Merge tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights:

   - Intel xe enable Panthor Lake, started adding WildCat Lake

   - amdgpu has a bunch of reset improvments along with the usual IP
     updates

   - msm got VM_BIND support which is important for vulkan sparse memory

   - more drm_panic users

   - gpusvm common code to handle a bunch of core SVM work outside
     drivers.

  Detail summary:

  Changes outside drm subdirectory:
   - 'shrink_shmem_memory()' for better shmem/hibernate interaction
   - Rust support infrastructure:
      - make ETIMEDOUT available
      - add size constants up to SZ_2G
      - add DMA coherent allocation bindings
   - mtd driver for Intel GPU non-volatile storage
   - i2c designware quirk for Intel xe

  core:
   - atomic helpers: tune enable/disable sequences
   - add task info to wedge API
   - refactor EDID quirks
   - connector: move HDR sink to drm_display_info
   - fourcc: half-float and 32-bit float formats
   - mode_config: pass format info to simplify

  dma-buf:
   - heaps: Give CMA heap a stable name

  ci:
   - add device tree validation and kunit

  displayport:
   - change AUX DPCD access probe address
   - add quirk for DPCD probe
   - add panel replay definitions
   - backlight control helpers

  fbdev:
   - make CONFIG_FIRMWARE_EDID available on all arches

  fence:
   - fix UAF issues

  format-helper:
   - improve tests

  gpusvm:
   - introduce devmem only flag for allocation
   - add timeslicing support to GPU SVM

  ttm:
   - improve eviction

  sched:
   - tracing improvements
   - kunit improvements
   - memory leak fixes
   - reset handling improvements

  color mgmt:
   - add hardware gamma LUT handling helpers

  bridge:
   - add destroy hook
   - switch to reference counted drm_bridge allocations
   - tc358767: convert to devm_drm_bridge_alloc
   - improve CEC handling

  panel:
   - switch to reference counter drm_panel allocations
   - fwnode panel lookup
   - Huiling hl055fhv028c support
   - Raspberry Pi 7" 720x1280 support
   - edp: KDC KD116N3730A05, N160JCE-ELL CMN, N116BCJ-EAK
   - simple: AUO P238HAN01
   - st7701: Winstar wf40eswaa6mnn0
   - visionox: rm69299-shift
   - Renesas R61307, Renesas R69328 support
   - DJN HX83112B

  hdmi:
   - add CEC handling
   - YUV420 output support

  xe:
   - WildCat Lake support
   - Enable PanthorLake by default
   - mark BMG as SRIOV capable
   - update firmware recommendations
   - Expose media OA units
   - aux-bux support for non-volatile memory
   - MTD intel-dg driver for non-volatile memory
   - Expose fan control and voltage regulator in sysfs
   - restructure migration for multi-device
   - Restore GuC submit UAF fix
   - make GEM shrinker drm managed
   - SRIOV VF Post-migration recovery of GGTT nodes
   - W/A additions/reworks
   - Prefetch support for svm ranges
   - Don't allocate managed BO for each policy change
   - HWMON fixes for BMG
   - Create LRC BO without VM
   - PCI ID updates
   - make SLPC debugfs files optional
   - rework eviction rejection of bound external BOs
   - consolidate PAT programming logic for pre/post Xe2
   - init changes for flicker-free boot
   - Enable GuC Dynamic Inhibit Context switch

  i915:
   - drm_panic support for i915/xe
   - initial flip queue off by default for LNL/PNL
   - Wildcat Lake Display support
   - Support for DSC fractional link bpp
   - Support for simultaneous Panel Replay and Adaptive sync
   - Support for PTL+ double buffer LUT
   - initial PIPEDMC event handling
   - drm_panel_follower support
   - DPLL interface renames
   - allocate struct intel_display dynamically
   - flip queue preperation
   - abstract DRAM detection better
   - avoid GuC scheduling stalls
   - remove DG1 force probe requirement
   - fix MEI interrupt handler on RT kernels
   - use backlight control helpers for eDP
   - more shared display code refactoring

