Merge tag 'drm-fixes-2021-09-17' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie: "Slightly busier than usual rc2, but mostly scattered amdgpu fixes, some i915 and etnaviv resolves an MMU/runtime PM blowup. amdgpu: - UBSAN fix - Powerplay table update fix - Fix use after free in BO moves - Debugfs init fixes - vblank workqueue fixes for headless devices - FPU fixes - sysfs_emit fixes - SMU updates for cyan skillfish - Backlight fixes when DMCU is not initialized - DP MST fixes - HDCP compliance fix - Link training fix - Runtime pm fix - Panel orientation fixes - Display GPUVM fix for yellow carp - Add missing license amdkfd: - Drop PCI atomics requirement if proper firmware is available - Suspend/resume fixes for IOMMUv2 cases radeon: - AGP fix i915: - Propagate DP link training error returns - Use max link params for eDP 1.3 and earlier - Build warning fixes - Gem selftest fixes - Ensure wakeref is held before hardware access etnaviv: - MMU context vs runtime PM fix" * tag 'drm-fixes-2021-09-17' of git://anongit.freedesktop.org/drm/drm: (44 commits) drm/amdgpu/display: add a proper license to dc_link_dp.c drm/amd/display: Fix white screen page fault for gpuvm amd/display: enable panel orientation quirks drm/amdgpu: Demote TMZ unsupported log message from warning to info drm/amdgpu: Drop inline from amdgpu_ras_eeprom_max_record_count drm/amd/pm: fix runpm hang when amdgpu loaded prior to sound driver drm/radeon: pass drm dev radeon_agp_head_init directly drm/amdgpu: move iommu_resume before ip init/resume drm/amdgpu: add amdgpu_amdkfd_resume_iommu drm/amdkfd: separate kfd_iommu_resume from kfd_resume drm/amd/display: Link training retry fix for abort case drm/amd/display: Fix unstable HPCP compliance on Chrome Barcelo drm/amd/display: dsc mst 2 4K displays go dark with 2 lane HBR3 drm/amd/display: Get backlight from PWM if DMCU is not initialized drm/amdkfd: make needs_pcie_atomics FW-version dependent drm/amdgpu: add manual sclk/vddc setting support for cyan skilfish(v3) drm/amdgpu: add some pptable funcs for cyan skilfish(v3) drm/amdgpu: update SMU driver interface for cyan skilfish(v3) drm/amdgpu: update SMU PPSMC for cyan skilfish drm/amdgpu: fix sysfs_emit/sysfs_emit_at warnings(v2) ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2021-09-16 23:28:52 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2021-09-16 23:28:52 +0300
commit: bdb575f872175ed0ecf2638369da1cb7a6e86a14 (patch)
tree: 1b6996552c18be4a13c17174508eaae6ac68b6eb /drivers/gpu
parent: fc0c0548c1a2e676d3a928aaed70f2d4d254e395 (diff)
parent: 109f7ea9aedce437b4b7737ab60bfea65d9dbdd3 (diff)
download: linux-bdb575f872175ed0ecf2638369da1cb7a6e86a14.tar.xz
51 files changed, 945 insertions, 218 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index dc3c6b3a00e5..d356e329e6f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -758,7 +758,7 @@ enum amd_hw_ip_block_type {
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
 
 struct amd_powerplay {
 	void *pp_handle;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 3003ee1c9487..1d41c2c00623 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
 		kgd2kfd_suspend(adev->kfd.dev, run_pm);
 }
 
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_iommu(adev->kfd.dev);
+
+	return r;
+}
+
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
 {
 	int r = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ec028cf963f5..3bc52b2c604f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev);
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
@@ -327,6 +328,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -365,6 +367,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 }
 
+static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 277128846dd1..463b9c0283f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
-
-
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev,
 				  &fops_sclk_set);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	/* Register debugfs entries for amdgpu_ttm */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 41c6b3aacd37..ab3794c42d36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2394,6 +2394,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		goto init_failed;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	r = amdgpu_device_ip_hw_init_phase1(adev);
 	if (r)
 		goto init_failed;
@@ -3148,6 +3152,10 @@ 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;
@@ -4601,6 +4609,10 @@ 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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index c7797eac83c3..9ff600a38559 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	default:
 		adev->gmc.tmz_enabled = false;
-		dev_warn(adev->dev,
+		dev_info(adev->dev,
 			 "Trusted Memory Zone (TMZ) feature not supported\n");
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index dc44c946a244..98732518543e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -757,7 +757,7 @@ Out:
 	return res;
 }
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void)
+uint32_t amdgpu_ras_eeprom_max_record_count(void)
 {
 	return RAS_MAX_RECORD_COUNT;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index f95fc61b3021..6bb00578bfbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 			     struct eeprom_table_record *records, const u32 num);
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void);
+uint32_t amdgpu_ras_eeprom_max_record_count(void);
 
 void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 7b634a1517f9..0554576d3695 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	ent = debugfs_create_file(name,
 				  S_IFREG | S_IRUGO, root,
 				  ring, &amdgpu_debugfs_ring_fops);
-	if (!ent)
-		return -ENOMEM;
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
 
 	i_size_write(ent->d_inode, ring->ring_size + 12);
 	ring->ent = ent;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 38dade421d46..94126dc39688 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		goto out;
 	}
 
+	if (bo->type == ttm_bo_type_device &&
+	    new_mem->mem_type == TTM_PL_VRAM &&
+	    old_mem->mem_type != TTM_PL_VRAM) {
+		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
+		 * accesses the BO after it's moved.
+		 */
+		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+	}
+
 	if (adev->mman.buffer_funcs_enabled) {
 		if (((old_mem->mem_type == TTM_PL_SYSTEM &&
 		      new_mem->mem_type == TTM_PL_VRAM) ||
@@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	if (bo->type == ttm_bo_type_device &&
-	    new_mem->mem_type == TTM_PL_VRAM &&
-	    old_mem->mem_type != TTM_PL_VRAM) {
-		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
-		 * accesses the BO after it's moved.
-		 */
-		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	}
-
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 16a57b70cc1a..98d1b3ab3a46 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -468,6 +468,7 @@ static const struct kfd_device_info navi10_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -487,6 +488,7 @@ static const struct kfd_device_info navi12_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -506,6 +508,7 @@ static const struct kfd_device_info navi14_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 145,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -525,6 +528,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 4,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -544,6 +548,7 @@ static const struct kfd_device_info navy_flounder_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -562,7 +567,8 @@ static const struct kfd_device_info vangogh_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
@@ -582,6 +588,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -601,6 +608,7 @@ static const struct kfd_device_info beige_goby_device_info = {
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
 	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -619,7 +627,8 @@ static const struct kfd_device_info yellow_carp_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
+	.no_atomic_fw_version = 92,
 	.num_sdma_engines = 1,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
@@ -708,20 +717,6 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	if (!kfd)
 		return NULL;
 
-	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
-	 * 32 and 64-bit requests are possible and must be
-	 * supported.
-	 */
-	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd);
-	if (device_info->needs_pci_atomics &&
-	    !kfd->pci_atomic_requested) {
-		dev_info(kfd_device,
-			 "skipped device %x:%x, PCI rejects atomics\n",
-			 pdev->vendor, pdev->device);
-		kfree(kfd);
-		return NULL;
-	}
-
 	kfd->kgd = kgd;
 	kfd->device_info = device_info;
 	kfd->pdev = pdev;
@@ -821,6 +816,23 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
 			- kfd->vm_info.first_vmid_kfd + 1;
 
+	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
+	 * 32 and 64-bit requests are possible and must be
+	 * supported.
+	 */
+	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kfd->kgd);
+	if (!kfd->pci_atomic_requested &&
+	    kfd->device_info->needs_pci_atomics &&
+	    (!kfd->device_info->no_atomic_fw_version ||
+	     kfd->mec_fw_version < kfd->device_info->no_atomic_fw_version)) {
+		dev_info(kfd_device,
+			 "skipped device %x:%x, PCI rejects atomics %d<%d\n",
+			 kfd->pdev->vendor, kfd->pdev->device,
+			 kfd->mec_fw_version,
+			 kfd->device_info->no_atomic_fw_version);
+		return false;
+	}
+
 	/* Verify module parameters regarding mapped process number*/
 	if ((hws_max_conc_proc < 0)
 			|| (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) {
@@ -1057,17 +1069,21 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 	return ret;
 }
 
