Merge tag 'drm-xe-next-2025-03-07' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

UAPI Changes:
 - Expose per-engine activity via perf pmu (Riana, Lucas, Umesh)
 - Add support for EU stall sampling (Harish, Ashutosh)
 - Allow userspace to provide low latency hint for submission (Tejas)
 - GPU SVM and Xe SVM implementation (Matthew Brost)

Cross-subsystem Changes:
 - devres handling for component drivers (Lucas)
 - Backmege drm-next to allow cross dependent change with i915
 - GPU SVM and Xe SVM implementation (Matthew Brost)

Core Changes:

Driver Changes:
 - Fixes to userptr and missing validations (Matthew Auld, Thomas
   Hellström, Matthew Brost)
 - devcoredump typos and error handling improvement (Shuicheng)
 - Allow oa_exponent value of 0 (Umesh)
 - Finish moving device probe to devm (Lucas)
 - Fix race between submission restart and scheduled being freed (Tejas)
 - Fix counter overflows in gt_stats (Francois)
 - Refactor and add missing workarounds and tunings for pre-Xe2 platforms
   (Aradhya, Tvrtko)
 - Fix PXP locks interaction with exec queues being killed (Daniele)
 - Eliminate TIMESTAMP_OVERRIDE from xe (Matt Roper)
 - Change xe_gen_wa_oob to allow building on MacOS (Daniel Gomez)
 - New workarounds for Panther Lake (Tejas)
 - Fix VF resume errors (Satyanarayana)
 - Fix workaround infra skipping some workarounds dependent on engine
   initialization (Tvrtko)
 - Improve per-IP descriptors (Gustavo)
 - Add more error injections to probe sequence (Francois)

Signed-off-by: Dave Airlie <[email protected]>

From: Lucas De Marchi <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/ilc5jvtyaoyi6woyhght5a6sw5jcluiojjueorcyxbynrcpcjp@mw2mi6rd6a7l

Author: airlied

Documentation/gpu/rfc/gpusvm.rst

@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+===============
+GPU SVM Section
+===============
+
+Agreed upon design principles
+=============================
+
+* migrate_to_ram path
+	* Rely only on core MM concepts (migration PTEs, page references, and
+	  page locking).
+	* No driver specific locks other than locks for hardware interaction in
+	  this path. These are not required and generally a bad idea to
+	  invent driver defined locks to seal core MM races.
+	* An example of a driver-specific lock causing issues occurred before
+	  fixing do_swap_page to lock the faulting page. A driver-exclusive lock
+	  in migrate_to_ram produced a stable livelock if enough threads read
+	  the faulting page.
+	* Partial migration is supported (i.e., a subset of pages attempting to
+	  migrate can actually migrate, with only the faulting page guaranteed
+	  to migrate).
+	* Driver handles mixed migrations via retry loops rather than locking.
+* Eviction
+	* Eviction is defined as migrating data from the GPU back to the
+	  CPU without a virtual address to free up GPU memory.
+	* Only looking at physical memory data structures and locks as opposed to
+	  looking at virtual memory data structures and locks.
+	* No looking at mm/vma structs or relying on those being locked.
+	* The rationale for the above two points is that CPU virtual addresses
+	  can change at any moment, while the physical pages remain stable.
+	* GPU page table invalidation, which requires a GPU virtual address, is
+	  handled via the notifier that has access to the GPU virtual address.
+* GPU fault side
+	* mmap_read only used around core MM functions which require this lock
+	  and should strive to take mmap_read lock only in GPU SVM layer.
+	* Big retry loop to handle all races with the mmu notifier under the gpu
+	  pagetable locks/mmu notifier range lock/whatever we end up calling
+          those.
+	* Races (especially against concurrent eviction or migrate_to_ram)
+	  should not be handled on the fault side by trying to hold locks;
+	  rather, they should be handled using retry loops. One possible
+	  exception is holding a BO's dma-resv lock during the initial migration
+	  to VRAM, as this is a well-defined lock that can be taken underneath
+	  the mmap_read lock.
+	* One possible issue with the above approach is if a driver has a strict
+	  migration policy requiring GPU access to occur in GPU memory.
+	  Concurrent CPU access could cause a livelock due to endless retries.
+	  While no current user (Xe) of GPU SVM has such a policy, it is likely
+	  to be added in the future. Ideally, this should be resolved on the
+	  core-MM side rather than through a driver-side lock.
+* Physical memory to virtual backpointer
+	* This does not work, as no pointers from physical memory to virtual
+	  memory should exist. mremap() is an example of the core MM updating
+	  the virtual address without notifying the driver of address
+	  change rather the driver only receiving the invalidation notifier.
+	* The physical memory backpointer (page->zone_device_data) should remain
+	  stable from allocation to page free. Safely updating this against a
+	  concurrent user would be very difficult unless the page is free.
+* GPU pagetable locking
+	* Notifier lock only protects range tree, pages valid state for a range
+	  (rather than seqno due to wider notifiers), pagetable entries, and
+	  mmu notifier seqno tracking, it is not a global lock to protect
+          against races.
+	* All races handled with big retry as mentioned above.
+
+Overview of baseline design
+===========================
+
+Baseline design is simple as possible to get a working basline in which can be
+built upon.
+
+.. kernel-doc:: drivers/gpu/drm/xe/drm_gpusvm.c
+   :doc: Overview
+   :doc: Locking
+   :doc: Migrataion
+   :doc: Partial Unmapping of Ranges
+   :doc: Examples
+
+Possible future design features
+===============================
+
+* Concurrent GPU faults
+	* CPU faults are concurrent so makes sense to have concurrent GPU
+	  faults.
+	* Should be possible with fined grained locking in the driver GPU
+	  fault handler.
+	* No expected GPU SVM changes required.
+* Ranges with mixed system and device pages
+	* Can be added if required to drm_gpusvm_get_pages fairly easily.
+* Multi-GPU support
+	* Work in progress and patches expected after initially landing on GPU
+	  SVM.
+	* Ideally can be done with little to no changes to GPU SVM.
+* Drop ranges in favor of radix tree
+	* May be desirable for faster notifiers.
+* Compound device pages
+	* Nvidia, AMD, and Intel all have agreed expensive core MM functions in
+	  migrate device layer are a performance bottleneck, having compound
+	  device pages should help increase performance by reducing the number
+	  of these expensive calls.
+* Higher order dma mapping for migration
+	* 4k dma mapping adversely affects migration performance on Intel
+	  hardware, higher order (2M) dma mapping should help here.
+* Build common userptr implementation on top of GPU SVM
+* Driver side madvise implementation and migration policies
+* Pull in pending dma-mapping API changes from Leon / Nvidia when these land

