[PATCH v6 00/12] drm/xe: Make all xe_ggtt structs private.

[PATCH v6 00/12] drm/xe: Make all xe_ggtt structs private.

[Maarten Lankhorst]

The previous approach iterated over the entire GGTT, but it's easier to hide
even the xe_ggtt_node struct and only provide a xe_ggtt_node_addr() function.

While cleaning up, also remove xe_ggtt_node_alloc()/fini(), this can be
handled in xe_ggtt_insert() instead as all the other users are already
internal.

This makes the final cleanup the removal of xe_ggtt_node_allocated(),
as it can be changed to a simple null check instead.

Maarten Lankhorst (12):
  drm/xe: Start using ggtt->start in preparation of balloon removal
  drm/xe: Convert xe_fb_pin to use a callback for insertion into GGTT
  drm/xe: Add xe_ggtt_node_addr() to avoid dereferencing xe_ggtt_node
  drm/xe/display: Avoid dereferencing xe_ggtt_node
  drm/xe: Do not dereference ggtt_node in xe_bo.c
  drm/xe: Improve xe_gt_sriov_pf_config GGTT handling
  drm/xe: Privatize xe_ggtt_node
  drm/xe: Make xe_ggtt_node offset relative to starting offset
  drm/xe: Rewrite GGTT VF initialisation
  drm/xe: Move struct xe_ggtt to xe_ggtt.c
  drm/xe: Make xe_ggtt_node_insert return a node
  drm/xe: Remove xe_ggtt_node_allocated

 .../gpu/drm/xe/compat-i915-headers/i915_vma.h |   4 +-
 drivers/gpu/drm/xe/display/xe_fb_pin.c        | 114 ++---
 drivers/gpu/drm/xe/display/xe_stolen.c        |   2 +-
 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c   |   8 +-
 drivers/gpu/drm/xe/xe_bo.c                    |   6 +-
 drivers/gpu/drm/xe/xe_bo.h                    |   8 +-
 drivers/gpu/drm/xe/xe_device_types.h          |   2 -
 drivers/gpu/drm/xe/xe_ggtt.c                  | 476 +++++++++---------
 drivers/gpu/drm/xe/xe_ggtt.h                  |  27 +-
 drivers/gpu/drm/xe/xe_ggtt_types.h            |  78 +--
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c    |  53 +-
 .../gpu/drm/xe/xe_gt_sriov_pf_config_types.h  |   8 +-
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c           |   5 +-
 drivers/gpu/drm/xe/xe_tile.c                  |  18 +
 drivers/gpu/drm/xe/xe_tile_sriov_vf.c         | 197 +-------
 drivers/gpu/drm/xe/xe_tile_sriov_vf.h         |   4 +-
 drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h   |   4 +
 17 files changed, 402 insertions(+), 612 deletions(-)

-- 
2.51.0

[PATCH v6 01/12] 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/xe_ggtt.c               | 82 ++++++++++++++--------
 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 +-
 4 files changed, 59 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index aca7ae5489b91..9480b4c2320c0 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -124,10 +124,32 @@ static void ggtt_update_access_counter(struct xe_ggtt *ggtt)
 	}
 }
 
+/**
+ * xe_ggtt_start - Get starting offset of GGTT.
+ * @ggtt: &xe_ggtt
+ *
+ * Returns: Starting offset for this &xe_ggtt.
+ */
+u64 xe_ggtt_start(struct xe_ggtt *ggtt)
+{
+	return ggtt->start;
+}
+
+/**
+ * xe_ggtt_size - Get size of GGTT.
+ * @ggtt: &xe_ggtt
+ *
+ * Returns: Total usable size of this &xe_ggtt.
+ */
+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]);
 }
@@ -232,16 +254,16 @@ 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, size);
 }
 
-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);
@@ -269,26 +291,32 @@ 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 &&
@@ -299,7 +327,7 @@ 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)
@@ -537,11 +565,9 @@ 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);
 }
 
 /**
@@ -850,14 +876,12 @@ 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)
@@ -950,15 +974,13 @@ 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 v6 02/12] drm/xe: Convert xe_fb_pin to use a callback for insertion into GGTT

[Maarten Lankhorst]

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           |  90 ++++++++++++++------
 drivers/gpu/drm/xe/xe_ggtt.h           |   9 +-
 drivers/gpu/drm/xe/xe_ggtt_types.h     |   8 +-
 4 files changed, 130 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 9480b4c2320c0..60019ef508696 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -610,19 +610,7 @@ void xe_ggtt_shift_nodes_locked(struct xe_ggtt *ggtt, s64 shift)
 	}
 }
 
-/**
- * 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,
@@ -661,9 +649,11 @@ int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align)
  * 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().
- * 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.
+ *
+ * Having %xe_ggtt_node struct allocated doesn't mean that the node is already
+ * allocated in GGTT. Only xe_ggtt_node_insert(), allocation through
+ * xe_ggtt_node_insert_transform(), or xe_ggtt_node_insert_balloon_locked() will ensure the node is inserted or reserved
+ * in GGTT.
  *
  * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
  **/
@@ -712,13 +702,12 @@ 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))
@@ -727,7 +716,6 @@ 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);
 
@@ -757,10 +745,63 @@ 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,
@@ -801,8 +842,9 @@ 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 6482bddb2ef36..d54a2ae2b4aa8 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -27,12 +27,13 @@ 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 v6 03/12] drm/xe: Add xe_ggtt_node_addr() to avoid dereferencing xe_ggtt_node

[Maarten Lankhorst]

This function makes it possible to add an offset that is applied to
all xe_ggtt_node's, and hides the internals from all its users.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_bo.h   |  8 +++++---
 drivers/gpu/drm/xe/xe_ggtt.c | 11 +++++++++++
 drivers/gpu/drm/xe/xe_ggtt.h |  2 ++
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 353d607d301da..dd67a6f40a16d 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -9,6 +9,7 @@
 #include <drm/ttm/ttm_tt.h>
 
 #include "xe_bo_types.h"
+#include "xe_ggtt.h"
 #include "xe_macros.h"
 #include "xe_validation.h"
 #include "xe_vm_types.h"
@@ -251,13 +252,14 @@ static inline u32
 __xe_bo_ggtt_addr(struct xe_bo *bo, u8 tile_id)
 {
 	struct xe_ggtt_node *ggtt_node = bo->ggtt_node[tile_id];
+	u64 offset;
 
 	if (XE_WARN_ON(!ggtt_node))
 		return 0;
 
