Merge tag 'amd-drm-fixes-6.3-2023-03-15' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.3-2023-03-15:

amdgpu:
- SMU 13 update
- RDNA2 suspend/resume fix when overclocking is enabled
- SRIOV VCN fixes
- HDCP suspend/resume fix
- Fix drm polling splat regression
- Fix dirty rectangle tracking for PSR
- Fix vangogh regression on certain BIOSes
- Misc display fixes
- Suspend/resume IOMMU regression fix

amdkfd:
- Fix BO offset for multi-VMA page migration
- Fix a possible double free
- Fix potential use after free
- Fix process cleanup on module exit

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230315224400.7558-1-alexander.deucher@amd.com

23 files changed, 281 insertions, 69 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c4a4e2fe6681..da5b0258a237 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4145,8 +4145,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3))
 		DRM_WARN("smart shift update failed\n");
 
-	drm_kms_helper_poll_disable(dev);
-
 	if (fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
@@ -4243,8 +4241,6 @@ exit:
 	if (fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false);
 
-	drm_kms_helper_poll_enable(dev);
-
 	amdgpu_ras_resume(adev);
 
 	if (adev->mode_info.num_crtc) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 503f89a766c3..d60fe7eb5579 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -1618,6 +1618,8 @@ int amdgpu_display_suspend_helper(struct amdgpu_device *adev)
 	struct drm_connector_list_iter iter;
 	int r;
 
+	drm_kms_helper_poll_disable(dev);
+
 	/* turn off display hw */
 	drm_modeset_lock_all(dev);
 	drm_connector_list_iter_begin(dev, &iter);
@@ -1694,6 +1696,8 @@ int amdgpu_display_resume_helper(struct amdgpu_device *adev)
 
 	drm_modeset_unlock_all(dev);
 
+	drm_kms_helper_poll_enable(dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 25217b05c0ea..e7974de8b035 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -26,6 +26,7 @@
 
 #include <linux/firmware.h>
 #include <linux/module.h>
+#include <linux/dmi.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
 #include <drm/drm_drv.h>
@@ -114,6 +115,24 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
 		adev->vcn.indirect_sram = true;
 
+	/*
+	 * Some Steam Deck's BIOS versions are incompatible with the
+	 * indirect SRAM mode, leading to amdgpu being unable to get
+	 * properly probed (and even potentially crashing the kernel).
+	 * Hence, check for these versions here - notice this is
+	 * restricted to Vangogh (Deck's APU).
+	 */
+	if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 0, 2)) {
+		const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION);
+
+		if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) ||
+		     !strncmp("F7A0114", bios_ver, 7))) {
+			adev->vcn.indirect_sram = false;
+			dev_info(adev->dev,
+				"Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver);
+		}
+	}
+
 	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b9e9480448af..4f7bab52282a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -124,6 +124,8 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_PP_ONE_VF = (1 << 4),
 	/* Indirect Reg Access enabled */
 	AMDGIM_FEATURE_INDIRECT_REG_ACCESS = (1 << 5),
+	/* AV1 Support MODE*/
+	AMDGIM_FEATURE_AV1_SUPPORT = (1 << 6),
 };
 
 enum AMDGIM_REG_ACCESS_FLAG {
@@ -322,6 +324,8 @@ static inline bool is_virtual_machine(void)
 	((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug)
 #define amdgpu_sriov_is_normal(adev) \
 	((!amdgpu_in_reset(adev)) && (!adev->virt.tdr_debug))
+#define amdgpu_sriov_is_av1_support(adev) \
+	((adev)->virt.gim_feature & AMDGIM_FEATURE_AV1_SUPPORT)
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
 void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
index 6c97148ca0ed..24d42d24e6a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -93,7 +93,8 @@ union amd_sriov_msg_feature_flags {
 		uint32_t mm_bw_management  : 1;
 		uint32_t pp_one_vf_mode	   : 1;
 		uint32_t reg_indirect_acc  : 1;
-		uint32_t reserved	   : 26;
+		uint32_t av1_support       : 1;
+		uint32_t reserved	   : 25;
 	} flags;
 	uint32_t all;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 855d390c41de..22e25ca285f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -1055,8 +1055,8 @@ static int nv_common_late_init(void *handle)
 			amdgpu_virt_update_sriov_video_codec(adev,
 							     sriov_sc_video_codecs_encode_array,
 							     ARRAY_SIZE(sriov_sc_video_codecs_encode_array),
-							     sriov_sc_video_codecs_decode_array_vcn1,
-							     ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1));
+							     sriov_sc_video_codecs_decode_array_vcn0,
+							     ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn0));
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 061793d390cc..c82b3a7ea5f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -102,6 +102,59 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 =
 	.codec_array = vcn_4_0_0_video_codecs_decode_array_vcn1,
 };
 
