[PATCH v4 6/6] drm/xe: Move struct xe_ggtt to xe_ggtt.c

[PATCH v4 6/6] drm/xe: Move struct xe_ggtt to xe_ggtt.c

[Maarten Lankhorst]

No users left outside of xe_ggtt.c, so we can make the struct private.

This prevents us from accidentally touching it before init.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_ggtt.c       | 49 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_ggtt_types.h | 48 -----------------------------
 2 files changed, 49 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 213a6c0b10b7c..088778e80e4d1 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -64,6 +64,55 @@
  * give us the correct placement for free.
  */
 
+/**
+ * struct xe_ggtt_pt_ops - GGTT Page table operations
+ * Which can vary from platform to platform.
+ */
+struct xe_ggtt_pt_ops {
+	/** @pte_encode_bo: Encode PTE address for a given BO */
+	xe_ggtt_pte_encode_bo_fn pte_encode_bo;
+	/** @ggtt_set_pte: Directly write into GGTT's PTE */
+	xe_ggtt_set_pte_fn ggtt_set_pte;
+};
+
+/**
+ * struct xe_ggtt - Main GGTT struct
+ *
+ * In general, each tile can contains its own Global Graphics Translation Table
+ * (GGTT) instance.
+ */
+struct xe_ggtt {
+	/** @tile: Back pointer to tile where this GGTT belongs */
+	struct xe_tile *tile;
+	/** @size: Total size of this GGTT */
+	u64 size;
+
+#define XE_GGTT_FLAGS_64K BIT(0)
+	/**
+	 * @flags: Flags for this GGTT
+	 * Acceptable flags:
+	 * - %XE_GGTT_FLAGS_64K - if PTE size is 64K. Otherwise, regular is 4K.
+	 */
+	unsigned int flags;
+	/** @scratch: Internal object allocation used as a scratch page */
+	struct xe_bo *scratch;
+	/** @lock: Mutex lock to protect GGTT data */
+	struct mutex lock;
+	/**
+	 *  @gsm: The iomem pointer to the actual location of the translation
+	 * table located in the GSM for easy PTE manipulation
+	 */
+	u64 __iomem *gsm;
+	/** @pt_ops: Page Table operations per platform */
+	const struct xe_ggtt_pt_ops *pt_ops;
+	/** @mm: The memory manager used to manage individual GGTT allocations */
+	struct drm_mm mm;
+	/** @access_count: counts GGTT writes */
+	unsigned int access_count;
+	/** @wq: Dedicated unordered work queue to process node removals */
+	struct workqueue_struct *wq;
+};
+
 static u64 xelp_ggtt_pte_encode_bo(struct xe_bo *bo, u64 bo_offset,
 				   u16 pat_index)
 {
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index 34ef713b5245c..b33c2b5706df0 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -13,44 +13,6 @@
 struct xe_bo;
 struct xe_gt;
 
-/**
- * struct xe_ggtt - Main GGTT struct
- *
- * In general, each tile can contains its own Global Graphics Translation Table
- * (GGTT) instance.
- */
-struct xe_ggtt {
-	/** @tile: Back pointer to tile where this GGTT belongs */
-	struct xe_tile *tile;
-	/** @size: Total size of this GGTT */
-	u64 size;
-
-#define XE_GGTT_FLAGS_64K BIT(0)
-	/**
-	 * @flags: Flags for this GGTT
-	 * Acceptable flags:
-	 * - %XE_GGTT_FLAGS_64K - if PTE size is 64K. Otherwise, regular is 4K.
-	 */
-	unsigned int flags;
-	/** @scratch: Internal object allocation used as a scratch page */
-	struct xe_bo *scratch;
-	/** @lock: Mutex lock to protect GGTT data */
-	struct mutex lock;
-	/**
-	 *  @gsm: The iomem pointer to the actual location of the translation
-	 * table located in the GSM for easy PTE manipulation
-	 */
-	u64 __iomem *gsm;
-	/** @pt_ops: Page Table operations per platform */
-	const struct xe_ggtt_pt_ops *pt_ops;
-	/** @mm: The memory manager used to manage individual GGTT allocations */
-	struct drm_mm mm;
-	/** @access_count: counts GGTT writes */
-	unsigned int access_count;
-	/** @wq: Dedicated unordered work queue to process node removals */
-	struct workqueue_struct *wq;
-};
-
 /**
  * struct xe_ggtt_node - A node in GGTT.
  *
@@ -74,15 +36,5 @@ typedef void (*xe_ggtt_set_pte_fn)(struct xe_ggtt *ggtt, u64 addr, u64 pte);
 typedef void (*xe_ggtt_transform_cb)(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
 				     xe_ggtt_pte_encode_bo_fn pte_encode_bo,
 				     xe_ggtt_set_pte_fn set_pte, void *arg);
-/**
- * struct xe_ggtt_pt_ops - GGTT Page table operations
- * Which can vary from platform to platform.
- */
-struct xe_ggtt_pt_ops {
-	/** @pte_encode_bo: Encode PTE address for a given BO */
-	xe_ggtt_pte_encode_bo_fn pte_encode_bo;
-	/** @ggtt_set_pte: Directly write into GGTT's PTE */
-	xe_ggtt_set_pte_fn ggtt_set_pte;
-};
 
 #endif
-- 
2.45.2

[PATCH v4 0/6] drm/xe: Make struct xe_ggtt private.

[Maarten Lankhorst]

SRIOV-VF node shifting code uses a complicated system with balloons
to limit allocation and size. Since size never changes after init,
shifting can simply be done by taking the the GGTT lock and then
moving each offset.

First introduce a function to shift an entire GGTT, this removes the
need for the balloons, then also perform the display code pinning
through a callback, and finally privatize the struct.

No other users outside of xe_ggtt remain, and we can make xe_ggtt private.

Rebased, no functional changes since v3.

Maarten Lankhorst (5):
  drm/xe: Only have a single drmm release action.
  drm/xe: Start using ggtt->start in preparation of balloon removal
  drm/xe: Rewrite GGTT VF initialisation
  drm/xe: Convert xe_fb_pin to use a callback for insertion into GGTT
  drm/xe: Move struct xe_ggtt to xe_ggtt.c

Tomasz Lis (1):
  drm/mm: Introduce address space shifting

 drivers/gpu/drm/drm_mm.c                    |  24 ++
 drivers/gpu/drm/xe/Makefile                 |   3 +-
 drivers/gpu/drm/xe/display/xe_fb_pin.c      | 111 +++---
 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c |   2 +-
 drivers/gpu/drm/xe/xe_ggtt.c                | 357 ++++++++++----------
 drivers/gpu/drm/xe/xe_ggtt.h                |  16 +-
 drivers/gpu/drm/xe/xe_ggtt_types.h          |  53 +--
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c  |   4 +-
 drivers/gpu/drm/xe/xe_sriov_vf.c            |   4 +-
 drivers/gpu/drm/xe/xe_tile_sriov_vf.c       | 254 --------------
 drivers/gpu/drm/xe/xe_tile_sriov_vf.h       |  18 -
 include/drm/drm_mm.h                        |   1 +
 12 files changed, 276 insertions(+), 571 deletions(-)
 delete mode 100644 drivers/gpu/drm/xe/xe_tile_sriov_vf.c
 delete mode 100644 drivers/gpu/drm/xe/xe_tile_sriov_vf.h

-- 
2.51.0

[PATCH v4 1/6] drm/xe: Only have a single drmm release action.

[Maarten Lankhorst]

The broken action happened after ggtt_early_fini, so
it's safe to put the drain_workqueue in there instead of
creating a new place.