-	XE_WARN_ON(ggtt_node->base.size > xe_bo_size(bo));
-	XE_WARN_ON(ggtt_node->base.start + ggtt_node->base.size > (1ull << 32));
-	return ggtt_node->base.start;
+	offset = xe_ggtt_node_addr(ggtt_node);
+	XE_WARN_ON(offset + xe_bo_size(bo) > (1ull << 32));
+	return offset;
 }
 
 static inline u32
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 60019ef508696..ea7ebaad891be 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -1066,3 +1066,14 @@ u64 xe_ggtt_read_pte(struct xe_ggtt *ggtt, u64 offset)
 {
 	return ioread64(ggtt->gsm + (offset / XE_PAGE_SIZE));
 }
+
+/**
+ * xe_ggtt_node_addr - Get @node offset in GGTT.
+ * @node: &xe_ggtt_node
+ *
+ * Get the GGTT offset for allocated node.
+ */
+u64 xe_ggtt_node_addr(const struct xe_ggtt_node *node)
+{
+	return node->base.start;
+}
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index d54a2ae2b4aa8..4a8ef1b824156 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -58,4 +58,6 @@ void xe_ggtt_might_lock(struct xe_ggtt *ggtt);
 u64 xe_ggtt_encode_pte_flags(struct xe_ggtt *ggtt, struct xe_bo *bo, u16 pat_index);
 u64 xe_ggtt_read_pte(struct xe_ggtt *ggtt, u64 offset);
 
+u64 xe_ggtt_node_addr(const struct xe_ggtt_node *node);
+
 #endif
-- 
2.51.0

[PATCH v6 04/12] drm/xe/display: Avoid dereferencing xe_ggtt_node

[Maarten Lankhorst]

Start using xe_ggtt_node_addr, and avoid comparing the base offset
as vma->node is dynamically allocated.

Also sneak in a xe_bo_size() for stolen, too small to put as separate commit.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h | 4 ++--
 drivers/gpu/drm/xe/display/xe_fb_pin.c            | 4 ++--
 drivers/gpu/drm/xe/display/xe_stolen.c            | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h
index 4465c40f81341..1c599963169a0 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h
@@ -8,7 +8,7 @@
 
 #include <uapi/drm/i915_drm.h>
 
-#include "xe_ggtt_types.h"
+#include "xe_ggtt.h"
 
 #include <linux/refcount.h>
 
@@ -32,7 +32,7 @@ struct i915_vma {
 
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
-	return vma->node->base.start;
+	return xe_ggtt_node_addr(vma->node);
 }
 
 #endif
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index d2e4903de0977..784d2db5fd0db 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -206,7 +206,7 @@ static void write_ggtt_rotated_node(struct xe_ggtt *ggtt, struct xe_ggtt_node *n
 	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;
+	u32 ggtt_ofs = xe_ggtt_node_addr(node);
 
 	for (u32 i = 0; i < ARRAY_SIZE(rot_info->plane); i++)
 		write_ggtt_rotated(ggtt, &ggtt_ofs, pte_flags, write_pte,
@@ -351,7 +351,7 @@ static void __xe_unpin_fb_vma(struct i915_vma *vma)
 	if (vma->dpt)
 		xe_bo_unpin_map_no_vm(vma->dpt);
 	else if (!xe_ggtt_node_allocated(vma->bo->ggtt_node[tile_id]) ||
-		 vma->bo->ggtt_node[tile_id]->base.start != vma->node->base.start)
+		 vma->bo->ggtt_node[tile_id] != vma->node)
 		xe_ggtt_node_remove(vma->node, false);
 
 	ttm_bo_reserve(&vma->bo->ttm, false, false, NULL);
diff --git a/drivers/gpu/drm/xe/display/xe_stolen.c b/drivers/gpu/drm/xe/display/xe_stolen.c
index 9f04ba36e930b..ef5ef5aa8d847 100644
--- a/drivers/gpu/drm/xe/display/xe_stolen.c
+++ b/drivers/gpu/drm/xe/display/xe_stolen.c
@@ -100,7 +100,7 @@ u64 i915_gem_stolen_node_address(struct intel_stolen_node *node)
 
 u64 i915_gem_stolen_node_size(const struct intel_stolen_node *node)
 {
-	return node->bo->ttm.base.size;
+	return xe_bo_size(node->bo);
 }
 
 struct intel_stolen_node *i915_gem_stolen_node_alloc(struct drm_device *drm)
-- 
2.51.0

[PATCH v6 05/12] drm/xe: Do not dereference ggtt_node in xe_bo.c

[Maarten Lankhorst]

A careful inspection of __xe_ggtt_insert_bo_at() shows that
the ggtt_node can always be seen as inserted from xe_bo.c
due to the way error handling is performed.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_bo.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 7b65020818738..c895214a7a570 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1700,7 +1700,7 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
 	xe_assert(xe, list_empty(&ttm_bo->base.gpuva.list));
 
 	for_each_tile(tile, xe, id)
-		if (bo->ggtt_node[id] && bo->ggtt_node[id]->base.size)
+		if (bo->ggtt_node[id])
 			xe_ggtt_remove_bo(tile->mem.ggtt, bo);
 
 #ifdef CONFIG_PROC_FS
@@ -3581,8 +3581,8 @@ void xe_bo_put(struct xe_bo *bo)
 			might_lock(&bo->client->bos_lock);
 #endif
 		for_each_tile(tile, xe_bo_device(bo), id)
-			if (bo->ggtt_node[id] && bo->ggtt_node[id]->ggtt)
-				xe_ggtt_might_lock(bo->ggtt_node[id]->ggtt);
+			if (bo->ggtt_node[id])
+				xe_ggtt_might_lock(tile->mem.ggtt);
 		drm_gem_object_put(&bo->ttm.base);
 	}
 }
-- 
2.51.0

[PATCH v6 06/12] drm/xe: Improve xe_gt_sriov_pf_config GGTT handling

[Maarten Lankhorst]

Do not directly dereference xe_ggtt_node, and add
a member to store the GGTT size.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c       | 15 ++++++++-------
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h |  8 ++++++--
 2 files changed, 14 insertions(+), 9 deletions(-)

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 2289756761636..c0dfffd5c553b 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -264,7 +264,7 @@ static u32 encode_config_ggtt(u32 *cfg, const struct xe_gt_sriov_config *config,
 	if (!xe_ggtt_node_allocated(node))
 		return 0;
 
-	return encode_ggtt(cfg, node->base.start, node->base.size, details);
+	return encode_ggtt(cfg, xe_ggtt_node_addr(node), config->ggtt_size, details);
 }
 
 /* Return: number of configuration dwords written */
@@ -495,13 +495,14 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 
 	xe_ggtt_assign(node, vfid);
 	xe_gt_sriov_dbg_verbose(gt, "VF%u assigned GGTT %llx-%llx\n",
-				vfid, node->base.start, node->base.start + node->base.size - 1);
+				vfid, xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + size - 1);
 
