Merge tag 'drm-xe-next-2025-07-10' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

UAPI Changes:
 - Documentation fixes (Shuicheng)

Cross-subsystem Changes:
 - MTD intel-dg driver for dgfx non-volatile memory device (Sasha)
 - i2c: designware changes to allow i2c integration with BMG (Heikki)

Core Changes:
 - Restructure migration in preparation for multi-device (Brost, Thomas)
 - Expose fan control and voltage regulator version on sysfs (Raag)

Driver Changes:
 - Add WildCat Lake support (Roper)
 - Add aux bus child device driver for NVM on DGFX (Sasha)
 - Some refactor and fixes to allow cleaner BMG w/a (Lucas, Maarten, Auld)
 - BMG w/a (Vinay)
 - Improve handling of aborted probe (Michal)
 - Do not wedge device on killed exec queues (Brost)
 - Init changes for flicker-free boot (Maarten)
 - Fix out-of-bounds field write in MI_STORE_DATA_IMM (Jia)
 - Enable the GuC Dynamic Inhibit Context Switch optimization (Daniele)
 - Drop bo->size (Brost)
 - Builds and KConfig fixes (Harry, Maarten)
 - Consolidate LRC offset calculations (Tvrtko)
 - Fix potential leak in hw_engine_group (Michal)
 - Future-proof for multi-tile + multi-GT cases (Roper)
 - Validate gt in pmu event (Riana)
 - SRIOV PF: Clear all LMTT pages on alloc (Michal)
 - Allocate PF queue size on pow2 boundary (Brost)
 - SRIOV VF: Make multi-GT migration less error prone (Tomasz)
 - Revert indirect ring state patch to fix random LRC context switches failures (Brost)
 - Fix compressed VRAM handling (Auld)
 - Add one additional BMG PCI ID (Ravi)
 - Recommend GuC v70.46.2 for BMG, LNL, DG2 (Julia)
 - Add GuC and HuC to PTL (Daniele)
 - Drop PTL force_probe requirement (Atwood)
 - Fix error flow in display suspend (Shuicheng)
 - Disable GuC communication on hardware initialization error (Zhanjun)
 - Devcoredump fixes and clean up (Shuicheng)
 - SRIOV PF: Downgrade some info to debug (Michal)
 - Don't allocate temporary GuC policies object (Michal)
 - Support for I2C attached MCUs (Heikki, Raag, Riana)
 - Add GPU memory bo trace points (Juston)
 - SRIOV VF: Skip some W/a (Michal)
 - Correct comment of xe_pm_set_vram_threshold (Shuicheng)
 - Cancel ongoing H2G requests when stopping CT (Michal)

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/aHA7184UnWlONORU@intel.com

5 files changed, 175 insertions, 101 deletions

diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index 6a5156476bf4..4aedc5423aff 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -16,92 +16,10 @@ struct drm_gpusvm;
 struct drm_gpusvm_notifier;
 struct drm_gpusvm_ops;
 struct drm_gpusvm_range;
-struct drm_gpusvm_devmem;
 struct drm_pagemap;
 struct drm_pagemap_device_addr;
 