-static int kfd_resume(struct kfd_dev *kfd)
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd)
 {
 	int err = 0;
 
 	err = kfd_iommu_resume(kfd);
-	if (err) {
+	if (err)
 		dev_err(kfd_device,
 			"Failed to resume IOMMU for device %x:%x\n",
 			kfd->pdev->vendor, kfd->pdev->device);
-		return err;
-	}
+	return err;
+}
+
+static int kfd_resume(struct kfd_dev *kfd)
+{
+	int err = 0;
 
 	err = kfd->dqm->ops.start(kfd->dqm);
 	if (err) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ab83b0de6b22..6d8f9bb2d905 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -207,6 +207,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	uint32_t no_atomic_fw_version;
 	unsigned int num_sdma_engines;
 	unsigned int num_xgmi_sdma_engines;
 	unsigned int num_sdma_queues_per_engine;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 9b1fc54555ee..66c799f5c7cf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -998,6 +998,8 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 	uint32_t agp_base, agp_bot, agp_top;
 	PHYSICAL_ADDRESS_LOC page_table_start, page_table_end, page_table_base;
 
+	memset(pa_config, 0, sizeof(*pa_config));
+
 	logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
 	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
@@ -6024,21 +6026,23 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 		return 0;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return -ENOMEM;
+	if (dm->vblank_control_workqueue) {
+		work = kzalloc(sizeof(*work), GFP_ATOMIC);
+		if (!work)
+			return -ENOMEM;
 
-	INIT_WORK(&work->work, vblank_control_worker);
-	work->dm = dm;
-	work->acrtc = acrtc;
-	work->enable = enable;
+		INIT_WORK(&work->work, vblank_control_worker);
+		work->dm = dm;
+		work->acrtc = acrtc;
+		work->enable = enable;
 
-	if (acrtc_state->stream) {
-		dc_stream_retain(acrtc_state->stream);
-		work->stream = acrtc_state->stream;
-	}
+		if (acrtc_state->stream) {
+			dc_stream_retain(acrtc_state->stream);
+			work->stream = acrtc_state->stream;
+		}
 
-	queue_work(dm->vblank_control_workqueue, &work->work);
+		queue_work(dm->vblank_control_workqueue, &work->work);
+	}
 #endif
 
 	return 0;
@@ -6792,14 +6796,15 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = {
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
-					    struct dc_state *dc_state)
+					    struct dc_state *dc_state,
+					    struct dsc_mst_fairness_vars *vars)
 {
 	struct dc_stream_state *stream = NULL;
 	struct drm_connector *connector;
 	struct drm_connector_state *new_con_state;
 	struct amdgpu_dm_connector *aconnector;
 	struct dm_connector_state *dm_conn_state;
-	int i, j, clock, bpp;
+	int i, j, clock;
 	int vcpi, pbn_div, pbn = 0;
 
 	for_each_new_connector_in_state(state, connector, new_con_state, i) {
@@ -6838,9 +6843,15 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 		}
 
 		pbn_div = dm_mst_get_pbn_divider(stream->link);
-		bpp = stream->timing.dsc_cfg.bits_per_pixel;
 		clock = stream->timing.pix_clk_100hz / 10;
-		pbn = drm_dp_calc_pbn_mode(clock, bpp, true);
+		/* pbn is calculated by compute_mst_dsc_configs_for_state*/
+		for (j = 0; j < dc_state->stream_count; j++) {
+			if (vars[j].aconnector == aconnector) {
+				pbn = vars[j].pbn;
+				break;
+			}
+		}
+
 		vcpi = drm_dp_mst_atomic_enable_dsc(state,
 						    aconnector->port,
 						    pbn, pbn_div,
@@ -7519,6 +7530,32 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder,
 	}
 }
 
+static void amdgpu_set_panel_orientation(struct drm_connector *connector)
+{
+	struct drm_encoder *encoder;
+	struct amdgpu_encoder *amdgpu_encoder;
+	const struct drm_display_mode *native_mode;
+
+	if (connector->connector_type != DRM_MODE_CONNECTOR_eDP &&
+	    connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
+		return;
+
+	encoder = amdgpu_dm_connector_to_encoder(connector);
+	if (!encoder)
+		return;
+
+	amdgpu_encoder = to_amdgpu_encoder(encoder);
+
+	native_mode = &amdgpu_encoder->native_mode;
+	if (native_mode->hdisplay == 0 || native_mode->vdisplay == 0)
+		return;
+
+	drm_connector_set_panel_orientation_with_quirk(connector,
+						       DRM_MODE_PANEL_ORIENTATION_UNKNOWN,
+						       native_mode->hdisplay,
+						       native_mode->vdisplay);
+}
+
 static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 					      struct edid *edid)
 {
@@ -7547,6 +7584,8 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		 * restored here.
 		 */
 		amdgpu_dm_update_freesync_caps(connector, edid);
+
+		amdgpu_set_panel_orientation(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
 	}
@@ -8058,8 +8097,26 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED)
 		state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
 
-	/* Check if something is connected/enabled, otherwise we start hdcp but nothing is connected/enabled
-	 * hot-plug, headless s3, dpms
+	/* Stream removed and re-enabled
+	 *
+	 * Can sometimes overlap with the HPD case,
+	 * thus set update_hdcp to false to avoid
+	 * setting HDCP multiple times.
+	 *
+	 * Handles:	DESIRED -> DESIRED (Special case)
+	 */
+	if (!(old_state->crtc && old_state->crtc->enabled) &&
+		state->crtc && state->crtc->enabled &&
+		connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) {
+		dm_con_state->update_hdcp = false;
+		return true;
+	}
+
+	/* Hot-plug, headless s3, dpms
+	 *
+	 * Only start HDCP if the display is connected/enabled.
+	 * update_hdcp flag will be set to false until the next
+	 * HPD comes in.
 	 *
 	 * Handles:	DESIRED -> DESIRED (Special case)
 	 */
@@ -8648,7 +8705,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		 * If PSR or idle optimizations are enabled then flush out
 		 * any pending work before hardware programming.
 		 */
-		flush_workqueue(dm->vblank_control_workqueue);
+		if (dm->vblank_control_workqueue)
+			flush_workqueue(dm->vblank_control_workqueue);
 #endif
 
 		bundle->stream_update.stream = acrtc_state->stream;
@@ -8983,7 +9041,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		/* if there mode set or reset, disable eDP PSR */
 		if (mode_set_reset_required) {
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-			flush_workqueue(dm->vblank_control_workqueue);
+			if (dm->vblank_control_workqueue)
+				flush_workqueue(dm->vblank_control_workqueue);
 #endif
 			amdgpu_dm_psr_disable_all(dm);
 		}
@@ -10243,6 +10302,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	int ret, i;
 	bool lock_and_validation_needed = false;
 	struct dm_crtc_state *dm_old_crtc_state;
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	struct dsc_mst_fairness_vars vars[MAX_PIPES];
+#endif
 
 	trace_amdgpu_dm_atomic_check_begin(state);
 
@@ -10473,10 +10535,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-		if (!compute_mst_dsc_configs_for_state(state, dm_state->context))
+		if (!compute_mst_dsc_configs_for_state(state, dm_state->context, vars))
 			goto fail;
 