-	err = pf_distribute_config_ggtt(gt->tile, vfid, node->base.start, node->base.size);
+	err = pf_distribute_config_ggtt(gt->tile, vfid, xe_ggtt_node_addr(node), size);
 	if (unlikely(err))
 		goto err;
 
 	config->ggtt_region = node;
+	config->ggtt_size = size;
 	return 0;
 err:
 	pf_release_ggtt(tile, node);
@@ -514,7 +515,7 @@ static u64 pf_get_vf_config_ggtt(struct xe_gt *gt, unsigned int vfid)
 	struct xe_ggtt_node *node = config->ggtt_region;
 
 	xe_gt_assert(gt, xe_gt_is_main_type(gt));
-	return xe_ggtt_node_allocated(node) ? node->base.size : 0;
+	return xe_ggtt_node_allocated(node) ? config->ggtt_size : 0;
 }
 
 /**
@@ -2516,11 +2517,11 @@ int xe_gt_sriov_pf_config_print_ggtt(struct xe_gt *gt, struct drm_printer *p)
 		if (!xe_ggtt_node_allocated(config->ggtt_region))
 			continue;
 
-		string_get_size(config->ggtt_region->base.size, 1, STRING_UNITS_2,
+		string_get_size(config->ggtt_size, 1, STRING_UNITS_2,
 				buf, sizeof(buf));
 		drm_printf(p, "VF%u:\t%#0llx-%#llx\t(%s)\n",
-			   n, config->ggtt_region->base.start,
-			   config->ggtt_region->base.start + config->ggtt_region->base.size - 1,
+			   n, xe_ggtt_node_addr(config->ggtt_region),
+			   xe_ggtt_node_addr(config->ggtt_region) + config->ggtt_size - 1,
 			   buf);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
index 686c7b3b6d7a5..9a8e66c8b539f 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
@@ -17,10 +17,14 @@ struct xe_bo;
  * Used by the PF driver to maintain per-VF provisioning data.
  */
 struct xe_gt_sriov_config {
-	/** @ggtt_region: GGTT region assigned to the VF. */
-	struct xe_ggtt_node *ggtt_region;
 	/** @lmem_obj: LMEM allocation for use by the VF. */
 	struct xe_bo *lmem_obj;
+
+	/** @ggtt_region: GGTT region assigned to the VF. */
+	struct xe_ggtt_node *ggtt_region;
+	/** @ggtt_size: Size of GGTT region */
+	u64 ggtt_size;
+
 	/** @num_ctxs: number of GuC contexts IDs.  */
 	u16 num_ctxs;
 	/** @begin_ctx: start index of GuC context ID range. */
-- 
2.51.0

[PATCH v6 07/12] drm/xe: Privatize xe_ggtt_node

[Maarten Lankhorst]

Nothing requires it any more, make the member private.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_ggtt.c       | 18 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_ggtt_types.h | 19 +------------------
 2 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index ea7ebaad891be..d73ed0103f50f 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -34,6 +34,24 @@
 #include "xe_wa.h"
 #include "xe_wopcm.h"
 
+/**
+ * struct xe_ggtt_node - A node in GGTT.
+ *
+ * This struct needs to be initialized (only-once) with xe_ggtt_node_init() before any node
+ * insertion, reservation, or 'ballooning'.
+ * It will, then, be finalized by either xe_ggtt_node_remove() or xe_ggtt_node_deballoon().
+ */
+struct xe_ggtt_node {
+	/** @ggtt: Back pointer to xe_ggtt where this region will be inserted at */
+	struct xe_ggtt *ggtt;
+	/** @base: A drm_mm_node */
+	struct drm_mm_node base;
+	/** @delayed_removal_work: The work struct for the delayed removal */
+	struct work_struct delayed_removal_work;
+	/** @invalidate_on_remove: If it needs invalidation upon removal */
+	bool invalidate_on_remove;
+};
+
 /**
  * DOC: Global Graphics Translation Table (GGTT)
  *
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index f4aa5671cb3e3..31054e00daa6b 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -11,6 +11,7 @@
 #include "xe_pt_types.h"
 
 struct xe_bo;
+struct xe_ggtt_node;
 struct xe_gt;
 
 /**
@@ -53,24 +54,6 @@ struct xe_ggtt {
 	struct workqueue_struct *wq;
 };
 
-/**
- * struct xe_ggtt_node - A node in GGTT.
- *
- * This struct needs to be initialized (only-once) with xe_ggtt_node_init() before any node
- * insertion, reservation, or 'ballooning'.
- * It will, then, be finalized by either xe_ggtt_node_remove() or xe_ggtt_node_deballoon().
- */
-struct xe_ggtt_node {
-	/** @ggtt: Back pointer to xe_ggtt where this region will be inserted at */
-	struct xe_ggtt *ggtt;
-	/** @base: A drm_mm_node */
-	struct drm_mm_node base;
-	/** @delayed_removal_work: The work struct for the delayed removal */
-	struct work_struct delayed_removal_work;
-	/** @invalidate_on_remove: If it needs invalidation upon removal */
-	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,
-- 
2.51.0

[PATCH v6 08/12] drm/xe: Make xe_ggtt_node offset relative to starting offset

[Maarten Lankhorst]

This will make node shifting in the next commit a one-liner.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_ggtt.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index d73ed0103f50f..97ab38392c711 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -276,7 +276,7 @@ static void __xe_ggtt_init_early(struct xe_ggtt *ggtt, u64 start, u64 size)
 {
 	ggtt->start = start;
 	ggtt->size = size;
-	drm_mm_init(&ggtt->mm, start, size);
+	drm_mm_init(&ggtt->mm, 0, size - start);
 }
 
 int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 start, u32 size)
@@ -375,7 +375,7 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt)
 	/* Display may have allocated inside ggtt, so be careful with clearing here */
 	mutex_lock(&ggtt->lock);
 	drm_mm_for_each_hole(hole, &ggtt->mm, start, end)
-		xe_ggtt_clear(ggtt, start, end - start);
+		xe_ggtt_clear(ggtt, ggtt->start + start, end - start);
 
 	xe_ggtt_invalidate(ggtt);
 	mutex_unlock(&ggtt->lock);
@@ -392,7 +392,7 @@ static void ggtt_node_remove(struct xe_ggtt_node *node)
 
 	mutex_lock(&ggtt->lock);
 	if (bound)
-		xe_ggtt_clear(ggtt, node->base.start, node->base.size);
+		xe_ggtt_clear(ggtt, xe_ggtt_node_addr(node), node->base.size);
 	drm_mm_remove_node(&node->base);
 	node->base.size = 0;
 	mutex_unlock(&ggtt->lock);
@@ -548,13 +548,13 @@ int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node, u64 start, u64
 	lockdep_assert_held(&ggtt->lock);
 
 	node->base.color = 0;
-	node->base.start = start;
+	node->base.start = start - ggtt->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)))
+			 xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + node->base.size, ERR_PTR(err)))
 		return err;
 
 	xe_ggtt_dump_node(ggtt, &node->base, "balloon");
@@ -731,7 +731,7 @@ static void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
 	if (XE_WARN_ON(!node))
 		return;
 
