Merge tag 'drm-next-2025-10-01' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "cross-subsystem:
   - i2c-hid: Make elan touch controllers power on after panel is
     enabled
   - dt bindings for STM32MP25 SoC
   - pci vgaarb: use screen_info helpers
   - rust pin-init updates
   - add MEI driver for late binding firmware update/load

  uapi:
   - add ioctl for reassigning GEM handles
   - provide boot_display attribute on boot-up devices

  core:
   - document DRM_MODE_PAGE_FLIP_EVENT
   - add vendor specific recovery method to drm device wedged uevent

  gem:
   - Simplify gpuvm locking

  ttm:
   - add interface to populate buffers

  sched:
   - Fix race condition in trace code

  atomic:
   - Reallow no-op async page flips

  display:
   - dp: Fix command length

  video:
   - Improve pixel-format handling for struct screen_info

  rust:
   - drop Opaque<> from ioctl args
   - Alloc:
       - BorrowedPage type and AsPageIter traits
       - Implement Vmalloc::to_page() and VmallocPageIter
   - DMA/Scatterlist:
       - Add dma::DataDirection and type alias for dma_addr_t
       - Abstraction for struct scatterlist and sg_table
   - DRM:
       - simplify use of generics
       - add DriverFile type alias
       - drop Object::SIZE
   - Rust:
       - pin-init tree merge
       - Various methods for AsBytes and FromBytes traits

  gpuvm:
   - Support madvice in Xe driver

  gpusvm:
   - fix hmm_pfn_to_map_order usage in gpusvm

  bridge:
   - Improve and fix ref counting on bridge management
   - cdns-dsi: Various improvements to mode setting
   - Support Solomon SSD2825 plus DT bindings
   - Support Waveshare DSI2DPI plus DT bindings
   - Support Content Protection property
   - display-connector: Improve DP display detection
   - Add support for Radxa Ra620 plus DT bindings
   - adv7511: Provide SPD and HDMI infoframes
   - it6505: Replace crypto_shash with sha()
   - synopsys: Add support for DW DPTX Controller plus DT bindings
   - adv7511: Write full Audio infoframe
   - ite6263: Support vendor-specific infoframes
   - simple: Add support for Realtek RTD2171 DP-to-HDMI plus DT bindings

  panel:
   - panel-edp: Support mt8189 Chromebooks; Support BOE NV140WUM-N64;
     Support SHP LQ134Z1; Fixes
   - panel-simple: Support Olimex LCD-OLinuXino-5CTS plus DT bindings
   - Support Samsung AMS561RA01
   - Support Hydis HV101HD1 plus DT bindings
   - ilitek-ili9881c: Refactor mode setting; Add support for Bestar
     BSD1218-A101KL68 LCD plus DT bindings
   - lvds: Add support for Ampire AMP19201200B5TZQW-T03 to DT bindings
   - edp: Add support for additonal mt8189 Chromebook panels
   - lvds: Add DT bindings for EDT ETML0700Z8DHA

  amdgpu:
   - add CRIU support for gem objects
   - RAS updates
   - VCN SRAM load fixes
   - EDID read fixes
   - eDP ALPM support
   - Documentation updates
   - Rework PTE flag generation
   - DCE6 fixes
   - VCN devcoredump cleanup
   - MMHUB client id fixes
   - VCN 5.0.1 RAS support
   - SMU 13.0.x updates
   - Expanded PCIe DPC support
   - Expanded VCN reset support
   - VPE per queue reset support
   - give kernel jobs unique id for tracing
   - pre-populate exported buffers
   - cyan skillfish updates
   - make vbios build number available in sysfs
   - userq updates
   - HDCP updates
   - support MMIO remap page as ttm pool
   - JPEG parser updates
   - DCE6 DC updates
   - use devm for i2c buses
   - GPUVM locking updates
   - Drop non-DC DCE11 code
   - improve fallback handling for pixel encoding

  amdkfd:
   - SVM/page migration fixes
   - debugfs fixes
   - add CRIO support for gem objects
   - SVM updates