-		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context);
+		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
 		if (ret)
 			goto fail;
 #endif
@@ -10492,7 +10554,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		status = dc_validate_global_state(dc, dm_state->context, false);
 		if (status != DC_OK) {
-			DC_LOG_WARNING("DC global validation failure: %s (%d)",
+			drm_dbg_atomic(dev,
+				       "DC global validation failure: %s (%d)",
 				       dc_status_to_str(status), status);
 			ret = -EINVAL;
 			goto fail;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 1bcba6943fd7..7af0d58c231b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -518,12 +518,7 @@ struct dsc_mst_fairness_params {
 	uint32_t num_slices_h;
 	uint32_t num_slices_v;
 	uint32_t bpp_overwrite;
-};
-
-struct dsc_mst_fairness_vars {
-	int pbn;
-	bool dsc_enabled;
-	int bpp_x16;
+	struct amdgpu_dm_connector *aconnector;
 };
 
 static int kbps_to_peak_pbn(int kbps)
@@ -750,12 +745,12 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 
 static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 					     struct dc_state *dc_state,
-					     struct dc_link *dc_link)
+					     struct dc_link *dc_link,
+					     struct dsc_mst_fairness_vars *vars)
 {
 	int i;
 	struct dc_stream_state *stream;
 	struct dsc_mst_fairness_params params[MAX_PIPES];
-	struct dsc_mst_fairness_vars vars[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
 	int count = 0;
 	bool debugfs_overwrite = false;
@@ -776,6 +771,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		params[count].timing = &stream->timing;
 		params[count].sink = stream->sink;
 		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		params[count].aconnector = aconnector;
 		params[count].port = aconnector->port;
 		params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable;
 		if (params[count].clock_force_enable == DSC_CLK_FORCE_ENABLE)
@@ -798,6 +794,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 	}
 	/* Try no compression */
 	for (i = 0; i < count; i++) {
+		vars[i].aconnector = params[i].aconnector;
 		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
 		vars[i].dsc_enabled = false;
 		vars[i].bpp_x16 = 0;
@@ -851,7 +848,8 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 }
 
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
-				       struct dc_state *dc_state)
+				       struct dc_state *dc_state,
+				       struct dsc_mst_fairness_vars *vars)
 {
 	int i, j;
 	struct dc_stream_state *stream;
@@ -882,7 +880,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 			return false;
 
 		mutex_lock(&aconnector->mst_mgr.lock);
-		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) {
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) {
 			mutex_unlock(&aconnector->mst_mgr.lock);
 			return false;
 		}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index b38bd68121ce..900d3f7a8498 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -39,8 +39,17 @@ void
 dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
+
+struct dsc_mst_fairness_vars {
+	int pbn;
+	bool dsc_enabled;
+	int bpp_x16;
+	struct amdgpu_dm_connector *aconnector;
+};
+
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
-				       struct dc_state *dc_state);
+				       struct dc_state *dc_state,
+				       struct dsc_mst_fairness_vars *vars);
 #endif
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
index c9f47d167472..b1bf80da3a55 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -62,7 +62,7 @@ inline void dc_assert_fp_enabled(void)
 	depth = *pcpu;
 	put_cpu_ptr(&fpu_recursion_depth);
 
-	ASSERT(depth > 1);
+	ASSERT(depth >= 1);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 8bd7f42a8053..1e44b13c1c7d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2586,13 +2586,21 @@ static struct abm *get_abm_from_stream_res(const struct dc_link *link)
 
 int dc_link_get_backlight_level(const struct dc_link *link)
 {
-
 	struct abm *abm = get_abm_from_stream_res(link);
+	struct panel_cntl *panel_cntl = link->panel_cntl;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	bool fw_set_brightness = true;
 
-	if (abm == NULL || abm->funcs->get_current_backlight == NULL)
-		return DC_ERROR_UNEXPECTED;
+	if (dmcu)
+		fw_set_brightness = dmcu->funcs->is_dmcu_initialized(dmcu);
 
-	return (int) abm->funcs->get_current_backlight(abm);
+	if (!fw_set_brightness && panel_cntl->funcs->get_current_backlight)
+		return panel_cntl->funcs->get_current_backlight(panel_cntl);
+	else if (abm != NULL && abm->funcs->get_current_backlight != NULL)
+		return (int) abm->funcs->get_current_backlight(abm);
+	else
+		return DC_ERROR_UNEXPECTED;
 }
 
 int dc_link_get_target_backlight_pwm(const struct dc_link *link)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 330edd666b7d..f6dbc5a74757 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1,4 +1,26 @@
-/* Copyright 2015 Advanced Micro Devices, Inc. */
+/*
+ * Copyright 2015 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ */
 #include "dm_services.h"
 #include "dc.h"
 #include "dc_link_dp.h"
@@ -1840,9 +1862,13 @@ bool perform_link_training_with_retries(
 		dp_disable_link_phy(link, signal);
 
 		/* Abort link training if failure due to sink being unplugged. */
-		if (status == LINK_TRAINING_ABORT)
-			break;
-		else if (do_fallback) {
+		if (status == LINK_TRAINING_ABORT) {
+			enum dc_connection_type type = dc_connection_none;
+
+			dc_link_detect_sink(link, &type);
+			if (type == dc_connection_none)
+				break;
+		} else if (do_fallback) {
 			decide_fallback_link_setting(*link_setting, &current_setting, status);
 			/* Fail link training if reduced link bandwidth no longer meets
 			 * stream requirements.
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e92339235863..e8570060d007 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -49,7 +49,6 @@
 static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_cntl)
 {
 	uint64_t current_backlight;
-	uint32_t round_result;
 	uint32_t bl_period, bl_int_count;
 	uint32_t bl_pwm, fractional_duty_cycle_en;
 	uint32_t bl_period_mask, bl_pwm_mask;
@@ -84,15 +83,6 @@ static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_c
 	current_backlight = div_u64(current_backlight, bl_period);
 	current_backlight = (current_backlight + 1) >> 1;
 
-	current_backlight = (uint64_t)(current_backlight) * bl_period;
-
-	round_result = (uint32_t)(current_backlight & 0xFFFFFFFF);
-
-	round_result = (round_result >> (bl_int_count-1)) & 1;
-
-	current_backlight >>= bl_int_count;
-	current_backlight += round_result;
-
 	return (uint32_t)(current_backlight);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
index 8a08ecc34c69..4884a4e1f261 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h
@@ -33,63 +33,47 @@
 #define TABLE_PMSTATUSLOG        3 // Called by Tools for Agm logging
 #define TABLE_DPMCLOCKS          4 // Called by Driver; defined here, but not used, for backward compatible
 #define TABLE_MOMENTARY_PM       5 // Called by Tools; defined here, but not used, for backward compatible
-#define TABLE_COUNT              6
+#define TABLE_SMU_METRICS        6 // Called by Driver
+#define TABLE_COUNT              7
 
-#define NUM_DSPCLK_LEVELS		8
-#define NUM_SOCCLK_DPM_LEVELS	8
-#define NUM_DCEFCLK_DPM_LEVELS	4
-#define NUM_FCLK_DPM_LEVELS		4
-#define NUM_MEMCLK_DPM_LEVELS	4
+typedef struct SmuMetricsTable_t {
+	//CPU status
+	uint16_t CoreFrequency[6];              //[MHz]
+	uint32_t CorePower[6];                  //[mW]
+	uint16_t CoreTemperature[6];            //[centi-Celsius]
+	uint16_t L3Frequency[2];                //[MHz]
+	uint16_t L3Temperature[2];              //[centi-Celsius]
+	uint16_t C0Residency[6];                //Percentage
 
-#define NUMBER_OF_PSTATES		8
-#define NUMBER_OF_CORES			8
+	// GFX status
+	uint16_t GfxclkFrequency;               //[MHz]
+	uint16_t GfxTemperature;                //[centi-Celsius]
 
-typedef enum {
-	S3_TYPE_ENTRY,
-	S5_TYPE_ENTRY,
-} Sleep_Type_e;
+	// SOC IP info
+	uint16_t SocclkFrequency;               //[MHz]
+	uint16_t VclkFrequency;                 //[MHz]
+	uint16_t DclkFrequency;                 //[MHz]
+	uint16_t MemclkFrequency;               //[MHz]
 
-typedef enum {
-	GFX_OFF = 0,
-	GFX_ON  = 1,
-} GFX_Mode_e;
+	// power, VF info for CPU/GFX telemetry rails, and then socket power total
+	uint32_t Voltage[2];                    //[mV] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t Current[2];                    //[mA] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t Power[2];                      //[mW] indices: VDDCR_VDD, VDDCR_GFX
+	uint32_t CurrentSocketPower;            //[mW]
 
-typedef enum {
-	CPU_P0 = 0,
-	CPU_P1,
-	CPU_P2,
-	CPU_P3,
-	CPU_P4,
-	CPU_P5,
-	CPU_P6,
-	CPU_P7
-} CPU_PState_e;
+	uint16_t SocTemperature;                //[centi-Celsius]
+	uint16_t EdgeTemperature;
+	uint16_t ThrottlerStatus;
+	uint16_t Spare;
 