-	start = node->base.start;
+	start = xe_ggtt_node_addr(node);
 	end = start + xe_bo_size(bo);
 
 	if (!xe_bo_is_vram(bo) && !xe_bo_is_stolen(bo)) {
@@ -852,6 +852,13 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 	}
 
 	mutex_lock(&ggtt->lock);
+	if (start >= ggtt->start)
+		start -= ggtt->start;
+	else
+		start = 0;
+
+	end -= ggtt->start;
+
 	err = drm_mm_insert_node_in_range(&ggtt->mm, &bo->ggtt_node[tile_id]->base,
 					  xe_bo_size(bo), alignment, 0, start, end, 0);
 	if (err) {
@@ -1093,5 +1100,5 @@ u64 xe_ggtt_read_pte(struct xe_ggtt *ggtt, u64 offset)
  */
 u64 xe_ggtt_node_addr(const struct xe_ggtt_node *node)
 {
-	return node->base.start;
+	return node->base.start + READ_ONCE(node->ggtt->start);
 }
-- 
2.51.0

[PATCH v6 09/12] 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 readjust ggtt->start to have GGTT at the new offset.

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>
Co-developed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c |   2 +-
 drivers/gpu/drm/xe/xe_device_types.h        |   2 -
 drivers/gpu/drm/xe/xe_ggtt.c                | 158 +++-------------
 drivers/gpu/drm/xe/xe_ggtt.h                |   5 +-
 drivers/gpu/drm/xe/xe_ggtt_types.h          |   1 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c         |   5 +-
 drivers/gpu/drm/xe/xe_tile.c                |  18 ++
 drivers/gpu/drm/xe/xe_tile_sriov_vf.c       | 197 ++------------------
 drivers/gpu/drm/xe/xe_tile_sriov_vf.h       |   4 +-
 drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h |   4 +
 10 files changed, 71 insertions(+), 325 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_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 02c04ad7296e4..a05164cc669f9 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -192,8 +192,6 @@ struct xe_tile {
 			struct xe_lmtt lmtt;
 		} pf;
 		struct {
-			/** @sriov.vf.ggtt_balloon: GGTT regions excluded from use. */
-			struct xe_ggtt_node *ggtt_balloon[2];
 			/** @sriov.vf.self_config: VF configuration data */
 			struct xe_tile_sriov_vf_selfconfig self_config;
 		} vf;
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 97ab38392c711..89d06ee515a19 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -38,8 +38,8 @@
  * struct xe_ggtt_node - A node in GGTT.
  *
  * This struct needs to be initialized (only-once) with xe_ggtt_node_init() before any node
- * insertion, reservation, or 'ballooning'.
- * It will, then, be finalized by either xe_ggtt_node_remove() or xe_ggtt_node_deballoon().
+ * insertion or reservation.
+ * It will, then, be finalized by either xe_ggtt_node_remove().
  */
 struct xe_ggtt_node {
 	/** @ggtt: Back pointer to xe_ggtt where this region will be inserted at */
@@ -324,9 +324,15 @@ 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_tile_sriov_vf_ggtt_base(ggtt->tile);
+		ggtt_size = xe_tile_sriov_vf_ggtt(ggtt->tile);
+
+		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;
@@ -351,17 +357,7 @@ 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)
-			return err;
-	}
-
-	return 0;
+	return devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt);
 }
 ALLOW_ERROR_INJECTION(xe_ggtt_init_early, ERRNO); /* See xe_pci_probe() */
 
@@ -513,119 +509,29 @@ 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 - ggtt->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",
-			 xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + 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
  *
- * This function moves all nodes from the GGTT VM, to a temp list. These nodes are expected
- * to represent allocations in range formerly assigned to current VF, before the range changed.
- * When the GGTT VM is completely clear of any nodes, they are re-added with shifted offsets.
- *
- * The function has no ability of failing - because it shifts existing nodes, without
- * any additional processing. If the nodes were successfully existing at the old address,
- * they will do the same at the new one. A fail inside this function would indicate that
- * 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.
+ * Adjust the base offset of the GGTT.
  */
-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);
+	if (!ggtt->size) {
+		xe_tile_err(ggtt->tile, "Asked to resize before xe_ggtt_init_early()?\n");
+		return;
+	}
 
-	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);
+	guard(mutex)(&ggtt->lock);
 
-	drm_mm_for_each_node_safe(node, tmpn, &ggtt->mm) {
-		drm_mm_remove_node(node);
-		list_add(&node->node_list, &temp_list_head);
-	}
+	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);
 
-	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));
-	}
+	WRITE_ONCE(ggtt->start, new_start);
 }
 
 static int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
@@ -666,12 +572,8 @@ int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align)
  *
  * 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().
- *
- * Having %xe_ggtt_node struct allocated doesn't mean that the node is already
- * allocated in GGTT. Only xe_ggtt_node_insert(), allocation through
- * xe_ggtt_node_insert_transform(), or xe_ggtt_node_insert_balloon_locked() will ensure the node is inserted or reserved
- * in GGTT.
+ * 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.
  *
  * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
  **/
@@ -692,9 +594,9 @@ 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 4a8ef1b824156..dd321261bd599 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_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index 31054e00daa6b..2058082234591 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -59,6 +59,7 @@ 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.
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 46518e629ba36..dd3cd7f140cd1 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -442,7 +442,6 @@ u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt)
 static int vf_get_ggtt_info(struct xe_gt *gt)
 {
 	struct xe_tile *tile = gt_to_tile(gt);
-	struct xe_ggtt *ggtt = tile->mem.ggtt;
 	struct xe_guc *guc = &gt->uc.guc;
 	u64 start, size, ggtt_size;
 	s64 shift;
@@ -450,7 +449,7 @@ static int vf_get_ggtt_info(struct xe_gt *gt)
 
 	xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
 
-	guard(mutex)(&ggtt->lock);
+	guard(mutex)(&tile->sriov.vf.self_config.ggtt_move_mutex);
 
 	err = guc_action_query_single_klv64(guc, GUC_KLV_VF_CFG_GGTT_START_KEY, &start);
 	if (unlikely(err))
@@ -480,7 +479,7 @@ static int vf_get_ggtt_info(struct xe_gt *gt)
 	if (shift && shift != start) {
 		xe_gt_sriov_info(gt, "Shifting GGTT base by %lld to 0x%016llx\n",
 				 shift, start);
-		xe_tile_sriov_vf_fixup_ggtt_nodes_locked(gt_to_tile(gt), shift);
+		xe_ggtt_shift_nodes(tile->mem.ggtt, shift);
 	}
 
 	if (xe_sriov_vf_migration_supported(gt_to_xe(gt))) {
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 8fd6ee990d14f..d43202291779e 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -17,6 +17,7 @@
 #include "xe_sa.h"
 #include "xe_svm.h"
 #include "xe_tile.h"
+#include "xe_tile_sriov_vf.h"
 #include "xe_tile_sysfs.h"
 #include "xe_ttm_vram_mgr.h"
 #include "xe_vram.h"
@@ -157,6 +158,12 @@ int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id)
 	if (err)
 		return err;
 
