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, 119 insertions, 36 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index d65e21914d8c..20436f81856a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -23,6 +23,7 @@
 
 #include "amdgpu.h"
 #include "umc_v6_7.h"
+#define MAX_UMC_POISON_POLLING_TIME_SYNC   20  //ms
 
 static int amdgpu_umc_convert_error_address(struct amdgpu_device *adev,
 				    struct ras_err_data *err_data, uint64_t err_addr,
@@ -85,18 +86,21 @@ out_fini_err_data:
 	return ret;
 }
 
-static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
-		void *ras_error_status,
-		struct amdgpu_iv_entry *entry,
-		bool reset)
+static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
+			void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	unsigned int error_query_mode;
 	int ret = 0;
+	unsigned long err_count;
 
-	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+	amdgpu_ras_get_error_query_mode(adev, &error_query_mode);
+
+	mutex_lock(&con->page_retirement_lock);
 	ret = amdgpu_dpm_get_ecc_info(adev, (void *)&(con->umc_ecc));
-	if (ret == -EOPNOTSUPP) {
+	if (ret == -EOPNOTSUPP &&
+	    error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY) {
 		if (adev->umc.ras && adev->umc.ras->ras_block.hw_ops &&
 		    adev->umc.ras->ras_block.hw_ops->query_ras_error_count)
 		    adev->umc.ras->ras_block.hw_ops->query_ras_error_count(adev, ras_error_status);
@@ -120,7 +124,8 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 			 */
 			adev->umc.ras->ras_block.hw_ops->query_ras_error_address(adev, ras_error_status);
 		}
-	} else if (!ret) {
+	} else if (error_query_mode == AMDGPU_RAS_FIRMWARE_ERROR_QUERY ||
+	    (!ret && error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY)) {
 		if (adev->umc.ras &&
 		    adev->umc.ras->ecc_info_query_ras_error_count)
 		    adev->umc.ras->ecc_info_query_ras_error_count(adev, ras_error_status);
@@ -147,16 +152,13 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 	}
 
 	/* only uncorrectable error needs gpu reset */
-	if (err_data->ue_count) {
-		dev_info(adev->dev, "%ld uncorrectable hardware errors "
-				"detected in UMC block\n",
-				err_data->ue_count);
-
+	if (err_data->ue_count || err_data->de_count) {
+		err_count = err_data->ue_count + err_data->de_count;
 		if ((amdgpu_bad_page_threshold != 0) &&
 			err_data->err_addr_cnt) {
 			amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
 						err_data->err_addr_cnt);
-			amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count));
+			amdgpu_ras_save_bad_pages(adev, &err_count);
 
 			amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs);
 
@@ -165,20 +167,87 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 				con->update_channel_flag = false;
 			}
 		}
-
-		if (reset) {
-			/* use mode-2 reset for poison consumption */
-			if (!entry)
-				con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
-			amdgpu_ras_reset_gpu(adev);
-		}
 	}
 
 	kfree(err_data->err_addr);
+
+	mutex_unlock(&con->page_retirement_lock);
+}
+
+static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
+		void *ras_error_status,
+		struct amdgpu_iv_entry *entry,
+		bool reset)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+	amdgpu_umc_handle_bad_pages(adev, ras_error_status);
+
+	if (err_data->ue_count && reset) {
+		/* use mode-2 reset for poison consumption */
+		if (!entry)
+			con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
+		amdgpu_ras_reset_gpu(adev);
+	}
+
 	return AMDGPU_RAS_SUCCESS;
 }
 
-int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset)
+int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
+			bool reset, uint32_t timeout_ms)
+{
+	struct ras_err_data err_data;
+	struct ras_common_if head = {
+		.block = AMDGPU_RAS_BLOCK__UMC,
+	};
+	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
+	uint32_t timeout = timeout_ms;
+
+	memset(&err_data, 0, sizeof(err_data));
+	amdgpu_ras_error_data_init(&err_data);
+
+	do {
+
+		amdgpu_umc_handle_bad_pages(adev, &err_data);
+
+		if (timeout && !err_data.de_count) {
+			msleep(1);
+			timeout--;
+		}
+
+	} while (timeout && !err_data.de_count);
+
+	if (!timeout)
+		dev_warn(adev->dev, "Can't find bad pages\n");
+
+	if (err_data.de_count)
+		dev_info(adev->dev, "%ld new deferred hardware errors detected\n", err_data.de_count);
+
+	if (obj) {
+		obj->err_data.ue_count += err_data.ue_count;
+		obj->err_data.ce_count += err_data.ce_count;
+		obj->err_data.de_count += err_data.de_count;
+	}
+
+	amdgpu_ras_error_data_fini(&err_data);
+
+	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+
+	if (reset) {
+		struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+		/* use mode-2 reset for poison consumption */
+		con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
+		amdgpu_ras_reset_gpu(adev);
+	}
+
+	return 0;
+}
+
+int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
+			enum amdgpu_ras_block block, bool reset)
 {
 	int ret = AMDGPU_RAS_SUCCESS;
 
@@ -195,27 +264,41 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset)
 	}
 
 	if (!amdgpu_sriov_vf(adev)) {
-		struct ras_err_data err_data;
-		struct ras_common_if head = {
-			.block = AMDGPU_RAS_BLOCK__UMC,
-		};
-		struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
+		if (amdgpu_ip_version(adev, UMC_HWIP, 0) < IP_VERSION(12, 0, 0)) {
+			struct ras_err_data err_data;
+			struct ras_common_if head = {
+				.block = AMDGPU_RAS_BLOCK__UMC,
+			};
+			struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
+
+			ret = amdgpu_ras_error_data_init(&err_data);
+			if (ret)
+				return ret;
 
-		ret = amdgpu_ras_error_data_init(&err_data);
-		if (ret)
-			return ret;
+			ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset);
 
-		ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset);
+			if (ret == AMDGPU_RAS_SUCCESS && obj) {
+				obj->err_data.ue_count += err_data.ue_count;
+				obj->err_data.ce_count += err_data.ce_count;
+				obj->err_data.de_count += err_data.de_count;
+			}
 
-		if (ret == AMDGPU_RAS_SUCCESS && obj) {
-			obj->err_data.ue_count += err_data.ue_count;
-			obj->err_data.ce_count += err_data.ce_count;
-		}
+			amdgpu_ras_error_data_fini(&err_data);
+		} else {
+			if (reset) {
+				amdgpu_umc_bad_page_polling_timeout(adev,
+							reset, MAX_UMC_POISON_POLLING_TIME_SYNC);
+			} else {
+				struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
-		amdgpu_ras_error_data_fini(&err_data);
+				atomic_inc(&con->page_retirement_req_cnt);
+
+				wake_up(&con->page_retirement_wq);
+			}
+		}
 	} else {
 		if (adev->virt.ops && adev->virt.ops->ras_poison_handler)
-			adev->virt.ops->ras_poison_handler(adev);
+			adev->virt.ops->ras_poison_handler(adev, block);
 		else
 			dev_warn(adev->dev,
 				"No ras_poison_handler interface in SRIOV!\n");