diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 69796d264f0638457526345f5cc423bf2c27bf17..6aebea2b18cbddf737521cd6f4d8cbe37b779eb6 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -27,6 +27,9 @@ struct xdp_umem_fq_reuse {
 	u64 handles[];
 };
 
+/* Flags for the umem flags field. */
+#define XDP_UMEM_USES_NEED_WAKEUP (1 << 0)
+
 struct xdp_umem {
 	struct xsk_queue *fq;
 	struct xsk_queue *cq;
@@ -41,10 +44,12 @@ struct xdp_umem {
 	struct work_struct work;
 	struct page **pgs;
 	u32 npgs;
+	u16 queue_id;
+	u8 need_wakeup;
+	u8 flags;
 	int id;
 	struct net_device *dev;
 	struct xdp_umem_fq_reuse *fq_reuse;
-	u16 queue_id;
 	bool zc;
 	spinlock_t xsk_list_lock;
 	struct list_head xsk_list;
@@ -95,6 +100,11 @@ struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
 					  struct xdp_umem_fq_reuse *newq);
 void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
 struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
+bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
 
 static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
 {
@@ -241,6 +251,27 @@ static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
 {
 }
 
+static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+{
+	return false;
+}
+
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index faaa5ca2a11767a3cfd967661f21645799b95f9c..62b80d57b72a58eacecb46fe7b441ca6976e59f2 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -16,6 +16,15 @@
 #define XDP_SHARED_UMEM	(1 << 0)
 #define XDP_COPY	(1 << 1) /* Force copy-mode */
 #define XDP_ZEROCOPY	(1 << 2) /* Force zero-copy mode */
+/* If this option is set, the driver might go sleep and in that case
+ * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be
+ * set. If it is set, the application need to explicitly wake up the
+ * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are
+ * running the driver and the application on the same core, you should
+ * use this option so that the kernel will yield to the user space
+ * application.
+ */
+#define XDP_USE_NEED_WAKEUP (1 << 3)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -25,10 +34,14 @@ struct sockaddr_xdp {
 	__u32 sxdp_shared_umem_fd;
 };
 
+/* XDP_RING flags */
+#define XDP_RING_NEED_WAKEUP (1 << 0)
+
 struct xdp_ring_offset {
 	__u64 producer;
 	__u64 consumer;
 	__u64 desc;
+	__u64 flags;
 };
 
 struct xdp_mmap_offsets {
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 6e2d4da4cdcdf255b87fc96b6aa25f1969e7c0ef..cda6feb1edb092ff7f95eda971080ff4ae21307e 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -106,6 +106,15 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	umem->dev = dev;
 	umem->queue_id = queue_id;
 
+	if (flags & XDP_USE_NEED_WAKEUP) {
+		umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
+		/* Tx needs to be explicitly woken up the first time.
+		 * Also for supporting drivers that do not implement this
+		 * feature. They will always have to call sendto().
+		 */
+		xsk_set_tx_need_wakeup(umem);
+	}
+
 	dev_hold(dev);
 
 	if (force_copy)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 1fe40a93645600c19a0ea14c09e5c62891fbebf6..9f900b56b15bed344f5b5492d2660ddf5a94bd5a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -55,6 +55,66 @@ void xsk_umem_discard_addr(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_umem_discard_addr);
 
+void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+{
+	if (umem->need_wakeup & XDP_WAKEUP_RX)
+		return;
+
+	umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
+	umem->need_wakeup |= XDP_WAKEUP_RX;
+}
+EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
+
+void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+{
+	struct xdp_sock *xs;
+
+	if (umem->need_wakeup & XDP_WAKEUP_TX)
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+		xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
+	}
+	rcu_read_unlock();
+
+	umem->need_wakeup |= XDP_WAKEUP_TX;
+}
+EXPORT_SYMBOL(xsk_set_tx_need_wakeup);
+
+void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+{
+	if (!(umem->need_wakeup & XDP_WAKEUP_RX))
+		return;
+
+	umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
+	umem->need_wakeup &= ~XDP_WAKEUP_RX;
+}
+EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
+
+void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+{
+	struct xdp_sock *xs;
+
+	if (!(umem->need_wakeup & XDP_WAKEUP_TX))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+		xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
+	}
+	rcu_read_unlock();
+
+	umem->need_wakeup &= ~XDP_WAKEUP_TX;
+}
+EXPORT_SYMBOL(xsk_clear_tx_need_wakeup);
+
+bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+{
+	return umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
+}
+EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
+
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	void *to_buf, *from_buf;
@@ -320,6 +380,12 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock,
 	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
+	struct net_device *dev = xs->dev;
+	struct xdp_umem *umem = xs->umem;
+
+	if (umem->need_wakeup)
+		dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
+						umem->need_wakeup);
 
 	if (xs->rx && !xskq_empty_desc(xs->rx))
 		mask |= POLLIN | POLLRDNORM;
@@ -428,7 +494,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		return -EINVAL;
 
 	flags = sxdp->sxdp_flags;
-	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
+	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY |
+		      XDP_USE_NEED_WAKEUP))
 		return -EINVAL;
 
 	rtnl_lock();
@@ -455,7 +522,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		struct xdp_sock *umem_xs;
 		struct socket *sock;
 