+	if (IS_SRIOV_VF(xe)) {
+		err = xe_tile_sriov_vf_init(tile);
+		if (err)
+			return err;
+	}
+
 	tile->primary_gt = xe_gt_alloc(tile);
 	if (IS_ERR(tile->primary_gt))
 		return PTR_ERR(tile->primary_gt);
@@ -201,6 +208,17 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
 	return xe_tile_sysfs_init(tile);
 }
 
+/**
+ * xe_tile_init - Initialize the remainder of the tile.
+ * @tile: The tile to initialize.
+ *
+ * This function is used for all tile initialization calls that may allocate memory.
+ *
+ * Note that since this is tile initialization, it should not perform any
+ * GT-specific operations, and thus does not need to hold GT forcewake.
+ *
+ * Returns: 0 on success, negative error code on error.
+ */
 int xe_tile_init(struct xe_tile *tile)
 {
 	int err;
diff --git a/drivers/gpu/drm/xe/xe_tile_sriov_vf.c b/drivers/gpu/drm/xe/xe_tile_sriov_vf.c
index c9bac2cfdd044..d1fa46e268350 100644
--- a/drivers/gpu/drm/xe/xe_tile_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_tile_sriov_vf.c
@@ -14,173 +14,12 @@
 #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.
- */
-static int xe_tile_sriov_vf_balloon_ggtt_locked(struct xe_tile *tile)
-{
-	u64 ggtt_base = tile->sriov.vf.self_config.ggtt_base;
-	u64 ggtt_size = tile->sriov.vf.self_config.ggtt_size;
-	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:
@@ -198,10 +37,6 @@ int xe_tile_sriov_vf_prepare_ggtt(struct xe_tile *tile)
  *
  *  |<------- 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.
@@ -219,35 +54,27 @@ int xe_tile_sriov_vf_prepare_ggtt(struct xe_tile *tile)
  * 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:
+ * have to be shifted, and the start offset for GGTT adjusted.
  *
- *     |<------ balloon ------>|<- nodes->|<----------- balloon ----------->|
- *
- * Due to use of GPU profiles, we do not expect the old and new GGTT ares to
+ * Due to use of GPU profiles, we do not expect the old and new GGTT areas to
  * overlap; but our node shifting will fix addresses properly regardless.
  */
 
 /**
- * xe_tile_sriov_vf_fixup_ggtt_nodes_locked - Shift GGTT allocations to match assigned range.
- * @tile: the &xe_tile struct instance
- * @shift: the shift value
+ * xe_tile_sriov_vf_init - Init tile specific GGTT configuration.
+ * @tile: the &xe_tile
  *
- * 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.
+ * This function is for VF use only.
+ *
+ * Return: 0 on success, negative value on error.
  */
-void xe_tile_sriov_vf_fixup_ggtt_nodes_locked(struct xe_tile *tile, s64 shift)
+int xe_tile_sriov_vf_init(struct xe_tile *tile)
 {
-	struct xe_ggtt *ggtt = tile->mem.ggtt;
+	struct xe_tile_sriov_vf_selfconfig *config = &tile->sriov.vf.self_config;
 
-	lockdep_assert_held(&ggtt->lock);
+	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
 
-	xe_tile_sriov_vf_deballoon_ggtt_locked(tile);
-	xe_ggtt_shift_nodes_locked(ggtt, shift);
-	xe_tile_sriov_vf_balloon_ggtt_locked(tile);
+	return drmm_mutex_init(&tile->xe->drm, &config->ggtt_move_mutex);
 }
 
 /**
@@ -312,6 +139,7 @@ void xe_tile_sriov_vf_ggtt_store(struct xe_tile *tile, u64 ggtt_size)
 	struct xe_tile_sriov_vf_selfconfig *config = &tile->sriov.vf.self_config;
 
 	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
+	lockdep_assert_held(&config->ggtt_move_mutex);
 
 	config->ggtt_size = ggtt_size;
 }
@@ -345,6 +173,7 @@ void xe_tile_sriov_vf_ggtt_base_store(struct xe_tile *tile, u64 ggtt_base)
 	struct xe_tile_sriov_vf_selfconfig *config = &tile->sriov.vf.self_config;
 
 	xe_tile_assert(tile, IS_SRIOV_VF(tile_to_xe(tile)));
+	lockdep_assert_held(&config->ggtt_move_mutex);
 
 	config->ggtt_base = ggtt_base;
 }
diff --git a/drivers/gpu/drm/xe/xe_tile_sriov_vf.h b/drivers/gpu/drm/xe/xe_tile_sriov_vf.h
index 749f41504883c..1ca5bc87963f0 100644
--- a/drivers/gpu/drm/xe/xe_tile_sriov_vf.h
+++ b/drivers/gpu/drm/xe/xe_tile_sriov_vf.h
@@ -10,9 +10,7 @@
 
 struct xe_tile;
 
-int xe_tile_sriov_vf_prepare_ggtt(struct xe_tile *tile);
-void xe_tile_sriov_vf_deballoon_ggtt_locked(struct xe_tile *tile);
-void xe_tile_sriov_vf_fixup_ggtt_nodes_locked(struct xe_tile *tile, s64 shift);
+int xe_tile_sriov_vf_init(struct xe_tile *tile);
 u64 xe_tile_sriov_vf_ggtt(struct xe_tile *tile);
 void xe_tile_sriov_vf_ggtt_store(struct xe_tile *tile, u64 ggtt_size);
 u64 xe_tile_sriov_vf_ggtt_base(struct xe_tile *tile);
diff --git a/drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h
index 4807ca51614cf..2cbbc51c101d4 100644
--- a/drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h
+++ b/drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h
@@ -7,11 +7,15 @@
 #define _XE_TILE_SRIOV_VF_TYPES_H_
 
 #include <linux/types.h>
+#include <linux/mutex.h>
 
 /**
  * struct xe_tile_sriov_vf_selfconfig - VF configuration data.
  */
 struct xe_tile_sriov_vf_selfconfig {
+	/** @ggtt_move_mutex: Prevents multiple movements from happening in parallel */
+	struct mutex ggtt_move_mutex;
+
 	/** @ggtt_base: assigned base offset of the GGTT region. */
 	u64 ggtt_base;
 	/** @ggtt_size: assigned size of the GGTT region. */
-- 
2.51.0

[PATCH v6 10/12] 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.h       |  1 +
 drivers/gpu/drm/xe/xe_ggtt_types.h | 58 ++----------------------------
 3 files changed, 55 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 89d06ee515a19..6b1684162400a 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -85,6 +85,58 @@ struct xe_ggtt_node {
  * 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.h b/drivers/gpu/drm/xe/xe_ggtt.h
index dd321261bd599..9f97f63496bcb 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -9,6 +9,7 @@
 #include "xe_ggtt_types.h"
 
 struct drm_printer;
+struct xe_bo;
 struct xe_tile;
 struct drm_exec;
 