 /**
- * struct drm_gpusvm_devmem_ops - Operations structure for GPU SVM device memory
- *
- * This structure defines the operations for GPU Shared Virtual Memory (SVM)
- * device memory. These operations are provided by the GPU driver to manage device memory
- * allocations and perform operations such as migration between device memory and system
- * RAM.
- */
-struct drm_gpusvm_devmem_ops {
-	/**
-	 * @devmem_release: Release device memory allocation (optional)
-	 * @devmem_allocation: device memory allocation
-	 *
-	 * Release device memory allocation and drop a reference to device
-	 * memory allocation.
-	 */
-	void (*devmem_release)(struct drm_gpusvm_devmem *devmem_allocation);
-
-	/**
-	 * @populate_devmem_pfn: Populate device memory PFN (required for migration)
-	 * @devmem_allocation: device memory allocation
-	 * @npages: Number of pages to populate
-	 * @pfn: Array of page frame numbers to populate
-	 *
-	 * Populate device memory page frame numbers (PFN).
-	 *
-	 * Return: 0 on success, a negative error code on failure.
-	 */
-	int (*populate_devmem_pfn)(struct drm_gpusvm_devmem *devmem_allocation,
-				   unsigned long npages, unsigned long *pfn);
-
-	/**
-	 * @copy_to_devmem: Copy to device memory (required for migration)
-	 * @pages: Pointer to array of device memory pages (destination)
-	 * @dma_addr: Pointer to array of DMA addresses (source)
-	 * @npages: Number of pages to copy
-	 *
-	 * Copy pages to device memory.
-	 *
-	 * Return: 0 on success, a negative error code on failure.
-	 */
-	int (*copy_to_devmem)(struct page **pages,
-			      dma_addr_t *dma_addr,
-			      unsigned long npages);
-
-	/**
-	 * @copy_to_ram: Copy to system RAM (required for migration)
-	 * @pages: Pointer to array of device memory pages (source)
-	 * @dma_addr: Pointer to array of DMA addresses (destination)
-	 * @npages: Number of pages to copy
-	 *
-	 * Copy pages to system RAM.
-	 *
-	 * Return: 0 on success, a negative error code on failure.
-	 */
-	int (*copy_to_ram)(struct page **pages,
-			   dma_addr_t *dma_addr,
-			   unsigned long npages);
-};
-
-/**
- * struct drm_gpusvm_devmem - Structure representing a GPU SVM device memory allocation
- *
- * @dev: Pointer to the device structure which device memory allocation belongs to
- * @mm: Pointer to the mm_struct for the address space
- * @detached: device memory allocations is detached from device pages
- * @ops: Pointer to the operations structure for GPU SVM device memory
- * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to.
- * @size: Size of device memory allocation
- * @timeslice_expiration: Timeslice expiration in jiffies
- */
-struct drm_gpusvm_devmem {
-	struct device *dev;
-	struct mm_struct *mm;
-	struct completion detached;
-	const struct drm_gpusvm_devmem_ops *ops;
-	struct drm_pagemap *dpagemap;
-	size_t size;
-	u64 timeslice_expiration;
-};
-
-/**
  * struct drm_gpusvm_ops - Operations structure for GPU SVM
  *
  * This structure defines the operations for GPU Shared Virtual Memory (SVM).
@@ -361,15 +279,6 @@ void drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 				  struct drm_gpusvm_range *range,
 				  const struct drm_gpusvm_ctx *ctx);
 
-int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm,
-				 struct drm_gpusvm_range *range,
-				 struct drm_gpusvm_devmem *devmem_allocation,
-				 const struct drm_gpusvm_ctx *ctx);
-
-int drm_gpusvm_evict_to_ram(struct drm_gpusvm_devmem *devmem_allocation);
-
-const struct dev_pagemap_ops *drm_gpusvm_pagemap_ops_get(void);
-
 bool drm_gpusvm_has_mapping(struct drm_gpusvm *gpusvm, unsigned long start,
 			    unsigned long end);
 
@@ -380,11 +289,6 @@ drm_gpusvm_range_find(struct drm_gpusvm_notifier *notifier, unsigned long start,
 void drm_gpusvm_range_set_unmapped(struct drm_gpusvm_range *range,
 				   const struct mmu_notifier_range *mmu_range);
 
-void drm_gpusvm_devmem_init(struct drm_gpusvm_devmem *devmem_allocation,
-			    struct device *dev, struct mm_struct *mm,
-			    const struct drm_gpusvm_devmem_ops *ops,
-			    struct drm_pagemap *dpagemap, size_t size);
-
 #ifdef CONFIG_LOCKDEP
 /**
  * drm_gpusvm_driver_set_lock() - Set the lock protecting accesses to GPU SVM
diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index 202c157ff4d7..e5f20a1235be 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 
 struct drm_pagemap;
+struct drm_pagemap_zdd;
 struct device;
 
 /**
@@ -91,6 +92,35 @@ struct drm_pagemap_ops {
 			     struct device *dev,
 			     struct drm_pagemap_device_addr addr);
 
