xsk: Move xsk_tx_list and its lock to buffer pool

Move the xsk_tx_list and the xsk_tx_list_lock from the umem to
the buffer pool. This so that we in a later commit can share the
umem between multiple HW queues. There is one xsk_tx_list per
device and queue id, so it should be located in the buffer pool.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-7-git-send-email-magnus.karlsson@intel.com

include/net/xdp_sock.h

@@ -29,8 +29,6 @@ struct xdp_umem {
 	u8 flags;
 	int id;
 	bool zc;
-	spinlock_t xsk_tx_list_lock;
-	struct list_head xsk_tx_list;
 };
 
 struct xsk_map {
@@ -57,7 +55,7 @@ struct xdp_sock {
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
-	struct list_head list;
+	struct list_head tx_list;
 	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
 	 * in the SKB destructor callback.
 	 */

include/net/xsk_buff_pool.h

@@ -52,6 +52,9 @@ struct xsk_buff_pool {
 	void *addrs;
 	struct device *dev;
 	struct net_device *netdev;
+	struct list_head xsk_tx_list;
+	/* Protects modifications to the xsk_tx_list */
+	spinlock_t xsk_tx_list_lock;
 	refcount_t users;
 	struct work_struct work;
 	struct xdp_buff_xsk *free_heads[];
@@ -67,6 +70,8 @@ void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
 void xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);

net/xdp/xdp_umem.c

@@ -23,30 +23,6 @@
 
 static DEFINE_IDA(umem_ida);
 
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_add_rcu(&xs->list, &umem->xsk_tx_list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_del_rcu(&xs->list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
@@ -205,8 +181,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	INIT_LIST_HEAD(&umem->xsk_tx_list);
-	spin_lock_init(&umem->xsk_tx_list_lock);
 
 	refcount_set(&umem->users, 1);
 

net/xdp/xdp_umem.h

@@ -10,8 +10,6 @@
 
 void xdp_get_umem(struct xdp_umem *umem);
 void xdp_put_umem(struct xdp_umem *umem);
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
 struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
 
 #endif /* XDP_UMEM_H_ */

net/xdp/xsk.c

@@ -51,14 +51,13 @@ EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
 
 void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -79,14 +78,13 @@ EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
 
 void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX))
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -302,7 +300,7 @@ void xsk_tx_release(struct xsk_buff_pool *pool)
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &pool->umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
@@ -312,11 +310,10 @@ EXPORT_SYMBOL(xsk_tx_release);
 
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
 			xs->tx->queue_empty_descs++;
 			continue;
@@ -524,7 +521,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 	WRITE_ONCE(xs->state, XSK_UNBOUND);
 
 	/* Wait for driver to stop using the xdp socket. */
-	xdp_del_sk_umem(xs->umem, xs);
+	xp_del_xsk(xs->pool, xs);
 	xs->dev = NULL;
 	synchronize_net();
 	dev_put(dev);
@@ -744,7 +741,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
 	xs->queue_id = qid;
-	xdp_add_sk_umem(xs->umem, xs);
+	xp_add_xsk(xs->pool, xs);
 
 out_unlock:
 	if (err) {

net/xdp/xsk_buff_pool.c

@@ -11,6 +11,30 @@
 #include "xdp_umem.h"
 #include "xsk.h"
 
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+}
+
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_del_rcu(&xs->tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+}
+
 static void xp_addr_unmap(struct xsk_buff_pool *pool)
 {
 	vunmap(pool->addrs);
@@ -63,6 +87,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xsk_tx_list);
+	spin_lock_init(&pool->xsk_tx_list_lock);
 	refcount_set(&pool->users, 1);
 
 	pool->fq = xs->fq_tmp;