  radeon:
   - use dev_warn_once in CS parsers

  xe:
   - add madvise interface
   - add DRM_IOCTL_XE_VM_QUERY_MEMORY_RANGE_ATTRS to query VMA count
     and memory attributes
   - drop L# bank mask reporting from media GT3 on Xe3+.
   - add SLPC power_profile sysfs interface
   - add configs attribs to add post/mid context-switch commands
   - handle firmware reported hardware errors notifying userspace with
     device wedged uevent
   - use same dir structure across sysfs/debugfs
   - cleanup and future proof vram region init
   - add G-states and PCI link states to debugfs
   - Add SRIOV support for CCS surfaces on Xe2+
   - Enable SRIOV PF mode by default on supported platforms
   - move flush to common code
   - extended core workarounds for Xe2/3
   - use DRM scheduler for delayed GT TLB invalidations
   - configs improvements and allow VF device enablement
   - prep work to expose mmio regions to userspace
   - VF migration support added
   - prepare GPU SVM for THP migration
   - start fixing XE_PAGE_SIZE vs PAGE_SIZE
   - add PSMI support for hw validation
   - resize VF bars to max possible size according to number of VFs
   - Ensure GT is in C0 during resume
   - pre-populate exported buffers
   - replace xe_hmm with gpusvm
   - add more SVM GT stats to debugfs
   - improve fake pci and WA kunnit handle for new platform testing
   - Test GuC to GuC comms to add debugging
   - use attribute groups to simplify sysfs registration
   - add Late Binding firmware code to interact with MEI

  i915:
   - apply multiple JSL/EHL/Gen7/Gen6 workarounds properly
   - protect against overflow in active_engine()
   - Use try_cmpxchg64() in __active_lookup()
   - include GuC registers in error state
   - get rid of dev->struct_mutex
   - iopoll: generalize read_poll_timout
   - lots more display refactoring
   - Reject HBR3 in any eDP Panel
   - Prune modes for YUV420
   - Display Wa fix, additions, and updates
   - DP: Fix 2.7 Gbps link training on g4x
   - DP: Adjust the idle pattern handling
   - DP: Shuffle the link training code a bit
   - Don't set/read the DSI C clock divider on GLK
   - Enable_psr kernel parameter changes
   - Type-C enabled/disconnected dp-alt sink
   - Wildcat Lake enabling
   - DP HDR updates
   - DRAM detection
   - wait PSR idle on dsb commit
   - Remove FBC modulo 4 restriction for ADL-P+
   - panic: refactor framebuffer allocation

  habanalabs:
   - debug/visibility improvements
   - vmalloc-backed coherent mmap support
   - HLDIO infrastructure

  nova-core:
   - various register!() macro improvements
   - minor vbios/firmware fixes/refactoring
   - advance firmware boot stages; process Booter and patch signatures
   - process GSP and GSP bootloader
   - Add r570.144 firmware bindings and update to it
   - Move GSP boot code to own module
   - Use new pin-init features to store driver's private data in a
     single allocation
   - Update ARef import from sync::aref

  nova-drm:
   - Update ARef import from sync::aref

  tyr:
   - initial driver skeleton for a rust driver for ARM Mali GPUs
   - capable of powering up, query metadata and provide it to userspace.

  msm:
   - GPU and Core:
      - in DT bindings describe clocks per GPU type
      - GMU bandwidth voting for x1-85
      - a623/a663 speedbins
      - cleanup some remaining no-iommu leftovers after VM_BIND conversion
      - fix GEM obj 32b size truncation
      - add missing VM_BIND param validation
      - IFPC for x1-85 and a750
      - register xml and gen_header.py sync from mesa
   - Display:
      - add missing bindings for display on SC8180X
      - added DisplayPort MST bindings
      - conversion from round_rate() to determine_rate()

  amdxdna:
   - add IOCTL_AMDXDNA_GET_ARRAY
   - support user space allocated buffers
   - streamline PM interfaces
   - Refactoring wrt. hardware contexts
   - improve error reporting

  nouveau:
   - use GSP firmware by default
   - improve error reporting
   - Pre-populate exported buffers