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index 2058082234591..cf754e4d502ad 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -6,53 +6,11 @@
 #ifndef _XE_GGTT_TYPES_H_
 #define _XE_GGTT_TYPES_H_
 
+#include <linux/types.h>
 #include <drm/drm_mm.h>
 
-#include "xe_pt_types.h"
-
-struct xe_bo;
+struct xe_ggtt;
 struct xe_ggtt_node;
-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;
-};
 
 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,
@@ -60,16 +18,4 @@ typedef void (*xe_ggtt_transform_cb)(struct xe_ggtt *ggtt,
 				     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

[PATCH v6 11/12] drm/xe: Make xe_ggtt_node_insert return a node

[Maarten Lankhorst]

This extra step is easier to handle inside xe_ggtt.c and makes
xe_ggtt_node_allocated a simple null check instead, as the intermediate
state 'allocated but not inserted' is no longer used.

Privatize xe_ggtt_node_fini() as it's no longer used outside of
xe_ggtt.c

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c |  6 +-
 drivers/gpu/drm/xe/xe_ggtt.c                | 76 +++++++++------------
 drivers/gpu/drm/xe/xe_ggtt.h                |  5 +-
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c  | 24 +------
 4 files changed, 38 insertions(+), 73 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 acddbedcf17cb..7aeee6680d78c 100644
--- a/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
+++ b/drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
@@ -38,12 +38,8 @@ static struct xe_bo *replacement_xe_managed_bo_create_pin_map(struct xe_device *
 	if (flags & XE_BO_FLAG_GGTT) {
 		struct xe_ggtt *ggtt = tile->mem.ggtt;
 
-		bo->ggtt_node[tile->id] = xe_ggtt_node_init(ggtt);
+		bo->ggtt_node[tile->id] = xe_ggtt_node_insert(ggtt, xe_bo_size(bo), SZ_4K);
 		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bo->ggtt_node[tile->id]);
-
-		KUNIT_ASSERT_EQ(test, 0,
-				xe_ggtt_node_insert(bo->ggtt_node[tile->id],
-						    xe_bo_size(bo), SZ_4K));
 	}
 
 	return bo;
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 6b1684162400a..4e54b00da4ef0 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -429,6 +429,11 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt)
 	mutex_unlock(&ggtt->lock);
 }
 
+static void xe_ggtt_node_fini(struct xe_ggtt_node *node)
+{
+	kfree(node);
+}
+
 static void ggtt_node_remove(struct xe_ggtt_node *node)
 {
 	struct xe_ggtt *ggtt = node->ggtt;
@@ -593,68 +598,51 @@ static int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
 					  mm_flags);
 }
 
+static struct xe_ggtt_node *xe_ggtt_node_init(struct xe_ggtt *ggtt)
+{
+	struct xe_ggtt_node *node = kzalloc(sizeof(*node), GFP_NOFS);
+
+	if (!node)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&node->delayed_removal_work, ggtt_node_remove_work_func);
+	node->ggtt = ggtt;
+
+	return node;
+}
+
 /**
  * xe_ggtt_node_insert - Insert a &xe_ggtt_node into the GGTT
- * @node: the &xe_ggtt_node to be inserted
+ * @ggtt: the @ggtt into which the node should be inserted.
  * @size: size of the node
  * @align: alignment constrain of the node
  *
- * It cannot be called without first having called xe_ggtt_init() once.
- *
- * Return: 0 on success or a negative error code on failure.
+ * Return: &xe_ggtt_node on success or a ERR_PTR on failure.
  */
-int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align)
+struct xe_ggtt_node *xe_ggtt_node_insert(struct xe_ggtt *ggtt, u32 size, u32 align)
 {
+	struct xe_ggtt_node *node;
 	int ret;
 
-	if (!node || !node->ggtt)
-		return -ENOENT;
+	if (!ggtt)
+		return ERR_PTR(-ENOENT);
+
+	node = xe_ggtt_node_init(ggtt);
+	if (IS_ERR(node))
+		return node;
 
 	mutex_lock(&node->ggtt->lock);
 	ret = xe_ggtt_node_insert_locked(node, size, align,
 					 DRM_MM_INSERT_HIGH);
 	mutex_unlock(&node->ggtt->lock);
-
-	return ret;
-}
-
-/**
- * xe_ggtt_node_init - Initialize %xe_ggtt_node struct
- * @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.
- *
- * Return: A pointer to %xe_ggtt_node struct on success. An ERR_PTR otherwise.
- **/
-struct xe_ggtt_node *xe_ggtt_node_init(struct xe_ggtt *ggtt)
-{
-	struct xe_ggtt_node *node = kzalloc(sizeof(*node), GFP_NOFS);
-
-	if (!node)
-		return ERR_PTR(-ENOMEM);
-
-	INIT_WORK(&node->delayed_removal_work, ggtt_node_remove_work_func);
-	node->ggtt = ggtt;
+	if (ret) {
+		xe_ggtt_node_fini(node);
+		return ERR_PTR(ret);
+	}
 
 	return node;
 }
 
-/**
- * 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() 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)
-{
-	kfree(node);
-}
-
 /**
  * xe_ggtt_node_allocated - Check if node is allocated in GGTT
  * @node: the &xe_ggtt_node to be inspected
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index 9f97f63496bcb..d0ad541a40baf 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -18,13 +18,12 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt);
 int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 reserved, u32 size);
 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);
 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);
 
-int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align);
+struct xe_ggtt_node *
+xe_ggtt_node_insert(struct xe_ggtt *ggtt, u32 size, u32 align);
 struct xe_ggtt_node *
 xe_ggtt_node_insert_transform(struct xe_ggtt *ggtt,
 			      struct xe_bo *bo, u64 pte,
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 c0dfffd5c553b..d71041a611d35 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -434,23 +434,9 @@ static int pf_distribute_config_ggtt(struct xe_tile *tile, unsigned int vfid, u6
 	return err ?: err2;
 }
 
-static void pf_release_ggtt(struct xe_tile *tile, struct xe_ggtt_node *node)
-{
-	if (xe_ggtt_node_allocated(node)) {
-		/*
-		 * explicit GGTT PTE assignment to the PF using xe_ggtt_assign()
-		 * is redundant, as PTE will be implicitly re-assigned to PF by
-		 * the xe_ggtt_clear() called by below xe_ggtt_remove_node().
-		 */
-		xe_ggtt_node_remove(node, false);
-	} else {
-		xe_ggtt_node_fini(node);
-	}
-}
-
 static void pf_release_vf_config_ggtt(struct xe_gt *gt, struct xe_gt_sriov_config *config)
 {
-	pf_release_ggtt(gt_to_tile(gt), config->ggtt_region);
+	xe_ggtt_node_remove(config->ggtt_region, false);
 	config->ggtt_region = NULL;
 }
 
