drm/xe: Strict migration policy for atomic SVM faults

Mixing GPU and CPU atomics does not work unless a strict migration
policy of GPU atomics must be device memory. Enforce a policy of must be
in VRAM with a retry loop of 3 attempts, if retry loop fails abort
fault.

Removing always_migrate_to_vram modparam as we now have real migration
policy.

v2:
 - Only retry migration on atomics
 - Drop alway migrate modparam
v3:
 - Only set vram_only on DGFX (Himal)
 - Bail on get_pages failure if vram_only and retry count exceeded (Himal)
 - s/vram_only/devmem_only
 - Update xe_svm_range_is_valid to accept devmem_only argument
v4:
 - Fix logic bug get_pages failure
v5:
 - Fix commit message (Himal)
 - Mention removing always_migrate_to_vram in commit message (Lucas)
 - Fix xe_svm_range_is_valid to check for devmem pages
 - Bail on devmem_only && !migrate_devmem (Thomas)
v6:
 - Add READ_ONCE barriers for opportunistic checks (Thomas)
 - Pair READ_ONCE with WRITE_ONCE (Thomas)
v7:
 - Adjust comments (Thomas)

Fixes: 2f118c949160 ("drm/xe: Add SVM VRAM migration")
Cc: stable@vger.kernel.org
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250512135500.1405019-3-matthew.brost@intel.com

1 files changed, 26 insertions, 14 deletions

diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index 9fd25fc880a4..653d48dbe1c1 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -186,6 +186,31 @@ struct drm_gpusvm_notifier {
 };
 
 /**
+ * struct drm_gpusvm_range_flags - Structure representing a GPU SVM range flags
+ *
+ * @migrate_devmem: Flag indicating whether the range can be migrated to device memory
+ * @unmapped: Flag indicating if the range has been unmapped
+ * @partial_unmap: Flag indicating if the range has been partially unmapped
+ * @has_devmem_pages: Flag indicating if the range has devmem pages
+ * @has_dma_mapping: Flag indicating if the range has a DMA mapping
+ * @__flags: Flags for range in u16 form (used for READ_ONCE)
+ */
+struct drm_gpusvm_range_flags {
+	union {
+		struct {
+			/* All flags below must be set upon creation */
+			u16 migrate_devmem : 1;
+			/* All flags below must be set / cleared under notifier lock */
+			u16 unmapped : 1;
+			u16 partial_unmap : 1;
+			u16 has_devmem_pages : 1;
+			u16 has_dma_mapping : 1;
+		};
+		u16 __flags;
+	};
+};
+
+/**
  * struct drm_gpusvm_range - Structure representing a GPU SVM range
  *
  * @gpusvm: Pointer to the GPU SVM structure
@@ -198,11 +223,6 @@ struct drm_gpusvm_notifier {
  * @dpagemap: The struct drm_pagemap of the device pages we're dma-mapping.
  *            Note this is assuming only one drm_pagemap per range is allowed.
  * @flags: Flags for range
- * @flags.migrate_devmem: Flag indicating whether the range can be migrated to device memory
- * @flags.unmapped: Flag indicating if the range has been unmapped
- * @flags.partial_unmap: Flag indicating if the range has been partially unmapped
- * @flags.has_devmem_pages: Flag indicating if the range has devmem pages
- * @flags.has_dma_mapping: Flag indicating if the range has a DMA mapping
  *
  * This structure represents a GPU SVM range used for tracking memory ranges
  * mapped in a DRM device.
@@ -216,15 +236,7 @@ struct drm_gpusvm_range {
 	unsigned long notifier_seq;
 	struct drm_pagemap_device_addr *dma_addr;
 	struct drm_pagemap *dpagemap;
-	struct {
-		/* All flags below must be set upon creation */
-		u16 migrate_devmem : 1;
-		/* All flags below must be set / cleared under notifier lock */
-		u16 unmapped : 1;
-		u16 partial_unmap : 1;
-		u16 has_devmem_pages : 1;
-		u16 has_dma_mapping : 1;
-	} flags;
+	struct drm_gpusvm_range_flags flags;
 };
 
 /**