bpf, arena: fix range_tree consistency on allocation failure

kernel/bpf/arena.c

@@ -766,7 +766,9 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 	bpf_map_memcg_exit(old_memcg, new_memcg);
 	return clear_lo32(arena->user_vm_start) + uaddr32;
 out:
-	range_tree_set(&arena->rt, pgoff + mapped, page_cnt - mapped);
+	if (range_tree_set(&arena->rt, pgoff + mapped, page_cnt - mapped))
+		pr_warn_ratelimited("bpf_arena: failed to restore free range %ld+%ld after partial alloc\n",
+				    pgoff + mapped, page_cnt - mapped);
 	raw_res_spin_unlock_irqrestore(&arena->spinlock, flags);
 	if (mapped) {
 		flush_vmap_cache(kern_vm_start + uaddr32, mapped << PAGE_SHIFT);
@@ -881,7 +883,18 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt,
 	if (ret)
 		goto defer;
 
-	range_tree_set(&arena->rt, pgoff, page_cnt);
+	ret = range_tree_set(&arena->rt, pgoff, page_cnt);
+	if (ret) {
+		/*
+		 * range_tree_set() is failure-atomic, so -ENOMEM leaves the
+		 * range allocated and the pages mapped. Abort the free rather
+		 * than returning pages the free tree does not track; a later
+		 * free of the same range can succeed.
+		 */
+		raw_res_spin_unlock_irqrestore(&arena->spinlock, flags);
+		bpf_map_memcg_exit(old_memcg, new_memcg);
+		return;
+	}
 
 	init_llist_head(&free_pages);
 	cdata.arena = arena;
@@ -977,12 +990,13 @@ static void arena_free_worker(struct work_struct *work)
 	struct llist_node *list, *pos, *t;
 	struct arena_free_span *s;
 	u64 arena_vm_start, user_vm_start;
-	struct llist_head free_pages;
+	struct llist_head free_pages, cleared;
 	struct clear_range_data cdata;
 	struct page *page;
 	unsigned long full_uaddr;
 	long kaddr, page_cnt, pgoff;
 	unsigned long flags;
+	bool retry = false;
 
 	if (raw_res_spin_lock_irqsave(&arena->spinlock, flags)) {
 		schedule_work(work);
@@ -992,28 +1006,43 @@ static void arena_free_worker(struct work_struct *work)
 	bpf_map_memcg_enter(&arena->map, &old_memcg, &new_memcg);
 
 	init_llist_head(&free_pages);
+	init_llist_head(&cleared);
 	cdata.arena = arena;
 	cdata.free_pages = &free_pages;
 	arena_vm_start = bpf_arena_get_kern_vm_start(arena);
 	user_vm_start = bpf_arena_get_user_vm_start(arena);
 
 	list = llist_del_all(&arena->free_spans);
-	llist_for_each(pos, list) {
+	llist_for_each_safe(pos, t, list) {
 		s = llist_entry(pos, struct arena_free_span, node);
 		page_cnt = s->page_cnt;
 		kaddr = arena_vm_start + s->uaddr;
 		pgoff = compute_pgoff(arena, s->uaddr);
 
+		/*
+		 * Set the range free before clearing PTEs, and requeue the
+		 * span on failure: the PTEs stay intact and the free is
+		 * retried later. Only spans moved to @cleared (PTE clearing
+		 * actually ran) reach the flush/zap/release loop below.
+		 */
+		if (range_tree_set(&arena->rt, pgoff, page_cnt)) {
+			llist_add(&s->node, &arena->free_spans);
+			retry = true;
+			continue;
+		}
+
 		/* clear ptes and collect pages in free_pages llist */
 		apply_to_existing_page_range(&init_mm, kaddr, page_cnt << PAGE_SHIFT,
 					     apply_range_clear_cb, &cdata);
-
-		range_tree_set(&arena->rt, pgoff, page_cnt);
+		llist_add(&s->node, &cleared);
 	}
 	raw_res_spin_unlock_irqrestore(&arena->spinlock, flags);
 
