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, 137 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index d6f50b13e2ba..2db9b2c63693 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -21,6 +21,7 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
+#include <drm/drm_drv.h>
 #include "amdgpu.h"
 #include "amdgpu_gfx.h"
 #include "mes_userqueue.h"
@@ -198,6 +199,53 @@ static int mes_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
 	return 0;
 }
 
+static int mes_userq_detect_and_reset(struct amdgpu_device *adev,
+				      int queue_type)
+{
+	int db_array_size = amdgpu_mes_get_hung_queue_db_array_size(adev);
+	struct mes_detect_and_reset_queue_input input;
+	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_userq_mgr *uqm, *tmp;
+	unsigned int hung_db_num = 0;
+	int queue_id, r, i;
+	u32 db_array[4];
+
+	if (db_array_size > 4) {
+		dev_err(adev->dev, "DB array size (%d vs 4) too small\n",
+			db_array_size);
+		return -EINVAL;
+	}
+
+	memset(&input, 0x0, sizeof(struct mes_detect_and_reset_queue_input));
+
+	input.queue_type = queue_type;
+
+	amdgpu_mes_lock(&adev->mes);
+	r = amdgpu_mes_detect_and_reset_hung_queues(adev, queue_type, false,
+						    &hung_db_num, db_array);
+	amdgpu_mes_unlock(&adev->mes);
+	if (r) {
+		dev_err(adev->dev, "Failed to detect and reset queues, err (%d)\n", r);
+	} else if (hung_db_num) {
+		list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
+			idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
+				if (queue->queue_type == queue_type) {
+					for (i = 0; i < hung_db_num; i++) {
+						if (queue->doorbell_index == db_array[i]) {
+							queue->state = AMDGPU_USERQ_STATE_HUNG;
+							atomic_inc(&adev->gpu_reset_counter);
+							amdgpu_userq_fence_driver_force_completion(queue);
+							drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
+						}
+					}
+				}
+			}
+		}
+	}
+
+	return r;
+}
+
 static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 				struct drm_amdgpu_userq_in *args_in,
 				struct amdgpu_usermode_queue *queue)
@@ -206,6 +254,7 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 	struct amdgpu_mqd *mqd_hw_default = &adev->mqds[queue->queue_type];
 	struct drm_amdgpu_userq_in *mqd_user = args_in;
 	struct amdgpu_mqd_prop *userq_props;
+	struct amdgpu_gfx_shadow_info shadow_info;
 	int r;
 
 	/* Structure to initialize MQD for userqueue using generic MQD init function */
@@ -215,13 +264,6 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 		return -ENOMEM;
 	}
 
-	if (!mqd_user->wptr_va || !mqd_user->rptr_va ||
-	    !mqd_user->queue_va || mqd_user->queue_size == 0) {
-		DRM_ERROR("Invalid MQD parameters for userqueue\n");
-		r = -EINVAL;
-		goto free_props;
-	}
-
 	r = amdgpu_userq_create_object(uq_mgr, &queue->mqd, mqd_hw_default->mqd_size);
 	if (r) {
 		DRM_ERROR("Failed to create MQD object for userqueue\n");
@@ -238,6 +280,8 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 	userq_props->doorbell_index = queue->doorbell_index;
 	userq_props->fence_address = queue->fence_drv->gpu_addr;
 
+	if (adev->gfx.funcs->get_gfx_shadow_info)
+		adev->gfx.funcs->get_gfx_shadow_info(adev, &shadow_info, true);
 	if (queue->queue_type == AMDGPU_HW_IP_COMPUTE) {
 		struct drm_amdgpu_userq_mqd_compute_gfx11 *compute_mqd;
 
@@ -254,6 +298,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 			goto free_mqd;
 		}
 
+		if (amdgpu_userq_input_va_validate(queue->vm, compute_mqd->eop_va,
+		    max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE)))
+			goto free_mqd;
+
 		userq_props->eop_gpu_addr = compute_mqd->eop_va;
 		userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL;
 		userq_props->hqd_queue_priority = AMDGPU_GFX_QUEUE_PRIORITY_MINIMUM;
@@ -281,6 +329,11 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 		userq_props->csa_addr = mqd_gfx_v11->csa_va;
 		userq_props->tmz_queue =
 			mqd_user->flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE;
+
+		if (amdgpu_userq_input_va_validate(queue->vm, mqd_gfx_v11->shadow_va,
+		    shadow_info.shadow_size))
+			goto free_mqd;
+
 		kfree(mqd_gfx_v11);
 	} else if (queue->queue_type == AMDGPU_HW_IP_DMA) {
 		struct drm_amdgpu_userq_mqd_sdma_gfx11 *mqd_sdma_v11;
@@ -298,6 +351,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 			goto free_mqd;
 		}
 
