Merge tag 'drm-xe-fixes-2025-10-23' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

UAPI Changes: - Make madvise autoreset an explicit behavior requested by userspace (Thomas Hellström) Driver Changes: - Drop XE_VMA flag conversion and ensure GPUVA flags are passed around (homas Hellström) - Fix missing wq allocation error checking (Matthew Brost) Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch> From: Lucas De Marchi <lucas.demarchi@intel.com> Link: https://lore.kernel.org/r/4p2glnvgifc6osjlvzv23xhsyqhw4diqlfxz54lmg7robv44bi@nwd37zpqfa2l
author: Simona Vetter <simona.vetter@ffwll.ch> 2025-10-24 13:39:21 +0200
committer: Simona Vetter <simona.vetter@ffwll.ch> 2025-10-24 13:39:21 +0200
commit: 18b1ce0b29c41833363b58ad030b76dabf984899 (patch)
tree: 6111bbec54ce8e7b8fd2f344cc08fe271396b6e4
parent: Merge tag 'drm-intel-fixes-2025-10-23' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-fixes (diff)
parent: drm/xe: Check return value of GGTT workqueue allocation (diff)
download: linux-rng-18b1ce0b29c41833363b58ad030b76dabf984899.tar.xz
linux-rng-18b1ce0b29c41833363b58ad030b76dabf984899.zip
6 files changed, 64 insertions, 69 deletions
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 7fdd0a97a628..5edc0cad47e2 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -292,6 +292,9 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 		ggtt->pt_ops = &xelp_pt_ops;
 
 	ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM);
+	if (!ggtt->wq)
+		return -ENOMEM;
+
 	__xe_ggtt_init_early(ggtt, xe_wopcm_size(xe));
 
 	err = drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt);
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index a1c88f9a6c76..07f96bda638a 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -2022,7 +2022,7 @@ static int op_prepare(struct xe_vm *vm,
 	case DRM_GPUVA_OP_MAP:
 		if ((!op->map.immediate && xe_vm_in_fault_mode(vm) &&
 		     !op->map.invalidate_on_bind) ||
-		    op->map.is_cpu_addr_mirror)
+		    (op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR))
 			break;
 
 		err = bind_op_prepare(vm, tile, pt_update_ops, op->map.vma,
@@ -2252,7 +2252,7 @@ static void op_commit(struct xe_vm *vm,
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) ||
-		    op->map.is_cpu_addr_mirror)
+		    (op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR))
 			break;
 
 		bind_op_commit(vm, tile, pt_update_ops, op->map.vma, fence,
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index da2a412f80c0..129e7818565c 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -302,6 +302,11 @@ static int xe_svm_range_set_default_attr(struct xe_vm *vm, u64 range_start, u64
 	if (!vma)
 		return -EINVAL;
 
+	if (!(vma->gpuva.flags & XE_VMA_MADV_AUTORESET)) {
+		drm_dbg(&vm->xe->drm, "Skipping madvise reset for vma.\n");
+		return 0;
+	}
+
 	if (xe_vma_has_default_mem_attrs(vma))
 		return 0;
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index f602b874e054..63c65e3d207b 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -616,6 +616,13 @@ static void xe_vma_ops_incr_pt_update_ops(struct xe_vma_ops *vops, u8 tile_mask,
 			vops->pt_update_ops[i].num_ops += inc_val;
 }
 
+#define XE_VMA_CREATE_MASK (		    \
+	XE_VMA_READ_ONLY |		    \
+	XE_VMA_DUMPABLE |		    \
+	XE_VMA_SYSTEM_ALLOCATOR |           \
+	DRM_GPUVA_SPARSE |		    \
+	XE_VMA_MADV_AUTORESET)
+
 static void xe_vm_populate_rebind(struct xe_vma_op *op, struct xe_vma *vma,
 				  u8 tile_mask)
 {
@@ -628,8 +635,7 @@ static void xe_vm_populate_rebind(struct xe_vma_op *op, struct xe_vma *vma,
 	op->base.map.gem.offset = vma->gpuva.gem.offset;
 	op->map.vma = vma;
 	op->map.immediate = true;
-	op->map.dumpable = vma->gpuva.flags & XE_VMA_DUMPABLE;
-	op->map.is_null = xe_vma_is_null(vma);
+	op->map.vma_flags = vma->gpuva.flags & XE_VMA_CREATE_MASK;
 }
 
 static int xe_vm_ops_add_rebind(struct xe_vma_ops *vops, struct xe_vma *vma,
@@ -932,11 +938,6 @@ static void xe_vma_free(struct xe_vma *vma)
 		kfree(vma);
 }
 