@@ -485,14 +471,10 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 	if (!size)
 		return 0;
 
-	node = xe_ggtt_node_init(ggtt);
+	node = xe_ggtt_node_insert(ggtt, size, alignment);
 	if (IS_ERR(node))
 		return PTR_ERR(node);
 
-	err = xe_ggtt_node_insert(node, size, alignment);
-	if (unlikely(err))
-		goto err;
-
 	xe_ggtt_assign(node, vfid);
 	xe_gt_sriov_dbg_verbose(gt, "VF%u assigned GGTT %llx-%llx\n",
 				vfid, xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + size - 1);
@@ -505,7 +487,7 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 	config->ggtt_size = size;
 	return 0;
 err:
-	pf_release_ggtt(tile, node);
+	xe_ggtt_node_remove(node, false);
 	return err;
 }
 
-- 
2.51.0

[PATCH v6 12/12] drm/xe: Remove xe_ggtt_node_allocated

[Maarten Lankhorst]

With the intermediate state gone, no longer useful. Just check against
NULL.

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c     |  3 +--
 drivers/gpu/drm/xe/xe_ggtt.c               | 14 --------------
 drivers/gpu/drm/xe/xe_ggtt.h               |  1 -
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 12 ++++++------
 4 files changed, 7 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 784d2db5fd0db..6592b000950ff 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -350,8 +350,7 @@ static void __xe_unpin_fb_vma(struct i915_vma *vma)
 
 	if (vma->dpt)
 		xe_bo_unpin_map_no_vm(vma->dpt);
-	else if (!xe_ggtt_node_allocated(vma->bo->ggtt_node[tile_id]) ||
-		 vma->bo->ggtt_node[tile_id] != vma->node)
+	else if (vma->bo->ggtt_node[tile_id] != vma->node)
 		xe_ggtt_node_remove(vma->node, false);
 
 	ttm_bo_reserve(&vma->bo->ttm, false, false, NULL);
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 4e54b00da4ef0..69e3ce03afe8c 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -643,20 +643,6 @@ struct xe_ggtt_node *xe_ggtt_node_insert(struct xe_ggtt *ggtt, u32 size, u32 ali
 	return node;
 }
 
-/**
- * xe_ggtt_node_allocated - Check if node is allocated in GGTT
- * @node: the &xe_ggtt_node to be inspected
- *
- * Return: True if allocated, False otherwise.
- */
-bool xe_ggtt_node_allocated(const struct xe_ggtt_node *node)
-{
-	if (!node || !node->ggtt)
-		return false;
-
-	return drm_mm_node_allocated(&node->base);
-}
-
 /**
  * xe_ggtt_map_bo - Map the BO into GGTT
  * @ggtt: the &xe_ggtt where node will be mapped
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index d0ad541a40baf..e32a14ac63665 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -30,7 +30,6 @@ xe_ggtt_node_insert_transform(struct xe_ggtt *ggtt,
 			      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_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_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index d71041a611d35..db47b49e5842c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -261,7 +261,7 @@ static u32 encode_config_ggtt(u32 *cfg, const struct xe_gt_sriov_config *config,
 {
 	struct xe_ggtt_node *node = config->ggtt_region;
 
-	if (!xe_ggtt_node_allocated(node))
+	if (!node)
 		return 0;
 
 	return encode_ggtt(cfg, xe_ggtt_node_addr(node), config->ggtt_size, details);
@@ -455,7 +455,7 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 
 	size = round_up(size, alignment);
 
-	if (xe_ggtt_node_allocated(config->ggtt_region)) {
+	if (config->ggtt_region) {
 		err = pf_distribute_config_ggtt(tile, vfid, 0, 0);
 		if (unlikely(err))
 			return err;
@@ -466,7 +466,7 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 		if (unlikely(err))
 			return err;
 	}
-	xe_gt_assert(gt, !xe_ggtt_node_allocated(config->ggtt_region));
+	xe_gt_assert(gt, !config->ggtt_region);
 
 	if (!size)
 		return 0;
@@ -497,7 +497,7 @@ static u64 pf_get_vf_config_ggtt(struct xe_gt *gt, unsigned int vfid)
 	struct xe_ggtt_node *node = config->ggtt_region;
 
 	xe_gt_assert(gt, xe_gt_is_main_type(gt));
-	return xe_ggtt_node_allocated(node) ? config->ggtt_size : 0;
+	return node ? config->ggtt_size : 0;
 }
 
 /**
@@ -2049,7 +2049,7 @@ int xe_gt_sriov_pf_config_release(struct xe_gt *gt, unsigned int vfid, bool forc
 
 static void pf_sanitize_ggtt(struct xe_ggtt_node *ggtt_region, unsigned int vfid)
 {
-	if (xe_ggtt_node_allocated(ggtt_region))
+	if (ggtt_region)
 		xe_ggtt_assign(ggtt_region, vfid);
 }
 
@@ -2496,7 +2496,7 @@ int xe_gt_sriov_pf_config_print_ggtt(struct xe_gt *gt, struct drm_printer *p)
 
 	for (n = 1; n <= total_vfs; n++) {
 		config = &gt->sriov.pf.vfs[n].config;
-		if (!xe_ggtt_node_allocated(config->ggtt_region))
+		if (!config->ggtt_region)
 			continue;
 
 		string_get_size(config->ggtt_size, 1, STRING_UNITS_2,
-- 
2.51.0

Re: [PATCH v6 06/12] drm/xe: Improve xe_gt_sriov_pf_config GGTT handling

[Michal Wajdeczko]

