Merge tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm subsystems for 6.10.

  In drivers the main thing is a new driver for ARM Mali firmware based
  GPUs, otherwise there are a lot of changes to amdgpu/xe/i915/msm and
  scattered changes to everything else.

  In the core a bunch of headers and Kconfig was refactored, along with
  the addition of a new panic handler which is meant to provide a user
  friendly message when a panic happens and graphical display is
  enabled.

  New drivers:
   - panthor: ARM Mali/Immortalis CSF-based GPU driver

  Core:
   - add a CONFIG_DRM_WERROR option
   - make more headers self-contained
   - grab resv lock in pin/unpin
   - fix vmap resv locking
   - EDID/eDP panel matching
   - Kconfig cleanups
   - DT sound bindings
   - Add SIZE_HINTS property for cursor planes
   - Add struct drm_edid_product_id and helpers.
   - Use drm device based logging in more drm functions.
   - drop seq_file.h from a bunch of places
   - use drm_edid driver conversions

  dp:
   - DP Tunnel documentation
   - MST read sideband cap
   - Adaptive sync SDP prep work

  ttm:
   - improve placement for TTM BOs in idle/busy handling

  panic:
   - Fixes for drm-panic, and option to test it.
   - Add drm panic to simpledrm, mgag200, imx, ast

  bridge:
   - improve init ordering
   - adv7511: allow GPIO pin sharing
   - tc358775: add tc358675 support

  panel:
   - AUO B120XAN01.0
   - Samsung s6e3fa7
   - BOE NT116WHM-N44
   - CMN N116BCA-EA1,
   - CrystalClear CMT430B19N00
   - Startek KD050HDFIA020-C020A
   - powertip PH128800T006-ZHC01
   - Innolux G121X1-L03
   - LG sw43408
   - Khadas TS050 V2
   - EDO RM69380 OLED
   - CSOT MNB601LS1-1

  amdgpu:
   - HDCP/ODM/RAS fixes
   - Devcoredump improvements
   - Expose VCN activity via sysfs
   - SMY 13.0.x updates
   - Enable fast updates on DCN 3.1.4
   - Add dclk and vclk reporting on additional devices
   - Add ACA RAS infrastructure
   - Implement TLB flush fence
   - EEPROM handling fixes
   - SMUIO 14.0.2 support
   - SMU 14.0.1 Updates
   - SMU 14.0.2 support
   - Sync page table freeing with TLB flushes
   - DML2 refactor
   - DC debug improvements
   - DCN 3.5.x Updates
   - GPU reset fixes
   - HDP fix for second GFX pipe on GC 10.x
   - Enable secondary GFX pipe on GC 10.3
   - Refactor and clean up BACO/BOCO/BAMACO handling
   - Remove invalid TTM resource start check
   - UAF fix in VA IOCTL
   - GPUVM page fault redirection to secondary IH rings for IH 6.x
   - Initial support for mapping kernel queues via MES
   - Fix VRAM memory accounting

  amdkfd:
   - MQD handling cleanup
   - Preemption handling fixes for XCDs
   - TLB flush fix for GC 9.4.2
   - Properly clean up workqueue during module unload
   - Fix memory leak process create failure
   - Range check CP bad op exception targets to avoid reporting invalid exceptions to userspace
   - Fix eviction fence handling
   - Fix leak in GPU memory allocation failure case
   - DMABuf import handling fix
   - Enable SQ watchpoint for gfx10

  i915:
   - Adding new DG2 PCI ID
   - add context hints for GT frequency
   - enable only one CCS for compute workloads
   - new workarounds
   - Fix UAF on destroy against retire race and remove two earlier partial fixes
   - Limit the reserved VM space to only the platforms that need it
   - Fix gt reset with GuC submission is disable
   - Add and use gt_to_guc() wrapper