-#define VMA_CREATE_FLAG_READ_ONLY		BIT(0)
-#define VMA_CREATE_FLAG_IS_NULL			BIT(1)
-#define VMA_CREATE_FLAG_DUMPABLE		BIT(2)
-#define VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR	BIT(3)
-
 static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 				    struct xe_bo *bo,
 				    u64 bo_offset_or_userptr,
@@ -947,11 +948,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	struct xe_vma *vma;
 	struct xe_tile *tile;
 	u8 id;
-	bool read_only = (flags & VMA_CREATE_FLAG_READ_ONLY);
-	bool is_null = (flags & VMA_CREATE_FLAG_IS_NULL);
-	bool dumpable = (flags & VMA_CREATE_FLAG_DUMPABLE);
-	bool is_cpu_addr_mirror =
-		(flags & VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR);
+	bool is_null = (flags & DRM_GPUVA_SPARSE);
+	bool is_cpu_addr_mirror = (flags & XE_VMA_SYSTEM_ALLOCATOR);
 
 	xe_assert(vm->xe, start < end);
 	xe_assert(vm->xe, end < vm->size);
@@ -972,10 +970,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 		if (!vma)
 			return ERR_PTR(-ENOMEM);
 
-		if (is_cpu_addr_mirror)
-			vma->gpuva.flags |= XE_VMA_SYSTEM_ALLOCATOR;
-		if (is_null)
-			vma->gpuva.flags |= DRM_GPUVA_SPARSE;
 		if (bo)
 			vma->gpuva.gem.obj = &bo->ttm.base;
 	}
@@ -986,10 +980,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	vma->gpuva.vm = &vm->gpuvm;
 	vma->gpuva.va.addr = start;
 	vma->gpuva.va.range = end - start + 1;
-	if (read_only)
-		vma->gpuva.flags |= XE_VMA_READ_ONLY;
-	if (dumpable)
-		vma->gpuva.flags |= XE_VMA_DUMPABLE;
+	vma->gpuva.flags = flags;
 
 	for_each_tile(tile, vm->xe, id)
 		vma->tile_mask |= 0x1 << id;
@@ -2272,12 +2263,16 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 		if (__op->op == DRM_GPUVA_OP_MAP) {
 			op->map.immediate =
 				flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE;
-			op->map.read_only =
-				flags & DRM_XE_VM_BIND_FLAG_READONLY;
-			op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL;
-			op->map.is_cpu_addr_mirror = flags &
-				DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR;
-			op->map.dumpable = flags & DRM_XE_VM_BIND_FLAG_DUMPABLE;
+			if (flags & DRM_XE_VM_BIND_FLAG_READONLY)
+				op->map.vma_flags |= XE_VMA_READ_ONLY;
+			if (flags & DRM_XE_VM_BIND_FLAG_NULL)
+				op->map.vma_flags |= DRM_GPUVA_SPARSE;
+			if (flags & DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR)
+				op->map.vma_flags |= XE_VMA_SYSTEM_ALLOCATOR;
+			if (flags & DRM_XE_VM_BIND_FLAG_DUMPABLE)
+				op->map.vma_flags |= XE_VMA_DUMPABLE;
+			if (flags & DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET)
+				op->map.vma_flags |= XE_VMA_MADV_AUTORESET;
 			op->map.pat_index = pat_index;
 			op->map.invalidate_on_bind =
 				__xe_vm_needs_clear_scratch_pages(vm, flags);
@@ -2590,14 +2585,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 				.pat_index = op->map.pat_index,
 			};
 
-			flags |= op->map.read_only ?
-				VMA_CREATE_FLAG_READ_ONLY : 0;
-			flags |= op->map.is_null ?
-				VMA_CREATE_FLAG_IS_NULL : 0;
-			flags |= op->map.dumpable ?
-				VMA_CREATE_FLAG_DUMPABLE : 0;
-			flags |= op->map.is_cpu_addr_mirror ?
-				VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0;
+			flags |= op->map.vma_flags & XE_VMA_CREATE_MASK;
 
 			vma = new_vma(vm, &op->base.map, &default_attr,
 				      flags);
@@ -2606,7 +2594,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			op->map.vma = vma;
 			if (((op->map.immediate || !xe_vm_in_fault_mode(vm)) &&
-			     !op->map.is_cpu_addr_mirror) ||
+			     !(op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR)) ||
 			    op->map.invalidate_on_bind)
 				xe_vma_ops_incr_pt_update_ops(vops,
 							      op->tile_mask, 1);
@@ -2637,18 +2625,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 			op->remap.start = xe_vma_start(old);
 			op->remap.range = xe_vma_size(old);
 