-		if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY)) {
+		if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) ||
+		    (flags & XDP_USE_NEED_WAKEUP)) {
 			/* Cannot specify flags for shared sockets. */
 			err = -EINVAL;
 			goto out_unlock;
@@ -550,6 +618,9 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		}
 		q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx;
 		err = xsk_init_queue(entries, q, false);
+		if (!err && optname == XDP_TX_RING)
+			/* Tx needs to be explicitly woken up the first time */
+			xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
@@ -611,6 +682,20 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 	return -ENOPROTOOPT;
 }
 
+static void xsk_enter_rxtx_offsets(struct xdp_ring_offset_v1 *ring)
+{
+	ring->producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
+	ring->consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
+	ring->desc = offsetof(struct xdp_rxtx_ring, desc);
+}
+
+static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring)
+{
+	ring->producer = offsetof(struct xdp_umem_ring, ptrs.producer);
+	ring->consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
+	ring->desc = offsetof(struct xdp_umem_ring, desc);
+}
+
 static int xsk_getsockopt(struct socket *sock, int level, int optname,
 			  char __user *optval, int __user *optlen)
 {
@@ -650,26 +735,49 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 	case XDP_MMAP_OFFSETS:
 	{
 		struct xdp_mmap_offsets off;
+		struct xdp_mmap_offsets_v1 off_v1;
+		bool flags_supported = true;
+		void *to_copy;
 
-		if (len < sizeof(off))
+		if (len < sizeof(off_v1))
 			return -EINVAL;
+		else if (len < sizeof(off))
+			flags_supported = false;
+
+		if (flags_supported) {
+			/* xdp_ring_offset is identical to xdp_ring_offset_v1
+			 * except for the flags field added to the end.
+			 */
+			xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *)
+					       &off.rx);
+			xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *)
+					       &off.tx);
+			xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *)
+					       &off.fr);
+			xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *)
+					       &off.cr);
+			off.rx.flags = offsetof(struct xdp_rxtx_ring,
+						ptrs.flags);
+			off.tx.flags = offsetof(struct xdp_rxtx_ring,
+						ptrs.flags);
+			off.fr.flags = offsetof(struct xdp_umem_ring,
+						ptrs.flags);
+			off.cr.flags = offsetof(struct xdp_umem_ring,
+						ptrs.flags);
+
+			len = sizeof(off);
+			to_copy = &off;
+		} else {
+			xsk_enter_rxtx_offsets(&off_v1.rx);
+			xsk_enter_rxtx_offsets(&off_v1.tx);
+			xsk_enter_umem_offsets(&off_v1.fr);
+			xsk_enter_umem_offsets(&off_v1.cr);
+
+			len = sizeof(off_v1);
+			to_copy = &off_v1;
+		}
 
-		off.rx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
-		off.rx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
-		off.rx.desc	= offsetof(struct xdp_rxtx_ring, desc);
-		off.tx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
-		off.tx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
-		off.tx.desc	= offsetof(struct xdp_rxtx_ring, desc);
-
-		off.fr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
-		off.fr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
-		off.fr.desc	= offsetof(struct xdp_umem_ring, desc);
-		off.cr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
-		off.cr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
-		off.cr.desc	= offsetof(struct xdp_umem_ring, desc);
-
-		len = sizeof(off);
-		if (copy_to_user(optval, &off, len))
+		if (copy_to_user(optval, to_copy, len))
 			return -EFAULT;
 		if (put_user(len, optlen))
 			return -EFAULT;
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index ba81206104266c4f662db880a757f30c8ff97fb7..4cfd106bdb5335ce878f936dd61b26f9914ff0b7 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -4,6 +4,19 @@
 #ifndef XSK_H_
 #define XSK_H_
 
+struct xdp_ring_offset_v1 {
+	__u64 producer;
+	__u64 consumer;
+	__u64 desc;
+};
+
+struct xdp_mmap_offsets_v1 {
+	struct xdp_ring_offset_v1 rx;
+	struct xdp_ring_offset_v1 tx;
+	struct xdp_ring_offset_v1 fr;
+	struct xdp_ring_offset_v1 cr;
+};
+
 static inline struct xdp_sock *xdp_sk(struct sock *sk)
 {
 	return (struct xdp_sock *)sk;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 909c5168ed0f87c3d0e1d14359efb67fe0bebab1..dd9e985c2461cdf0fbd442d979545182d33704c5 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -16,6 +16,7 @@
 struct xdp_ring {
 	u32 producer ____cacheline_aligned_in_smp;
 	u32 consumer ____cacheline_aligned_in_smp;
+	u32 flags;
 };
 
 /* Used for the RX and TX queues for packets */