xsk: add support for need_wakeup flag in AF_XDP rings

This commit adds support for a new flag called need_wakeup in the
AF_XDP Tx and fill rings. When this flag is set, it means that the
application has to explicitly wake up the kernel Rx (for the bit in
the fill ring) or kernel Tx (for bit in the Tx ring) processing by
issuing a syscall. Poll() can wake up both depending on the flags
submitted and sendto() will wake up tx processing only.

The main reason for introducing this new flag is to be able to
efficiently support the case when application and driver is executing
on the same core. Previously, the driver was just busy-spinning on the
fill ring if it ran out of buffers in the HW and there were none on
the fill ring. This approach works when the application is running on
another core as it can replenish the fill ring while the driver is
busy-spinning. Though, this is a lousy approach if both of them are
running on the same core as the probability of the fill ring getting
more entries when the driver is busy-spinning is zero. With this new
feature the driver now sets the need_wakeup flag and returns to the
application. The application can then replenish the fill queue and
then explicitly wake up the Rx processing in the kernel using the
syscall poll(). For Tx, the flag is only set to one if the driver has
no outstanding Tx completion interrupts. If it has some, the flag is
zero as it will be woken up by a completion interrupt anyway.

As a nice side effect, this new flag also improves the performance of
the case where application and driver are running on two different
cores as it reduces the number of syscalls to the kernel. The kernel
tells user space if it needs to be woken up by a syscall, and this
eliminates many of the syscalls.

This flag needs some simple driver support. If the driver does not
support this, the Rx flag is always zero and the Tx flag is always
one. This makes any application relying on this feature default to the
old behaviour of not requiring any syscalls in the Rx path and always
having to call sendto() in the Tx path.

For backwards compatibility reasons, this feature has to be explicitly
turned on using a new bind flag (XDP_USE_NEED_WAKEUP). I recommend
that you always turn it on as it so far always have had a positive
performance impact.

The name and inspiration of the flag has been taken from io_uring by
Jens Axboe. Details about this feature in io_uring can be found in
http://kernel.dk/io_uring.pdf, section 8.3.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 127 insertions, 19 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 1fe40a936456..9f900b56b15b 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;