drm/xe: Add helper to extend CPU-mirrored VMA range for merge

Introduce xe_vm_find_cpu_addr_mirror_vma_range(), which computes an
extended range around a given range by including adjacent VMAs that are
CPU-address-mirrored and have default memory attributes. This helper is
useful for determining mergeable range without performing the actual merge.

v2
- Add assert
- Move unmap check to this patch

v3
- Decrease offset to check by SZ_4K to avoid wrong vma return in fast
  lookup path

v4
- *start should be >= SZ_4K (Matt)

Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251125075628.1182481-2-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index f9989a7a710c188aad99439889bdb6aef2211def..fc11a1a6f979fc8f5471e7c2fd97bc7aaf81c67e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4383,6 +4383,47 @@ int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
        return xe_vm_alloc_vma(vm, &map_req, true);
 }
 
+static bool is_cpu_addr_vma_with_default_attr(struct xe_vma *vma)
+{
+       return vma && xe_vma_is_cpu_addr_mirror(vma) &&
+              !xe_svm_has_mapping(xe_vma_vm(vma), xe_vma_start(vma), xe_vma_end(vma)) &&
+              xe_vma_has_default_mem_attrs(vma);
+}
+
+/**
+ * xe_vm_find_cpu_addr_mirror_vma_range - Extend a VMA range to include adjacent CPU-mirrored VMAs
+ * @vm: VM to search within
+ * @start: Input/output pointer to the starting address of the range
+ * @end: Input/output pointer to the end address of the range
+ *
+ * Given a range defined by @start and @range, this function checks the VMAs
+ * immediately before and after the range. If those neighboring VMAs are
+ * CPU-address-mirrored and have default memory attributes, the function
+ * updates @start and @range to include them. This extended range can then
+ * be used for merging or other operations that require a unified VMA.
+ *
+ * The function does not perform the merge itself; it only computes the
+ * mergeable boundaries.
+ */
+void xe_vm_find_cpu_addr_mirror_vma_range(struct xe_vm *vm, u64 *start, u64 *end)
+{
+       struct xe_vma *prev, *next;
+
+       lockdep_assert_held(&vm->lock);
+
+       if (*start >= SZ_4K) {
+               prev = xe_vm_find_vma_by_addr(vm, *start - SZ_4K);
+               if (is_cpu_addr_vma_with_default_attr(prev))
+                       *start = xe_vma_start(prev);
+       }
+
+       if (*end < vm->size) {
+               next = xe_vm_find_vma_by_addr(vm, *end + 1);
+               if (is_cpu_addr_vma_with_default_attr(next))
+                       *end = xe_vma_end(next);
+       }
+}
+
 /**
  * xe_vm_alloc_cpu_addr_mirror_vma - Allocate CPU addr mirror vma
  * @vm: Pointer to the xe_vm structure

diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index ef8a5019574e6fb6e2a1ac9e03f54c37a1e651fa..361f10b3c453083d2c35f3913811086e02452a54 100644 (file)
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -68,6 +68,9 @@ xe_vm_find_overlapping_vma(struct xe_vm *vm, u64 start, u64 range);
 
 bool xe_vma_has_default_mem_attrs(struct xe_vma *vma);
 
+void xe_vm_find_cpu_addr_mirror_vma_range(struct xe_vm *vm,
+                                         u64 *start,
+                                         u64 *end);
 /**
  * xe_vm_has_scratch() - Whether the vm is configured for scratch PTEs
  * @vm: The vm