+/* SRIOV SOC21, not const since data is controlled by host */
+static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
+};
+
+static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+};
+
+static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = {
+	.codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0),
+	.codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn0,
+};
+
+static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn1 = {
+	.codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1),
+	.codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn1,
+};
+
+static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn0[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
+};
+
+static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn1[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
+static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn0 = {
+	.codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0),
+	.codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn0,
+};
+
+static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn1 = {
+	.codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1),
+	.codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn1,
+};
+
 static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
@@ -112,16 +165,31 @@ static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode,
 	case IP_VERSION(4, 0, 0):
 	case IP_VERSION(4, 0, 2):
 	case IP_VERSION(4, 0, 4):
-		if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
-			if (encode)
-				*codecs = &vcn_4_0_0_video_codecs_encode_vcn1;
-			else
-				*codecs = &vcn_4_0_0_video_codecs_decode_vcn1;
+		if (amdgpu_sriov_vf(adev)) {
+			if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) ||
+			!amdgpu_sriov_is_av1_support(adev)) {
+				if (encode)
+					*codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn1;
+				else
+					*codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn1;
+			} else {
+				if (encode)
+					*codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn0;
+				else
+					*codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn0;
+			}
 		} else {
-			if (encode)
-				*codecs = &vcn_4_0_0_video_codecs_encode_vcn0;
-			else
-				*codecs = &vcn_4_0_0_video_codecs_decode_vcn0;
+			if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)) {
+				if (encode)
+					*codecs = &vcn_4_0_0_video_codecs_encode_vcn1;
+				else
+					*codecs = &vcn_4_0_0_video_codecs_decode_vcn1;
+			} else {
+				if (encode)
+					*codecs = &vcn_4_0_0_video_codecs_encode_vcn0;
+				else
+					*codecs = &vcn_4_0_0_video_codecs_decode_vcn0;
+			}
 		}
 		return 0;
 	default:
@@ -730,8 +798,23 @@ static int soc21_common_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
 		xgpu_nv_mailbox_get_irq(adev);
+		if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) ||
+		!amdgpu_sriov_is_av1_support(adev)) {
+			amdgpu_virt_update_sriov_video_codec(adev,
+							     sriov_vcn_4_0_0_video_codecs_encode_array_vcn1,
+							     ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1),
+							     sriov_vcn_4_0_0_video_codecs_decode_array_vcn1,
+							     ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1));
+		} else {
+			amdgpu_virt_update_sriov_video_codec(adev,
+							     sriov_vcn_4_0_0_video_codecs_encode_array_vcn0,
+							     ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0),
+							     sriov_vcn_4_0_0_video_codecs_decode_array_vcn0,
+							     ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0));
+		}
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index a0e30f21e12e..de310ed367ca 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1312,14 +1312,14 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 		args->n_success = i+1;
 	}
 
-	mutex_unlock(&p->mutex);
-
 	err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev, (struct kgd_mem *) mem, true);
 	if (err) {
 		pr_debug("Sync memory failed, wait interrupted by user signal\n");
 		goto sync_memory_failed;
 	}
 
+	mutex_unlock(&p->mutex);
+
 	/* Flush TLBs after waiting for the page table updates to complete */
 	for (i = 0; i < args->n_devices; i++) {
 		peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
@@ -1335,9 +1335,9 @@ get_process_device_data_failed:
 bind_process_to_device_failed:
 get_mem_obj_from_handle_failed:
 map_memory_to_gpu_failed:
+sync_memory_failed:
 	mutex_unlock(&p->mutex);
 copy_from_user_failed:
-sync_memory_failed:
 	kfree(devices_arr);
 
 	return err;
@@ -1351,6 +1351,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 	void *mem;
 	long err = 0;
 	uint32_t *devices_arr = NULL, i;
+	bool flush_tlb;
 
 	if (!args->n_devices) {
 		pr_debug("Device IDs array empty\n");
@@ -1403,16 +1404,19 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 		}
 		args->n_success = i+1;
 	}
-	mutex_unlock(&p->mutex);
 