On 10/14/2025 11:20 PM, Maarten Lankhorst wrote:
> Do not directly dereference xe_ggtt_node, and add
> a member to store the GGTT size.
> 
> Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c       | 15 ++++++++-------
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h |  8 ++++++--
>  2 files changed, 14 insertions(+), 9 deletions(-)
> 
> 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 2289756761636..c0dfffd5c553b 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> @@ -264,7 +264,7 @@ static u32 encode_config_ggtt(u32 *cfg, const struct xe_gt_sriov_config *config,
>  	if (!xe_ggtt_node_allocated(node))
>  		return 0;
>  
> -	return encode_ggtt(cfg, node->base.start, node->base.size, details);
> +	return encode_ggtt(cfg, xe_ggtt_node_addr(node), config->ggtt_size, details);
>  }
>  
>  /* Return: number of configuration dwords written */
> @@ -495,13 +495,14 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
>  
>  	xe_ggtt_assign(node, vfid);
>  	xe_gt_sriov_dbg_verbose(gt, "VF%u assigned GGTT %llx-%llx\n",
> -				vfid, node->base.start, node->base.start + node->base.size - 1);
> +				vfid, xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + size - 1);
>  
> -	err = pf_distribute_config_ggtt(gt->tile, vfid, node->base.start, node->base.size);
> +	err = pf_distribute_config_ggtt(gt->tile, vfid, xe_ggtt_node_addr(node), size);
>  	if (unlikely(err))
>  		goto err;
>  
>  	config->ggtt_region = node;
> +	config->ggtt_size = size;
>  	return 0;
>  err:
>  	pf_release_ggtt(tile, node);
> @@ -514,7 +515,7 @@ static u64 pf_get_vf_config_ggtt(struct xe_gt *gt, unsigned int vfid)
>  	struct xe_ggtt_node *node = config->ggtt_region;
>  
>  	xe_gt_assert(gt, xe_gt_is_main_type(gt));
> -	return xe_ggtt_node_allocated(node) ? node->base.size : 0;
> +	return xe_ggtt_node_allocated(node) ? config->ggtt_size : 0;
>  }
>  
>  /**
> @@ -2516,11 +2517,11 @@ int xe_gt_sriov_pf_config_print_ggtt(struct xe_gt *gt, struct drm_printer *p)
>  		if (!xe_ggtt_node_allocated(config->ggtt_region))
>  			continue;
>  
> -		string_get_size(config->ggtt_region->base.size, 1, STRING_UNITS_2,
> +		string_get_size(config->ggtt_size, 1, STRING_UNITS_2,
>  				buf, sizeof(buf));
>  		drm_printf(p, "VF%u:\t%#0llx-%#llx\t(%s)\n",
> -			   n, config->ggtt_region->base.start,
> -			   config->ggtt_region->base.start + config->ggtt_region->base.size - 1,
> +			   n, xe_ggtt_node_addr(config->ggtt_region),
> +			   xe_ggtt_node_addr(config->ggtt_region) + config->ggtt_size - 1,
>  			   buf);
>  	}
>  
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
> index 686c7b3b6d7a5..9a8e66c8b539f 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config_types.h
> @@ -17,10 +17,14 @@ struct xe_bo;
>   * Used by the PF driver to maintain per-VF provisioning data.
>   */
>  struct xe_gt_sriov_config {
> -	/** @ggtt_region: GGTT region assigned to the VF. */
> -	struct xe_ggtt_node *ggtt_region;
>  	/** @lmem_obj: LMEM allocation for use by the VF. */
>  	struct xe_bo *lmem_obj;
> +
> +	/** @ggtt_region: GGTT region assigned to the VF. */
> +	struct xe_ggtt_node *ggtt_region;
> +	/** @ggtt_size: Size of GGTT region */
> +	u64 ggtt_size;

can't we just add another helper on GGTT side to get the size of the node?

	u64 xe_ggtt_node_size(node);

there is one for xe_bo, why can't we have another for xe_ggtt_node ?
> +
>  	/** @num_ctxs: number of GuC contexts IDs.  */
>  	u16 num_ctxs;
>  	/** @begin_ctx: start index of GuC context ID range. */

Re: [PATCH v6 08/12] drm/xe: Make xe_ggtt_node offset relative to starting offset

[Michal Wajdeczko]

On 10/14/2025 11:20 PM, Maarten Lankhorst wrote:
> This will make node shifting in the next commit a one-liner.
> 
> Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
> ---
>  drivers/gpu/drm/xe/xe_ggtt.c | 21 ++++++++++++++-------
>  1 file changed, 14 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
> index d73ed0103f50f..97ab38392c711 100644
> --- a/drivers/gpu/drm/xe/xe_ggtt.c
> +++ b/drivers/gpu/drm/xe/xe_ggtt.c
> @@ -276,7 +276,7 @@ static void __xe_ggtt_init_early(struct xe_ggtt *ggtt, u64 start, u64 size)
>  {
>  	ggtt->start = start;
>  	ggtt->size = size;
> -	drm_mm_init(&ggtt->mm, start, size);
> +	drm_mm_init(&ggtt->mm, 0, size - start);

that's little confusing

either "size" param should be named "end" or this should be just

	drm_mm_init(&ggtt->mm, 0, size);

or am I reading this wrong?

>  }
>  
>  int xe_ggtt_init_kunit(struct xe_ggtt *ggtt, u32 start, u32 size)
> @@ -375,7 +375,7 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt)
>  	/* Display may have allocated inside ggtt, so be careful with clearing here */
>  	mutex_lock(&ggtt->lock);
>  	drm_mm_for_each_hole(hole, &ggtt->mm, start, end)
> -		xe_ggtt_clear(ggtt, start, end - start);
> +		xe_ggtt_clear(ggtt, ggtt->start + start, end - start);

since xe_ggtt_clear is static/private then maybe "ggtt->start" shift can be done there?

>  
>  	xe_ggtt_invalidate(ggtt);
>  	mutex_unlock(&ggtt->lock);
> @@ -392,7 +392,7 @@ static void ggtt_node_remove(struct xe_ggtt_node *node)
>  
>  	mutex_lock(&ggtt->lock);
>  	if (bound)
> -		xe_ggtt_clear(ggtt, node->base.start, node->base.size);
> +		xe_ggtt_clear(ggtt, xe_ggtt_node_addr(node), node->base.size);
>  	drm_mm_remove_node(&node->base);
>  	node->base.size = 0;
>  	mutex_unlock(&ggtt->lock);
> @@ -548,13 +548,13 @@ int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node, u64 start, u64
>  	lockdep_assert_held(&ggtt->lock);
>  
>  	node->base.color = 0;
> -	node->base.start = start;
> +	node->base.start = start - ggtt->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)))
> +			 xe_ggtt_node_addr(node), xe_ggtt_node_addr(node) + node->base.size, ERR_PTR(err)))
>  		return err;
>  
>  	xe_ggtt_dump_node(ggtt, &node->base, "balloon");
> @@ -731,7 +731,7 @@ static void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node,
>  	if (XE_WARN_ON(!node))
>  		return;
>  
> -	start = node->base.start;
> +	start = xe_ggtt_node_addr(node);
>  	end = start + xe_bo_size(bo);
>  
>  	if (!xe_bo_is_vram(bo) && !xe_bo_is_stolen(bo)) {
> @@ -852,6 +852,13 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
>  	}
>  
>  	mutex_lock(&ggtt->lock);
> +	if (start >= ggtt->start)
> +		start -= ggtt->start;
> +	else
> +		start = 0;
> +
> +	end -= ggtt->start;
> +
>  	err = drm_mm_insert_node_in_range(&ggtt->mm, &bo->ggtt_node[tile_id]->base,
>  					  xe_bo_size(bo), alignment, 0, start, end, 0);
>  	if (err) {
> @@ -1093,5 +1100,5 @@ u64 xe_ggtt_read_pte(struct xe_ggtt *ggtt, u64 offset)
>   */
>  u64 xe_ggtt_node_addr(const struct xe_ggtt_node *node)
>  {
> -	return node->base.start;
> +	return node->base.start + READ_ONCE(node->ggtt->start);
>  }