  amdgpu:
   - add userq slot to INFO ioctl
   - SR-IOV hibernation support
   - Suspend improvements
   - Backlight improvements
   - Use scaling for non-native eDP modes
   - cleaner shader updates for GC 9.x
   - Remove fence slab
   - SDMA fw checks for userq support
   - RAS updates
   - DMCUB updates
   - DP tunneling fixes
   - Display idle D3 support
   - Per queue reset improvements
   - initial smartmux support

  amdkfd:
   - enable KFD on loongarch
   - mtype fix for ext coherent system memory

  radeon:
   - CS validation additional GL extensions
   - drop console lock during suspend/resume
   - bump driver version

  msm:
   - VM BIND support
   - CI: infrastructure updates
   - UBWC single source of truth
   - decouple GPU and KMS support
   - DP: rework I/O accessors
   - DPU: SM8750 support
   - DSI: SM8750 support
   - GPU: X1-45 support and speedbin support for X1-85
   - MDSS: SM8750 support

  nova:
   - register! macro improvements
   - DMA object abstraction
   - VBIOS parser + fwsec lookup
   - sysmem flush page support
   - falcon: generic falcon boot code and HAL
   - FWSEC-FRTS: fb setup and load/execute

  ivpu:
   - Add Wildcat Lake support
   - Add turbo flag

  ast:
   - improve hardware generations implementation

  imx:
   - IMX8qxq Display Controller support

  lima:
   - Rockchip RK3528 GPU support

  nouveau:
   - fence handling cleanup

  panfrost:
   - MT8370 support
   - bo labeling
   - 64-bit register access

  qaic:
   - add RAS support

  rockchip:
   - convert inno_hdmi to a bridge

  rz-du:
   - add RZ/V2H(P) support
   - MIPI-DSI DCS support

  sitronix:
   - ST7567 support

  sun4i:
   - add H616 support

  tidss:
   - add TI AM62L support
   - AM65x OLDI bridge support

  bochs:
   - drm panic support

  vkms:
   - YUV and R* format support
   - use faux device

  vmwgfx:
   - fence improvements

  hyperv:
   - move out of simple
   - add drm_panic support"

* tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel: (1479 commits)
  drm/tidss: oldi: convert to devm_drm_bridge_alloc() API
  drm/tidss: encoder: convert to devm_drm_bridge_alloc()
  drm/amdgpu: move reset support type checks into the caller
  drm/amdgpu/sdma7: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma6: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5.2: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx12: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx11: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx10: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx9.4.3: re-emit unprocessed state on kcq reset
  drm/amdgpu/gfx9: re-emit unprocessed state on kcq reset
  drm/amdgpu: Add WARN_ON to the resource clear function
  drm/amd/pm: Use cached metrics data on SMUv13.0.6
  drm/amd/pm: Use cached data for min/max clocks
  gpu: nova-core: fix bounds check in PmuLookupTableEntry::new
  drm/amdgpu: Replace HQD terminology with slots naming
  drm/amdgpu: Add user queue instance count in HW IP info
  drm/amd/amdgpu: Add helper functions for isp buffers
  drm/amd/amdgpu: Initialize swnode for ISP MFD device
  ...

1 files changed, 38 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 9c8829bd5a58..540817e296da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1107,6 +1107,9 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
 					      err_info->de_count, blk_name);
 			}
 		} else {
+			if (adev->debug_disable_ce_logs)
+				return;
+
 			for_each_ras_error(err_node, err_data) {
 				err_info = &err_node->err_info;
 				mcm_info = &err_info->mcm_info;
@@ -2854,6 +2857,13 @@ static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev,
 			if (amdgpu_umc_pages_in_a_row(adev, err_data,
 					bps[0].retired_page << AMDGPU_GPU_PAGE_SHIFT))
 				return -EINVAL;
+			for (i = 0; i < adev->umc.retire_unit; i++) {
+				err_data->err_addr[i].address = bps[0].address;
+				err_data->err_addr[i].mem_channel = bps[0].mem_channel;
+				err_data->err_addr[i].bank = bps[0].bank;
+				err_data->err_addr[i].err_type = bps[0].err_type;
+				err_data->err_addr[i].mcumc_id = bps[0].mcumc_id;
+			}
 		} else {
 			if (amdgpu_ras_mca2pa_by_idx(adev, &bps[0], err_data))
 				return -EINVAL;
@@ -2885,6 +2895,7 @@ static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev,
 				struct eeprom_table_record *bps, struct ras_err_data *err_data,
 				enum amdgpu_memory_partition nps)
 {
+	int i = 0;
 	enum amdgpu_memory_partition save_nps;
 
