[PATCH V16 07/12] drm/xe/vram: Add page offline data structures and lifecycle

Add xe_ttm_vram_offline_resource to track individual offlined VRAM
pages, and extend xe_ttm_vram_mgr with offlined_pages/queued_pages
lists and their counters.

Initialize the lists in __xe_ttm_vram_mgr_init() and add
xe_ttm_vram_free_bad_pages() to release all tracked pages during
xe_ttm_vram_mgr_fini() teardown.

v2(Himal):
- Address possible leak in xe_ttm_vram_mgr_fini()
- Remove unused dev and add comment for used_visible_size 0

Signed-off-by: Tejas Upadhyay <[email protected]>
---
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.c       | 25 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 28 ++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 49eeec90a470..1885f2aa64df 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -300,6 +300,25 @@ static const struct ttm_resource_manager_func xe_ttm_vram_mgr_func = {
 	.debug	= xe_ttm_vram_mgr_debug
 };
 
+static void xe_ttm_vram_free_bad_pages(struct xe_ttm_vram_mgr *mgr)
+{
+	struct xe_ttm_vram_offline_resource *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &mgr->offlined_pages, offlined_link) {
+		xe_ttm_vram_buddy_free(mgr, &pos->blocks, pos->used_visible_size);
+		list_del_rcu(&pos->offlined_link);
+		--mgr->n_offlined_pages;
+		kfree_rcu(pos, rcu);
+	}
+	list_for_each_entry_safe(pos, n, &mgr->queued_pages, queued_link) {
+		/* queued entries have no buddy reservation yet */
+		xe_ttm_vram_buddy_free(mgr, &pos->blocks, 0);
+		list_del_rcu(&pos->queued_link);
+		--mgr->n_queued_pages;
+		kfree_rcu(pos, rcu);
+	}
+}
+
 static void xe_ttm_vram_mgr_fini(struct drm_device *dev, void *arg)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -308,6 +327,10 @@ static void xe_ttm_vram_mgr_fini(struct drm_device *dev, void *arg)
 
 	ttm_resource_manager_set_used(man, false);
 
+	mutex_lock(&mgr->lock);
+	xe_ttm_vram_free_bad_pages(mgr);
+	mutex_unlock(&mgr->lock);
+
 	if (ttm_resource_manager_evict_all(&xe->ttm, man))
 		return;
 
@@ -338,6 +361,8 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
 	err = drmm_mutex_init(&xe->drm, &mgr->lock);
 	if (err)
 		return err;
+	INIT_LIST_HEAD(&mgr->offlined_pages);
+	INIT_LIST_HEAD(&mgr->queued_pages);
 	mgr->default_page_size = default_page_size;
 	mgr->visible_size = io_size;
 	mgr->visible_avail = io_size;
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
index 9106da056b49..9dc6fc5a3c38 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
@@ -19,6 +19,14 @@ struct xe_ttm_vram_mgr {
 	struct ttm_resource_manager manager;
 	/** @mm: DRM buddy allocator which manages the VRAM */
 	struct gpu_buddy mm;
+	/** @offlined_pages: List of offlined pages */
+	struct list_head offlined_pages;
+	/** @n_offlined_pages: Number of offlined pages */
+	u16 n_offlined_pages;
+	/** @queued_pages: List of queued pages */
+	struct list_head queued_pages;
+	/** @n_queued_pages: Number of queued pages */
+	u16 n_queued_pages;
 	/** @visible_size: Proped size of the CPU visible portion */
 	u64 visible_size;
 	/** @visible_avail: CPU visible portion still unallocated */
@@ -45,4 +53,24 @@ struct xe_ttm_vram_mgr_resource {
 	unsigned long flags;
 };
 
+/**
+ * struct xe_ttm_vram_offline_resource - Tracks a single offlined VRAM page
+ */
+struct xe_ttm_vram_offline_resource {
+	/** @offlined_link: Link into mgr->offlined_pages */
+	struct list_head offlined_link;
+	/** @queued_link: Link into mgr->queued_pages */
+	struct list_head queued_link;
+	/** @blocks: Buddy blocks reserved for this page */
+	struct list_head blocks;
+	/** @used_visible_size: CPU-visible bytes consumed */
+	u64 used_visible_size;
+	/** @addr: Faulty DPA reported by HW */
+	u64 addr;
+	/** @status: Reservation status (0=pending, 1=fail) */
+	bool status;
+	/** @rcu: RCU head for deferred freeing */
+	struct rcu_head rcu;
+};
+
 #endif
-- 
2.52.0