  ast:
   - Clean up detection of DRAM config

  exynos:
   - add DSIM bridge driver support for Exynos7870
   - Document Exynos7870 DSIM compatible in dt-binding

  panthor:
   - Print task/pid on errors
   - Add support for Mali G710, G510, G310, Gx15, Gx20, Gx25
   - Improve cache flushing
   - Fail VM bind if BO has offset

  renesas:
   - convert to RUNTIME_PM_OPS

  rcar-du:
   - Make number of lanes configurable
   - Use RUNTIME_PM_OPS
   - Add support for DSI commands

  rocket:
   - Add driver for Rockchip NPU plus DT bindings
   - Use kfree() and sizeof() correctly
   - Test DMA status

  rockchip:
   - dsi2: Add support for RK3576 plus DT bindings
   - Add support for RK3588 DPTX output

  tidss:
   - Use crtc_ fields for programming display mode
   - Remove other drivers from aperture

  pixpaper:
   - Add support for Mayqueen Pixpaper plus DT bindings

  v3d:
   - Support querying nubmer of GPU resets for KHR_robustness

  stm:
   - Clean up logging
   - ltdc: Add support support for STM32MP257F-EV1 plus DT bindings

  sitronix:
   - st7571-i2c: Add support for inverted displays and 2-bit grayscale

  tidss:
   - Convert to kernel's FIELD_ macros

  vesadrm:
   - Support 8-bit palette mode

  imagination:
   - Improve power management
   - Add support for TH1520 GPU
   - Support Risc-V architectures

  v3d:
   - Improve job management and locking

  vkms:
   - Support variants of ARGB8888, ARGB16161616, RGB565, RGB888 and P01x
   - Spport YUV with 16-bit components"

* tag 'drm-next-2025-10-01' of https://gitlab.freedesktop.org/drm/kernel: (1455 commits)
  drm/amd: Add name to modes from amdgpu_connector_add_common_modes()
  drm/amd: Drop some common modes from amdgpu_connector_add_common_modes()
  drm/amdgpu: update MODULE_PARM_DESC for freesync_video
  drm/amd: Use dynamic array size declaration for amdgpu_connector_add_common_modes()
  drm/amd/display: Share dce100_validate_global with DCE6-8
  drm/amd/display: Share dce100_validate_bandwidth with DCE6-8
  drm/amdgpu: Fix fence signaling race condition in userqueue
  amd/amdkfd: enhance kfd process check in switch partition
  amd/amdkfd: resolve a race in amdgpu_amdkfd_device_fini_sw
  drm/amd/display: Reject modes with too high pixel clock on DCE6-10
  drm/amd: Drop unnecessary check in amdgpu_connector_add_common_modes()
  drm/amd/display: Only enable common modes for eDP and LVDS
  drm/amdgpu: remove the redeclaration of variable i
  drm/amdgpu/userq: assign an error code for invalid userq va
  drm/amdgpu: revert "rework reserved VMID handling" v2
  drm/amdgpu: remove leftover from enforcing isolation by VMID
  drm/amdgpu: Add fallback to pipe reset if KCQ ring reset fails
  accel/habanalabs: add Infineon version check
  accel/habanalabs/gaudi2: read preboot status after recovering from dirty state
  accel/habanalabs: add HL_GET_P_STATE passthrough type
  ...

1 files changed, 227 insertions, 48 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c8459337fcb8..a77000c2e0bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -95,6 +95,7 @@ MODULE_FIRMWARE("amdgpu/picasso_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven2_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 #define AMDGPU_MAX_RETRY_LIMIT		2
@@ -178,6 +179,8 @@ struct amdgpu_init_level amdgpu_init_minimal_xgmi = {
 		BIT(AMD_IP_BLOCK_TYPE_PSP)
 };
 
+static void amdgpu_device_load_switch_state(struct amdgpu_device *adev);
+
 static inline bool amdgpu_ip_member_of_hwini(struct amdgpu_device *adev,
 					     enum amd_ip_block_type block)
 {
@@ -2445,6 +2448,33 @@ int amdgpu_device_ip_block_version_cmp(struct amdgpu_device *adev,
 	return 1;
 }
 