-typedef enum {
-	CPU_CORE0 = 0,
-	CPU_CORE1,
-	CPU_CORE2,
-	CPU_CORE3,
-	CPU_CORE4,
-	CPU_CORE5,
-	CPU_CORE6,
-	CPU_CORE7
-} CORE_ID_e;
+} SmuMetricsTable_t;
 
-typedef enum {
-	DF_DPM0 = 0,
-	DF_DPM1,
-	DF_DPM2,
-	DF_DPM3,
-	DF_PState_Count
-} DF_PState_e;
-
-typedef enum {
-	GFX_DPM0 = 0,
-	GFX_DPM1,
-	GFX_DPM2,
-	GFX_DPM3,
-	GFX_PState_Count
-} GFX_PState_e;
+typedef struct SmuMetrics_t {
+	SmuMetricsTable_t Current;
+	SmuMetricsTable_t Average;
+	uint32_t SampleStartTime;
+	uint32_t SampleStopTime;
+	uint32_t Accnt;
+} SmuMetrics_t;
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 6f1b1b50d527..18b862a90fbe 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -226,7 +226,10 @@
 	__SMU_DUMMY_MAP(SetUclkDpmMode),		\
 	__SMU_DUMMY_MAP(LightSBR),			\
 	__SMU_DUMMY_MAP(GfxDriverResetRecovery),	\
-	__SMU_DUMMY_MAP(BoardPowerCalibration),
+	__SMU_DUMMY_MAP(BoardPowerCalibration),   \
+	__SMU_DUMMY_MAP(RequestGfxclk),           \
+	__SMU_DUMMY_MAP(ForceGfxVid),             \
+	__SMU_DUMMY_MAP(UnforceGfxVid),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
index 6e6088760b18..909a86aa60f3 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h
@@ -65,6 +65,13 @@
 #define PPSMC_MSG_SetDriverTableVMID                    0x34
 #define PPSMC_MSG_SetSoftMinCclk                        0x35
 #define PPSMC_MSG_SetSoftMaxCclk                        0x36
-#define PPSMC_Message_Count                             0x37
+#define PPSMC_MSG_GetGfxFrequency                       0x37
+#define PPSMC_MSG_GetGfxVid                             0x38
+#define PPSMC_MSG_ForceGfxFreq                          0x39
+#define PPSMC_MSG_UnForceGfxFreq                        0x3A
+#define PPSMC_MSG_ForceGfxVid                           0x3B
+#define PPSMC_MSG_UnforceGfxVid                         0x3C
+#define PPSMC_MSG_GetEnabledSmuFeatures                 0x3D
+#define PPSMC_Message_Count                             0x3E
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 3ab1ce4d3419..04863a797115 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1404,7 +1404,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	 */
 	if (smu->uploading_custom_pp_table &&
 	    (adev->asic_type >= CHIP_NAVI10) &&
-	    (adev->asic_type <= CHIP_DIMGREY_CAVEFISH))
+	    (adev->asic_type <= CHIP_BEIGE_GOBY))
 		return smu_disable_all_features_with_exception(smu,
 							       true,
 							       SMU_FEATURE_COUNT);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index e343cc218990..082f01893f3d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -771,8 +771,12 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 	struct smu_11_0_dpm_context *dpm_context = NULL;
 	uint32_t gen_speed, lane_width;
 
-	if (amdgpu_ras_intr_triggered())
-		return sysfs_emit(buf, "unavailable\n");
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	if (amdgpu_ras_intr_triggered()) {
+		size += sysfs_emit_at(buf, size, "unavailable\n");
+		return size;
+	}
 
 	dpm_context = smu_dpm->dpm_context;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
index b05f9541accc..3d4c65bc29dc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -44,6 +44,27 @@
 #undef pr_info
 #undef pr_debug
 
+/* unit: MHz */
+#define CYAN_SKILLFISH_SCLK_MIN			1000
+#define CYAN_SKILLFISH_SCLK_MAX			2000
+#define CYAN_SKILLFISH_SCLK_DEFAULT			1800
+
+/* unit: mV */
+#define CYAN_SKILLFISH_VDDC_MIN			700
+#define CYAN_SKILLFISH_VDDC_MAX			1129
+#define CYAN_SKILLFISH_VDDC_MAGIC			5118 // 0x13fe
+
+static struct gfx_user_settings {
+	uint32_t sclk;
+	uint32_t vddc;
+} cyan_skillfish_user_settings;
+
+#define FEATURE_MASK(feature) (1ULL << feature)
+#define SMC_DPM_FEATURE ( \
+	FEATURE_MASK(FEATURE_FCLK_DPM_BIT)	|	\
+	FEATURE_MASK(FEATURE_SOC_DPM_BIT)	|	\
+	FEATURE_MASK(FEATURE_GFX_DPM_BIT))
+
 static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetSmuVersion,		0),
@@ -52,14 +73,473 @@ static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(SetDriverDramAddrLow,           PPSMC_MSG_SetDriverTableDramAddrLow,	0),
 	MSG_MAP(TransferTableSmu2Dram,          PPSMC_MSG_TransferTableSmu2Dram,	0),
 	MSG_MAP(TransferTableDram2Smu,          PPSMC_MSG_TransferTableDram2Smu,	0),
+	MSG_MAP(GetEnabledSmuFeatures,          PPSMC_MSG_GetEnabledSmuFeatures,	0),
+	MSG_MAP(RequestGfxclk,                  PPSMC_MSG_RequestGfxclk,		0),
+	MSG_MAP(ForceGfxVid,                    PPSMC_MSG_ForceGfxVid,			0),
+	MSG_MAP(UnforceGfxVid,                  PPSMC_MSG_UnforceGfxVid,		0),
+};
+
+static struct cmn2asic_mapping cyan_skillfish_table_map[SMU_TABLE_COUNT] = {
+	TAB_MAP_VALID(SMU_METRICS),
 };
 