Documentation/gpu/rfc/index.rst

@@ -16,6 +16,10 @@ host such documentation:
 * Once the code has landed move all the documentation to the right places in
   the main core, helper or driver sections.
 
+.. toctree::
+
+    gpusvm.rst
+
 .. toctree::
 
     i915_gem_lmem.rst

drivers/base/component.c

@@ -588,6 +588,9 @@ static void component_unbind(struct component *component,
 {
 	WARN_ON(!component->bound);
 
+	dev_dbg(adev->parent, "unbinding %s component %p (ops %ps)\n",
+		dev_name(component->dev), component, component->ops);
+
 	if (component->ops && component->ops->unbind)
 		component->ops->unbind(component->dev, adev->parent, data);
 	component->bound = false;

drivers/base/devres.c

@@ -576,7 +576,10 @@ void *devres_open_group(struct device *dev, void *id, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(devres_open_group);
 
-/* Find devres group with ID @id.  If @id is NULL, look for the latest. */
+/*
+ * Find devres group with ID @id.  If @id is NULL, look for the latest open
+ * group.
+ */
 static struct devres_group *find_group(struct device *dev, void *id)
 {
 	struct devres_node *node;
@@ -687,6 +690,13 @@ int devres_release_group(struct device *dev, void *id)
 		spin_unlock_irqrestore(&dev->devres_lock, flags);
 
 		release_nodes(dev, &todo);
+	} else if (list_empty(&dev->devres_head)) {
+		/*
+		 * dev is probably dying via devres_release_all(): groups
+		 * have already been removed and are on the process of
+		 * being released - don't touch and don't warn.
+		 */
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
 	} else {
 		WARN_ON(1);
 		spin_unlock_irqrestore(&dev->devres_lock, flags);

drivers/gpu/drm/Kconfig

@@ -278,6 +278,15 @@ config DRM_GPUVM
 	  GPU-VM representation providing helpers to manage a GPUs virtual
 	  address space
 
+config DRM_GPUSVM
+	tristate
+	depends on DRM && DEVICE_PRIVATE
+	select HMM_MIRROR
+	select MMU_NOTIFIER
+	help
+	  GPU-SVM representation providing helpers to manage a GPUs shared
+	  virtual memory
+
 config DRM_BUDDY
 	tristate
 	depends on DRM

drivers/gpu/drm/Makefile

@@ -104,6 +104,7 @@ obj-$(CONFIG_DRM_PANEL_BACKLIGHT_QUIRKS) += drm_panel_backlight_quirks.o
 #
 obj-$(CONFIG_DRM_EXEC) += drm_exec.o
 obj-$(CONFIG_DRM_GPUVM) += drm_gpuvm.o
+obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm.o
 
 obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o