-			flags |= op->base.remap.unmap->va->flags &
-				XE_VMA_READ_ONLY ?
-				VMA_CREATE_FLAG_READ_ONLY : 0;
-			flags |= op->base.remap.unmap->va->flags &
-				DRM_GPUVA_SPARSE ?
-				VMA_CREATE_FLAG_IS_NULL : 0;
-			flags |= op->base.remap.unmap->va->flags &
-				XE_VMA_DUMPABLE ?
-				VMA_CREATE_FLAG_DUMPABLE : 0;
-			flags |= xe_vma_is_cpu_addr_mirror(old) ?
-				VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0;
-
+			flags |= op->base.remap.unmap->va->flags & XE_VMA_CREATE_MASK;
 			if (op->base.remap.prev) {
 				vma = new_vma(vm, op->base.remap.prev,
 					      &old->attr, flags);
@@ -3279,7 +3256,8 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO);
 	 DRM_XE_VM_BIND_FLAG_NULL | \
 	 DRM_XE_VM_BIND_FLAG_DUMPABLE | \
 	 DRM_XE_VM_BIND_FLAG_CHECK_PXP | \
-	 DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR)
+	 DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR | \
+	 DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET)
 
 #ifdef TEST_VM_OPS_ERROR
 #define SUPPORTED_FLAGS	(SUPPORTED_FLAGS_STUB | FORCE_OP_ERROR)
@@ -3394,7 +3372,9 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 		    XE_IOCTL_DBG(xe,  (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC &&
 				       !(BIT(prefetch_region) & xe->info.mem_region_mask))) ||
 		    XE_IOCTL_DBG(xe, obj &&
-				 op == DRM_XE_VM_BIND_OP_UNMAP)) {
+				 op == DRM_XE_VM_BIND_OP_UNMAP) ||
+		    XE_IOCTL_DBG(xe, (flags & DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET) &&
+				 (!is_cpu_addr_mirror || op != DRM_XE_VM_BIND_OP_MAP))) {
 			err = -EINVAL;
 			goto free_bind_ops;
 		}
@@ -4212,7 +4192,7 @@ static int xe_vm_alloc_vma(struct xe_vm *vm,
 	struct xe_vma_ops vops;
 	struct drm_gpuva_ops *ops = NULL;
 	struct drm_gpuva_op *__op;
-	bool is_cpu_addr_mirror = false;
+	unsigned int vma_flags = 0;
 	bool remap_op = false;
 	struct xe_vma_mem_attr tmp_attr;
 	u16 default_pat;
@@ -4242,15 +4222,17 @@ static int xe_vm_alloc_vma(struct xe_vm *vm,
 				vma = gpuva_to_vma(op->base.unmap.va);
 				XE_WARN_ON(!xe_vma_has_default_mem_attrs(vma));
 				default_pat = vma->attr.default_pat_index;
+				vma_flags = vma->gpuva.flags;
 			}
 
 			if (__op->op == DRM_GPUVA_OP_REMAP) {
 				vma = gpuva_to_vma(op->base.remap.unmap->va);
 				default_pat = vma->attr.default_pat_index;
+				vma_flags = vma->gpuva.flags;
 			}
 
 			if (__op->op == DRM_GPUVA_OP_MAP) {
-				op->map.is_cpu_addr_mirror = true;
+				op->map.vma_flags |= vma_flags & XE_VMA_CREATE_MASK;
 				op->map.pat_index = default_pat;
 			}
 		} else {
@@ -4259,11 +4241,7 @@ static int xe_vm_alloc_vma(struct xe_vm *vm,
 				xe_assert(vm->xe, !remap_op);
 				xe_assert(vm->xe, xe_vma_has_no_bo(vma));
 				remap_op = true;
-
-				if (xe_vma_is_cpu_addr_mirror(vma))
-					is_cpu_addr_mirror = true;
-				else
-					is_cpu_addr_mirror = false;
+				vma_flags = vma->gpuva.flags;
 			}
 