+	if (retry)
+		irq_work_queue(&arena->free_irq);
+
 	/* Iterate the list again without holding spinlock to do the tlb flush and zap_pages */
-	llist_for_each_safe(pos, t, list) {
+	llist_for_each_safe(pos, t, cleared.first) {
 		s = llist_entry(pos, struct arena_free_span, node);
 		page_cnt = s->page_cnt;
 		full_uaddr = clear_lo32(user_vm_start) + s->uaddr;

kernel/bpf/range_tree.c

@@ -143,16 +143,22 @@ int range_tree_clear(struct range_tree *rt, u32 start, u32 len)
 		if (rn->rn_start < start && rn->rn_last > last) {
 			u32 old_last = rn->rn_last;
 
+			/*
+			 * Pre-allocate the right-half node before modifying
+			 * the tree. If allocation fails we return -ENOMEM
+			 * without altering the range tree.
+			 */
+			new_rn = kmalloc_nolock(sizeof(struct range_node),
+						__GFP_ACCOUNT, NUMA_NO_NODE);
+			if (!new_rn)
+				return -ENOMEM;
+
 			/* Overlaps with the entire clearing range */
 			range_it_remove(rn, rt);
 			rn->rn_last = start - 1;
 			range_it_insert(rn, rt);
 
-			/* Add a range */
-			new_rn = kmalloc_nolock(sizeof(struct range_node), __GFP_ACCOUNT,
-						NUMA_NO_NODE);
-			if (!new_rn)
-				return -ENOMEM;
+			/* Add right-half range */
 			new_rn->rn_start = last + 1;
 			new_rn->rn_last = old_last;
 			range_it_insert(new_rn, rt);
@@ -193,6 +199,7 @@ int is_range_tree_set(struct range_tree *rt, u32 start, u32 len)
 int range_tree_set(struct range_tree *rt, u32 start, u32 len)
 {
 	u32 last = start + len - 1;
+	struct range_node *new_rn = NULL;
 	struct range_node *right;
 	struct range_node *left;
 	int err;
@@ -202,20 +209,40 @@ int range_tree_set(struct range_tree *rt, u32 start, u32 len)
 	if (left && left->rn_start <= start && left->rn_last >= last)
 		return 0;
 
+	/*
+	 * A new node is needed only when the range has no adjacent free
+	 * range on either side.  This is known before clearing: any range
+	 * covering start - 1 or last + 1 survives the clear as an adjacent
+	 * piece.  Allocate only in that case, before modifying the tree, so
+	 * a failure leaves the range tree unmodified
+	 */
+	left = range_it_iter_first(rt, start - 1, start - 1);
+	right = range_it_iter_first(rt, last + 1, last + 1);
+	if (!left && !right) {
+		new_rn = kmalloc_nolock(sizeof(struct range_node),
+					__GFP_ACCOUNT, NUMA_NO_NODE);
+		if (!new_rn)
+			return -ENOMEM;
+	}
+
 	/* Clear out everything in the range we want to set. */
 	err = range_tree_clear(rt, start, len);
 	if (err)
-		return err;
+		goto out_free_new;
 
 	/* Do we have a left-adjacent range ? */
 	left = range_it_iter_first(rt, start - 1, start - 1);
-	if (left && left->rn_last + 1 != start)
-		return -EFAULT;
+	if (left && left->rn_last + 1 != start) {
+		err = -EFAULT;
+		goto out_free_new;
+	}
 
 	/* Do we have a right-adjacent range ? */
 	right = range_it_iter_first(rt, last + 1, last + 1);
-	if (right && right->rn_start != last + 1)
-		return -EFAULT;
+	if (right && right->rn_start != last + 1) {
+		err = -EFAULT;
+		goto out_free_new;
+	}
 
 	if (left && right) {
 		/* Combine left and right adjacent ranges */
@@ -235,14 +262,16 @@ int range_tree_set(struct range_tree *rt, u32 start, u32 len)
 		right->rn_start = start;
 		range_it_insert(right, rt);
 	} else {
-		left = kmalloc_nolock(sizeof(struct range_node), __GFP_ACCOUNT, NUMA_NO_NODE);
-		if (!left)
-			return -ENOMEM;
-		left->rn_start = start;
-		left->rn_last = last;
-		range_it_insert(left, rt);
+		/* No adjacent ranges; use the pre-allocated node */
+		new_rn->rn_start = start;
+		new_rn->rn_last = last;
+		range_it_insert(new_rn, rt);
 	}
 	return 0;
+
+out_free_new:
+	kfree_nolock(new_rn);
+	return err;
 }
 
 void range_tree_destroy(struct range_tree *rt)