+	/**
+	 * @populate_mm: Populate part of the mm with @dpagemap memory,
+	 * migrating existing data.
+	 * @dpagemap: The struct drm_pagemap managing the memory.
+	 * @start: The virtual start address in @mm
+	 * @end: The virtual end address in @mm
+	 * @mm: Pointer to a live mm. The caller must have an mmget()
+	 * reference.
+	 *
+	 * The caller will have the mm lock at least in read mode.
+	 * Note that there is no guarantee that the memory is resident
+	 * after the function returns, it's best effort only.
+	 * When the mm is not using the memory anymore,
+	 * it will be released. The struct drm_pagemap might have a
+	 * mechanism in place to reclaim the memory and the data will
+	 * then be migrated. Typically to system memory.
+	 * The implementation should hold sufficient runtime power-
+	 * references while pages are used in an address space and
+	 * should ideally guard against hardware device unbind in
+	 * a way such that device pages are migrated back to system
+	 * followed by device page removal. The implementation should
+	 * return -ENODEV after device removal.
+	 *
+	 * Return: 0 if successful. Negative error code on error.
+	 */
+	int (*populate_mm)(struct drm_pagemap *dpagemap,
+			   unsigned long start, unsigned long end,
+			   struct mm_struct *mm,
+			   unsigned long timeslice_ms);
 };
 
 /**
@@ -104,4 +134,109 @@ struct drm_pagemap {
 	struct device *dev;
 };
 
+struct drm_pagemap_devmem;
+
+/**
+ * struct drm_pagemap_devmem_ops - Operations structure for GPU SVM device memory
+ *
+ * This structure defines the operations for GPU Shared Virtual Memory (SVM)
+ * device memory. These operations are provided by the GPU driver to manage device memory
+ * allocations and perform operations such as migration between device memory and system
+ * RAM.
+ */
+struct drm_pagemap_devmem_ops {
+	/**
+	 * @devmem_release: Release device memory allocation (optional)
+	 * @devmem_allocation: device memory allocation
+	 *
+	 * Release device memory allocation and drop a reference to device
+	 * memory allocation.
+	 */
+	void (*devmem_release)(struct drm_pagemap_devmem *devmem_allocation);
+
+	/**
+	 * @populate_devmem_pfn: Populate device memory PFN (required for migration)
+	 * @devmem_allocation: device memory allocation
+	 * @npages: Number of pages to populate
+	 * @pfn: Array of page frame numbers to populate
+	 *
+	 * Populate device memory page frame numbers (PFN).
+	 *
+	 * Return: 0 on success, a negative error code on failure.
+	 */
+	int (*populate_devmem_pfn)(struct drm_pagemap_devmem *devmem_allocation,
+				   unsigned long npages, unsigned long *pfn);
+
+	/**
+	 * @copy_to_devmem: Copy to device memory (required for migration)
+	 * @pages: Pointer to array of device memory pages (destination)
+	 * @dma_addr: Pointer to array of DMA addresses (source)
+	 * @npages: Number of pages to copy
+	 *
+	 * Copy pages to device memory.
+	 *
+	 * Return: 0 on success, a negative error code on failure.
+	 */
+	int (*copy_to_devmem)(struct page **pages,
+			      dma_addr_t *dma_addr,
+			      unsigned long npages);
+
+	/**
+	 * @copy_to_ram: Copy to system RAM (required for migration)
+	 * @pages: Pointer to array of device memory pages (source)
+	 * @dma_addr: Pointer to array of DMA addresses (destination)
+	 * @npages: Number of pages to copy
+	 *
+	 * Copy pages to system RAM.
+	 *
+	 * Return: 0 on success, a negative error code on failure.
+	 */
+	int (*copy_to_ram)(struct page **pages,
+			   dma_addr_t *dma_addr,
+			   unsigned long npages);
+};
+
+/**
+ * struct drm_pagemap_devmem - Structure representing a GPU SVM device memory allocation
+ *
+ * @dev: Pointer to the device structure which device memory allocation belongs to
+ * @mm: Pointer to the mm_struct for the address space
+ * @detached: device memory allocations is detached from device pages
+ * @ops: Pointer to the operations structure for GPU SVM device memory
+ * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to.
+ * @size: Size of device memory allocation
+ * @timeslice_expiration: Timeslice expiration in jiffies
+ */
+struct drm_pagemap_devmem {
+	struct device *dev;
+	struct mm_struct *mm;
+	struct completion detached;
+	const struct drm_pagemap_devmem_ops *ops;
+	struct drm_pagemap *dpagemap;
+	size_t size;
+	u64 timeslice_expiration;
+};
+
+int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
+				  struct mm_struct *mm,
+				  unsigned long start, unsigned long end,
+				  unsigned long timeslice_ms,
+				  void *pgmap_owner);
+
+int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation);
+
+const struct dev_pagemap_ops *drm_pagemap_pagemap_ops_get(void);
+
+struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page);
+
+void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation,
+			     struct device *dev, struct mm_struct *mm,
+			     const struct drm_pagemap_devmem_ops *ops,
+			     struct drm_pagemap *dpagemap, size_t size);
+
+int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
+			    unsigned long start, unsigned long end,
+			    struct mm_struct *mm,
+			    unsigned long timeslice_ms);
+
 #endif
diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h
index 129c3172aa5f..76f8d26f9cc9 100644
--- a/include/drm/intel/pciids.h
+++ b/include/drm/intel/pciids.h
@@ -846,6 +846,7 @@
 /* BMG */
 #define INTEL_BMG_IDS(MACRO__, ...) \
 	MACRO__(0xE202, ## __VA_ARGS__), \
+	MACRO__(0xE209, ## __VA_ARGS__), \
 	MACRO__(0xE20B, ## __VA_ARGS__), \
 	MACRO__(0xE20C, ## __VA_ARGS__), \
 	MACRO__(0xE20D, ## __VA_ARGS__), \
@@ -871,6 +872,8 @@
 	MACRO__(0xB08F, ## __VA_ARGS__), \
 	MACRO__(0xB090, ## __VA_ARGS__), \
 	MACRO__(0xB0A0, ## __VA_ARGS__), \
-	MACRO__(0xB0B0, ## __VA_ARGS__)
+	MACRO__(0xB0B0, ## __VA_ARGS__), \
+	MACRO__(0xFD80, ## __VA_ARGS__), \
+	MACRO__(0xFD81, ## __VA_ARGS__)
 