-	if (kfd_flush_tlb_after_unmap(pdd->dev)) {
+	flush_tlb = kfd_flush_tlb_after_unmap(pdd->dev);
+	if (flush_tlb) {
 		err = amdgpu_amdkfd_gpuvm_sync_memory(pdd->dev->adev,
 				(struct kgd_mem *) mem, true);
 		if (err) {
 			pr_debug("Sync memory failed, wait interrupted by user signal\n");
 			goto sync_memory_failed;
 		}
+	}
+	mutex_unlock(&p->mutex);
 
+	if (flush_tlb) {
 		/* Flush TLBs after waiting for the page table updates to complete */
 		for (i = 0; i < args->n_devices; i++) {
 			peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
@@ -1428,9 +1432,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 bind_process_to_device_failed:
 get_mem_obj_from_handle_failed:
 unmap_memory_from_gpu_failed:
+sync_memory_failed:
 	mutex_unlock(&p->mutex);
 copy_from_user_failed:
-sync_memory_failed:
 	kfree(devices_arr);
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 3de7f616a001..ec70a1658dc3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -59,6 +59,7 @@ static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
 				unsigned int chunk_size);
 static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
 
+static int kfd_resume_iommu(struct kfd_dev *kfd);
 static int kfd_resume(struct kfd_dev *kfd);
 
 static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
@@ -624,7 +625,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	svm_migrate_init(kfd->adev);
 
-	if (kgd2kfd_resume_iommu(kfd))
+	if (kfd_resume_iommu(kfd))
 		goto device_iommu_error;
 
 	if (kfd_resume(kfd))
@@ -773,6 +774,14 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 
 int kgd2kfd_resume_iommu(struct kfd_dev *kfd)
 {
+	if (!kfd->init_complete)
+		return 0;
+
+	return kfd_resume_iommu(kfd);
+}
+
+static int kfd_resume_iommu(struct kfd_dev *kfd)
+{
 	int err = 0;
 
 	err = kfd_iommu_resume(kfd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index de8ce72344fc..54933903bcb8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -289,7 +289,7 @@ static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate)
 static int
 svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
-			 dma_addr_t *scratch)
+			 dma_addr_t *scratch, uint64_t ttm_res_offset)
 {
 	uint64_t npages = migrate->npages;
 	struct device *dev = adev->dev;
@@ -299,19 +299,13 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	uint64_t i, j;
 	int r;
 
-	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
-		 prange->last);
+	pr_debug("svms 0x%p [0x%lx 0x%lx 0x%llx]\n", prange->svms, prange->start,
+		 prange->last, ttm_res_offset);
 
 	src = scratch;
 	dst = (uint64_t *)(scratch + npages);
 
-	r = svm_range_vram_node_new(adev, prange, true);
-	if (r) {
-		dev_dbg(adev->dev, "fail %d to alloc vram\n", r);
-		goto out;
-	}
-
-	amdgpu_res_first(prange->ttm_res, prange->offset << PAGE_SHIFT,
+	amdgpu_res_first(prange->ttm_res, ttm_res_offset,
 			 npages << PAGE_SHIFT, &cursor);
 	for (i = j = 0; i < npages; i++) {
 		struct page *spage;
@@ -391,14 +385,14 @@ out_free_vram_pages:
 		migrate->dst[i + 3] = 0;
 	}
 #endif
-out:
+
 	return r;
 }
 
 static long
 svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			struct vm_area_struct *vma, uint64_t start,
-			uint64_t end, uint32_t trigger)
+			uint64_t end, uint32_t trigger, uint64_t ttm_res_offset)
 {
 	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
@@ -451,7 +445,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	else
 		pr_debug("0x%lx pages migrated\n", cpages);
 
-	r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch);
+	r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch, ttm_res_offset);
 	migrate_vma_pages(&migrate);
 
 	pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
@@ -499,6 +493,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	unsigned long addr, start, end;
 	struct vm_area_struct *vma;
 	struct amdgpu_device *adev;
+	uint64_t ttm_res_offset;
 	unsigned long cpages = 0;
 	long r = 0;
 
@@ -520,6 +515,13 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	start = prange->start << PAGE_SHIFT;
 	end = (prange->last + 1) << PAGE_SHIFT;
 
+	r = svm_range_vram_node_new(adev, prange, true);
+	if (r) {
+		dev_dbg(adev->dev, "fail %ld to alloc vram\n", r);
+		return r;
+	}
+	ttm_res_offset = prange->offset << PAGE_SHIFT;
+
 	for (addr = start; addr < end;) {
 		unsigned long next;
 