 			if (__op->op == DRM_GPUVA_OP_MAP) {
@@ -4272,10 +4250,10 @@ static int xe_vm_alloc_vma(struct xe_vm *vm,
 				/*
 				 * In case of madvise ops DRM_GPUVA_OP_MAP is
 				 * always after DRM_GPUVA_OP_REMAP, so ensure
-				 * we assign op->map.is_cpu_addr_mirror true
-				 * if REMAP is for xe_vma_is_cpu_addr_mirror vma
+				 * to propagate the flags from the vma we're
+				 * unmapping.
 				 */
-				op->map.is_cpu_addr_mirror = is_cpu_addr_mirror;
+				op->map.vma_flags |= vma_flags & XE_VMA_CREATE_MASK;
 			}
 		}
 		print_op(vm->xe, __op);
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 413353e1c225..d6e2a0fdd4b3 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -46,6 +46,7 @@ struct xe_vm_pgtable_update_op;
 #define XE_VMA_PTE_COMPACT	(DRM_GPUVA_USERBITS << 7)
 #define XE_VMA_DUMPABLE		(DRM_GPUVA_USERBITS << 8)
 #define XE_VMA_SYSTEM_ALLOCATOR	(DRM_GPUVA_USERBITS << 9)
+#define XE_VMA_MADV_AUTORESET	(DRM_GPUVA_USERBITS << 10)
 
 /**
  * struct xe_vma_mem_attr - memory attributes associated with vma
@@ -345,17 +346,10 @@ struct xe_vm {
 struct xe_vma_op_map {
 	/** @vma: VMA to map */
 	struct xe_vma *vma;
+	unsigned int vma_flags;
 	/** @immediate: Immediate bind */
 	bool immediate;
 	/** @read_only: Read only */
-	bool read_only;
-	/** @is_null: is NULL binding */
-	bool is_null;
-	/** @is_cpu_addr_mirror: is CPU address mirror binding */
-	bool is_cpu_addr_mirror;
-	/** @dumpable: whether BO is dumped on GPU hang */
-	bool dumpable;
-	/** @invalidate: invalidate the VMA before bind */
 	bool invalidate_on_bind;
 	/** @pat_index: The pat index to use for this operation. */
 	u16 pat_index;
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 40ff19f52a8d..517489a7ec60 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1013,6 +1013,20 @@ struct drm_xe_vm_destroy {
  *    valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address
  *    mirror flag are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
  *    handle MBZ, and the BO offset MBZ.
+ *  - %DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET - Can be used in combination with
+ *    %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR to reset madvises when the underlying
+ *    CPU address space range is unmapped (typically with munmap(2) or brk(2)).
+ *    The madvise values set with &DRM_IOCTL_XE_MADVISE are reset to the values
+ *    that were present immediately after the &DRM_IOCTL_XE_VM_BIND.
+ *    The reset GPU virtual address range is the intersection of the range bound
+ *    using &DRM_IOCTL_XE_VM_BIND and the virtual CPU address space range
+ *    unmapped.
+ *    This functionality is present to mimic the behaviour of CPU address space
+ *    madvises set using madvise(2), which are typically reset on unmap.
+ *    Note: free(3) may or may not call munmap(2) and/or brk(2), and may thus
+ *    not invoke autoreset. Neither will stack variables going out of scope.
+ *    Therefore it's recommended to always explicitly reset the madvises when
+ *    freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call.
  *
  * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be:
  *  - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in
@@ -1119,6 +1133,7 @@ struct drm_xe_vm_bind_op {
 #define DRM_XE_VM_BIND_FLAG_DUMPABLE	(1 << 3)
 #define DRM_XE_VM_BIND_FLAG_CHECK_PXP	(1 << 4)
 #define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR	(1 << 5)
+#define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET	(1 << 6)
 	/** @flags: Bind flags */
 	__u32 flags;
author	Simona Vetter <simona.vetter@ffwll.ch>	2025-10-24 13:39:21 +0200
committer	Simona Vetter <simona.vetter@ffwll.ch>	2025-10-24 13:39:21 +0200
commit	18b1ce0b29c41833363b58ad030b76dabf984899 (patch)
tree	6111bbec54ce8e7b8fd2f344cc08fe271396b6e4
parent	Merge tag 'drm-intel-fixes-2025-10-23' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-fixes (diff)
parent	drm/xe: Check return value of GGTT workqueue allocation (diff)
download	linux-rng-18b1ce0b29c41833363b58ad030b76dabf984899.tar.xz linux-rng-18b1ce0b29c41833363b58ad030b76dabf984899.zip