Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

1 files changed, 50 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 94bdb5fa6ebc..1e9454e6e4cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -96,6 +96,9 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 #define AMDGPU_RESUME_MS		2000
 #define AMDGPU_MAX_RETRY_LIMIT		2
 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
+#define AMDGPU_PCIE_INDEX_FALLBACK (0x38 >> 2)
+#define AMDGPU_PCIE_INDEX_HI_FALLBACK (0x44 >> 2)
+#define AMDGPU_PCIE_DATA_FALLBACK (0x3C >> 2)
 
 static const struct drm_driver amdgpu_kms_driver;
 
@@ -781,12 +784,22 @@ u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev,
 	void __iomem *pcie_index_hi_offset;
 	void __iomem *pcie_data_offset;
 
-	pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
-	pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
-	if ((reg_addr >> 32) && (adev->nbio.funcs->get_pcie_index_hi_offset))
-		pcie_index_hi = adev->nbio.funcs->get_pcie_index_hi_offset(adev);
-	else
+	if (unlikely(!adev->nbio.funcs)) {
+		pcie_index = AMDGPU_PCIE_INDEX_FALLBACK;
+		pcie_data = AMDGPU_PCIE_DATA_FALLBACK;
+	} else {
+		pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
+		pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
+	}
+
+	if (reg_addr >> 32) {
+		if (unlikely(!adev->nbio.funcs))
+			pcie_index_hi = AMDGPU_PCIE_INDEX_HI_FALLBACK;
+		else
+			pcie_index_hi = adev->nbio.funcs->get_pcie_index_hi_offset(adev);
+	} else {
 		pcie_index_hi = 0;
+	}
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4;
@@ -1218,8 +1231,6 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 	    amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0)) {
 		amdgpu_psp_wait_for_bootloader(adev);
 		ret = amdgpu_atomfirmware_asic_init(adev, true);
-		/* TODO: check the return val and stop device initialization if boot fails */
-		amdgpu_psp_query_boot_status(adev);
 		return ret;
 	} else {
 		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -1442,6 +1453,10 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
+	/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
+	if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
+		DRM_WARN("System can't access extended configuration space,please check!!\n");
+
 	/* skip if the bios has already enabled large BAR */
 	if (adev->gmc.real_vram_size &&
 	    (pci_resource_len(adev->pdev, 0) >= adev->gmc.real_vram_size))
@@ -4025,8 +4040,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * early on during init and before calling to RREG32.
 	 */
 	adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");
-	if (!adev->reset_domain)
-		return -ENOMEM;
+	if (!adev->reset_domain) {
+		r = -ENOMEM;
+		goto unmap_memory;
+	}
 
 	/* detect hw virtualization here */
 	amdgpu_detect_virtualization(adev);
@@ -4036,20 +4053,20 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_device_get_job_timeout_settings(adev);
 	if (r) {
 		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		return r;
+		goto unmap_memory;
 	}
 
+	amdgpu_device_set_mcbp(adev);
+
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
-		return r;
-
-	amdgpu_device_set_mcbp(adev);
+		goto unmap_memory;
 
 	/* Get rid of things like offb */
 	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
 	if (r)
-		return r;
+		goto unmap_memory;
 
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
@@ -4059,7 +4076,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (adev->gmc.xgmi.supported) {
 		r = adev->gfxhub.funcs->get_xgmi_info(adev);
 		if (r)
-			return r;
+			goto unmap_memory;
 	}
 
 	/* enable PCIE atomic ops */
@@ -4328,6 +4345,8 @@ release_ras_con:
 failed:
 	amdgpu_vf_error_trans_all(adev);
 
+unmap_memory:
+	iounmap(adev->rmmio);
 	return r;
 }
 
@@ -5306,6 +5325,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		if (need_full_reset) {
 			/* post card */
+			amdgpu_ras_set_fed(tmp_adev, false);
 			r = amdgpu_device_asic_init(tmp_adev);
 			if (r) {
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
@@ -5686,6 +5706,7 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		/* Aldebaran and gfx_11_0_3 support ras in SRIOV, so need resume ras during reset */
 		if (amdgpu_ip_version(adev, GC_HWIP, 0) ==
 			    IP_VERSION(9, 4, 2) ||
+		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
 		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 0, 3))
 			amdgpu_ras_resume(adev);
 	} else {
@@ -6107,6 +6128,20 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	struct amdgpu_reset_context reset_context;
 	u32 memsize;
 	struct list_head device_list;
+	struct amdgpu_hive_info *hive;
+	int hive_ras_recovery = 0;
+	struct amdgpu_ras *ras;
+
+	/* PCI error slot reset should be skipped During RAS recovery */
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		hive_ras_recovery = atomic_read(&hive->ras_recovery);
+		amdgpu_put_xgmi_hive(hive);
+	}
+	ras = amdgpu_ras_get_context(adev);
+	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) &&
+		 ras && (atomic_read(&ras->in_recovery) || hive_ras_recovery))
+		return PCI_ERS_RESULT_RECOVERED;
 
 	DRM_INFO("PCI error: slot reset callback!!\n");