Fixes: 89d2835c3680 ("drm/xe: Process deferred GGTT node removals on device unwind")
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_ggtt.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 7fdd0a97a6281..c2f23926b5a7b 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -179,6 +179,7 @@ static void ggtt_fini_early(struct drm_device *drm, void *arg)
 {
 	struct xe_ggtt *ggtt = arg;
 
+	drain_workqueue(ggtt->wq);
 	destroy_workqueue(ggtt->wq);
 	mutex_destroy(&ggtt->lock);
 	drm_mm_takedown(&ggtt->mm);
@@ -239,13 +240,6 @@ int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 reserved, u32 size)
 }
 EXPORT_SYMBOL_IF_KUNIT(xe_ggtt_init_kunit);
 
-static void dev_fini_ggtt(void *arg)
-{
-	struct xe_ggtt *ggtt = arg;
-
-	drain_workqueue(ggtt->wq);
-}
-
 /**
  * xe_ggtt_init_early - Early GGTT initialization
  * @ggtt: the &xe_ggtt to be initialized
@@ -298,10 +292,6 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	if (err)
 		return err;
 
-	err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt);
-	if (err)
-		return err;
-
 	if (IS_SRIOV_VF(xe)) {
 		err = xe_tile_sriov_vf_prepare_ggtt(ggtt->tile);
 		if (err)
-- 
2.51.0

[PATCH v4 2/6] drm/mm: Introduce address space shifting

[Maarten Lankhorst]

From: Tomasz Lis <tomasz.lis@intel.com>

Due to resource reprovisioning, sometimes a need arises to move
a living address space to a new area, preserving all the nodes
and holes stored within.

It is possible to do that by removing all nodes to a temporary list,
reiniting the drm_mm instance and re-adding everything while applying
a shift to each node. But that is a lot of extra work for a task
which could be done internally without any node shuffle operations.

This change introduces an interface which allows to shift the range
without pruning the whole drm_mm instance.

Having a drm_mm interface for such shift significantly simplifies
the code required to adjust a KMD for a change in base address
of a space managed by drm_mm instance.

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20250204224136.3183710-2-tomasz.lis@intel.com
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/drm_mm.c | 24 ++++++++++++++++++++++++
 include/drm/drm_mm.h     |  1 +
 2 files changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index ca254611b3823..ce3bd8b5e41f0 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -917,6 +917,30 @@ struct drm_mm_node *drm_mm_scan_color_evict(struct drm_mm_scan *scan)
 }
 EXPORT_SYMBOL(drm_mm_scan_color_evict);
 
+/**
+ * drm_mm_shift - move the range of addresses managed by this @mm
+ * @mm: the drm_mm structure instance to shift
+ * @shift: the shift value to be added to addresses of all nodes
+ *
+ * The function shifts all nodes by given offset, moving the address space
+ * range managed by this @mm.
+ */
+void drm_mm_shift(struct drm_mm *mm, s64 shift)
+{
+	struct drm_mm_node *node;
+
+	/*
+	 * Head node represents a hole, with negative size and start at the end
+	 * of addressable area. This means it is never present within nodes
+	 * list - needs to be shifted separately.
+	 */
+	mm->head_node.start += shift;
+
+	drm_mm_for_each_node(node, mm)
+		node->start += shift;
+}
+EXPORT_SYMBOL(drm_mm_shift);
+
 /**
  * drm_mm_init - initialize a drm-mm allocator
  * @mm: the drm_mm structure to initialize
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index f654874c4ce67..798e5a4f07add 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -465,6 +465,7 @@ static inline int drm_mm_insert_node(struct drm_mm *mm,
 void drm_mm_remove_node(struct drm_mm_node *node);
 void drm_mm_init(struct drm_mm *mm, u64 start, u64 size);
 void drm_mm_takedown(struct drm_mm *mm);
+void drm_mm_shift(struct drm_mm *mm, s64 shift);
 
 /**
  * drm_mm_clean - checks whether an allocator is clean
-- 
2.51.0

[PATCH v4 3/6] drm/xe: Start using ggtt->start in preparation of balloon removal

[Maarten Lankhorst]

Instead of having ggtt->size point to the end of ggtt, have ggtt->size
be the actual size of the GGTT, and introduce ggtt->start to point to
the beginning of GGTT.

This will allow a massive cleanup of GGTT in case of SRIOV-VF.

Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c |  2 +-
 drivers/gpu/drm/xe/xe_ggtt.c                | 70 ++++++++++++---------
 drivers/gpu/drm/xe/xe_ggtt.h                |  2 +
 drivers/gpu/drm/xe/xe_ggtt_types.h          |  4 +-
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c  |  4 +-
 5 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c b/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
index d266882adc0e0..acddbedcf17cb 100644
--- a/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
+++ b/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
@@ -67,7 +67,7 @@ static int guc_buf_test_init(struct kunit *test)
 
 	KUNIT_ASSERT_EQ(test, 0,
 			xe_ggtt_init_kunit(ggtt, DUT_GGTT_START,
-					   DUT_GGTT_START + DUT_GGTT_SIZE));
+					   DUT_GGTT_SIZE));
 
 	kunit_activate_static_stub(test, xe_managed_bo_create_pin_map,
 				   replacement_xe_managed_bo_create_pin_map);
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index c2f23926b5a7b..c53fe9f7ce4da 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -124,10 +124,20 @@ static void ggtt_update_access_counter(struct xe_ggtt *ggtt)
 	}
 }
 
+u64 xe_ggtt_start(struct xe_ggtt *ggtt)
+{
+	return ggtt->start;
+}
+
+u64 xe_ggtt_size(struct xe_ggtt *ggtt)
+{
+	return ggtt->size;
+}
+
 static void xe_ggtt_set_pte(struct xe_ggtt *ggtt, u64 addr, u64 pte)
 {
 	xe_tile_assert(ggtt->tile, !(addr & XE_PTE_MASK));
-	xe_tile_assert(ggtt->tile, addr < ggtt->size);
+	xe_tile_assert(ggtt->tile, addr < ggtt->start + ggtt->size);
 
 	writeq(pte, &ggtt->gsm[addr >> XE_PTE_SHIFT]);
 }
@@ -224,18 +234,18 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = {
 	.ggtt_set_pte = xe_ggtt_set_pte_and_flush,
 };
 
-static void __xe_ggtt_init_early(struct xe_ggtt *ggtt, u32 reserved)
+static void __xe_ggtt_init_early(struct xe_ggtt *ggtt, u64 start, u64 size)
 {
-	drm_mm_init(&ggtt->mm, reserved,
-		    ggtt->size - reserved);
+	ggtt->start = start;
+	ggtt->size = size;
+	drm_mm_init(&ggtt->mm, start, ggtt->size);
 	mutex_init(&ggtt->lock);
 	primelockdep(ggtt);
 }
 
-int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 reserved, u32 size)
+int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 start, u32 size)
 {
-	ggtt->size = size;
-	__xe_ggtt_init_early(ggtt, reserved);
+	__xe_ggtt_init_early(ggtt, start, size);
 	return 0;
 }
 EXPORT_SYMBOL_IF_KUNIT(xe_ggtt_init_kunit);
@@ -256,26 +266,32 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	struct xe_device *xe = tile_to_xe(ggtt->tile);
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	unsigned int gsm_size;
+	u64 ggtt_start, wopcm = xe_wopcm_size(xe), ggtt_size;
 	int err;
 
-	if (IS_SRIOV_VF(xe) || GRAPHICS_VERx100(xe) >= 1250)
-		gsm_size = SZ_8M; /* GGTT is expected to be 4GiB */
-	else
-		gsm_size = probe_gsm_size(pdev);
-
-	if (gsm_size == 0) {
-		xe_tile_err(ggtt->tile, "Hardware reported no preallocated GSM\n");
-		return -ENOMEM;
+	if (!IS_SRIOV_VF(xe)) {
+		if (GRAPHICS_VERx100(xe) >= 1250)
+			gsm_size = SZ_8M; /* GGTT is expected to be 4GiB */
+		else
+			gsm_size = probe_gsm_size(pdev);
+		if (gsm_size == 0) {
+			xe_tile_err(ggtt->tile, "Hardware reported no preallocated GSM\n");
+			return -ENOMEM;
+		}
+		ggtt_start = wopcm;
+		ggtt_size = (gsm_size / 8) * (u64) XE_PAGE_SIZE - ggtt_start;
+	} else {
+		/* GGTT is expected to be 4GiB */
+		ggtt_start = wopcm;
+		ggtt_size = SZ_4G - ggtt_start;
 	}
 
 	ggtt->gsm = ggtt->tile->mmio.regs + SZ_8M;
-	ggtt->size = (gsm_size / 8) * (u64) XE_PAGE_SIZE;
-
 	if (IS_DGFX(xe) && xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K)
 		ggtt->flags |= XE_GGTT_FLAGS_64K;
 
