4892,7 @@ retry:
 
 		/* got the hw fence, signal finished fence */
 		atomic_dec(ring->sched.score);
+		dma_fence_put(s_job->s_fence->parent);
 		dma_fence_get(&s_job->s_fence->finished);
 		dma_fence_signal(&s_job->s_fence->finished);
 		dma_fence_put(&s_job->s_fence->finished);
@@ -5027,7 +5037,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		 */
 		amdgpu_unregister_gpu_instance(tmp_adev);
 
-		amdgpu_fbdev_set_suspend(tmp_adev, 1);
+		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 		/* disable ras on ALL IPs */
 		if (!need_emergency_restart &&
@@ -5077,7 +5087,7 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 
 	tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter));
 	/* Actual ASIC resets if needed.*/
-	/* TODO Implement XGMI hive reset logic for SRIOV */
+	/* Host driver will handle XGMI hive reset for SRIOV */
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_device_reset_sriov(adev, job ? false : true);
 		if (r)
@@ -5118,7 +5128,7 @@ skip_hw_reset:
 			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
 		}
 
-		if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
+		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 		}
 
@@ -5139,7 +5149,7 @@ skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		/* unlock kfd: SRIOV would do it separately */
 		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
-	                amdgpu_amdkfd_post_reset(tmp_adev);
+			amdgpu_amdkfd_post_reset(tmp_adev);
 
 		/* kfd_post_reset will do nothing if kfd device is not initialized,
 		 * need to bring up kfd here if it's not be initialized before
@@ -5387,6 +5397,8 @@ 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 +5541,10 @@ 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];