@@ -528,18 +530,21 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 			break;
 
 		next = min(vma->vm_end, end);
-		r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger);
+		r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger, ttm_res_offset);
 		if (r < 0) {
 			pr_debug("failed %ld to migrate\n", r);
 			break;
 		} else {
 			cpages += r;
 		}
+		ttm_res_offset += next - addr;
 		addr = next;
 	}
 
 	if (cpages)
 		prange->actual_loc = best_loc;
+	else
+		svm_range_vram_node_free(prange);
 
 	return r < 0 ? r : 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 09b966dc3768..aee2212e52f6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -77,6 +77,7 @@ err_ioctl:
 
 static void kfd_exit(void)
 {
+	kfd_cleanup_processes();
 	kfd_debugfs_fini();
 	kfd_process_destroy_wq();
 	kfd_procfs_shutdown();
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index bfa30d12406b..7e4d992e48b3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -928,6 +928,7 @@ bool kfd_dev_is_large_bar(struct kfd_dev *dev);
 
 int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
+void kfd_cleanup_processes(void);
 struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *task);
 struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 7acd55a814b2..4208e0f01064 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1167,6 +1167,17 @@ static void kfd_process_free_notifier(struct mmu_notifier *mn)
 	kfd_unref_process(container_of(mn, struct kfd_process, mmu_notifier));
 }
 
+static void kfd_process_notifier_release_internal(struct kfd_process *p)
+{
+	cancel_delayed_work_sync(&p->eviction_work);
+	cancel_delayed_work_sync(&p->restore_work);
+
+	/* Indicate to other users that MM is no longer valid */
+	p->mm = NULL;
+
+	mmu_notifier_put(&p->mmu_notifier);
+}
+
 static void kfd_process_notifier_release(struct mmu_notifier *mn,
 					struct mm_struct *mm)
 {
@@ -1181,17 +1192,22 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 		return;
 
 	mutex_lock(&kfd_processes_mutex);
+	/*
+	 * Do early return if table is empty.
+	 *
+	 * This could potentially happen if this function is called concurrently
+	 * by mmu_notifier and by kfd_cleanup_pocesses.
+	 *
+	 */
+	if (hash_empty(kfd_processes_table)) {
+		mutex_unlock(&kfd_processes_mutex);
+		return;
+	}
 	hash_del_rcu(&p->kfd_processes);
 	mutex_unlock(&kfd_processes_mutex);
 	synchronize_srcu(&kfd_processes_srcu);
 
-	cancel_delayed_work_sync(&p->eviction_work);
-	cancel_delayed_work_sync(&p->restore_work);
-
-	/* Indicate to other users that MM is no longer valid */
-	p->mm = NULL;
-
-	mmu_notifier_put(&p->mmu_notifier);
+	kfd_process_notifier_release_internal(p);
 }
 
 static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = {
@@ -1200,6 +1216,43 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = {
 	.free_notifier = kfd_process_free_notifier,
 };
 
+/*
+ * This code handles the case when driver is being unloaded before all
+ * mm_struct are released.  We need to safely free the kfd_process and
+ * avoid race conditions with mmu_notifier that might try to free them.
+ *
+ */
+void kfd_cleanup_processes(void)
+{
+	struct kfd_process *p;
+	struct hlist_node *p_temp;
+	unsigned int temp;
+	HLIST_HEAD(cleanup_list);
+
+	/*
+	 * Move all remaining kfd_process from the process table to a
+	 * temp list for processing.   Once done, callback from mmu_notifier
+	 * release will not see the kfd_process in the table and do early return,
+	 * avoiding double free issues.
+	 */
+	mutex_lock(&kfd_processes_mutex);
+	hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) {
+		hash_del_rcu(&p->kfd_processes);
+		synchronize_srcu(&kfd_processes_srcu);
+		hlist_add_head(&p->kfd_processes, &cleanup_list);
+	}
+	mutex_unlock(&kfd_processes_mutex);
+
+	hlist_for_each_entry_safe(p, p_temp, &cleanup_list, kfd_processes)
+		kfd_process_notifier_release_internal(p);
+
+	/*
+	 * Ensures that all outstanding free_notifier get called, triggering
+	 * the release of the kfd_process struct.
+	 */
+	mmu_notifier_synchronize();
+}
+
 static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep)
 {
 	unsigned long  offset;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 5137476ec18e..4236539d9f93 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -218,8 +218,8 @@ static int init_user_queue(struct process_queue_manager *pqm,
 	return 0;
 
 cleanup:
-	if (dev->shared_resources.enable_mes)
-		uninit_queue(*q);
+	uninit_queue(*q);
+	*q = NULL;
 	return retval;
 }
 