+static int cyan_skillfish_tables_init(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+
+	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS,
+				sizeof(SmuMetrics_t),
+				PAGE_SIZE,
+				AMDGPU_GEM_DOMAIN_VRAM);
+
+	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+	if (!smu_table->metrics_table)
+		goto err0_out;
+
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2);
+	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
+	if (!smu_table->gpu_metrics_table)
+		goto err1_out;
+
+	smu_table->metrics_time = 0;
+
+	return 0;
+
+err1_out:
+	smu_table->gpu_metrics_table_size = 0;
+	kfree(smu_table->metrics_table);
+err0_out:
+	return -ENOMEM;
+}
+
+static int cyan_skillfish_init_smc_tables(struct smu_context *smu)
+{
+	int ret = 0;
+
+	ret = cyan_skillfish_tables_init(smu);
+	if (ret)
+		return ret;
+
+	return smu_v11_0_init_smc_tables(smu);
+}
+
+static int cyan_skillfish_finit_smc_tables(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+
+	kfree(smu_table->metrics_table);
+	smu_table->metrics_table = NULL;
+
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+	smu_table->gpu_metrics_table_size = 0;
+
+	smu_table->metrics_time = 0;
+
+	return 0;
+}
+
+static int
+cyan_skillfish_get_smu_metrics_data(struct smu_context *smu,
+					MetricsMember_t member,
+					uint32_t *value)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table;
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+
+	ret = smu_cmn_get_metrics_table_locked(smu, NULL, false);
+	if (ret) {
+		mutex_unlock(&smu->metrics_lock);
+		return ret;
+	}
+
+	switch (member) {
+	case METRICS_CURR_GFXCLK:
+		*value = metrics->Current.GfxclkFrequency;
+		break;
+	case METRICS_CURR_SOCCLK:
+		*value = metrics->Current.SocclkFrequency;
+		break;
+	case METRICS_CURR_VCLK:
+		*value = metrics->Current.VclkFrequency;
+		break;
+	case METRICS_CURR_DCLK:
+		*value = metrics->Current.DclkFrequency;
+		break;
+	case METRICS_CURR_UCLK:
+		*value = metrics->Current.MemclkFrequency;
+		break;
+	case METRICS_AVERAGE_SOCKETPOWER:
+		*value = (metrics->Current.CurrentSocketPower << 8) /
+				1000;
+		break;
+	case METRICS_TEMPERATURE_EDGE:
+		*value = metrics->Current.GfxTemperature / 100 *
+				SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+		break;
+	case METRICS_TEMPERATURE_HOTSPOT:
+		*value = metrics->Current.SocTemperature / 100 *
+				SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+		break;
+	case METRICS_VOLTAGE_VDDSOC:
+		*value = metrics->Current.Voltage[0];
+		break;
+	case METRICS_VOLTAGE_VDDGFX:
+		*value = metrics->Current.Voltage[1];
+		break;
+	case METRICS_THROTTLER_STATUS:
+		*value = metrics->Current.ThrottlerStatus;
+		break;
+	default:
+		*value = UINT_MAX;
+		break;
+	}
+
+	mutex_unlock(&smu->metrics_lock);
+
+	return ret;
+}
+
+static int cyan_skillfish_read_sensor(struct smu_context *smu,
+					enum amd_pp_sensors sensor,
+					void *data,
+					uint32_t *size)
+{
+	int ret = 0;
+
+	if (!data || !size)
+		return -EINVAL;
+
+	mutex_lock(&smu->sensor_lock);
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GFX_SCLK:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_CURR_GFXCLK,
+						   (uint32_t *)data);
+		*(uint32_t *)data *= 100;
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GFX_MCLK:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_CURR_UCLK,
+						   (uint32_t *)data);
+		*(uint32_t *)data *= 100;
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GPU_POWER:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_AVERAGE_SOCKETPOWER,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_HOTSPOT_TEMP:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_TEMPERATURE_HOTSPOT,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_EDGE_TEMP:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_TEMPERATURE_EDGE,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_VDDNB:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_VOLTAGE_VDDSOC,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_VDDGFX:
+		ret = cyan_skillfish_get_smu_metrics_data(smu,
+						   METRICS_VOLTAGE_VDDGFX,
+						   (uint32_t *)data);
+		*size = 4;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	mutex_unlock(&smu->sensor_lock);
+
+	return ret;
+}
+
+static int cyan_skillfish_get_current_clk_freq(struct smu_context *smu,
+						enum smu_clk_type clk_type,
+						uint32_t *value)
+{
+	MetricsMember_t member_type;
+
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		member_type = METRICS_CURR_GFXCLK;
+		break;
+	case SMU_FCLK:
+	case SMU_MCLK:
+		member_type = METRICS_CURR_UCLK;
+		break;
+	case SMU_SOCCLK:
+		member_type = METRICS_CURR_SOCCLK;
+		break;
+	case SMU_VCLK:
+		member_type = METRICS_CURR_VCLK;
+		break;
+	case SMU_DCLK:
+		member_type = METRICS_CURR_DCLK;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cyan_skillfish_get_smu_metrics_data(smu, member_type, value);
+}
+
+static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
+					enum smu_clk_type clk_type,
+					char *buf)
+{
+	int ret = 0, size = 0;
+	uint32_t cur_value = 0;
+
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	switch (clk_type) {
+	case SMU_OD_SCLK:
+		ret  = cyan_skillfish_get_smu_metrics_data(smu, METRICS_CURR_GFXCLK, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size,"%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
+		break;
+	case SMU_OD_VDDC_CURVE:
+		ret  = cyan_skillfish_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDGFX, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size,"%s:\n", "OD_VDDC");
+		size += sysfs_emit_at(buf, size, "0: %umV *\n", cur_value);
+		break;
+	case SMU_OD_RANGE:
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+						CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+		size += sysfs_emit_at(buf, size, "VDDC: %7umV  %10umV\n",
+						CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+	case SMU_FCLK:
+	case SMU_MCLK:
+	case SMU_SOCCLK:
+	case SMU_VCLK:
+	case SMU_DCLK:
+		ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			return ret;
+		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
+		break;
+	default:
+		dev_warn(smu->adev->dev, "Unsupported clock type\n");
+		return ret;
+	}
+
+	return size;
+}
+
+static bool cyan_skillfish_is_dpm_running(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+	uint32_t feature_mask[2];
+	uint64_t feature_enabled;
+
+	/* we need to re-init after suspend so return false */
+	if (adev->in_suspend)
+		return false;
+
+	ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2);
+
+	if (ret)
+		return false;
+
+	feature_enabled = (uint64_t)feature_mask[0] |
+				((uint64_t)feature_mask[1] << 32);
+
+	return !!(feature_enabled & SMC_DPM_FEATURE);
+}
+
+static ssize_t cyan_skillfish_get_gpu_metrics(struct smu_context *smu,
+						void **table)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct gpu_metrics_v2_2 *gpu_metrics =
+		(struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table;
+	SmuMetrics_t metrics;
+	int i, ret = 0;
+
+	ret = smu_cmn_get_metrics_table(smu, &metrics, true);
+	if (ret)
+		return ret;
+
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2);
+
+	gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature;
+	gpu_metrics->temperature_soc = metrics.Current.SocTemperature;
+
+	gpu_metrics->average_socket_power = metrics.Current.CurrentSocketPower;
+	gpu_metrics->average_soc_power = metrics.Current.Power[0];
+	gpu_metrics->average_gfx_power = metrics.Current.Power[1];
+
+	gpu_metrics->average_gfxclk_frequency = metrics.Average.GfxclkFrequency;
+	gpu_metrics->average_socclk_frequency = metrics.Average.SocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.Average.MemclkFrequency;
+	gpu_metrics->average_fclk_frequency = metrics.Average.MemclkFrequency;
+	gpu_metrics->average_vclk_frequency = metrics.Average.VclkFrequency;
+	gpu_metrics->average_dclk_frequency = metrics.Average.DclkFrequency;
+
+	gpu_metrics->current_gfxclk = metrics.Current.GfxclkFrequency;
+	gpu_metrics->current_socclk = metrics.Current.SocclkFrequency;
+	gpu_metrics->current_uclk = metrics.Current.MemclkFrequency;
+	gpu_metrics->current_fclk = metrics.Current.MemclkFrequency;
+	gpu_metrics->current_vclk = metrics.Current.VclkFrequency;
+	gpu_metrics->current_dclk = metrics.Current.DclkFrequency;
+
+	for (i = 0; i < 6; i++) {
+		gpu_metrics->temperature_core[i] = metrics.Current.CoreTemperature[i];
+		gpu_metrics->average_core_power[i] = metrics.Average.CorePower[i];
+		gpu_metrics->current_coreclk[i] = metrics.Current.CoreFrequency[i];
+	}
+
+	for (i = 0; i < 2; i++) {
+		gpu_metrics->temperature_l3[i] = metrics.Current.L3Temperature[i];
+		gpu_metrics->current_l3clk[i] = metrics.Current.L3Frequency[i];
+	}
+
+	gpu_metrics->throttle_status = metrics.Current.ThrottlerStatus;
+	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
+
+	*table = (void *)gpu_metrics;
+
+	return sizeof(struct gpu_metrics_v2_2);
+}
+
+static int cyan_skillfish_od_edit_dpm_table(struct smu_context *smu,
+					enum PP_OD_DPM_TABLE_COMMAND type,
+					long input[], uint32_t size)
+{
+	int ret = 0;
+	uint32_t vid;
+
+	switch (type) {
+	case PP_OD_EDIT_VDDC_CURVE:
+		if (size != 3 || input[0] != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		if (input[1] <= CYAN_SKILLFISH_SCLK_MIN ||
+			input[1] > CYAN_SKILLFISH_SCLK_MAX) {
+			dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n",
+					CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+			return -EINVAL;
+		}
+
+		if (input[2] <= CYAN_SKILLFISH_VDDC_MIN ||
+			input[2] > CYAN_SKILLFISH_VDDC_MAX) {
+			dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n",
+					CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+			return -EINVAL;
+		}
+
+		cyan_skillfish_user_settings.sclk = input[1];
+		cyan_skillfish_user_settings.vddc = input[2];
+
+		break;
+	case PP_OD_RESTORE_DEFAULT_TABLE:
+		if (size != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		cyan_skillfish_user_settings.sclk = CYAN_SKILLFISH_SCLK_DEFAULT;
+		cyan_skillfish_user_settings.vddc = CYAN_SKILLFISH_VDDC_MAGIC;
+
+		break;
+	case PP_OD_COMMIT_DPM_TABLE:
+		if (size != 0) {
+			dev_err(smu->adev->dev, "Invalid parameter!\n");
+			return -EINVAL;
+		}
+
+		if (cyan_skillfish_user_settings.sclk < CYAN_SKILLFISH_SCLK_MIN ||
+		    cyan_skillfish_user_settings.sclk > CYAN_SKILLFISH_SCLK_MAX) {
+			dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n",
+					CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX);
+			return -EINVAL;
+		}
+
+		if ((cyan_skillfish_user_settings.vddc != CYAN_SKILLFISH_VDDC_MAGIC) &&
+			(cyan_skillfish_user_settings.vddc < CYAN_SKILLFISH_VDDC_MIN ||
+			cyan_skillfish_user_settings.vddc > CYAN_SKILLFISH_VDDC_MAX)) {
+			dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n",
+					CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
+			return -EINVAL;
+		}
+
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_RequestGfxclk,
+					cyan_skillfish_user_settings.sclk, NULL);
+		if (ret) {
+			dev_err(smu->adev->dev, "Set sclk failed!\n");
+			return ret;
+		}
+
+		if (cyan_skillfish_user_settings.vddc == CYAN_SKILLFISH_VDDC_MAGIC) {
+			ret = smu_cmn_send_smc_msg(smu, SMU_MSG_UnforceGfxVid, NULL);
+			if (ret) {
+				dev_err(smu->adev->dev, "Unforce vddc failed!\n");
+				return ret;
+			}
+		} else {
+			/*
+			 * PMFW accepts SVI2 VID code, convert voltage to VID:
+			 * vid = (uint32_t)((1.55 - voltage) * 160.0 + 0.00001)
+			 */
+			vid = (1550 - cyan_skillfish_user_settings.vddc) * 160 / 1000;
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ForceGfxVid, vid, NULL);
+			if (ret) {
+				dev_err(smu->adev->dev, "Force vddc failed!\n");
+				return ret;
+			}
+		}
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
 static const struct pptable_funcs cyan_skillfish_ppt_funcs = {
 
