Merge tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR<->non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo->ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...

1 files changed, 69 insertions, 38 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index a060c28f0877..2452dfa6314f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -681,6 +681,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping &&
 		ring->funcs->emit_wreg;
 
+	if (adev->gfx.enable_cleaner_shader &&
+	    ring->funcs->emit_cleaner_shader &&
+	    job->enforce_isolation)
+		ring->funcs->emit_cleaner_shader(ring);
+
 	if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync)
 		return 0;
 
@@ -742,6 +747,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 		amdgpu_ring_emit_switch_buffer(ring);
 		amdgpu_ring_emit_switch_buffer(ring);
 	}
+
 	amdgpu_ring_ib_end(ring);
 	return 0;
 }
@@ -838,7 +844,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	params.vm = vm;
 	params.immediate = immediate;
 
-	r = vm->update_funcs->prepare(&params, NULL, AMDGPU_SYNC_EXPLICIT);
+	r = vm->update_funcs->prepare(&params, NULL);
 	if (r)
 		goto error;
 
@@ -902,10 +908,12 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
 {
 	struct amdgpu_vm *vm = params->vm;
 
-	if (!fence || !*fence)
+	tlb_cb->vm = vm;
+	if (!fence || !*fence) {
+		amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
 		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);
@@ -933,7 +941,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
  * @unlocked: unlocked invalidation during MM callback
  * @flush_tlb: trigger tlb invalidation after update completed
  * @allow_override: change MTYPE for local NUMA nodes
- * @resv: fences we need to sync to
+ * @sync: fences we need to sync to
  * @start: start of mapped range
  * @last: last mapped entry
  * @flags: flags for the entries
@@ -949,16 +957,16 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
  * 0 for success, negative erro code for failure.
  */
 int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			   bool immediate, bool unlocked, bool flush_tlb, bool allow_override,
-			   struct dma_resv *resv, uint64_t start, uint64_t last,
-			   uint64_t flags, uint64_t offset, uint64_t vram_base,
+			   bool immediate, bool unlocked, bool flush_tlb,
+			   bool allow_override, struct amdgpu_sync *sync,
+			   uint64_t start, uint64_t last, uint64_t flags,
+			   uint64_t offset, uint64_t vram_base,
 			   struct ttm_resource *res, dma_addr_t *pages_addr,
 			   struct dma_fence **fence)
 {
 	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;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx))
@@ -991,14 +999,6 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	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.
-	 */
-	if (!(flags & AMDGPU_PTE_VALID))
-		sync_mode = AMDGPU_SYNC_EQ_OWNER;
-	else
-		sync_mode = AMDGPU_SYNC_EXPLICIT;
-
 	amdgpu_vm_eviction_lock(vm);
 	if (vm->evicting) {
 		r = -EBUSY;
@@ -1013,7 +1013,7 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		dma_fence_put(tmp);
 	}
 
-	r = vm->update_funcs->prepare(&params, resv, sync_mode);
+	r = vm->update_funcs->prepare(&params, sync);
 	if (r)
 		goto error_free;
 
@@ -1155,23 +1155,30 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 	struct amdgpu_bo *bo = bo_va->base.bo;
 	struct amdgpu_vm *vm = bo_va->base.vm;
 	struct amdgpu_bo_va_mapping *mapping;
+	struct dma_fence **last_update;
 	dma_addr_t *pages_addr = NULL;
 	struct ttm_resource *mem;
-	struct dma_fence **last_update;
+	struct amdgpu_sync sync;
 	bool flush_tlb = clear;
-	bool uncached;
-	struct dma_resv *resv;
 	uint64_t vram_base;
 	uint64_t flags;
+	bool uncached;
 	int r;
 
+	amdgpu_sync_create(&sync);
 	if (clear || !bo) {
 		mem = NULL;
-		resv = vm->root.bo->tbo.base.resv;
+
+		/* Implicitly sync to command submissions in the same VM before
+		 * unmapping.
+		 */
+		r = amdgpu_sync_resv(adev, &sync, vm->root.bo->tbo.base.resv,
+				     AMDGPU_SYNC_EQ_OWNER, vm);
+		if (r)
+			goto error_free;
 	} else {
 		struct drm_gem_object *obj = &bo->tbo.base;
 