 	save_nps = (bps->retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK;
@@ -2894,6 +2905,13 @@ static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev,
 		if (amdgpu_umc_pages_in_a_row(adev, err_data,
 				bps->retired_page << AMDGPU_GPU_PAGE_SHIFT))
 			return -EINVAL;
+		for (i = 0; i < adev->umc.retire_unit; i++) {
+			err_data->err_addr[i].address = bps->address;
+			err_data->err_addr[i].mem_channel = bps->mem_channel;
+			err_data->err_addr[i].bank = bps->bank;
+			err_data->err_addr[i].err_type = bps->err_type;
+			err_data->err_addr[i].mcumc_id = bps->mcumc_id;
+		}
 	} else {
 		if (bps->address) {
 			if (amdgpu_ras_mca2pa_by_idx(adev, bps, err_data))
@@ -3003,6 +3021,15 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 		return 0;
 	}
 
+	if (!con->eeprom_control.is_eeprom_valid) {
+		dev_warn(adev->dev,
+			"Failed to save EEPROM table data because of EEPROM data corruption!");
+		if (new_cnt)
+			*new_cnt = 0;
+
+		return 0;
+	}
+
 	mutex_lock(&con->recovery_lock);
 	control = &con->eeprom_control;
 	data = con->eh_data;
@@ -3294,7 +3321,6 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,
 	uint64_t de_queried_count;
 	uint32_t new_detect_count, total_detect_count;
 	uint32_t need_query_count = poison_creation_count;
-	bool query_data_timeout = false;
 	enum ras_event_type type = RAS_EVENT_TYPE_POISON_CREATION;
 
 	memset(&info, 0, sizeof(info));
@@ -3323,21 +3349,13 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,
 				timeout = MAX_UMC_POISON_POLLING_TIME_ASYNC;
 
 			if (timeout) {
-				if (!--timeout) {
-					query_data_timeout = true;
+				if (!--timeout)
 					break;
-				}
 				msleep(1);
 			}
 		}
 	} while (total_detect_count < need_query_count);
 
-	if (query_data_timeout) {
-		dev_warn(adev->dev, "Can't find deferred error! count: %u\n",
-			(need_query_count - total_detect_count));
-		return -ENOENT;
-	}
-
 	if (total_detect_count)
 		schedule_delayed_work(&ras->page_retirement_dwork, 0);
 
@@ -3488,8 +3506,7 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 
 	control = &con->eeprom_control;
 	ret = amdgpu_ras_eeprom_init(control);
-	if (ret)
-		return ret;
+	control->is_eeprom_valid = !ret;
 
 	if (!adev->umc.ras || !adev->umc.ras->convert_ras_err_addr)
 		control->ras_num_pa_recs = control->ras_num_recs;
@@ -3498,10 +3515,12 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 	    adev->umc.ras->get_retire_flip_bits)
 		adev->umc.ras->get_retire_flip_bits(adev);
 
-	if (control->ras_num_recs) {
+	if (control->ras_num_recs && control->is_eeprom_valid) {
 		ret = amdgpu_ras_load_bad_pages(adev);
-		if (ret)
-			return ret;
+		if (ret) {
+			control->is_eeprom_valid = false;
+			return 0;
+		}
 
 		amdgpu_dpm_send_hbm_bad_pages_num(
 			adev, control->ras_num_bad_pages);
@@ -3520,7 +3539,7 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 					dev_warn(adev->dev, "Failed to format RAS EEPROM data in V3 version!\n");
 	}
 
-	return ret;
+	return 0;
 }
 
 int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
@@ -4414,8 +4433,10 @@ void amdgpu_ras_clear_err_state(struct amdgpu_device *adev)
 	struct amdgpu_ras *ras;
 
 	ras = amdgpu_ras_get_context(adev);
-	if (ras)
+	if (ras) {
 		ras->ras_err_state = 0;
+		ras->gpu_reset_flags = 0;
+	}
 }
 
 void amdgpu_ras_set_err_poison(struct amdgpu_device *adev,