  i915/xe display:
   - Lunar Lake display enabling, including cdclk and other refactors
   - BIOS/VBT/opregion related refactor
   - Digital port related refactor/clean-up
   - Fix 2s boot time regression on DP panel replay init
   - Remove duplication on audio enable/disable on SDVO and g4x+ DP
   - Disable AuxCCS framebuffers if built for Xe
   - Make crtc disable more atomic
   - Increase DP idle pattern wait timeout to 2ms
   - Start using container_of_const() for some extra const safety
   - Fix Jasper Lake boot freeze
   - Enable MST mode for 128b/132b single-stream sideband
   - Enable Adaptive Sync SDP Support for DP
   - Fix MTL supported DP rates - removal of UHBR13.5
   - PLL refactoring
   - Limit eDP MSO pipe only for display version 20
   - More display refactor towards independence from i915 dev_priv
   - Convert i915/xe fbdev to DRM client
   - More initial work to make display code more independent from i915

  xe:
   - improved error capture
   - clean up some uAPI leftovers
   - devcoredump update
   - Add BMG mocs table
   - Handle GSCCS ER interrupt
   - Implement xe2- and GuC workarounds
   - struct xe_device cleanup
   - Hwmon updates
   - Add LRC parsing for more GPU instruction
   - Increase VM_BIND number of per-ioctl Ops
   - drm/xe: Add XE_BO_GGTT_INVALIDATE flag
   - Initial development for SR-IOV support
   - Add new PCI IDs to DG2 platform
   - Move userptr over to start using hmm_range_fault

  msm:
   - Switched to generating register header files during build process
     instead of shipping pre-generated headers
   - Merged DPU and MDP4 format databases.
   - DP:
     - Stop using compat string to distinguish DP and eDP cases
     - Added support for X Elite platform (X1E80100)
     - Reworked DP aux/audio support
     - Added SM6350 DP to the bindings
   - GPU:
     - a7xx perfcntr reg fixes
     - MAINTAINERS updates
     - a750 devcoredump support

  radeon:
   - Silence UBSAN warnings related to flexible arrays

  nouveau:
   - move some uAPI objects to uapi headers

  omapdrm:
   - console fix

  ast:
   - add i2c polling

  qaic:
   - add debugfs entries

  exynos:
   - fix platform_driver .owner
   - drop cleanup code

  mediatek:
   - Use devm_platform_get_and_ioremap_resource() in mtk_hdmi_ddc_probe()
   - Add GAMMA 12-bit LUT support for MT8188
   - Rename mtk_drm_* to mtk_*
   - Drop driver owner initialization
   - Correct calculation formula of PHY Timing"

* tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel: (1477 commits)
  drm/xe/ads: Use flexible-array
  drm/xe: Use ordered WQ for G2H handler
  drm/msm/gen_header: allow skipping the validation
  drm/msm/a6xx: Cleanup indexed regs const'ness
  drm/msm: Add devcoredump support for a750
  drm/msm: Adjust a7xx GBIF debugbus dumping
  drm/msm: Update a6xx registers XML
  drm/msm: Fix imported a750 snapshot header for upstream
  drm/msm: Import a750 snapshot registers from kgsl
  MAINTAINERS: Add Konrad Dybcio as a reviewer for the Adreno driver
  MAINTAINERS: Add a separate entry for Qualcomm Adreno GPU drivers
  drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails
  drm/msm/adreno: fix CP cycles stat retrieval on a7xx
  drm/msm/a7xx: allow writing to CP_BV counter selection registers
  drm: zynqmp_dpsub: Always register bridge
  Revert "drm/bridge: ti-sn65dsi83: Fix enable error path"
  drm/fb_dma: Add checks in drm_fb_dma_get_scanout_buffer()
  drm/fbdev-generic: Do not set physical framebuffer address
  drm/panthor: Fix the FW reset logic
  drm/panthor: Make sure we handle 'unknown group state' case properly
  ...

1 files changed, 58 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 94089069c9ad..4e2391c83d7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -886,6 +886,44 @@ static void amdgpu_vm_tlb_seq_cb(struct dma_fence *fence,
 }
 