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 009ef917dad4..32abbafd43fa 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5105,9 +5105,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 
 		for (; flip_addrs->dirty_rect_count < num_clips; clips++)
 			fill_dc_dirty_rect(new_plane_state->plane,
-					   &dirty_rects[i], clips->x1,
-					   clips->y1, clips->x2 - clips->x1,
-					   clips->y2 - clips->y1,
+					   &dirty_rects[flip_addrs->dirty_rect_count],
+					   clips->x1, clips->y1,
+					   clips->x2 - clips->x1, clips->y2 - clips->y1,
 					   &flip_addrs->dirty_rect_count,
 					   false);
 		return;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 8e572f07ec47..4abfd2c9679f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -561,7 +561,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	link->dp.mst_enabled = config->mst_enabled;
 	link->dp.usb4_enabled = config->usb4_enabled;
 	display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION;
-	link->adjust.auth_delay = 0;
+	link->adjust.auth_delay = 2;
 	link->adjust.hdcp1.disable = 0;
 	conn_state = aconnector->base.state;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 3b4d4d68359b..df787fcf8e86 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -998,8 +998,5 @@ void dcn30_prepare_bandwidth(struct dc *dc,
 			dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz);
 
 	dcn20_prepare_bandwidth(dc, context);
-
-	dc_dmub_srv_p_state_delegate(dc,
-		context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching, context);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index 16f892125b6f..9d14045cccd6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -1104,7 +1104,7 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign
 			*k2_div = PIXEL_RATE_DIV_BY_2;
 		else
 			*k2_div = PIXEL_RATE_DIV_BY_4;
-	} else if (dc_is_dp_signal(stream->signal) || dc_is_virtual_signal(stream->signal)) {
+	} else if (dc_is_dp_signal(stream->signal)) {
 		if (two_pix_per_container) {
 			*k1_div = PIXEL_RATE_DIV_BY_1;
 			*k2_div = PIXEL_RATE_DIV_BY_2;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 74e50c09bb62..d024007f0f65 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -1915,6 +1915,7 @@ int dcn32_populate_dml_pipes_from_context(
 	bool subvp_in_use = false;
 	uint8_t is_pipe_split_expected[MAX_PIPES] = {0};
 	struct dc_crtc_timing *timing;
+	bool vsr_odm_support = false;
 
 	dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate);
 
@@ -1932,12 +1933,15 @@ int dcn32_populate_dml_pipes_from_context(
 		timing = &pipe->stream->timing;
 
 		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		vsr_odm_support = (res_ctx->pipe_ctx[i].stream->src.width >= 5120 &&
+				res_ctx->pipe_ctx[i].stream->src.width > res_ctx->pipe_ctx[i].stream->dst.width);
 		if (context->stream_count == 1 &&
 				context->stream_status[0].plane_count == 1 &&
 				!dc_is_hdmi_signal(res_ctx->pipe_ctx[i].stream->signal) &&
 				is_h_timing_divisible_by_2(res_ctx->pipe_ctx[i].stream) &&
 				pipe->stream->timing.pix_clk_100hz * 100 > DCN3_2_VMIN_DISPCLK_HZ &&
-				dc->debug.enable_single_display_2to1_odm_policy) {
+				dc->debug.enable_single_display_2to1_odm_policy &&
+				!vsr_odm_support) { //excluding 2to1 ODM combine on >= 5k vsr
 			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
 		}
 		pipe_cnt++;
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index 38216c789d77..f70025ef7b69 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -855,6 +855,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 	struct dc_sink *prev_sink = NULL;
 	struct dpcd_caps prev_dpcd_caps;
 	enum dc_connection_type new_connection_type = dc_connection_none;
+	enum dc_connection_type pre_connection_type = link->type;
 	const uint32_t post_oui_delay = 30; // 30ms
 
 	DC_LOGGER_INIT(link->ctx->logger);
@@ -957,6 +958,8 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 			}
 
 			if (!detect_dp(link, &sink_caps, reason)) {
+				link->type = pre_connection_type;
+
 				if (prev_sink)
 					dc_sink_release(prev_sink);
 				return false;
@@ -1244,11 +1247,16 @@ bool link_detect(struct dc_link *link, enum dc_detect_reason reason)
 	bool is_delegated_to_mst_top_mgr = false;
 	enum dc_connection_type pre_link_type = link->type;
 