-		resv = bo->tbo.base.resv;
 		if (obj->import_attach && bo_va->is_xgmi) {
 			struct dma_buf *dma_buf = obj->import_attach->dmabuf;
 			struct drm_gem_object *gobj = dma_buf->priv;
@@ -1185,6 +1192,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 		if (mem && (mem->mem_type == TTM_PL_TT ||
 			    mem->mem_type == AMDGPU_PL_PREEMPT))
 			pages_addr = bo->tbo.ttm->dma_address;
+
+		/* Implicitly sync to moving fences before mapping anything */
+		r = amdgpu_sync_resv(adev, &sync, bo->tbo.base.resv,
+				     AMDGPU_SYNC_EXPLICIT, vm);
+		if (r)
+			goto error_free;
 	}
 
 	if (bo) {
@@ -1234,12 +1247,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 		trace_amdgpu_vm_bo_update(mapping);
 
 		r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb,
-					   !uncached, resv, mapping->start, mapping->last,
-					   update_flags, mapping->offset,
-					   vram_base, mem, pages_addr,
-					   last_update);
+					   !uncached, &sync, mapping->start,
+					   mapping->last, update_flags,
+					   mapping->offset, vram_base, mem,
+					   pages_addr, last_update);
 		if (r)
-			return r;
+			goto error_free;
 	}
 
 	/* If the BO is not in its preferred location add it back to
@@ -1267,7 +1280,9 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 			trace_amdgpu_vm_bo_mapping(mapping);
 	}
 
-	return 0;
+error_free:
+	amdgpu_sync_free(&sync);
+	return r;
 }
 
 /**
@@ -1414,25 +1429,34 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
 			  struct dma_fence **fence)
 {
-	struct dma_resv *resv = vm->root.bo->tbo.base.resv;
 	struct amdgpu_bo_va_mapping *mapping;
-	uint64_t init_pte_value = 0;
 	struct dma_fence *f = NULL;
+	struct amdgpu_sync sync;
 	int r;
 
+
+	/*
+	 * Implicitly sync to command submissions in the same VM before
+	 * unmapping.
+	 */
+	amdgpu_sync_create(&sync);
+	r = amdgpu_sync_resv(adev, &sync, vm->root.bo->tbo.base.resv,
+			     AMDGPU_SYNC_EQ_OWNER, vm);
+	if (r)
+		goto error_free;
+
 	while (!list_empty(&vm->freed)) {
 		mapping = list_first_entry(&vm->freed,
 			struct amdgpu_bo_va_mapping, list);
 		list_del(&mapping->list);
 
 		r = amdgpu_vm_update_range(adev, vm, false, false, true, false,
-					   resv, mapping->start, mapping->last,
-					   init_pte_value, 0, 0, NULL, NULL,
-					   &f);
+					   &sync, mapping->start, mapping->last,
+					   0, 0, 0, NULL, NULL, &f);
 		amdgpu_vm_free_mapping(adev, vm, mapping, f);
 		if (r) {
 			dma_fence_put(f);
-			return r;
+			goto error_free;
 		}
 	}
 
@@ -1443,7 +1467,9 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 		dma_fence_put(f);
 	}
 
-	return 0;
+error_free:
+	amdgpu_sync_free(&sync);
+	return r;
 
 }
 
@@ -2218,7 +2244,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
 		phys_ram_gb = ((uint64_t)si.totalram * si.mem_unit +
 			       (1 << 30) - 1) >> 30;
 		vm_size = roundup_pow_of_two(
-			min(max(phys_ram_gb * 3, min_vm_size), max_size));
+			clamp(phys_ram_gb * 3, min_vm_size, max_size));
 	}
 
 	adev->vm_manager.max_pfn = (uint64_t)vm_size << 18;
@@ -2421,6 +2447,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		return r;
 
+	ttm_lru_bulk_move_init(&vm->lru_bulk_move);
+
 	vm->is_compute_context = false;
 
 	vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
@@ -2485,6 +2513,7 @@ error_free_root:
 error_free_delayed:
 	dma_fence_put(vm->last_tlb_flush);
 	dma_fence_put(vm->last_unlocked);
+	ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move);
 	amdgpu_vm_fini_entities(vm);
 
 	return r;
@@ -2641,6 +2670,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		}
 	}
 
+	ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move);
 }
 
 /**
@@ -2754,6 +2784,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * amdgpu_vm_handle_fault - graceful handling of VM faults.
  * @adev: amdgpu device pointer
  * @pasid: PASID of the VM
+ * @ts: Timestamp of the fault
  * @vmid: VMID, only used for GFX 9.4.3.
  * @node_id: Node_id received in IH cookie. Only applicable for
  *           GFX 9.4.3.
@@ -2764,7 +2795,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * shouldn't be reported any more.
  */
 bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
-			    u32 vmid, u32 node_id, uint64_t addr,
+			    u32 vmid, u32 node_id, uint64_t addr, uint64_t ts,
 			    bool write_fault)
 {
 	bool is_compute_context = false;
@@ -2790,7 +2821,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 	addr /= AMDGPU_GPU_PAGE_SIZE;
 
 	if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid,
-	    node_id, addr, write_fault)) {
+	    node_id, addr, ts, write_fault)) {
 		amdgpu_bo_unref(&root);
 		return true;
 	}