 #endif /* __PCIIDS_H__ */
diff --git a/include/linux/intel_dg_nvm_aux.h b/include/linux/intel_dg_nvm_aux.h
new file mode 100644
index 000000000000..625d46a6b96e
--- /dev/null
+++ b/include/linux/intel_dg_nvm_aux.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright(c) 2019-2025, Intel Corporation. All rights reserved.
+ */
+
+#ifndef __INTEL_DG_NVM_AUX_H__
+#define __INTEL_DG_NVM_AUX_H__
+
+#include <linux/auxiliary_bus.h>
+#include <linux/container_of.h>
+#include <linux/ioport.h>
+#include <linux/types.h>
+
+#define INTEL_DG_NVM_REGIONS 13
+
+struct intel_dg_nvm_region {
+	const char *name;
+};
+
+struct intel_dg_nvm_dev {
+	struct auxiliary_device aux_dev;
+	bool writable_override;
+	bool non_posted_erase;
+	struct resource bar;
+	struct resource bar2;
+	const struct intel_dg_nvm_region *regions;
+};
+
+#define auxiliary_dev_to_intel_dg_nvm_dev(auxiliary_dev) \
+	container_of(auxiliary_dev, struct intel_dg_nvm_dev, aux_dev)
+
+#endif /* __INTEL_DG_NVM_AUX_H__ */
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 8e8bbdec8c5c..e2426413488f 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -925,9 +925,9 @@ struct drm_xe_gem_mmap_offset {
  *  - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts
  *    exec submissions to its exec_queues that don't have an upper time
  *    limit on the job execution time. But exec submissions to these
- *    don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ,
- *    DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF,
- *    used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL.
+ *    don't allow any of the sync types DRM_XE_SYNC_TYPE_SYNCOBJ,
+ *    DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ, used as out-syncobjs, that is,
+ *    together with sync flag DRM_XE_SYNC_FLAG_SIGNAL.
  *    LR VMs can be created in recoverable page-fault mode using
  *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it.
  *    If that flag is omitted, the UMD can not rely on the slightly
@@ -1394,7 +1394,7 @@ struct drm_xe_sync {
 
 	/**
 	 * @timeline_value: Input for the timeline sync object. Needs to be
-	 * different than 0 when used with %DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ.
+	 * different than 0 when used with %DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ.
 	 */
 	__u64 timeline_value;