-	if (ggtt->size > GUC_GGTT_TOP)
-		ggtt->size = GUC_GGTT_TOP;
+	if (ggtt_size + ggtt_start > GUC_GGTT_TOP)
+		ggtt_size = GUC_GGTT_TOP - ggtt_start;
 
 	if (GRAPHICS_VERx100(xe) >= 1270)
 		ggtt->pt_ops = (ggtt->tile->media_gt &&
@@ -286,7 +302,7 @@ 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);
-	__xe_ggtt_init_early(ggtt, xe_wopcm_size(xe));
+	__xe_ggtt_init_early(ggtt, ggtt_start, ggtt_size);
 
 	err = drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt);
 	if (err)
@@ -520,11 +536,9 @@ void xe_ggtt_node_remove_balloon_locked(struct xe_ggtt_node *node)
 static void xe_ggtt_assert_fit(struct xe_ggtt *ggtt, u64 start, u64 size)
 {
 	struct xe_tile *tile = ggtt->tile;
-	struct xe_device *xe = tile_to_xe(tile);
-	u64 __maybe_unused wopcm = xe_wopcm_size(xe);
 
-	xe_tile_assert(tile, start >= wopcm);
-	xe_tile_assert(tile, start + size < ggtt->size - wopcm);
+	xe_tile_assert(tile, start >= ggtt->start);
+	xe_tile_assert(tile, start + size <= ggtt->start + ggtt->size);
 }
 
 /**
@@ -833,14 +847,12 @@ u64 xe_ggtt_largest_hole(struct xe_ggtt *ggtt, u64 alignment, u64 *spare)
 {
 	const struct drm_mm *mm = &ggtt->mm;
 	const struct drm_mm_node *entry;
-	u64 hole_min_start = xe_wopcm_size(tile_to_xe(ggtt->tile));
 	u64 hole_start, hole_end, hole_size;
 	u64 max_hole = 0;
 
 	mutex_lock(&ggtt->lock);
-
 	drm_mm_for_each_hole(entry, mm, hole_start, hole_end) {
-		hole_start = max(hole_start, hole_min_start);
+		hole_start = max(hole_start, ggtt->start);
 		hole_start = ALIGN(hole_start, alignment);
 		hole_end = ALIGN_DOWN(hole_end, alignment);
 		if (hole_start >= hole_end)
@@ -933,15 +945,13 @@ u64 xe_ggtt_print_holes(struct xe_ggtt *ggtt, u64 alignment, struct drm_printer
 {
 	const struct drm_mm *mm = &ggtt->mm;
 	const struct drm_mm_node *entry;
-	u64 hole_min_start = xe_wopcm_size(tile_to_xe(ggtt->tile));
 	u64 hole_start, hole_end, hole_size;
 	u64 total = 0;
 	char buf[10];
 
 	mutex_lock(&ggtt->lock);
-
 	drm_mm_for_each_hole(entry, mm, hole_start, hole_end) {
-		hole_start = max(hole_start, hole_min_start);
+		hole_start = max(hole_start, ggtt->start);
 		hole_start = ALIGN(hole_start, alignment);
 		hole_end = ALIGN_DOWN(hole_end, alignment);
 		if (hole_start >= hole_end)
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index 75fc7a1efea76..6482bddb2ef36 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -23,6 +23,8 @@ int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node,
 				       u64 start, u64 size);
 void xe_ggtt_node_remove_balloon_locked(struct xe_ggtt_node *node);
 void xe_ggtt_shift_nodes_locked(struct xe_ggtt *ggtt, s64 shift);
+u64 xe_ggtt_start(struct xe_ggtt *ggtt);
+u64 xe_ggtt_size(struct xe_ggtt *ggtt);
 
 int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align);
 int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index c5e999d58ff2a..a27919302d6b2 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -22,7 +22,9 @@ struct xe_gt;
 struct xe_ggtt {
 	/** @tile: Back pointer to tile where this GGTT belongs */
 	struct xe_tile *tile;
-	/** @size: Total size of this GGTT */
+	/** @start: Start offset of GGTT */
+	u64 start;
+	/** @size: Total usable size of this GGTT */
 	u64 size;
 
 #define XE_GGTT_FLAGS_64K BIT(0)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index b2e5c52978e6a..2289756761636 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -343,8 +343,8 @@ static int pf_push_full_vf_config(struct xe_gt *gt, unsigned int vfid)
 	xe_gt_assert(gt, num_dwords <= max_cfg_dwords);
 
 	if (vfid == PFID) {
-		u64 ggtt_start = xe_wopcm_size(gt_to_xe(gt));
-		u64 ggtt_size = gt_to_tile(gt)->mem.ggtt->size - ggtt_start;
+		u64 ggtt_start = xe_ggtt_start(gt_to_tile(gt)->mem.ggtt);
+		u64 ggtt_size = xe_ggtt_size(gt_to_tile(gt)->mem.ggtt);
 
 		/* plain PF config data will never include a real GGTT region */
 		xe_gt_assert(gt, !encode_config_ggtt(cfg + num_dwords, config, true));
-- 
2.51.0

[PATCH v4 4/6] drm/xe: Rewrite GGTT VF initialisation

[Maarten Lankhorst]

The previous code was using a complicated system with 2 balloons to
set GGTT size and adjust GGTT offset. While it works, it's overly
complicated.

A better approach is to set the offset and size when initialising GGTT,
this removes the need for adding balloons. The resize function only
needs to re-initialise GGTT at the new offset.

We use the newly created drm_mm_shift to shift the nodes.

This removes the need to manipulate the internals of xe_ggtt outside
of xe_ggtt, and cleans up a lot of now unneeded code.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/Makefile           |   3 +-
 drivers/gpu/drm/xe/xe_ggtt.c          | 143 +++------------
 drivers/gpu/drm/xe/xe_ggtt.h          |   5 +-
 drivers/gpu/drm/xe/xe_sriov_vf.c      |   4 +-
 drivers/gpu/drm/xe/xe_tile_sriov_vf.c | 254 --------------------------
 drivers/gpu/drm/xe/xe_tile_sriov_vf.h |  18 --
 6 files changed, 29 insertions(+), 398 deletions(-)
 delete mode 100644 drivers/gpu/drm/xe/xe_tile_sriov_vf.c
 delete mode 100644 drivers/gpu/drm/xe/xe_tile_sriov_vf.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 84321fad32658..1f573bf53cf1a 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -158,8 +158,7 @@ xe-y += \
 	xe_memirq.o \
 	xe_sriov.o \
 	xe_sriov_vf.o \
-	xe_sriov_vf_ccs.o \
-	xe_tile_sriov_vf.o
+	xe_sriov_vf_ccs.o
 
 xe-$(CONFIG_PCI_IOV) += \
 	xe_gt_sriov_pf.o \
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index c53fe9f7ce4da..3429e54a43eb5 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -23,13 +23,13 @@
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_gt_printk.h"
+#include "xe_gt_sriov_vf.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_res_cursor.h"
 #include "xe_sriov.h"
 #include "xe_tile_printk.h"
-#include "xe_tile_sriov_vf.h"
 #include "xe_tlb_inval.h"
 #include "xe_wa.h"
 #include "xe_wopcm.h"
@@ -267,7 +267,6 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	unsigned int gsm_size;
 	u64 ggtt_start, wopcm = xe_wopcm_size(xe), ggtt_size;
-	int err;
 
 	if (!IS_SRIOV_VF(xe)) {
 		if (GRAPHICS_VERx100(xe) >= 1250)
@@ -281,9 +280,15 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 		ggtt_start = wopcm;
 		ggtt_size = (gsm_size / 8) * (u64) XE_PAGE_SIZE - ggtt_start;
 	} else {
-		/* GGTT is expected to be 4GiB */
-		ggtt_start = wopcm;
-		ggtt_size = SZ_4G - ggtt_start;
+		ggtt_start = xe_gt_sriov_vf_ggtt_base(ggtt->tile->primary_gt);
+		ggtt_size = xe_gt_sriov_vf_ggtt(ggtt->tile->primary_gt);
+
+		if (ggtt_start < wopcm || ggtt_start > GUC_GGTT_TOP ||
+		    ggtt_size > GUC_GGTT_TOP - ggtt_start) {
+			xe_tile_err(ggtt->tile, "tile%u: Invalid GGTT configuration: %#llx-%#llx\n",
+				     ggtt->tile->id, ggtt_start, ggtt_start + ggtt_size - 1);
+			return -ERANGE;
+		}
 	}
 
 	ggtt->gsm = ggtt->tile->mmio.regs + SZ_8M;
@@ -304,17 +309,7 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM);
 	__xe_ggtt_init_early(ggtt, ggtt_start, ggtt_size);
 
