[PATCH 05/10] xfrm: avoid lock inversion in nat keepalive work

From: Zihan Xi <[email protected]>

nat_keepalive_work() walks the state table while xfrm_state_walk()
holds net->xfrm.xfrm_state_lock. Its callback then acquires x->lock,
which conflicts with the delete path taking the same locks in reverse
order via xfrm_state_delete() and __xfrm_state_delete(). This creates
an AB-BA deadlock that is reported by lockdep when a NAT keepalive
worker races with SA deletion.

Fix this by splitting the keepalive walk into two phases. First,
collect the candidate states while the walk holds xfrm_state_lock and
take a reference on each state. Then, after the walk completes, process
each collected state and acquire x->lock without nesting it under
xfrm_state_lock.

Fixes: f531d13bdfe3 ("xfrm: support sending NAT keepalives in ESP in UDP states")
Cc: [email protected]
Reported-by: Vega <[email protected]>
Assisted-by: Codex:gpt-5.4
Signed-off-by: Zihan Xi <[email protected]>
Signed-off-by: Ren Wei <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>
---
 net/xfrm/xfrm_nat_keepalive.c | 57 +++++++++++++++++++++++++++++------
 1 file changed, 48 insertions(+), 9 deletions(-)

diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c
index eb1b6f67739e..8679c68c10a1 100644
--- a/net/xfrm/xfrm_nat_keepalive.c
+++ b/net/xfrm/xfrm_nat_keepalive.c
@@ -156,24 +156,51 @@ static void nat_keepalive_send(struct nat_keepalive *ka)
 }
 
 struct nat_keepalive_work_ctx {
+	struct list_head states;
 	time64_t next_run;
 	time64_t now;
 };
 
-static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr)
+struct nat_keepalive_state {
+	struct list_head list;
+	struct xfrm_state *x;
+};
+
+static int nat_keepalive_work_collect(struct xfrm_state *x, int count, void *ptr)
 {
 	struct nat_keepalive_work_ctx *ctx = ptr;
+	struct nat_keepalive_state *state;
+
+	if (!READ_ONCE(x->nat_keepalive_interval))
+		return 0;
+
+	state = kmalloc_obj(*state, GFP_ATOMIC);
+	if (!state)
+		return -ENOMEM;
+
+	xfrm_state_hold(x);
+	state->x = x;
+	list_add_tail(&state->list, &ctx->states);
+	return 0;
+}
+
+static void nat_keepalive_work_single(struct xfrm_state *x,
+				      struct nat_keepalive_work_ctx *ctx)
+{
 	bool send_keepalive = false;
 	struct nat_keepalive ka;
-	time64_t next_run;
+	time64_t next_run = 0;
 	u32 interval;
 	int delta;
 
+	spin_lock_bh(&x->lock);
+
+	if (x->km.state == XFRM_STATE_DEAD)
+		goto out;
+
 	interval = x->nat_keepalive_interval;
 	if (!interval)
-		return 0;
-
-	spin_lock(&x->lock);
+		goto out;
 
 	delta = (int)(ctx->now - x->lastused);
 	if (delta < interval) {
@@ -187,29 +214,41 @@ static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr)
 		send_keepalive = true;
 	}
 
-	spin_unlock(&x->lock);
+out:
+	spin_unlock_bh(&x->lock);
 
 	if (send_keepalive)
 		nat_keepalive_send(&ka);
 
-	if (!ctx->next_run || next_run < ctx->next_run)
+	if (next_run && (!ctx->next_run || next_run < ctx->next_run))
 		ctx->next_run = next_run;
-	return 0;
 }
 
 static void nat_keepalive_work(struct work_struct *work)
 {
+	struct nat_keepalive_state *state, *tmp;
 	struct nat_keepalive_work_ctx ctx;
 	struct xfrm_state_walk walk;
 	struct net *net;
+	int err;
 
+	INIT_LIST_HEAD(&ctx.states);
 	ctx.next_run = 0;
 	ctx.now = ktime_get_real_seconds();
 
 	net = container_of(work, struct net, xfrm.nat_keepalive_work.work);
 	xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL);
-	xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx);
+	err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx);
 	xfrm_state_walk_done(&walk, net);
+	list_for_each_entry_safe(state, tmp, &ctx.states, list) {
+		nat_keepalive_work_single(state->x, &ctx);
+		xfrm_state_put(state->x);
+		kfree(state);
+	}
+	if (err == -ENOMEM) {
+		schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0);
+		return;
+	}
 	if (ctx.next_run)
 		schedule_delayed_work(&net->xfrm.nat_keepalive_work,
 				      (ctx.next_run - ctx.now) * HZ);
-- 
2.43.0