net: Generic XDP

This provides a generic SKB based non-optimized XDP path which is used
if either the driver lacks a specific XDP implementation, or the user
requests it via a new IFLA_XDP_FLAGS value named XDP_FLAGS_SKB_MODE.

It is arguable that perhaps I should have required something like
this as part of the initial XDP feature merge.

I believe this is critical for two reasons:

1) Accessibility.  More people can play with XDP with less
   dependencies.  Yes I know we have XDP support in virtio_net, but
   that just creates another depedency for learning how to use this
   facility.

   I wrote this to make life easier for the XDP newbies.

2) As a model for what the expected semantics are.  If there is a pure
   generic core implementation, it serves as a semantic example for
   driver folks adding XDP support.

One thing I have not tried to address here is the issue of
XDP_PACKET_HEADROOM, thanks to Daniel for spotting that.  It seems
incredibly expensive to do a skb_cow(skb, XDP_PACKET_HEADROOM) or
whatever even if the XDP program doesn't try to push headers at all.
I think we really need the verifier to somehow propagate whether
certain XDP helpers are used or not.

v5:
 - Handle both negative and positive offset after running prog
 - Fix mac length in XDP_TX case (Alexei)
 - Use rcu_dereference_protected() in free_netdev (kbuild test robot)

v4:
 - Fix MAC header adjustmnet before calling prog (David Ahern)
 - Disable LRO when generic XDP is installed (Michael Chan)
 - Bypass qdisc et al. on XDP_TX and record the event (Alexei)
 - Do not perform generic XDP on reinjected packets (DaveM)

v3:
 - Make sure XDP program sees packet at MAC header, push back MAC
   header if we do XDP_TX.  (Alexei)
 - Elide GRO when generic XDP is in use.  (Alexei)
 - Add XDP_FLAG_SKB_MODE flag which the user can use to request generic
   XDP even if the driver has an XDP implementation.  (Alexei)
 - Report whether SKB mode is in use in rtnl_xdp_fill() via XDP_FLAGS
   attribute.  (Daniel)

v2:
 - Add some "fall through" comments in switch statements based
   upon feedback from Andrew Lunn
 - Use RCU for generic xdp_prog, thanks to Johannes Berg.

Tested-by: Andy Gospodarek <andy@greyhouse.net>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 150 insertions, 5 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index db6e31564d06..1b3317c026c6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -95,6 +95,7 @@
 #include <linux/notifier.h>
 #include <linux/skbuff.h>
 #include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/busy_poll.h>
@@ -4251,6 +4252,125 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	return ret;
 }
 
+static struct static_key generic_xdp_needed __read_mostly;
+
+static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	struct bpf_prog *new = xdp->prog;
+	int ret = 0;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG: {
+		struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
+
+		rcu_assign_pointer(dev->xdp_prog, new);
+		if (old)
+			bpf_prog_put(old);
+
+		if (old && !new) {
+			static_key_slow_dec(&generic_xdp_needed);
+		} else if (new && !old) {
+			static_key_slow_inc(&generic_xdp_needed);
+			dev_disable_lro(dev);
+		}
+		break;
+	}
+
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!rcu_access_pointer(dev->xdp_prog);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct bpf_prog *xdp_prog)
+{
+	struct xdp_buff xdp;
+	u32 act = XDP_DROP;
+	void *orig_data;
+	int hlen, off;
+	u32 mac_len;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_cloned(skb))
+		return XDP_PASS;
+
+	if (skb_linearize(skb))
+		goto do_drop;
+
+	/* The XDP program wants to see the packet starting at the MAC
+	 * header.
+	 */
+	mac_len = skb->data - skb_mac_header(skb);
+	hlen = skb_headlen(skb) + mac_len;
+	xdp.data = skb->data - mac_len;
+	xdp.data_end = xdp.data + hlen;
+	xdp.data_hard_start = skb->data - skb_headroom(skb);
+	orig_data = xdp.data;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	off = xdp.data - orig_data;
+	if (off > 0)
+		__skb_pull(skb, off);
+	else if (off < 0)
+		__skb_push(skb, -off);
+
+	switch (act) {
+	case XDP_TX:
+		__skb_push(skb, mac_len);
+		/* fall through */
+	case XDP_PASS:
+		break;
+
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(skb->dev, xdp_prog, act);
+		/* fall through */
+	case XDP_DROP:
+	do_drop:
+		kfree_skb(skb);
+		break;
+	}
+
+	return act;
+}
+
+/* When doing generic XDP we have to bypass the qdisc layer and the
+ * network taps in order to match in-driver-XDP behavior.
+ */
+static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_queue *txq;
+	bool free_skb = true;
+	int cpu, rc;
+
+	txq = netdev_pick_tx(dev, skb, NULL);
+	cpu = smp_processor_id();
+	HARD_TX_LOCK(dev, txq, cpu);
+	if (!netif_xmit_stopped(txq)) {
+		rc = netdev_start_xmit(skb, dev, txq, 0);
+		if (dev_xmit_complete(rc))
+			free_skb = false;
+	}
+	HARD_TX_UNLOCK(dev, txq);
+	if (free_skb) {
+		trace_xdp_exception(dev, xdp_prog, XDP_TX);
+		kfree_skb(skb);
+	}
+}
+
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
@@ -4262,6 +4382,21 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 
 	rcu_read_lock();
 
+	if (static_key_false(&generic_xdp_needed)) {
+		struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog);
+
+		if (xdp_prog) {
+			u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+
+			if (act != XDP_PASS) {
+				rcu_read_unlock();
+				if (act == XDP_TX)
+					generic_xdp_tx(skb, xdp_prog);
+				return NET_RX_DROP;
+			}
+		}
+	}
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -4494,7 +4629,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	enum gro_result ret;
 	int grow;
 
-	if (!(skb->dev->features & NETIF_F_GRO))
+	if (netif_elide_gro(skb->dev))
 		goto normal;
 
 	if (skb->csum_bad)
@@ -6723,6 +6858,7 @@ EXPORT_SYMBOL(dev_change_proto_down);
  */
 int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 {
+	int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp);
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct bpf_prog *prog = NULL;
 	struct netdev_xdp xdp;
@@ -6730,14 +6866,16 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 
 	ASSERT_RTNL();
 
-	if (!ops->ndo_xdp)
-		return -EOPNOTSUPP;
+	xdp_op = ops->ndo_xdp;
+	if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
+		xdp_op = generic_xdp_install;
+
 	if (fd >= 0) {
 		if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) {
 			memset(&xdp, 0, sizeof(xdp));
 			xdp.command = XDP_QUERY_PROG;
 
-			err = ops->ndo_xdp(dev, &xdp);
+			err = xdp_op(dev, &xdp);
 			if (err < 0)
 				return err;
 			if (xdp.prog_attached)
@@ -6753,7 +6891,7 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
 	xdp.command = XDP_SETUP_PROG;
 	xdp.prog = prog;
 
-	err = ops->ndo_xdp(dev, &xdp);
+	err = xdp_op(dev, &xdp);
 	if (err < 0 && prog)
 		bpf_prog_put(prog);
 
@@ -7793,6 +7931,7 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
 void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
+	struct bpf_prog *prog;
 
 	might_sleep();
 	netif_free_tx_queues(dev);
@@ -7811,6 +7950,12 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
 
+	prog = rcu_dereference_protected(dev->xdp_prog, 1);
+	if (prog) {
+		bpf_prog_put(prog);
+		static_key_slow_dec(&generic_xdp_needed);
+	}
+
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);