-	err = drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt);
-	if (err)
-		return err;
-
-	if (IS_SRIOV_VF(xe)) {
-		err = xe_tile_sriov_vf_prepare_ggtt(ggtt->tile);
-		if (err)
-			return err;
-	}
-
-	return 0;
+	return drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt);
 }
 ALLOW_ERROR_INJECTION(xe_ggtt_init_early, ERRNO); /* See xe_pci_probe() */
 
@@ -466,83 +461,8 @@ static void xe_ggtt_invalidate(struct xe_ggtt *ggtt)
 	ggtt_invalidate_gt_tlb(ggtt->tile->media_gt);
 }
 
-static void xe_ggtt_dump_node(struct xe_ggtt *ggtt,
-			      const struct drm_mm_node *node, const char *description)
-{
-	char buf[10];
-
-	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG)) {
-		string_get_size(node->size, 1, STRING_UNITS_2, buf, sizeof(buf));
-		xe_tile_dbg(ggtt->tile, "GGTT %#llx-%#llx (%s) %s\n",
-			    node->start, node->start + node->size, buf, description);
-	}
-}
-
-/**
- * xe_ggtt_node_insert_balloon_locked - prevent allocation of specified GGTT addresses
- * @node: the &xe_ggtt_node to hold reserved GGTT node
- * @start: the starting GGTT address of the reserved region
- * @end: then end GGTT address of the reserved region
- *
- * To be used in cases where ggtt->lock is already taken.
- * Use xe_ggtt_node_remove_balloon_locked() to release a reserved GGTT node.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node, u64 start, u64 end)
-{
-	struct xe_ggtt *ggtt = node->ggtt;
-	int err;
-
-	xe_tile_assert(ggtt->tile, start < end);
-	xe_tile_assert(ggtt->tile, IS_ALIGNED(start, XE_PAGE_SIZE));
-	xe_tile_assert(ggtt->tile, IS_ALIGNED(end, XE_PAGE_SIZE));
-	xe_tile_assert(ggtt->tile, !drm_mm_node_allocated(&node->base));
-	lockdep_assert_held(&ggtt->lock);
-
-	node->base.color = 0;
-	node->base.start = start;
-	node->base.size = end - start;
-
-	err = drm_mm_reserve_node(&ggtt->mm, &node->base);
-
-	if (xe_tile_WARN(ggtt->tile, err, "Failed to balloon GGTT %#llx-%#llx (%pe)\n",
-			 node->base.start, node->base.start + node->base.size, ERR_PTR(err)))
-		return err;
-
-	xe_ggtt_dump_node(ggtt, &node->base, "balloon");
-	return 0;
-}
-
 /**
- * xe_ggtt_node_remove_balloon_locked - release a reserved GGTT region
- * @node: the &xe_ggtt_node with reserved GGTT region
- *
- * To be used in cases where ggtt->lock is already taken.
- * See xe_ggtt_node_insert_balloon_locked() for details.
- */
-void xe_ggtt_node_remove_balloon_locked(struct xe_ggtt_node *node)
-{
-	if (!xe_ggtt_node_allocated(node))
-		return;
-
-	lockdep_assert_held(&node->ggtt->lock);
-
-	xe_ggtt_dump_node(node->ggtt, &node->base, "remove-balloon");
-
-	drm_mm_remove_node(&node->base);
-}
-
-static void xe_ggtt_assert_fit(struct xe_ggtt *ggtt, u64 start, u64 size)
-{
-	struct xe_tile *tile = ggtt->tile;
-
-	xe_tile_assert(tile, start >= ggtt->start);
-	xe_tile_assert(tile, start + size <= ggtt->start + ggtt->size);
-}
-
-/**
- * xe_ggtt_shift_nodes_locked - Shift GGTT nodes to adjust for a change in usable address range.
+ * xe_ggtt_shift_nodes - Shift GGTT nodes to adjust for a change in usable address range.
  * @ggtt: the &xe_ggtt struct instance
  * @shift: change to the location of area provisioned for current VF
  *
@@ -556,29 +476,18 @@ static void xe_ggtt_assert_fit(struct xe_ggtt *ggtt, u64 start, u64 size)
  * the list of nodes was either already damaged, or that the shift brings the address range
  * outside of valid bounds. Both cases justify an assert rather than error code.
  */
-void xe_ggtt_shift_nodes_locked(struct xe_ggtt *ggtt, s64 shift)
+void xe_ggtt_shift_nodes(struct xe_ggtt *ggtt, s64 shift)
 {
-	struct xe_tile *tile __maybe_unused = ggtt->tile;
-	struct drm_mm_node *node, *tmpn;
-	LIST_HEAD(temp_list_head);
+	s64 new_start;
 
-	lockdep_assert_held(&ggtt->lock);
+	mutex_lock(&ggtt->lock);
 
-	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG))
-		drm_mm_for_each_node_safe(node, tmpn, &ggtt->mm)
-			xe_ggtt_assert_fit(ggtt, node->start + shift, node->size);
+	new_start = ggtt->start + shift;
+	xe_tile_assert(ggtt->tile, new_start >= xe_wopcm_size(tile_to_xe(ggtt->tile)));
+	xe_tile_assert(ggtt->tile, new_start + ggtt->size <= GUC_GGTT_TOP);
 
-	drm_mm_for_each_node_safe(node, tmpn, &ggtt->mm) {
-		drm_mm_remove_node(node);
-		list_add(&node->node_list, &temp_list_head);
-	}
-
-	list_for_each_entry_safe(node, tmpn, &temp_list_head, node_list) {
-		list_del(&node->node_list);
-		node->start += shift;
-		drm_mm_reserve_node(&ggtt->mm, node);
-		xe_tile_assert(tile, drm_mm_node_allocated(node));
-	}
+	drm_mm_shift(&ggtt->mm, shift);
+	mutex_unlock(&ggtt->lock);
 }
 
 /**
@@ -630,11 +539,9 @@ int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align)
  * @ggtt: the &xe_ggtt where the new node will later be inserted/reserved.
  *
  * This function will allocate the struct %xe_ggtt_node and return its pointer.
- * This struct will then be freed after the node removal upon xe_ggtt_node_remove()
- * or xe_ggtt_node_remove_balloon_locked().
+ * This struct will then be freed after the node removal upon xe_ggtt_node_remove().
  * Having %xe_ggtt_node struct allocated doesn't mean that the node is already allocated
- * in GGTT. Only the xe_ggtt_node_insert(), xe_ggtt_node_insert_locked(),
- * xe_ggtt_node_insert_balloon_locked() will ensure the node is inserted or reserved in GGTT.
+ * in GGTT. Only xe_ggtt_node_insert() will ensure the node is inserted or reserved in GGTT.
  *
  * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
  **/
@@ -655,9 +562,9 @@ struct xe_ggtt_node *xe_ggtt_node_init(struct xe_ggtt *ggtt)
  * xe_ggtt_node_fini - Forcebly finalize %xe_ggtt_node struct
  * @node: the &xe_ggtt_node to be freed
  *
- * If anything went wrong with either xe_ggtt_node_insert(), xe_ggtt_node_insert_locked(),
- * or xe_ggtt_node_insert_balloon_locked(); and this @node is not going to be reused, then,
- * this function needs to be called to free the %xe_ggtt_node struct
+ * If anything went wrong with either xe_ggtt_node_insert() and this @node is
+ * not going to be reused, then this function needs to be called to free the
+ * %xe_ggtt_node struct
  **/
 void xe_ggtt_node_fini(struct xe_ggtt_node *node)
 {
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index 6482bddb2ef36..eccef2d2b3cee 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -19,10 +19,7 @@ int xe_ggtt_init(struct xe_ggtt *ggtt);
 
 struct xe_ggtt_node *xe_ggtt_node_init(struct xe_ggtt *ggtt);
 void xe_ggtt_node_fini(struct xe_ggtt_node *node);
-int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node,
-				       u64 start, u64 size);
-void xe_ggtt_node_remove_balloon_locked(struct xe_ggtt_node *node);
-void xe_ggtt_shift_nodes_locked(struct xe_ggtt *ggtt, s64 shift);
+void xe_ggtt_shift_nodes(struct xe_ggtt *ggtt, s64 shift);
 u64 xe_ggtt_start(struct xe_ggtt *ggtt);
 u64 xe_ggtt_size(struct xe_ggtt *ggtt);
 