+static const char *ip_block_names[] = {
+	[AMD_IP_BLOCK_TYPE_COMMON] = "common",
+	[AMD_IP_BLOCK_TYPE_GMC] = "gmc",
+	[AMD_IP_BLOCK_TYPE_IH] = "ih",
+	[AMD_IP_BLOCK_TYPE_SMC] = "smu",
+	[AMD_IP_BLOCK_TYPE_PSP] = "psp",
+	[AMD_IP_BLOCK_TYPE_DCE] = "dce",
+	[AMD_IP_BLOCK_TYPE_GFX] = "gfx",
+	[AMD_IP_BLOCK_TYPE_SDMA] = "sdma",
+	[AMD_IP_BLOCK_TYPE_UVD] = "uvd",
+	[AMD_IP_BLOCK_TYPE_VCE] = "vce",
+	[AMD_IP_BLOCK_TYPE_ACP] = "acp",
+	[AMD_IP_BLOCK_TYPE_VCN] = "vcn",
+	[AMD_IP_BLOCK_TYPE_MES] = "mes",
+	[AMD_IP_BLOCK_TYPE_JPEG] = "jpeg",
+	[AMD_IP_BLOCK_TYPE_VPE] = "vpe",
+	[AMD_IP_BLOCK_TYPE_UMSCH_MM] = "umsch_mm",
+	[AMD_IP_BLOCK_TYPE_ISP] = "isp",
+};
+
+static const char *ip_block_name(struct amdgpu_device *adev, enum amd_ip_block_type type)
+{
+	int idx = (int)type;
+
+	return idx < ARRAY_SIZE(ip_block_names) ? ip_block_names[idx] : "unknown";
+}
+
 /**
  * amdgpu_device_ip_block_add
  *
@@ -2473,8 +2503,13 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
 		break;
 	}
 
-	dev_info(adev->dev, "detected ip block number %d <%s>\n",
-		 adev->num_ip_blocks, ip_block_version->funcs->name);
+	dev_info(adev->dev, "detected ip block number %d <%s_v%d_%d_%d> (%s)\n",
+		 adev->num_ip_blocks,
+		 ip_block_name(adev, ip_block_version->type),
+		 ip_block_version->major,
+		 ip_block_version->minor,
+		 ip_block_version->rev,
+		 ip_block_version->funcs->name);
 
 	adev->ip_blocks[adev->num_ip_blocks].adev = adev;
 
@@ -2595,6 +2630,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 			return 0;
 		chip_name = "navi12";
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		chip_name = "cyan_skillfish";
+		break;
 	}
 
 	err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw,
@@ -2674,6 +2712,24 @@ out:
 	return err;
 }
 
+static void amdgpu_uid_init(struct amdgpu_device *adev)
+{
+	/* Initialize the UID for the device */
+	adev->uid_info = kzalloc(sizeof(struct amdgpu_uid), GFP_KERNEL);
+	if (!adev->uid_info) {
+		dev_warn(adev->dev, "Failed to allocate memory for UID\n");
+		return;
+	}
+	adev->uid_info->adev = adev;
+}
+
+static void amdgpu_uid_fini(struct amdgpu_device *adev)
+{
+	/* Free the UID memory */
+	kfree(adev->uid_info);
+	adev->uid_info = NULL;
+}
+
 /**
  * amdgpu_device_ip_early_init - run early init for hardware IPs
  *
@@ -2857,6 +2913,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (adev->gmc.xgmi.supported)
 		amdgpu_xgmi_early_init(adev);
 
+	if (amdgpu_is_multi_aid(adev))
+		amdgpu_uid_init(adev);
 	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
 	if (ip_block->status.valid != false)
 		amdgpu_amdkfd_device_probe(adev);
@@ -3389,7 +3447,7 @@ static int amdgpu_device_enable_mgpu_fan_boost(void)
 	for (i = 0; i < mgpu_info.num_dgpu; i++) {
 		gpu_ins = &(mgpu_info.gpu_ins[i]);
 		adev = gpu_ins->adev;
-		if (!(adev->flags & AMD_IS_APU) &&
+		if (!(adev->flags & AMD_IS_APU || amdgpu_sriov_multi_vf_mode(adev)) &&
 		    !gpu_ins->mgpu_fan_enabled) {
 			ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
 			if (ret)
@@ -3648,6 +3706,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	}
 