+	DC_LOGGER_INIT(link->ctx->logger);
+
 	is_local_sink_detect_success = detect_link_and_local_sink(link, reason);
 
 	if (is_local_sink_detect_success && link->local_sink)
 		verify_link_capability(link, link->local_sink, reason);
 
+	DC_LOG_DC("%s: link_index=%d is_local_sink_detect_success=%d pre_link_type=%d link_type=%d\n", __func__,
+				link->link_index, is_local_sink_detect_success, pre_link_type, link->type);
+
 	if (is_local_sink_detect_success && link->local_sink &&
 			dc_is_dp_signal(link->local_sink->sink_signal) &&
 			link->dpcd_caps.is_mst_capable)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
index f77401709d83..2162ecd1057d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 7
+#define PMFW_DRIVER_IF_VERSION 8
 
 typedef struct {
   int32_t value;
@@ -198,7 +198,7 @@ typedef struct {
   uint16_t SkinTemp;
   uint16_t DeviceState;
   uint16_t CurTemp;                     //[centi-Celsius]
-  uint16_t spare2;
+  uint16_t FilterAlphaValue;
 
   uint16_t AverageGfxclkFrequency;
   uint16_t AverageFclkFrequency;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 1c0ae2cb757b..f085cb97a620 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -29,7 +29,7 @@
 #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x08
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37
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 697e98a0a20a..75f18681e984 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
@@ -2143,16 +2143,9 @@ static int sienna_cichlid_set_default_od_settings(struct smu_context *smu)
 		(OverDriveTable_t *)smu->smu_table.boot_overdrive_table;
 	OverDriveTable_t *user_od_table =
 		(OverDriveTable_t *)smu->smu_table.user_overdrive_table;
+	OverDriveTable_t user_od_table_bak;
 	int ret = 0;
 
-	/*
-	 * For S3/S4/Runpm resume, no need to setup those overdrive tables again as
-	 *   - either they already have the default OD settings got during cold bootup
-	 *   - or they have some user customized OD settings which cannot be overwritten
-	 */
-	if (smu->adev->in_suspend)
-		return 0;
-
 	ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE,
 				   0, (void *)boot_od_table, false);
 	if (ret) {
@@ -2163,7 +2156,23 @@ static int sienna_cichlid_set_default_od_settings(struct smu_context *smu)
 	sienna_cichlid_dump_od_table(smu, boot_od_table);
 
 	memcpy(od_table, boot_od_table, sizeof(OverDriveTable_t));
-	memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t));
+
+	/*
+	 * For S3/S4/Runpm resume, we need to setup those overdrive tables again,
+	 * but we have to preserve user defined values in "user_od_table".
+	 */
+	if (!smu->adev->in_suspend) {
+		memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t));
+		smu->user_dpm_profile.user_od = false;
+	} else if (smu->user_dpm_profile.user_od) {
+		memcpy(&user_od_table_bak, user_od_table, sizeof(OverDriveTable_t));
+		memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t));
+		user_od_table->GfxclkFmin = user_od_table_bak.GfxclkFmin;
+		user_od_table->GfxclkFmax = user_od_table_bak.GfxclkFmax;
+		user_od_table->UclkFmin = user_od_table_bak.UclkFmin;
+		user_od_table->UclkFmax = user_od_table_bak.UclkFmax;
+		user_od_table->VddGfxOffset = user_od_table_bak.VddGfxOffset;
+	}
 
 	return 0;
 }
@@ -2373,6 +2382,20 @@ static int sienna_cichlid_od_edit_dpm_table(struct smu_context *smu,
 	return ret;
 }
 
+static int sienna_cichlid_restore_user_od_settings(struct smu_context *smu)
+{
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTable_t *od_table = table_context->overdrive_table;
+	OverDriveTable_t *user_od_table = table_context->user_overdrive_table;
+	int res;
+
+	res = smu_v11_0_restore_user_od_settings(smu);
+	if (res == 0)
+		memcpy(od_table, user_od_table, sizeof(OverDriveTable_t));
+
+	return res;
+}
+
 static int sienna_cichlid_run_btc(struct smu_context *smu)
 {
 	int res;
@@ -4400,7 +4423,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.set_default_od_settings = sienna_cichlid_set_default_od_settings,
 	.od_edit_dpm_table = sienna_cichlid_od_edit_dpm_table,
-	.restore_user_od_settings = smu_v11_0_restore_user_od_settings,
+	.restore_user_od_settings = sienna_cichlid_restore_user_od_settings,
 	.run_btc = sienna_cichlid_run_btc,
 	.set_power_source = smu_v11_0_set_power_source,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,