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index c1830ec8f0fd6..4bfd9013187b2 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -8,6 +8,7 @@
 
 #include "xe_assert.h"
 #include "xe_device.h"
+#include "xe_ggtt.h"
 #include "xe_gt.h"
 #include "xe_gt_sriov_printk.h"
 #include "xe_gt_sriov_vf.h"
@@ -20,7 +21,6 @@
 #include "xe_sriov_printk.h"
 #include "xe_sriov_vf.h"
 #include "xe_sriov_vf_ccs.h"
-#include "xe_tile_sriov_vf.h"
 
 /**
  * DOC: VF restore procedure in PF KMD and VF KMD
@@ -328,7 +328,7 @@ static int gt_vf_post_migration_fixups(struct xe_gt *gt)
 
 	shift = xe_gt_sriov_vf_ggtt_shift(gt);
 	if (shift) {
-		xe_tile_sriov_vf_fixup_ggtt_nodes(gt_to_tile(gt), shift);
+		xe_ggtt_shift_nodes(gt_to_tile(gt)->mem.ggtt, shift);
 		xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
 		err = xe_guc_contexts_hwsp_rebase(&gt->uc.guc, buf);
 		if (err)
diff --git a/drivers/gpu/drm/xe/xe_tile_sriov_vf.c b/drivers/gpu/drm/xe/xe_tile_sriov_vf.c
deleted file mode 100644
index f221dbed16f09..0000000000000
--- a/drivers/gpu/drm/xe/xe_tile_sriov_vf.c
+++ /dev/null
@@ -1,254 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2025 Intel Corporation
- */
-
-#include <drm/drm_managed.h>
-
-#include "regs/xe_gtt_defs.h"
-
-#include "xe_assert.h"
-#include "xe_ggtt.h"
-#include "xe_gt_sriov_vf.h"
-#include "xe_sriov.h"
-#include "xe_sriov_printk.h"
-#include "xe_tile_sriov_vf.h"
-#include "xe_wopcm.h"
-
-static int vf_init_ggtt_balloons(struct xe_tile *tile)
-{
-	struct xe_ggtt *ggtt = tile->mem.ggtt;
-
-	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
-
-	tile->sriov.vf.ggtt_balloon[0] = xe_ggtt_node_init(ggtt);
-	if (IS_ERR(tile->sriov.vf.ggtt_balloon[0]))
-		return PTR_ERR(tile->sriov.vf.ggtt_balloon[0]);
-
-	tile->sriov.vf.ggtt_balloon[1] = xe_ggtt_node_init(ggtt);
-	if (IS_ERR(tile->sriov.vf.ggtt_balloon[1])) {
-		xe_ggtt_node_fini(tile->sriov.vf.ggtt_balloon[0]);
-		return PTR_ERR(tile->sriov.vf.ggtt_balloon[1]);
-	}
-
-	return 0;
-}
-
-/**
- * xe_tile_sriov_vf_balloon_ggtt_locked - Insert balloon nodes to limit used GGTT address range.
- * @tile: the &xe_tile struct instance
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int xe_tile_sriov_vf_balloon_ggtt_locked(struct xe_tile *tile)
-{
-	u64 ggtt_base = xe_gt_sriov_vf_ggtt_base(tile->primary_gt);
-	u64 ggtt_size = xe_gt_sriov_vf_ggtt(tile->primary_gt);
-	struct xe_device *xe = tile_to_xe(tile);
-	u64 wopcm = xe_wopcm_size(xe);
-	u64 start, end;
-	int err;
-
-	xe_tile_assert(tile, IS_SRIOV_VF(xe));
-	xe_tile_assert(tile, ggtt_size);
-	lockdep_assert_held(&tile->mem.ggtt->lock);
-
-	/*
-	 * VF can only use part of the GGTT as allocated by the PF:
-	 *
-	 *      WOPCM                                  GUC_GGTT_TOP
-	 *      |<------------ Total GGTT size ------------------>|
-	 *
-	 *           VF GGTT base -->|<- size ->|
-	 *
-	 *      +--------------------+----------+-----------------+
-	 *      |////////////////////|   block  |\\\\\\\\\\\\\\\\\|
-	 *      +--------------------+----------+-----------------+
-	 *
-	 *      |<--- balloon[0] --->|<-- VF -->|<-- balloon[1] ->|
-	 */
-
-	if (ggtt_base < wopcm || ggtt_base > GUC_GGTT_TOP ||
-	    ggtt_size > GUC_GGTT_TOP - ggtt_base) {
-		xe_sriov_err(xe, "tile%u: Invalid GGTT configuration: %#llx-%#llx\n",
-			     tile->id, ggtt_base, ggtt_base + ggtt_size - 1);
-		return -ERANGE;
-	}
-
-	start = wopcm;
-	end = ggtt_base;
-	if (end != start) {
-		err = xe_ggtt_node_insert_balloon_locked(tile->sriov.vf.ggtt_balloon[0],
-							 start, end);
-		if (err)
-			return err;
-	}
-
-	start = ggtt_base + ggtt_size;
-	end = GUC_GGTT_TOP;
-	if (end != start) {
-		err = xe_ggtt_node_insert_balloon_locked(tile->sriov.vf.ggtt_balloon[1],
-							 start, end);
-		if (err) {
-			xe_ggtt_node_remove_balloon_locked(tile->sriov.vf.ggtt_balloon[0]);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-static int vf_balloon_ggtt(struct xe_tile *tile)
-{
-	struct xe_ggtt *ggtt = tile->mem.ggtt;
-	int err;
-
-	mutex_lock(&ggtt->lock);
-	err = xe_tile_sriov_vf_balloon_ggtt_locked(tile);
-	mutex_unlock(&ggtt->lock);
-
-	return err;
-}
-
-/**
- * xe_tile_sriov_vf_deballoon_ggtt_locked - Remove balloon nodes.
- * @tile: the &xe_tile struct instance
- */
-void xe_tile_sriov_vf_deballoon_ggtt_locked(struct xe_tile *tile)
-{
-	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
-
-	xe_ggtt_node_remove_balloon_locked(tile->sriov.vf.ggtt_balloon[1]);
-	xe_ggtt_node_remove_balloon_locked(tile->sriov.vf.ggtt_balloon[0]);
-}
-
-static void vf_deballoon_ggtt(struct xe_tile *tile)
-{
-	mutex_lock(&tile->mem.ggtt->lock);
-	xe_tile_sriov_vf_deballoon_ggtt_locked(tile);
-	mutex_unlock(&tile->mem.ggtt->lock);
-}
-
-static void vf_fini_ggtt_balloons(struct xe_tile *tile)
-{
-	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
-
-	xe_ggtt_node_fini(tile->sriov.vf.ggtt_balloon[1]);
-	xe_ggtt_node_fini(tile->sriov.vf.ggtt_balloon[0]);
-}
-
-static void cleanup_ggtt(struct drm_device *drm, void *arg)
-{
-	struct xe_tile *tile = arg;
-
-	vf_deballoon_ggtt(tile);
-	vf_fini_ggtt_balloons(tile);
-}
-
-/**
- * xe_tile_sriov_vf_prepare_ggtt - Prepare a VF's GGTT configuration.
- * @tile: the &xe_tile
- *
- * This function is for VF use only.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int xe_tile_sriov_vf_prepare_ggtt(struct xe_tile *tile)
-{
-	struct xe_device *xe = tile_to_xe(tile);
-	int err;
-
-	err = vf_init_ggtt_balloons(tile);
-	if (err)
-		return err;
-
-	err = vf_balloon_ggtt(tile);
-	if (err) {
-		vf_fini_ggtt_balloons(tile);
-		return err;
-	}
-
-	return drmm_add_action_or_reset(&xe->drm, cleanup_ggtt, tile);
-}
-
-/**
- * DOC: GGTT nodes shifting during VF post-migration recovery
- *
- * The first fixup applied to the VF KMD structures as part of post-migration
- * recovery is shifting nodes within &xe_ggtt instance. The nodes are moved
- * from range previously assigned to this VF, into newly provisioned area.
- * The changes include balloons, which are resized accordingly.
- *
- * The balloon nodes are there to eliminate unavailable ranges from use: one
- * reserves the GGTT area below the range for current VF, and another one
- * reserves area above.
- *
- * Below is a GGTT layout of example VF, with a certain address range assigned to
- * said VF, and inaccessible areas above and below:
- *
- *  0                                                                        4GiB
- *  |<--------------------------- Total GGTT size ----------------------------->|
- *      WOPCM                                                         GUC_TOP
- *      |<-------------- Area mappable by xe_ggtt instance ---------------->|
- *
- *  +---+---------------------------------+----------+----------------------+---+
- *  |\\\|/////////////////////////////////|  VF mem  |//////////////////////|\\\|
- *  +---+---------------------------------+----------+----------------------+---+
- *
- * Hardware enforced access rules before migration:
- *
- *  |<------- inaccessible for VF ------->|<VF owned>|<-- inaccessible for VF ->|
- *
- * GGTT nodes used for tracking allocations:
- *
- *      |<---------- balloon ------------>|<- nodes->|<----- balloon ------>|
- *
- * After the migration, GGTT area assigned to the VF might have shifted, either
- * to lower or to higher address. But we expect the total size and extra areas to
- * be identical, as migration can only happen between matching platforms.
- * Below is an example of GGTT layout of the VF after migration. Content of the
- * GGTT for VF has been moved to a new area, and we receive its address from GuC:
- *
- *  +---+----------------------+----------+---------------------------------+---+
- *  |\\\|//////////////////////|  VF mem  |/////////////////////////////////|\\\|
- *  +---+----------------------+----------+---------------------------------+---+
- *
- * Hardware enforced access rules after migration:
- *
- *  |<- inaccessible for VF -->|<VF owned>|<------- inaccessible for VF ------->|
- *
- * So the VF has a new slice of GGTT assigned, and during migration process, the
- * memory content was copied to that new area. But the &xe_ggtt nodes are still
- * tracking allocations using the old addresses. The nodes within VF owned area
- * have to be shifted, and balloon nodes need to be resized to properly mask out
- * areas not owned by the VF.
- *
- * Fixed &xe_ggtt nodes used for tracking allocations:
- *
- *     |<------ balloon ------>|<- nodes->|<----------- balloon ----------->|
- *
- * Due to use of GPU profiles, we do not expect the old and new GGTT ares to
- * overlap; but our node shifting will fix addresses properly regardless.
- */
-
-/**
- * xe_tile_sriov_vf_fixup_ggtt_nodes - Shift GGTT allocations to match assigned range.
- * @tile: the &xe_tile struct instance
- * @shift: the shift value
- *
- * Since Global GTT is not virtualized, each VF has an assigned range
- * within the global space. This range might have changed during migration,
- * which requires all memory addresses pointing to GGTT to be shifted.
- */
-void xe_tile_sriov_vf_fixup_ggtt_nodes(struct xe_tile *tile, s64 shift)
-{
-	struct xe_ggtt *ggtt = tile->mem.ggtt;
-
-	mutex_lock(&ggtt->lock);
-
-	xe_tile_sriov_vf_deballoon_ggtt_locked(tile);
-	xe_ggtt_shift_nodes_locked(ggtt, shift);
-	xe_tile_sriov_vf_balloon_ggtt_locked(tile);
-
-	mutex_unlock(&ggtt->lock);
-}
diff --git a/drivers/gpu/drm/xe/xe_tile_sriov_vf.h b/drivers/gpu/drm/xe/xe_tile_sriov_vf.h
deleted file mode 100644
index 93eb043171e83..0000000000000
--- a/drivers/gpu/drm/xe/xe_tile_sriov_vf.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2025 Intel Corporation
- */
-
-#ifndef _XE_TILE_SRIOV_VF_H_
-#define _XE_TILE_SRIOV_VF_H_
-
-#include <linux/types.h>
-
-struct xe_tile;
-
-int xe_tile_sriov_vf_prepare_ggtt(struct xe_tile *tile);
-int xe_tile_sriov_vf_balloon_ggtt_locked(struct xe_tile *tile);
-void xe_tile_sriov_vf_deballoon_ggtt_locked(struct xe_tile *tile);
-void xe_tile_sriov_vf_fixup_ggtt_nodes(struct xe_tile *tile, s64 shift);
-
-#endif
-- 
2.51.0

