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, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 4db92e0a60da..395c6be901ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -144,6 +144,7 @@ enum AMDGPU_DEBUG_MASK {
 	AMDGPU_DEBUG_DISABLE_GPU_RING_RESET = BIT(6),
 	AMDGPU_DEBUG_SMU_POOL = BIT(7),
 	AMDGPU_DEBUG_VM_USERPTR = BIT(8),
+	AMDGPU_DEBUG_DISABLE_RAS_CE_LOG = BIT(9)
 };
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -361,12 +362,12 @@ module_param_named(svm_default_granularity, amdgpu_svm_default_granularity, uint
  *   The second one is for Compute. The third and fourth ones are
  *   for SDMA and Video.
  *
- * By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
- * jobs is 10000. The timeout for compute is 60000.
+ * By default(with no lockup_timeout settings), the timeout for all jobs is 10000.
  */
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and 60000 for compute jobs; "
-		"for passthrough or sriov, 10000 for all jobs. 0: keep default value. negative: infinity timeout), format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
-		"for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
+MODULE_PARM_DESC(lockup_timeout,
+		 "GPU lockup timeout in ms (default: 10000 for all jobs. "
+		 "0: keep default value. negative: infinity timeout), format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
+		 "for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
 module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
 
 /**
@@ -2278,6 +2279,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 		pr_info("debug: VM mode debug for userptr is enabled\n");
 		adev->debug_vm_userptr = true;
 	}
+
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_DISABLE_RAS_CE_LOG) {
+		pr_info("debug: disable kernel logs of correctable errors\n");
+		adev->debug_disable_ce_logs = true;
+	}
 }
 
 static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
@@ -2321,7 +2327,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		amdgpu_aspm = 0;
 
 	if (amdgpu_virtual_display ||
-	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
+	    amdgpu_device_asic_has_dc_support(pdev, flags & AMD_ASIC_MASK))
 		supports_atomic = true;
 
 	if ((flags & AMD_EXP_HW_SUPPORT) && !amdgpu_exp_hw_support) {
@@ -2451,10 +2457,10 @@ retry_init:
 
 	if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) {
 		/* only need to skip on ATPX */
-		if (amdgpu_device_supports_px(ddev))
+		if (amdgpu_device_supports_px(adev))
 			dev_pm_set_driver_flags(ddev->dev, DPM_FLAG_NO_DIRECT_COMPLETE);
 		/* we want direct complete for BOCO */
-		if (amdgpu_device_supports_boco(ddev))
+		if (amdgpu_device_supports_boco(adev))
 			dev_pm_set_driver_flags(ddev->dev, DPM_FLAG_SMART_PREPARE |
 						DPM_FLAG_SMART_SUSPEND |
 						DPM_FLAG_MAY_SKIP_RESUME);
@@ -2487,9 +2493,9 @@ retry_init:
 		 * into D0 state. Then there will be a PMFW-aware D-state
 		 * transition(D0->D3) on runpm suspend.
 		 */
-		if (amdgpu_device_supports_baco(ddev) &&
+		if (amdgpu_device_supports_baco(adev) &&
 		    !(adev->flags & AMD_IS_APU) &&
-		    (adev->asic_type >= CHIP_NAVI10))
+		    adev->asic_type >= CHIP_NAVI10)
 			amdgpu_get_secondary_funcs(adev);
 	}
 
@@ -2506,6 +2512,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
+	amdgpu_ras_eeprom_check_and_recover(adev);
 	amdgpu_xcp_dev_unplug(adev);
 	amdgpu_gmc_prepare_nps_mode_change(adev);
 	drm_dev_unplug(dev);
@@ -2535,6 +2542,10 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	if (amdgpu_ras_intr_triggered())
 		return;
 
+	/* device maybe not resumed here, return immediately in this case */
+	if (adev->in_s4 && adev->in_suspend)
+		return;
+
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown.
 	 * unfortunately we can't detect certain
@@ -2551,11 +2562,14 @@ static int amdgpu_pmops_prepare(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	/* device maybe not resumed here, return immediately in this case */
+	if (adev->in_s4 && adev->in_suspend)
+		return 0;
+
 	/* Return a positive number here so
 	 * DPM_FLAG_SMART_SUSPEND works properly
 	 */
-	if (amdgpu_device_supports_boco(drm_dev) &&
-	    pm_runtime_suspended(dev))
+	if (amdgpu_device_supports_boco(adev) && pm_runtime_suspended(dev))
 		return 1;
 
 	/* if we will not support s3 or s2i for the device
@@ -2570,7 +2584,7 @@ static int amdgpu_pmops_prepare(struct device *dev)
 
 static void amdgpu_pmops_complete(struct device *dev)
 {
-	/* nothing to do */
+	amdgpu_device_complete(dev_get_drvdata(dev));
 }
 
 static int amdgpu_pmops_suspend(struct device *dev)
@@ -2650,12 +2664,21 @@ static int amdgpu_pmops_thaw(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
+	/* do not resume device if it's normal hibernation */
+	if (!pm_hibernate_is_recovering())
+		return 0;
+
 	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+
+	/* device maybe not resumed here, return immediately in this case */
+	if (adev->in_s4 && adev->in_suspend)
+		return 0;
 
 	return amdgpu_device_suspend(drm_dev, true);
 }
@@ -2828,7 +2851,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 		/* nothing to do */
 	} else if ((adev->pm.rpm_mode == AMDGPU_RUNPM_BACO) ||
 			(adev->pm.rpm_mode == AMDGPU_RUNPM_BAMACO)) {
-		amdgpu_device_baco_enter(drm_dev);
+		amdgpu_device_baco_enter(adev);
 	}
 
 	dev_dbg(&pdev->dev, "asic/device is runtime suspended\n");
@@ -2869,7 +2892,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 		pci_set_master(pdev);
 	} else if ((adev->pm.rpm_mode == AMDGPU_RUNPM_BACO) ||
 			(adev->pm.rpm_mode == AMDGPU_RUNPM_BAMACO)) {
-		amdgpu_device_baco_exit(drm_dev);
+		amdgpu_device_baco_exit(adev);
 	}
 	ret = amdgpu_device_resume(drm_dev, false);
 	if (ret) {
@@ -3107,10 +3130,6 @@ static int __init amdgpu_init(void)
 	if (r)
 		goto error_sync;
 
-	r = amdgpu_fence_slab_init();
-	if (r)
-		goto error_fence;
-
 	r = amdgpu_userq_fence_slab_init();
 	if (r)
 		goto error_fence;
@@ -3145,7 +3164,6 @@ static void __exit amdgpu_exit(void)
 	amdgpu_unregister_atpx_handler();
 	amdgpu_acpi_release();
 	amdgpu_sync_fini();
-	amdgpu_fence_slab_fini();
 	amdgpu_userq_fence_slab_fini();
 	mmu_notifier_synchronize();
 	amdgpu_xcp_drv_release();