 	.check_fw_status = smu_v11_0_check_fw_status,
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.init_power = smu_v11_0_init_power,
 	.fini_power = smu_v11_0_fini_power,
+	.init_smc_tables = cyan_skillfish_init_smc_tables,
+	.fini_smc_tables = cyan_skillfish_finit_smc_tables,
+	.read_sensor = cyan_skillfish_read_sensor,
+	.print_clk_levels = cyan_skillfish_print_clk_levels,
+	.is_dpm_running = cyan_skillfish_is_dpm_running,
+	.get_gpu_metrics = cyan_skillfish_get_gpu_metrics,
+	.od_edit_dpm_table = cyan_skillfish_od_edit_dpm_table,
 	.register_irq_handler = smu_v11_0_register_irq_handler,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param,
@@ -72,5 +552,6 @@ void cyan_skillfish_set_ppt_funcs(struct smu_context *smu)
 {
 	smu->ppt_funcs = &cyan_skillfish_ppt_funcs;
 	smu->message_map = cyan_skillfish_message_map;
+	smu->table_map = cyan_skillfish_table_map;
 	smu->is_apu = true;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index a5fc5d7cb6c7..b1ad451af06b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1279,6 +1279,8 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	struct smu_11_0_overdrive_table *od_settings = smu->od_settings;
 	uint32_t min_value, max_value;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
@@ -1392,7 +1394,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 	case SMU_OD_RANGE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN,
@@ -2272,7 +2274,27 @@ static int navi10_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	/*
+	 * This aims the case below:
+	 *   amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded
+	 *
+	 * For NAVI10 and later ASICs, we rely on PMFW to handle the runpm. To
+	 * make that possible, PMFW needs to acknowledge the dstate transition
+	 * process for both gfx(function 0) and audio(function 1) function of
+	 * the ASIC.
+	 *
+	 * The PCI device's initial runpm status is RUNPM_SUSPENDED. So as the
+	 * device representing the audio function of the ASIC. And that means
+	 * even if the sound driver(snd_hda_intel) was not loaded yet, it's still
+	 * possible runpm suspend kicked on the ASIC. However without the dstate
+	 * transition notification from audio function, pmfw cannot handle the
+	 * BACO in/exit correctly. And that will cause driver hang on runpm
+	 * resuming.
+	 *
+	 * To address this, we revert to legacy message way(driver masters the
+	 * timing for BACO in/exit) on sound driver missing.
+	 */
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2282,7 +2304,7 @@ static int navi10_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 5e292c3f5050..ca57221e3962 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -1058,6 +1058,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 	uint32_t min_value, max_value;
 	uint32_t smu_version;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
@@ -1180,7 +1182,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
 
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_GFXCLK_LIMITS)) {
 			sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_GFXCLKFMIN,
@@ -2187,7 +2189,7 @@ static int sienna_cichlid_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2197,7 +2199,7 @@ static int sienna_cichlid_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 3a3421452e57..f6ef0ce6e9e2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -589,10 +589,12 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -601,7 +603,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -610,7 +612,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
@@ -688,10 +690,12 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -700,7 +704,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_CCLK:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+			size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -709,7 +713,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 5aa175e12a78..145f13b8c977 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -497,6 +497,8 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	if (ret)
 		return ret;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_RANGE:
 		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index ab652028e003..5019903db492 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -733,15 +733,19 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 	uint32_t freq_values[3] = {0};
 	uint32_t min_clk, max_clk;
 
-	if (amdgpu_ras_intr_triggered())
-		return sysfs_emit(buf, "unavailable\n");
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
+	if (amdgpu_ras_intr_triggered()) {
+		size += sysfs_emit_at(buf, size, "unavailable\n");
+		return size;
+	}
 
 	dpm_context = smu_dpm->dpm_context;
 
 	switch (type) {
 
 	case SMU_OD_SCLK:
-		size = sysfs_emit(buf, "%s:\n", "GFXCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "GFXCLK");
 		fallthrough;
 	case SMU_SCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_GFXCLK, &now);
@@ -795,7 +799,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu,
 		break;
 
 	case SMU_OD_MCLK:
-		size = sysfs_emit(buf, "%s:\n", "MCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "MCLK");
 		fallthrough;
 	case SMU_MCLK:
 		ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_UCLK, &now);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 627ba2eec7fd..a403657151ba 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -1052,16 +1052,18 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 
+	smu_cmn_get_sysfs_buf(&buf, &size);
+
 	switch (clk_type) {
 	case SMU_OD_SCLK:
-		size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 		size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 		(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
 		size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 		(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		break;
 	case SMU_OD_RANGE:
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
 						smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
 		break;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 66711ab24c15..843d2cbfc71d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1053,3 +1053,24 @@ int smu_cmn_set_mp1_state(struct smu_context *smu,
 
 	return ret;
 }
+
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev)
+{
+	struct pci_dev *p = NULL;
+	bool snd_driver_loaded;
+
+	/*
+	 * If the ASIC comes with no audio function, we always assume
+	 * it is "enabled".
+	 */
+	p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus),
+			adev->pdev->bus->number, 1);
+	if (!p)
+		return true;
+
+	snd_driver_loaded = pci_is_enabled(p) ? true : false;
+
+	pci_dev_put(p);
+
+	return snd_driver_loaded;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 16993daa2ae0..beea03810bca 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -110,5 +110,20 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev);
 int smu_cmn_set_mp1_state(struct smu_context *smu,
 			  enum pp_mp1_state mp1_state);
 
+/*
+ * Helper function to make sysfs_emit_at() happy. Align buf to
+ * the current page boundary and record the offset.
+ */
+static inline void smu_cmn_get_sysfs_buf(char **buf, int *offset)
+{
+	if (!*buf || !offset)
+		return;
+
+	*offset = offset_in_page(*buf);
+	*buf -= *offset;
+}
+
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index 76d38561c910..cf741c5c82d2 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -397,8 +397,7 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, u32 exec_state,
 		if (switch_mmu_context) {
 			struct etnaviv_iommu_context *old_context = gpu->mmu_context;
 