[PATCH v4 5/6] drm/xe: Convert xe_fb_pin to use a callback for insertion into GGTT

[Maarten Lankhorst]

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

The rotation details belong in xe_fb_pin.c, while the operations involving
GGTT belong to xe_ggtt.c. As directly locking xe_ggtt etc results in
exposing all of xe_ggtt details anyway, create a special function that
allocates a ggtt_node, and allow display to populate it using a callback
as a compromise.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c | 111 ++++++++++++-------------
 drivers/gpu/drm/xe/xe_ggtt.c           |  92 ++++++++++++++------
 drivers/gpu/drm/xe/xe_ggtt.h           |   9 +-
 drivers/gpu/drm/xe/xe_ggtt_types.h     |   8 +-
 4 files changed, 132 insertions(+), 88 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 1fd4a815e784b..d2e4903de0977 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -171,12 +171,13 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 }
 
 static void
-write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo_ofs,
+write_ggtt_rotated(struct xe_ggtt *ggtt, u32 *ggtt_ofs,
+		   u64 pte_flags,
+		   xe_ggtt_set_pte_fn write_pte,
+		   struct xe_bo *bo, u32 bo_ofs,
 		   u32 width, u32 height, u32 src_stride, u32 dst_stride)
 {
-	struct xe_device *xe = xe_bo_device(bo);
 	u32 column, row;
-	u64 pte = ggtt->pt_ops->pte_encode_flags(bo, xe->pat.idx[XE_CACHE_NONE]);
 
 	for (column = 0; column < width; column++) {
 		u32 src_idx = src_stride * (height - 1) + column + bo_ofs;
@@ -184,7 +185,7 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo
 		for (row = 0; row < height; row++) {
 			u64 addr = xe_bo_addr(bo, src_idx * XE_PAGE_SIZE, XE_PAGE_SIZE);
 
-			ggtt->pt_ops->ggtt_set_pte(ggtt, *ggtt_ofs, pte | addr);
+			write_pte(ggtt, *ggtt_ofs, pte_flags | addr);
 			*ggtt_ofs += XE_PAGE_SIZE;
 			src_idx -= src_stride;
 		}
@@ -194,6 +195,28 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo
 	}
 }
 
+struct fb_rotate_args {
+	const struct i915_gtt_view *view;
+	struct xe_bo *bo;
+};
+
+static void write_ggtt_rotated_node(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
+				    u64 pte_flags, xe_ggtt_set_pte_fn write_pte, void *data)
+{
+	struct fb_rotate_args *args = data;
+	struct xe_bo *bo = args->bo;
+	const struct intel_rotation_info *rot_info = &args->view->rotated;
+	u32 ggtt_ofs = node->base.start;
+
+	for (u32 i = 0; i < ARRAY_SIZE(rot_info->plane); i++)
+		write_ggtt_rotated(ggtt, &ggtt_ofs, pte_flags, write_pte,
+				   bo, rot_info->plane[i].offset,
+				   rot_info->plane[i].width,
+				   rot_info->plane[i].height,
+				   rot_info->plane[i].src_stride,
+				   rot_info->plane[i].dst_stride);
+}
+
 static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb,
 				const struct i915_gtt_view *view,
 				struct i915_vma *vma,
@@ -204,70 +227,40 @@ static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb,
 	struct xe_device *xe = to_xe_device(fb->base.dev);
 	struct xe_tile *tile0 = xe_device_get_root_tile(xe);
 	struct xe_ggtt *ggtt = tile0->mem.ggtt;
+	u64 pte, size;
 	u32 align;
-	int ret;
-
-	/* TODO: Consider sharing framebuffer mapping?
-	 * embed i915_vma inside intel_framebuffer
-	 */
-	xe_pm_runtime_get_noresume(xe);
-	ret = mutex_lock_interruptible(&ggtt->lock);
-	if (ret)
-		goto out;
+	int ret = 0;
 
 	align = XE_PAGE_SIZE;
-	if (xe_bo_is_vram(bo) && ggtt->flags & XE_GGTT_FLAGS_64K)
-		align = max_t(u32, align, SZ_64K);
+	if (xe_bo_is_vram(bo) && xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K)
+		align = max(align, SZ_64K);
 