 /**
+ * amdgpu_vm_tlb_flush - prepare TLB flush
+ *
+ * @params: parameters for update
+ * @fence: input fence to sync TLB flush with
+ * @tlb_cb: the callback structure
+ *
+ * Increments the tlb sequence to make sure that future CS execute a VM flush.
+ */
+static void
+amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
+		    struct dma_fence **fence,
+		    struct amdgpu_vm_tlb_seq_struct *tlb_cb)
+{
+	struct amdgpu_vm *vm = params->vm;
+
+	if (!fence || !*fence)
+		return;
+
+	tlb_cb->vm = vm;
+	if (!dma_fence_add_callback(*fence, &tlb_cb->cb,
+				    amdgpu_vm_tlb_seq_cb)) {
+		dma_fence_put(vm->last_tlb_flush);
+		vm->last_tlb_flush = dma_fence_get(*fence);
+	} else {
+		amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
+	}
+
+	/* Prepare a TLB flush fence to be attached to PTs */
+	if (!params->unlocked && vm->is_compute_context) {
+		amdgpu_vm_tlb_fence_create(params->adev, vm, fence);
+
+		/* Makes sure no PD/PT is freed before the flush */
+		dma_resv_add_fence(vm->root.bo->tbo.base.resv, *fence,
+				   DMA_RESV_USAGE_BOOKKEEP);
+	}
+}
+
+/**
  * amdgpu_vm_update_range - update a range in the vm page table
  *
  * @adev: amdgpu_device pointer to use for commands
@@ -916,8 +954,8 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			   struct ttm_resource *res, dma_addr_t *pages_addr,
 			   struct dma_fence **fence)
 {
-	struct amdgpu_vm_update_params params;
 	struct amdgpu_vm_tlb_seq_struct *tlb_cb;
+	struct amdgpu_vm_update_params params;
 	struct amdgpu_res_cursor cursor;
 	enum amdgpu_sync_mode sync_mode;
 	int r, idx;
@@ -927,8 +965,8 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	tlb_cb = kmalloc(sizeof(*tlb_cb), GFP_KERNEL);
 	if (!tlb_cb) {
-		r = -ENOMEM;
-		goto error_unlock;
+		drm_dev_exit(idx);
+		return -ENOMEM;
 	}
 
 	/* Vega20+XGMI where PTEs get inadvertently cached in L2 texture cache,
@@ -948,7 +986,9 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	params.immediate = immediate;
 	params.pages_addr = pages_addr;
 	params.unlocked = unlocked;
+	params.needs_flush = flush_tlb;
 	params.allow_override = allow_override;
+	INIT_LIST_HEAD(&params.tlb_flush_waitlist);
 
 	/* Implicitly sync to command submissions in the same VM before
 	 * unmapping. Sync to moving fences before mapping.
@@ -1031,24 +1071,18 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = vm->update_funcs->commit(&params, fence);
+	if (r)
+		goto error_free;
 
-	if (flush_tlb || params.table_freed) {
-		tlb_cb->vm = vm;
-		if (fence && *fence &&
-		    !dma_fence_add_callback(*fence, &tlb_cb->cb,
-					   amdgpu_vm_tlb_seq_cb)) {
-			dma_fence_put(vm->last_tlb_flush);
-			vm->last_tlb_flush = dma_fence_get(*fence);
-		} else {
-			amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
-		}
+	if (params.needs_flush) {
+		amdgpu_vm_tlb_flush(&params, fence, tlb_cb);
 		tlb_cb = NULL;
 	}
 
+	amdgpu_vm_pt_free_list(adev, &params);
+
 error_free:
 	kfree(tlb_cb);
-
-error_unlock:
 	amdgpu_vm_eviction_unlock(vm);
 	drm_dev_exit(idx);
 	return r;
@@ -2411,6 +2445,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	mutex_init(&vm->eviction_lock);
 	vm->evicting = false;
+	vm->tlb_fence_context = dma_fence_context_alloc(1);
 
 	r = amdgpu_vm_pt_create(adev, vm, adev->vm_manager.root_level,
 				false, &root, xcp_id);
@@ -2944,6 +2979,14 @@ void amdgpu_vm_update_fault_cache(struct amdgpu_device *adev,
 	if (vm && status) {
 		vm->fault_info.addr = addr;
 		vm->fault_info.status = status;
+		/*
+		 * Update the fault information globally for later usage
+		 * when vm could be stale or freed.
+		 */
+		adev->vm_manager.fault_info.addr = addr;
+		adev->vm_manager.fault_info.vmhub = vmhub;
+		adev->vm_manager.fault_info.status = status;
+
 		if (AMDGPU_IS_GFXHUB(vmhub)) {
 			vm->fault_info.vmhub = AMDGPU_VMHUB_TYPE_GFX;
 			vm->fault_info.vmhub |=