 	amdgpu_ras_fini(adev);
+	amdgpu_uid_fini(adev);
 
 	return 0;
 }
@@ -4992,7 +5051,8 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 	adev->reset_domain = NULL;
 
 	kfree(adev->pci_state);
-
+	kfree(adev->pcie_reset_ctx.swds_pcistate);
+	kfree(adev->pcie_reset_ctx.swus_pcistate);
 }
 
 /**
@@ -5012,6 +5072,10 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
 	if (!adev->in_s4 && (adev->flags & AMD_IS_APU))
 		return 0;
 
+	/* No need to evict when going to S5 through S4 callbacks */
+	if (system_state == SYSTEM_POWER_OFF)
+		return 0;
+
 	ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM);
 	if (ret) {
 		dev_warn(adev->dev, "evicting device resources failed\n");
@@ -5697,7 +5761,7 @@ int amdgpu_device_link_reset(struct amdgpu_device *adev)
 
 	dev_info(adev->dev, "GPU link reset\n");
 
-	if (!adev->pcie_reset_ctx.occurs_dpc)
+	if (!amdgpu_reset_in_dpc(adev))
 		ret = amdgpu_dpm_link_reset(adev);
 
 	if (ret)
@@ -5826,6 +5890,7 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 		amdgpu_set_init_level(tmp_adev, init_level);
 		if (full_reset) {
 			/* post card */
+			amdgpu_reset_set_dpc_status(tmp_adev, false);
 			amdgpu_ras_clear_err_state(tmp_adev);
 			r = amdgpu_device_asic_init(tmp_adev);
 			if (r) {
@@ -6132,12 +6197,11 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle)
 	return ret;
 }
 
-static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
+static void amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 					  struct list_head *device_list,
 					  struct amdgpu_hive_info *hive)
 {
 	struct amdgpu_device *tmp_adev = NULL;
-	int r;
 
 	/*
 	 * Build list of devices to reset.
@@ -6149,7 +6213,7 @@ static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 			list_add_tail(&tmp_adev->reset_list, device_list);
 			if (adev->shutdown)
 				tmp_adev->shutdown = true;
-			if (adev->pcie_reset_ctx.occurs_dpc)
+			if (amdgpu_reset_in_dpc(adev))
 				tmp_adev->pcie_reset_ctx.in_link_reset = true;
 		}
 		if (!list_is_first(&adev->reset_list, device_list))
@@ -6157,14 +6221,6 @@ static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 	} else {
 		list_add_tail(&adev->reset_list, device_list);
 	}
-
-	if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) {
-		r = amdgpu_device_health_check(device_list);
-		if (r)
-			return r;
-	}
-
-	return 0;
 }
 
 static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev,
@@ -6233,9 +6289,8 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,
 		drm_client_dev_suspend(adev_to_drm(tmp_adev), false);
 
 		/* disable ras on ALL IPs */
-		if (!need_emergency_restart &&
-		      (!adev->pcie_reset_ctx.occurs_dpc) &&
-		      amdgpu_device_ip_need_full_reset(tmp_adev))
+		if (!need_emergency_restart && !amdgpu_reset_in_dpc(adev) &&
+		    amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -6263,11 +6318,7 @@ static int amdgpu_device_asic_reset(struct amdgpu_device *adev,
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list, reset_list) {
-		if (adev->pcie_reset_ctx.occurs_dpc)
-			tmp_adev->no_hw_access = true;
 		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
-		if (adev->pcie_reset_ctx.occurs_dpc)
-			tmp_adev->no_hw_access = false;
 		/*TODO Should we stop ?*/
 		if (r) {
 			dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
@@ -6445,8 +6496,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		emergency_restart();
 	}
 