+	/* Fast case, preallocated GGTT view? */
 	if (bo->ggtt_node[tile0->id] && view->type == I915_GTT_VIEW_NORMAL) {
 		vma->node = bo->ggtt_node[tile0->id];
-	} else if (view->type == I915_GTT_VIEW_NORMAL) {
-		vma->node = xe_ggtt_node_init(ggtt);
-		if (IS_ERR(vma->node)) {
-			ret = PTR_ERR(vma->node);
-			goto out_unlock;
-		}
-
-		ret = xe_ggtt_node_insert_locked(vma->node, xe_bo_size(bo), align, 0);
-		if (ret) {
-			xe_ggtt_node_fini(vma->node);
-			goto out_unlock;
-		}
-
-		xe_ggtt_map_bo(ggtt, vma->node, bo, xe->pat.idx[XE_CACHE_NONE]);
-	} else {
-		u32 i, ggtt_ofs;
-		const struct intel_rotation_info *rot_info = &view->rotated;
-
-		/* display seems to use tiles instead of bytes here, so convert it back.. */
-		u32 size = intel_rotation_info_size(rot_info) * XE_PAGE_SIZE;
-
-		vma->node = xe_ggtt_node_init(ggtt);
-		if (IS_ERR(vma->node)) {
-			ret = PTR_ERR(vma->node);
-			goto out_unlock;
-		}
-
-		ret = xe_ggtt_node_insert_locked(vma->node, size, align, 0);
-		if (ret) {
-			xe_ggtt_node_fini(vma->node);
-			goto out_unlock;
-		}
+		return 0;
+	}
 
-		ggtt_ofs = vma->node->base.start;
+	/* TODO: Consider sharing framebuffer mapping?
+	 * embed i915_vma inside intel_framebuffer
+	 */
+	xe_pm_runtime_get_noresume(xe);
 
-		for (i = 0; i < ARRAY_SIZE(rot_info->plane); i++)
-			write_ggtt_rotated(bo, ggtt, &ggtt_ofs,
-					   rot_info->plane[i].offset,
-					   rot_info->plane[i].width,
-					   rot_info->plane[i].height,
-					   rot_info->plane[i].src_stride,
-					   rot_info->plane[i].dst_stride);
-	}
+	if (view->type == I915_GTT_VIEW_NORMAL)
+		size = xe_bo_size(bo);
+	else
+		/* display uses tiles instead of bytes here, so convert it back.. */
+		size = intel_rotation_info_size(&view->rotated) * XE_PAGE_SIZE;
+
+	pte = xe_ggtt_encode_pte_flags(ggtt, bo, xe->pat.idx[XE_CACHE_NONE]);
+	vma->node = xe_ggtt_node_insert_transform(ggtt, bo, pte,
+						  ALIGN(size, align), align,
+						  view->type == I915_GTT_VIEW_NORMAL ?
+						  NULL : write_ggtt_rotated_node,
+						  &(struct fb_rotate_args){view, bo});
+	if (IS_ERR(vma->node))
+		ret = PTR_ERR(vma->node);
 
-out_unlock:
-	mutex_unlock(&ggtt->lock);
-out:
 	xe_pm_runtime_put(xe);
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 3429e54a43eb5..e6412046a6489 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -490,19 +490,7 @@ void xe_ggtt_shift_nodes(struct xe_ggtt *ggtt, s64 shift)
 	mutex_unlock(&ggtt->lock);
 }
 
-/**
- * xe_ggtt_node_insert_locked - Locked version to insert a &xe_ggtt_node into the GGTT
- * @node: the &xe_ggtt_node to be inserted
- * @size: size of the node
- * @align: alignment constrain of the node
- * @mm_flags: flags to control the node behavior
- *
- * It cannot be called without first having called xe_ggtt_init() once.
- * To be used in cases where ggtt->lock is already taken.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
+static int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
 			       u32 size, u32 align, u32 mm_flags)
 {
 	return drm_mm_insert_node_generic(&node->ggtt->mm, &node->base, size, align, 0,
@@ -539,9 +527,13 @@ int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align)
  * @ggtt: the &xe_ggtt where the new node will later be inserted/reserved.
  *
  * This function will allocate the struct %xe_ggtt_node and return its pointer.
- * This struct will then be freed after the node removal upon xe_ggtt_node_remove().
- * Having %xe_ggtt_node struct allocated doesn't mean that the node is already allocated
- * in GGTT. Only xe_ggtt_node_insert() will ensure the node is inserted or reserved in GGTT.
+ * This struct will then be freed after the node removal upon
+ * xe_ggtt_node_remove().
+ *
+ * Having %xe_ggtt_node struct allocated doesn't mean that the node is already
+ * allocated in GGTT. Only xe_ggtt_node_insert() or allocation through
+ * xe_ggtt_node_insert_transform() will ensure the node is inserted or reserved
+ * in GGTT.
  *
  * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
  **/
@@ -590,13 +582,12 @@ bool xe_ggtt_node_allocated(const struct xe_ggtt_node *node)
  * @ggtt: the &xe_ggtt where node will be mapped
  * @node: the &xe_ggtt_node where this BO is mapped
  * @bo: the &xe_bo to be mapped
- * @pat_index: Which pat_index to use.
+ * @pte: The pte flags to append.
  */
-void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
-		    struct xe_bo *bo, u16 pat_index)
+static void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
+			   struct xe_bo *bo, u64 pte)
 {
-
-	u64 start, pte, end;
+	u64 start, end;
 	struct xe_res_cursor cur;
 
 	if (XE_WARN_ON(!node))
@@ -605,7 +596,6 @@ void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
 	start = node->base.start;
 	end = start + xe_bo_size(bo);
 
-	pte = ggtt->pt_ops->pte_encode_flags(bo, pat_index);
 	if (!xe_bo_is_vram(bo) && !xe_bo_is_stolen(bo)) {
 		xe_assert(xe_bo_device(bo), bo->ttm.ttm);
 
@@ -635,12 +625,65 @@ void xe_ggtt_map_bo_unlocked(struct xe_ggtt *ggtt, struct xe_bo *bo)
 {
 	u16 cache_mode = bo->flags & XE_BO_FLAG_NEEDS_UC ? XE_CACHE_NONE : XE_CACHE_WB;
 	u16 pat_index = tile_to_xe(ggtt->tile)->pat.idx[cache_mode];
+	u64 pte;
 
 	mutex_lock(&ggtt->lock);
-	xe_ggtt_map_bo(ggtt, bo->ggtt_node[ggtt->tile->id], bo, pat_index);
+	pte = ggtt->pt_ops->pte_encode_flags(bo, pat_index);
+	xe_ggtt_map_bo(ggtt, bo->ggtt_node[ggtt->tile->id], bo, pte);
 	mutex_unlock(&ggtt->lock);
 }
 
+/**
+ * xe_ggtt_node_insert_transform - Insert a newly allocated &xe_ggtt_node into the GGTT
+ * @ggtt: the &xe_ggtt where the node will inserted/reserved.
+ * @bo: The bo to be transformed
+ * @pte_flags: The extra GGTT flags to add to mapping.
+ * @size: size of the node
+ * @align: required alignment for node
+ * @transform: transformation function that will populate the GGTT node, or NULL for linear mapping.
+ * @arg: Extra argument to pass to the transformation function.
+ *
+ * This function allows inserting a GGTT node with a custom transformation function.
+ * This is useful for display to allow inserting rotated framebuffers to GGTT.
+ *
+ * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
+ */
+struct xe_ggtt_node *xe_ggtt_node_insert_transform(struct xe_ggtt *ggtt,
+						   struct xe_bo *bo, u64 pte_flags,
+						   u64 size, u32 align,
+						   xe_ggtt_transform_cb transform, void *arg)
+{
+	struct xe_ggtt_node *node;
+	int ret;
+
+	node = xe_ggtt_node_init(ggtt);
+	if (IS_ERR(node))
+		return ERR_CAST(node);
+
+	if (mutex_lock_interruptible(&ggtt->lock) < 0) {
+		ret = -ERESTARTSYS;
+		goto err;
+	}
+
+	ret = xe_ggtt_node_insert_locked(node, size, align, 0);
+	if (ret)
+		goto err_unlock;
+
+	if (transform)
+		transform(ggtt, node, pte_flags, ggtt->pt_ops->ggtt_set_pte, arg);
+	else
+		xe_ggtt_map_bo(ggtt, node, bo, pte_flags);
+
+	mutex_unlock(&ggtt->lock);
+	return node;
+
+err_unlock:
+	mutex_unlock(&ggtt->lock);
+err:
+	xe_ggtt_node_fini(node);
+	return ERR_PTR(ret);
+}
+
 static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 				  u64 start, u64 end, struct drm_exec *exec)
 {
@@ -679,8 +722,9 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 	} else {
 		u16 cache_mode = bo->flags & XE_BO_FLAG_NEEDS_UC ? XE_CACHE_NONE : XE_CACHE_WB;
 		u16 pat_index = tile_to_xe(ggtt->tile)->pat.idx[cache_mode];
+		u64 pte = ggtt->pt_ops->pte_encode_flags(bo, pat_index);
 