-			etnaviv_iommu_context_get(mmu_context);
-			gpu->mmu_context = mmu_context;
+			gpu->mmu_context = etnaviv_iommu_context_get(mmu_context);
 			etnaviv_iommu_context_put(old_context);
 		}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 8f1b5af47dd6..f0b2540e60e4 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -294,8 +294,7 @@ struct etnaviv_vram_mapping *etnaviv_gem_mapping_get(
 		list_del(&mapping->obj_node);
 	}
 
-	etnaviv_iommu_context_get(mmu_context);
-	mapping->context = mmu_context;
+	mapping->context = etnaviv_iommu_context_get(mmu_context);
 	mapping->use = 1;
 
 	ret = etnaviv_iommu_map_gem(mmu_context, etnaviv_obj,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 4dd7d9d541c0..486259e154af 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -532,8 +532,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto err_submit_objects;
 
 	submit->ctx = file->driver_priv;
-	etnaviv_iommu_context_get(submit->ctx->mmu);
-	submit->mmu_context = submit->ctx->mmu;
+	submit->mmu_context = etnaviv_iommu_context_get(submit->ctx->mmu);
 	submit->exec_state = args->exec_state;
 	submit->flags = args->flags;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index c297fffe06eb..cc5b07f86346 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -569,6 +569,12 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu)
 	/* We rely on the GPU running, so program the clock */
 	etnaviv_gpu_update_clock(gpu);
 
+	gpu->fe_running = false;
+	gpu->exec_state = -1;
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = NULL;
+
 	return 0;
 }
 
@@ -637,19 +643,23 @@ void etnaviv_gpu_start_fe(struct etnaviv_gpu *gpu, u32 address, u16 prefetch)
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_ENABLE |
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_PREFETCH(prefetch));
 	}
+
+	gpu->fe_running = true;
 }
 
-static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu)
+static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu,
+					  struct etnaviv_iommu_context *context)
 {
-	u32 address = etnaviv_cmdbuf_get_va(&gpu->buffer,
-				&gpu->mmu_context->cmdbuf_mapping);
 	u16 prefetch;
+	u32 address;
 
 	/* setup the MMU */
-	etnaviv_iommu_restore(gpu, gpu->mmu_context);
+	etnaviv_iommu_restore(gpu, context);
 
 	/* Start command processor */
 	prefetch = etnaviv_buffer_init(gpu);
+	address = etnaviv_cmdbuf_get_va(&gpu->buffer,
+					&gpu->mmu_context->cmdbuf_mapping);
 
 	etnaviv_gpu_start_fe(gpu, address, prefetch);
 }
@@ -832,7 +842,6 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	/* Now program the hardware */
 	mutex_lock(&gpu->lock);
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
 	mutex_unlock(&gpu->lock);
 
 	pm_runtime_mark_last_busy(gpu->dev);
@@ -1057,8 +1066,6 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 	spin_unlock(&gpu->event_spinlock);
 
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
-	gpu->mmu_context = NULL;
 
 	mutex_unlock(&gpu->lock);
 	pm_runtime_mark_last_busy(gpu->dev);
@@ -1370,14 +1377,12 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit)
 		goto out_unlock;
 	}
 
-	if (!gpu->mmu_context) {
-		etnaviv_iommu_context_get(submit->mmu_context);
-		gpu->mmu_context = submit->mmu_context;
-		etnaviv_gpu_start_fe_idleloop(gpu);
-	} else {
-		etnaviv_iommu_context_get(gpu->mmu_context);
-		submit->prev_mmu_context = gpu->mmu_context;
-	}
+	if (!gpu->fe_running)
+		etnaviv_gpu_start_fe_idleloop(gpu, submit->mmu_context);
+
+	if (submit->prev_mmu_context)
+		etnaviv_iommu_context_put(submit->prev_mmu_context);
+	submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context);
 
 	if (submit->nr_pmrs) {
 		gpu->event[event[1]].sync_point = &sync_point_perfmon_sample_pre;
@@ -1579,7 +1584,7 @@ int etnaviv_gpu_wait_idle(struct etnaviv_gpu *gpu, unsigned int timeout_ms)
 
 static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu)
 {
-	if (gpu->initialized && gpu->mmu_context) {
+	if (gpu->initialized && gpu->fe_running) {
 		/* Replace the last WAIT with END */
 		mutex_lock(&gpu->lock);
 		etnaviv_buffer_end(gpu);
@@ -1592,8 +1597,7 @@ static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu)
 		 */
 		etnaviv_gpu_wait_idle(gpu, 100);
 
-		etnaviv_iommu_context_put(gpu->mmu_context);
-		gpu->mmu_context = NULL;
+		gpu->fe_running = false;
 	}
 
 	gpu->exec_state = -1;
@@ -1741,6 +1745,9 @@ static void etnaviv_gpu_unbind(struct device *dev, struct device *master,
 	etnaviv_gpu_hw_suspend(gpu);
 #endif
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+
 	if (gpu->initialized) {
 		etnaviv_cmdbuf_free(&gpu->buffer);
 		etnaviv_iommu_global_fini(gpu);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 8ea48697d132..1c75c8ed5bce 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -101,6 +101,7 @@ struct etnaviv_gpu {
 	struct workqueue_struct *wq;
 	struct drm_gpu_scheduler sched;
 	bool initialized;
+	bool fe_running;
 
 	/* 'ring'-buffer: */
 	struct etnaviv_cmdbuf buffer;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 1a7c89a67bea..afe5dd6a9925 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -92,6 +92,10 @@ static void etnaviv_iommuv1_restore(struct etnaviv_gpu *gpu,
 	struct etnaviv_iommuv1_context *v1_context = to_v1_context(context);
 	u32 pgtable;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	/* set base addresses */
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_RA, context->global->memory_base);
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_FE, context->global->memory_base);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index f8bf488e9d71..d664ae29ae20 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -172,6 +172,10 @@ static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
 	if (gpu_read(gpu, VIVS_MMUv2_CONTROL) & VIVS_MMUv2_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	prefetch = etnaviv_buffer_config_mmuv2(gpu,
 				(u32)v2_context->mtlb_dma,
 				(u32)context->global->bad_page_dma);
@@ -192,6 +196,10 @@ static void etnaviv_iommuv2_restore_sec(struct etnaviv_gpu *gpu,
 	if (gpu_read(gpu, VIVS_MMUv2_SEC_CONTROL) & VIVS_MMUv2_SEC_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_LOW,
 		  lower_32_bits(context->global->v2.pta_dma));
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_HIGH,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index dab1b58006d8..9fb1a2aadbcb 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -199,6 +199,7 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context,
 		 */
 		list_for_each_entry_safe(m, n, &list, scan_node) {
 			etnaviv_iommu_remove_mapping(context, m);
+			etnaviv_iommu_context_put(m->context);
 			m->context = NULL;
 			list_del_init(&m->mmu_node);
 			list_del_init(&m->scan_node);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
index d1d6902fd13b..e4a0b7d09c2e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
@@ -105,9 +105,11 @@ void etnaviv_iommu_dump(struct etnaviv_iommu_context *ctx, void *buf);
 struct etnaviv_iommu_context *
 etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 			   struct etnaviv_cmdbuf_suballoc *suballoc);
-static inline void etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
+static inline struct etnaviv_iommu_context *
+etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
 {
 	kref_get(&ctx->refcount);
+	return ctx;
 }
 void etnaviv_iommu_context_put(struct etnaviv_iommu_context *ctx);
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 642a5b5a1b81..335ba9f43d8f 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -19,7 +19,6 @@ subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers)
 subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
 # clang warnings
 subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
-subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized)
 subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides)
 subdir-ccflags-y += $(call cc-disable-warning, frame-address)
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 04175f359fd6..abe3d61b6243 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2445,11 +2445,14 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	 */
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
 			     intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
-			     sizeof(intel_dp->edp_dpcd))
+			     sizeof(intel_dp->edp_dpcd)) {
 		drm_dbg_kms(&dev_priv->drm, "eDP DPCD: %*ph\n",
 			    (int)sizeof(intel_dp->edp_dpcd),
 			    intel_dp->edp_dpcd);
 
