xsk: Fix race condition in AF_XDP generic RX path

Move rx_lock from xsk_socket to xsk_buff_pool.
Fix synchronization for shared umem mode in
generic RX path where multiple sockets share
single xsk_buff_pool.

RX queue is exclusive to xsk_socket, while FILL
queue can be shared between multiple sockets.
This could result in race condition where two
CPU cores access RX path of two different sockets
sharing the same umem.

Protect both queues by acquiring spinlock in shared
xsk_buff_pool.

Lock contention may be minimized in the future by some
per-thread FQ buffering.

It's safe and necessary to move spin_lock_bh(rx_lock)
after xsk_rcv_check():
* xs->pool and spinlock_init is synchronized by
  xsk_bind() -> xsk_is_bound() memory barriers.
* xsk_rcv_check() may return true at the moment
  of xsk_release() or xsk_unbind_dev(),
  however this will not cause any data races or
  race conditions. xsk_unbind_dev() removes xdp
  socket from all maps and waits for completion
  of all outstanding rx operations. Packets in
  RX path will either complete safely or drop.

Signed-off-by: Eryk Kubanski <[email protected]>
Fixes: bf0bdd1 ("xdp: fix race on generic receive path")
Acked-by: Magnus Karlsson <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: e.kubanski

include/net/xdp_sock.h

@@ -71,9 +71,6 @@ struct xdp_sock {
 	 */
 	u32 tx_budget_spent;
 
-	/* Protects generic receive. */
-	spinlock_t rx_lock;
-
 	/* Statistics */
 	u64 rx_dropped;
 	u64 rx_queue_full;

include/net/xsk_buff_pool.h

@@ -53,6 +53,8 @@ struct xsk_buff_pool {
 	refcount_t users;
 	struct xdp_umem *umem;
 	struct work_struct work;
+	/* Protects generic receive in shared and non-shared umem mode. */
+	spinlock_t rx_lock;
 	struct list_head free_list;
 	struct list_head xskb_list;
 	u32 heads_cnt;

net/xdp/xsk.c

@@ -338,13 +338,14 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u32 len = xdp_get_buff_len(xdp);
 	int err;
 
-	spin_lock_bh(&xs->rx_lock);
 	err = xsk_rcv_check(xs, xdp, len);
 	if (!err) {
+		spin_lock_bh(&xs->pool->rx_lock);
 		err = __xsk_rcv(xs, xdp, len);
 		xsk_flush(xs);
+		spin_unlock_bh(&xs->pool->rx_lock);
 	}
-	spin_unlock_bh(&xs->rx_lock);
+
 	return err;
 }
 
@@ -1734,7 +1735,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 	xs = xdp_sk(sk);
 	xs->state = XSK_READY;
 	mutex_init(&xs->mutex);
-	spin_lock_init(&xs->rx_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);

net/xdp/xsk_buff_pool.c

@@ -89,6 +89,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->addrs = umem->addrs;
 	pool->tx_metadata_len = umem->tx_metadata_len;
 	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
+	spin_lock_init(&pool->rx_lock);
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);