-	dev_info(adev->dev, "GPU %s begin!\n",
-		need_emergency_restart ? "jobs stop":"reset");
+	dev_info(adev->dev, "GPU %s begin!. Source:  %d\n",
+		 need_emergency_restart ? "jobs stop" : "reset",
+		 reset_context->src);
 
 	if (!amdgpu_sriov_vf(adev))
 		hive = amdgpu_get_xgmi_hive(adev);
@@ -6457,8 +6509,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	reset_context->hive = hive;
 	INIT_LIST_HEAD(&device_list);
 
-	if (amdgpu_device_recovery_prepare(adev, &device_list, hive))
-		goto end_reset;
+	amdgpu_device_recovery_prepare(adev, &device_list, hive);
+
+	if (!amdgpu_sriov_vf(adev)) {
+		r = amdgpu_device_health_check(&device_list);
+		if (r)
+			goto end_reset;
+	}
 
 	/* We need to lock reset domain only once both for XGMI and single device */
 	amdgpu_device_recovery_get_reset_lock(adev, &device_list);
@@ -6880,17 +6937,13 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
+	struct amdgpu_hive_info *hive __free(xgmi_put_hive) =
+		amdgpu_get_xgmi_hive(adev);
 	struct amdgpu_reset_context reset_context;
 	struct list_head device_list;
 
 	dev_info(adev->dev, "PCI error: detected callback!!\n");
 
-	if (!amdgpu_dpm_is_link_reset_supported(adev)) {
-		dev_warn(adev->dev, "No support for XGMI hive yet...\n");
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-
 	adev->pci_channel_state = state;
 
 	switch (state) {
@@ -6900,10 +6953,23 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 	case pci_channel_io_frozen:
 		/* Fatal error, prepare for slot reset */
 		dev_info(adev->dev, "pci_channel_io_frozen: state(%d)!!\n", state);
+		if (hive) {
+			/* Hive devices should be able to support FW based
+			 * link reset on other devices, if not return.
+			 */
+			if (!amdgpu_dpm_is_link_reset_supported(adev)) {
+				dev_warn(adev->dev,
+					 "No support for XGMI hive yet...\n");
+				return PCI_ERS_RESULT_DISCONNECT;
+			}
+			/* Set dpc status only if device is part of hive
+			 * Non-hive devices should be able to recover after
+			 * link reset.
+			 */
+			amdgpu_reset_set_dpc_status(adev, true);
 
-		if (hive)
 			mutex_lock(&hive->hive_lock);
-		adev->pcie_reset_ctx.occurs_dpc = true;
+		}
 		memset(&reset_context, 0, sizeof(reset_context));
 		INIT_LIST_HEAD(&device_list);
 
@@ -6911,10 +6977,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		amdgpu_device_recovery_get_reset_lock(adev, &device_list);
 		amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list,
 					      hive, false);
-		if (hive) {
+		if (hive)
 			mutex_unlock(&hive->hive_lock);
-			amdgpu_put_xgmi_hive(hive);
-		}
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		/* Permanent error, prepare for device removal */
@@ -6962,22 +7026,34 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	struct amdgpu_device *tmp_adev;
 	struct amdgpu_hive_info *hive;
 	struct list_head device_list;
-	int r = 0, i;
+	struct pci_dev *link_dev;
+	int r = 0, i, timeout;
 	u32 memsize;
-
-	/* PCI error slot reset should be skipped During RAS recovery */
-	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
-	    amdgpu_ras_in_recovery(adev))
-		return PCI_ERS_RESULT_RECOVERED;
+	u16 status;
 
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
 
-	/* wait for asic to come out of reset */
-	msleep(700);
+	if (adev->pcie_reset_ctx.swus)
+		link_dev = adev->pcie_reset_ctx.swus;
+	else
+		link_dev = adev->pdev;
+	/* wait for asic to come out of reset, timeout = 10s */
+	timeout = 10000;
+	do {
+		usleep_range(10000, 10500);
+		r = pci_read_config_word(link_dev, PCI_VENDOR_ID, &status);
+		timeout -= 10;
+	} while (timeout > 0 && (status != PCI_VENDOR_ID_ATI) &&
+		 (status != PCI_VENDOR_ID_AMD));
 