+		intel_dp->use_max_params = intel_dp->edp_dpcd[0] < DP_EDP_14;
+	}
+
 	/*
 	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
 	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 053a3c2f7267..508a514c5e37 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -848,7 +848,7 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	}
 
 	if (ret)
-		intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
+		ret = intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
 
 	if (intel_dp->set_idle_link_train)
 		intel_dp->set_idle_link_train(intel_dp, crtc_state);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index cff72679ad7c..9ccf4b29b82e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -986,6 +986,9 @@ void i915_gem_context_release(struct kref *ref)
 	trace_i915_context_free(ctx);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
+	if (ctx->syncobj)
+		drm_syncobj_put(ctx->syncobj);
+
 	mutex_destroy(&ctx->engines_mutex);
 	mutex_destroy(&ctx->lut_mutex);
 
@@ -1205,9 +1208,6 @@ static void context_close(struct i915_gem_context *ctx)
 	if (vm)
 		i915_vm_close(vm);
 
-	if (ctx->syncobj)
-		drm_syncobj_put(ctx->syncobj);
-
 	ctx->file_priv = ERR_PTR(-EBADF);
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index ffae7df5e4d7..4a6bb64c3a35 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -59,13 +59,13 @@ static int igt_dmabuf_import_self(void *arg)
 		err = PTR_ERR(import);
 		goto out_dmabuf;
 	}
+	import_obj = to_intel_bo(import);
 
 	if (import != &obj->base) {
 		pr_err("i915_gem_prime_import created a new object!\n");
 		err = -EINVAL;
 		goto out_import;
 	}
-	import_obj = to_intel_bo(import);
 
 	i915_gem_object_lock(import_obj, NULL);
 	err = __i915_gem_object_get_pages(import_obj);
@@ -128,6 +128,8 @@ static int igt_dmabuf_import_same_driver_lmem(void *arg)
 		pr_err("i915_gem_prime_import failed with the wrong err=%ld\n",
 		       PTR_ERR(import));
 		err = PTR_ERR(import);
+	} else {
+		err = 0;
 	}
 
 	dma_buf_put(dmabuf);
@@ -176,6 +178,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 		err = PTR_ERR(import);
 		goto out_dmabuf;
 	}
+	import_obj = to_intel_bo(import);
 
 	if (import == &obj->base) {
 		pr_err("i915_gem_prime_import reused gem object!\n");
@@ -183,8 +186,6 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915,
 		goto out_import;
 	}
 
-	import_obj = to_intel_bo(import);
-
 	i915_gem_object_lock(import_obj, NULL);
 	err = __i915_gem_object_get_pages(import_obj);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index b20f5621f62b..a2c34e5a1c54 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -581,6 +581,20 @@ static enum i915_mmap_type default_mapping(struct drm_i915_private *i915)
 	return I915_MMAP_TYPE_GTT;
 }
 
+static struct drm_i915_gem_object *
+create_sys_or_internal(struct drm_i915_private *i915,
+		       unsigned long size)
+{
+	if (HAS_LMEM(i915)) {
+		struct intel_memory_region *sys_region =
+			i915->mm.regions[INTEL_REGION_SMEM];
+
+		return __i915_gem_object_create_user(i915, size, &sys_region, 1);
+	}
+
+	return i915_gem_object_create_internal(i915, size);
+}
+
 static bool assert_mmap_offset(struct drm_i915_private *i915,
 			       unsigned long size,
 			       int expected)
@@ -589,7 +603,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 	u64 offset;
 	int ret;
 
-	obj = i915_gem_object_create_internal(i915, size);
+	obj = create_sys_or_internal(i915, size);
 	if (IS_ERR(obj))
 		return expected && expected == PTR_ERR(obj);
 
@@ -633,6 +647,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	struct drm_mm_node *hole, *next;
 	int loop, err = 0;
 	u64 offset;
+	int enospc = HAS_LMEM(i915) ? -ENXIO : -ENOSPC;
 
 	/* Disable background reaper */
 	disable_retire_worker(i915);
@@ -683,14 +698,14 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	}
 
 	/* Too large */
-	if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, -ENOSPC)) {
+	if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, enospc)) {
 		pr_err("Unexpectedly succeeded in inserting too large object into single page hole\n");
 		err = -EINVAL;
 		goto out;
 	}
 
 	/* Fill the hole, further allocation attempts should then fail */
-	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	obj = create_sys_or_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		pr_err("Unable to create object for reclaimed hole\n");
@@ -703,7 +718,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		goto err_obj;
 	}
 
-	if (!assert_mmap_offset(i915, PAGE_SIZE, -ENOSPC)) {
+	if (!assert_mmap_offset(i915, PAGE_SIZE, enospc)) {
 		pr_err("Unexpectedly succeeded in inserting object into no holes!\n");
 		err = -EINVAL;
 		goto err_obj;
@@ -839,10 +854,9 @@ static int wc_check(struct drm_i915_gem_object *obj)
 
 static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	bool no_map;
 
-	if (HAS_LMEM(i915))
+	if (obj->ops->mmap_offset)
 		return type == I915_MMAP_TYPE_FIXED;
 	else if (type == I915_MMAP_TYPE_FIXED)
 		return false;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index d812b27835f8..591a5224287e 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1973,8 +1973,14 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
 u32 intel_rps_read_punit_req(struct intel_rps *rps)
 {
 	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
+	intel_wakeref_t wakeref;
+	u32 freq = 0;
 
-	return intel_uncore_read(uncore, GEN6_RPNSWREQ);
+	with_intel_runtime_pm_if_in_use(rpm, wakeref)
+		freq = intel_uncore_read(uncore, GEN6_RPNSWREQ);
+
+	return freq;
 }
 
 static u32 intel_rps_get_req(u32 pureq)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index b104fb7607eb..86c318516e14 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -172,11 +172,6 @@ void intel_uc_driver_remove(struct intel_uc *uc)
 	__uc_free_load_err_log(uc);
 }
 
-static inline bool guc_communication_enabled(struct intel_guc *guc)
-{
-	return intel_guc_ct_enabled(&guc->ct);
-}
-
 /*
  * Events triggered while CT buffers are disabled are logged in the SCRATCH_15
  * register using the same bits used in the CT message payload. Since our
@@ -210,7 +205,7 @@ static void guc_get_mmio_msg(struct intel_guc *guc)
 static void guc_handle_mmio_msg(struct intel_guc *guc)
 {
 	/* we need communication to be enabled to reply to GuC */
-	GEM_BUG_ON(!guc_communication_enabled(guc));
+	GEM_BUG_ON(!intel_guc_ct_enabled(&guc->ct));
 
 	spin_lock_irq(&guc->irq_lock);
 	if (guc->mmio_msg) {
@@ -226,7 +221,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	struct drm_i915_private *i915 = gt->i915;
 	int ret;
 
-	GEM_BUG_ON(guc_communication_enabled(guc));
+	GEM_BUG_ON(intel_guc_ct_enabled(&guc->ct));
 
 	ret = i915_inject_probe_error(i915, -ENXIO);
 	if (ret)
@@ -662,7 +657,7 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication)
 		return 0;
 
 	/* Make sure we enable communication if and only if it's disabled */
-	GEM_BUG_ON(enable_communication == guc_communication_enabled(guc));
+	GEM_BUG_ON(enable_communication == intel_guc_ct_enabled(&guc->ct));
 
 	if (enable_communication)
 		guc_enable_communication(guc);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0473583dcdac..482fb0ae6cb5 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -119,7 +119,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 #endif
 
 	if (pci_find_capability(pdev, PCI_CAP_ID_AGP))
-		rdev->agp = radeon_agp_head_init(rdev->ddev);
+		rdev->agp = radeon_agp_head_init(dev);
 	if (rdev->agp) {
 		rdev->agp->agp_mtrr = arch_phys_wc_add(
 			rdev->agp->agp_info.aper_base,
author	Linus Torvalds <torvalds@linux-foundation.org>	2021-09-16 23:28:52 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2021-09-16 23:28:52 +0300
commit	bdb575f872175ed0ecf2638369da1cb7a6e86a14 (patch)
tree	1b6996552c18be4a13c17174508eaae6ac68b6eb /drivers/gpu
parent	fc0c0548c1a2e676d3a928aaed70f2d4d254e395 (diff)
parent	109f7ea9aedce437b4b7737ab60bfea65d9dbdd3 (diff)
download	linux-bdb575f872175ed0ecf2638369da1cb7a6e86a14.tar.xz