-		xe_ggtt_map_bo(ggtt, bo->ggtt_node[tile_id], bo, pat_index);
+		xe_ggtt_map_bo(ggtt, bo->ggtt_node[tile_id], bo, pte);
 	}
 	mutex_unlock(&ggtt->lock);
 
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index eccef2d2b3cee..fb518696c3280 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -24,12 +24,13 @@ u64 xe_ggtt_start(struct xe_ggtt *ggtt);
 u64 xe_ggtt_size(struct xe_ggtt *ggtt);
 
 int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align);
-int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
-			       u32 size, u32 align, u32 mm_flags);
+struct xe_ggtt_node *
+xe_ggtt_node_insert_transform(struct xe_ggtt *ggtt,
+			      struct xe_bo *bo, u64 pte,
+			      u64 size, u32 align,
+			      xe_ggtt_transform_cb transform, void *arg);
 void xe_ggtt_node_remove(struct xe_ggtt_node *node, bool invalidate);
 bool xe_ggtt_node_allocated(const struct xe_ggtt_node *node);
-void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
-		    struct xe_bo *bo, u16 pat_index);
 void xe_ggtt_map_bo_unlocked(struct xe_ggtt *ggtt, struct xe_bo *bo);
 int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo, struct drm_exec *exec);
 int xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index a27919302d6b2..f4aa5671cb3e3 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -71,6 +71,11 @@ struct xe_ggtt_node {
 	bool invalidate_on_remove;
 };
 
+typedef void (*xe_ggtt_set_pte_fn)(struct xe_ggtt *ggtt, u64 addr, u64 pte);
+typedef void (*xe_ggtt_transform_cb)(struct xe_ggtt *ggtt,
+				     struct xe_ggtt_node *node,
+				     u64 pte_flags,
+				     xe_ggtt_set_pte_fn set_pte, void *arg);
 /**
  * struct xe_ggtt_pt_ops - GGTT Page table operations
  * Which can vary from platform to platform.
@@ -78,8 +83,9 @@ struct xe_ggtt_node {
 struct xe_ggtt_pt_ops {
 	/** @pte_encode_flags: Encode PTE flags for a given BO */
 	u64 (*pte_encode_flags)(struct xe_bo *bo, u16 pat_index);
+
 	/** @ggtt_set_pte: Directly write into GGTT's PTE */
-	void (*ggtt_set_pte)(struct xe_ggtt *ggtt, u64 addr, u64 pte);
+	xe_ggtt_set_pte_fn ggtt_set_pte;
 };
 
 #endif
-- 
2.51.0

[PATCH v4 6/6] drm/xe: Move struct xe_ggtt to xe_ggtt.c

[Maarten Lankhorst]

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

No users left outside of xe_ggtt.c, so we can make the struct private.

This prevents us from accidentally touching it before init.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_ggtt.c       | 52 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_ggtt_types.h | 51 -----------------------------
 2 files changed, 52 insertions(+), 51 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index e6412046a6489..718abe0023b1d 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -67,6 +67,58 @@
  * give us the correct placement for free.
  */
 
+/**
+ * struct xe_ggtt_pt_ops - GGTT Page table operations
+ * Which can vary from platform to platform.
+ */
+struct xe_ggtt_pt_ops {
+	/** @pte_encode_flags: Encode PTE flags for a given BO */
+	u64 (*pte_encode_flags)(struct xe_bo *bo, u16 pat_index);
+
+	/** @ggtt_set_pte: Directly write into GGTT's PTE */
+	xe_ggtt_set_pte_fn ggtt_set_pte;
+};
+
+/**
+ * struct xe_ggtt - Main GGTT struct
+ *
+ * In general, each tile can contains its own Global Graphics Translation Table
+ * (GGTT) instance.
+ */
+struct xe_ggtt {
+	/** @tile: Back pointer to tile where this GGTT belongs */
+	struct xe_tile *tile;
+        /** @start: Start offset of GGTT */
+	u64 start;
+	/** @size: Total usable size of this GGTT */
+	u64 size;
+
+#define XE_GGTT_FLAGS_64K BIT(0)
+	/**
+	 * @flags: Flags for this GGTT
+	 * Acceptable flags:
+	 * - %XE_GGTT_FLAGS_64K - if PTE size is 64K. Otherwise, regular is 4K.
+	 */
+	unsigned int flags;
+	/** @scratch: Internal object allocation used as a scratch page */
+	struct xe_bo *scratch;
+	/** @lock: Mutex lock to protect GGTT data */
+	struct mutex lock;
+	/**
+	 *  @gsm: The iomem pointer to the actual location of the translation
+	 * table located in the GSM for easy PTE manipulation
+	 */
+	u64 __iomem *gsm;
+	/** @pt_ops: Page Table operations per platform */
+	const struct xe_ggtt_pt_ops *pt_ops;
+	/** @mm: The memory manager used to manage individual GGTT allocations */
+	struct drm_mm mm;
+	/** @access_count: counts GGTT writes */
+	unsigned int access_count;
+	/** @wq: Dedicated unordered work queue to process node removals */
+	struct workqueue_struct *wq;
+};
+
 static u64 xelp_ggtt_pte_flags(struct xe_bo *bo, u16 pat_index)
 {
 	u64 pte = XE_PAGE_PRESENT;
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index f4aa5671cb3e3..4f1fd3c456a3b 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -13,46 +13,6 @@
 struct xe_bo;
 struct xe_gt;
 
-/**
- * struct xe_ggtt - Main GGTT struct
- *
- * In general, each tile can contains its own Global Graphics Translation Table
- * (GGTT) instance.
- */
-struct xe_ggtt {
-	/** @tile: Back pointer to tile where this GGTT belongs */
-	struct xe_tile *tile;
-	/** @start: Start offset of GGTT */
-	u64 start;
-	/** @size: Total usable size of this GGTT */
-	u64 size;
-
-#define XE_GGTT_FLAGS_64K BIT(0)
-	/**
-	 * @flags: Flags for this GGTT
-	 * Acceptable flags:
-	 * - %XE_GGTT_FLAGS_64K - if PTE size is 64K. Otherwise, regular is 4K.
-	 */
-	unsigned int flags;
-	/** @scratch: Internal object allocation used as a scratch page */
-	struct xe_bo *scratch;
-	/** @lock: Mutex lock to protect GGTT data */
-	struct mutex lock;
-	/**
-	 *  @gsm: The iomem pointer to the actual location of the translation
-	 * table located in the GSM for easy PTE manipulation
-	 */
-	u64 __iomem *gsm;
-	/** @pt_ops: Page Table operations per platform */
-	const struct xe_ggtt_pt_ops *pt_ops;
-	/** @mm: The memory manager used to manage individual GGTT allocations */
-	struct drm_mm mm;
-	/** @access_count: counts GGTT writes */
-	unsigned int access_count;
-	/** @wq: Dedicated unordered work queue to process node removals */
-	struct workqueue_struct *wq;
-};
-
 /**
  * struct xe_ggtt_node - A node in GGTT.
  *
@@ -76,16 +36,5 @@ typedef void (*xe_ggtt_transform_cb)(struct xe_ggtt *ggtt,
 				     struct xe_ggtt_node *node,
 				     u64 pte_flags,
 				     xe_ggtt_set_pte_fn set_pte, void *arg);
-/**
- * struct xe_ggtt_pt_ops - GGTT Page table operations
- * Which can vary from platform to platform.
- */
-struct xe_ggtt_pt_ops {
-	/** @pte_encode_flags: Encode PTE flags for a given BO */
-	u64 (*pte_encode_flags)(struct xe_bo *bo, u16 pat_index);
-
-	/** @ggtt_set_pte: Directly write into GGTT's PTE */
-	xe_ggtt_set_pte_fn ggtt_set_pte;
-};
 
 #endif
-- 
2.51.0