+	if ((status != PCI_VENDOR_ID_ATI) && (status != PCI_VENDOR_ID_AMD)) {
+		r = -ETIME;
+		goto out;
+	}
+
+	amdgpu_device_load_switch_state(adev);
 	/* Restore PCI confspace */
 	amdgpu_device_load_pci_state(pdev);
 
@@ -7072,7 +7148,6 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	amdgpu_device_sched_resume(&device_list, NULL, NULL);
 	amdgpu_device_gpu_resume(adev, &device_list, false);
 	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
-	adev->pcie_reset_ctx.occurs_dpc = false;
 
 	if (hive) {
 		mutex_unlock(&hive->hive_lock);
@@ -7080,6 +7155,58 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	}
 }
 
+static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev)
+{
+	struct pci_dev *parent = pci_upstream_bridge(adev->pdev);
+	int r;
+
+	if (!parent || parent->vendor != PCI_VENDOR_ID_ATI)
+		return;
+
+	/* If already saved, return */
+	if (adev->pcie_reset_ctx.swus)
+		return;
+	/* Upstream bridge is ATI, assume it's SWUS/DS architecture */
+	r = pci_save_state(parent);
+	if (r)
+		return;
+	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent);
+
+	parent = pci_upstream_bridge(parent);
+	r = pci_save_state(parent);
+	if (r)
+		return;
+	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent);
+
+	adev->pcie_reset_ctx.swus = parent;
+}
+
+static void amdgpu_device_load_switch_state(struct amdgpu_device *adev)
+{
+	struct pci_dev *pdev;
+	int r;
+
+	if (!adev->pcie_reset_ctx.swds_pcistate ||
+	    !adev->pcie_reset_ctx.swus_pcistate)
+		return;
+
+	pdev = adev->pcie_reset_ctx.swus;
+	r = pci_load_saved_state(pdev, adev->pcie_reset_ctx.swus_pcistate);
+	if (!r) {
+		pci_restore_state(pdev);
+	} else {
+		dev_warn(adev->dev, "Failed to load SWUS state, err:%d\n", r);
+		return;
+	}
+
+	pdev = pci_upstream_bridge(adev->pdev);
+	r = pci_load_saved_state(pdev, adev->pcie_reset_ctx.swds_pcistate);
+	if (!r)
+		pci_restore_state(pdev);
+	else
+		dev_warn(adev->dev, "Failed to load SWDS state, err:%d\n", r);
+}
+
 bool amdgpu_device_cache_pci_state(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
@@ -7104,6 +7231,8 @@ bool amdgpu_device_cache_pci_state(struct pci_dev *pdev)
 		return false;
 	}
 
+	amdgpu_device_cache_switch_state(adev);
+
 	return true;
 }
 
@@ -7490,3 +7619,53 @@ ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset)
 	size += sysfs_emit_at(buf, size, "\n");
 	return size;
 }
+
+void amdgpu_device_set_uid(struct amdgpu_uid *uid_info,
+			   enum amdgpu_uid_type type, uint8_t inst,
+			   uint64_t uid)
+{
+	if (!uid_info)
+		return;
+
+	if (type >= AMDGPU_UID_TYPE_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID type %d\n",
+			     type);
+		return;
+	}
+
+	if (inst >= AMDGPU_UID_INST_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID instance %d\n",
+			     inst);
+		return;
+	}
+
+	if (uid_info->uid[type][inst] != 0) {
+		dev_warn_once(
+			uid_info->adev->dev,
+			"Overwriting existing UID %llu for type %d instance %d\n",
+			uid_info->uid[type][inst], type, inst);
+	}
+
+	uid_info->uid[type][inst] = uid;
+}
+
+u64 amdgpu_device_get_uid(struct amdgpu_uid *uid_info,
+			  enum amdgpu_uid_type type, uint8_t inst)
+{
+	if (!uid_info)
+		return 0;
+
+	if (type >= AMDGPU_UID_TYPE_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID type %d\n",
+			     type);
+		return 0;
+	}
+
+	if (inst >= AMDGPU_UID_INST_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID instance %d\n",
+			     inst);
+		return 0;
+	}
+
+	return uid_info->uid[type][inst];
+}