+		if (amdgpu_userq_input_va_validate(queue->vm, mqd_sdma_v11->csa_va,
+		    shadow_info.csa_size))
+			goto free_mqd;
+
 		userq_props->csa_addr = mqd_sdma_v11->csa_va;
 		kfree(mqd_sdma_v11);
 	}
@@ -347,9 +404,82 @@ mes_userq_mqd_destroy(struct amdgpu_userq_mgr *uq_mgr,
 	amdgpu_userq_destroy_object(uq_mgr, &queue->mqd);
 }
 
+static int mes_userq_preempt(struct amdgpu_userq_mgr *uq_mgr,
+				struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_device *adev = uq_mgr->adev;
+	struct mes_suspend_gang_input queue_input;
+	struct amdgpu_userq_obj *ctx = &queue->fw_obj;
+	signed long timeout = 2100000; /* 2100 ms */
+	u64 fence_gpu_addr;
+	u32 fence_offset;
+	u64 *fence_ptr;
+	int i, r;
+
+	if (queue->state != AMDGPU_USERQ_STATE_MAPPED)
+		return 0;
+	r = amdgpu_device_wb_get(adev, &fence_offset);
+	if (r)
+		return r;
+
+	fence_gpu_addr = adev->wb.gpu_addr + (fence_offset * 4);
+	fence_ptr = (u64 *)&adev->wb.wb[fence_offset];
+	*fence_ptr = 0;
+
+	memset(&queue_input, 0x0, sizeof(struct mes_suspend_gang_input));
+	queue_input.gang_context_addr = ctx->gpu_addr + AMDGPU_USERQ_PROC_CTX_SZ;
+	queue_input.suspend_fence_addr = fence_gpu_addr;
+	queue_input.suspend_fence_value = 1;
+	amdgpu_mes_lock(&adev->mes);
+	r = adev->mes.funcs->suspend_gang(&adev->mes, &queue_input);
+	amdgpu_mes_unlock(&adev->mes);
+	if (r) {
+		DRM_ERROR("Failed to suspend gang: %d\n", r);
+		goto out;
+	}
+
+	for (i = 0; i < timeout; i++) {
+		if (*fence_ptr == 1)
+			goto out;
+		udelay(1);
+	}
+	r = -ETIMEDOUT;
+
+out:
+	amdgpu_device_wb_free(adev, fence_offset);
+	return r;
+}
+
+static int mes_userq_restore(struct amdgpu_userq_mgr *uq_mgr,
+				struct amdgpu_usermode_queue *queue)
+{
+	struct amdgpu_device *adev = uq_mgr->adev;
+	struct mes_resume_gang_input queue_input;
+	struct amdgpu_userq_obj *ctx = &queue->fw_obj;
+	int r;
+
+	if (queue->state == AMDGPU_USERQ_STATE_HUNG)
+		return -EINVAL;
+	if (queue->state != AMDGPU_USERQ_STATE_PREEMPTED)
+		return 0;
+
+	memset(&queue_input, 0x0, sizeof(struct mes_resume_gang_input));
+	queue_input.gang_context_addr = ctx->gpu_addr + AMDGPU_USERQ_PROC_CTX_SZ;
+
+	amdgpu_mes_lock(&adev->mes);
+	r = adev->mes.funcs->resume_gang(&adev->mes, &queue_input);
+	amdgpu_mes_unlock(&adev->mes);
+	if (r)
+		dev_err(adev->dev, "Failed to resume queue, err (%d)\n", r);
+	return r;
+}
+
 const struct amdgpu_userq_funcs userq_mes_funcs = {
 	.mqd_create = mes_userq_mqd_create,
 	.mqd_destroy = mes_userq_mqd_destroy,
 	.unmap = mes_userq_unmap,
 	.map = mes_userq_map,
+	.detect_and_reset = mes_userq_detect_and_reset,
+	.preempt = mes_userq_preempt,
+	.restore = mes_userq_restore,
 };