netdev - [PATCH RFC v2 5/9] veth: Add ndo_xdp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20180610160217.3146-6-toshiaki.makita1@gmail.com>
Date:   Mon, 11 Jun 2018 01:02:13 +0900
From:   Toshiaki Makita <toshiaki.makita1@...il.com>
To:     netdev@...r.kernel.org
Cc:     Toshiaki Makita <makita.toshiaki@....ntt.co.jp>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>
Subject: [PATCH RFC v2 5/9] veth: Add ndo_xdp_xmit

From: Toshiaki Makita <makita.toshiaki@....ntt.co.jp>

This allows NIC's XDP to redirect packets to veth. The destination veth
device enqueues redirected packets to the napi ring of its peer, then
they are processed by XDP on its peer veth device.
This can be thought as calling another XDP program by XDP program using
REDIRECT, when the peer enables driver XDP.

Note that when the peer veth device does not set driver xdp, redirected
packets will be dropped because the peer is not ready for NAPI.

v2:
- Drop the part converting xdp_frame into skb when XDP is not enabled.
- Implement bulk interface of ndo_xdp_xmit.
- Implement XDP_XMIT_FLUSH bit and drop ndo_xdp_flush.

Signed-off-by: Toshiaki Makita <makita.toshiaki@....ntt.co.jp>
---
 drivers/net/veth.c     | 39 +++++++++++++++++++++++++++++++++++++++
 include/linux/filter.h | 16 ++++++++++++++++
 net/core/filter.c      | 11 +----------
 3 files changed, 56 insertions(+), 10 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index cb3fa558fbe0..b809d609a642 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,6 +17,7 @@
 #include <net/rtnetlink.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 #include <linux/veth.h>
 #include <linux/module.h>
 #include <linux/bpf.h>
@@ -254,6 +255,43 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static int veth_xdp_xmit(struct net_device *dev, int n,
+			 struct xdp_frame **frames, u32 flags)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		return -ENXIO;
+
+	rcv_priv = netdev_priv(rcv);
+	/* xdp_ring is initialized on receive side? */
+	if (!rcu_access_pointer(rcv_priv->xdp_prog))
+		return -ENXIO;
+
+	spin_lock(&rcv_priv->xdp_tx_ring.producer_lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *frame = frames[i];
+
+		if (unlikely(xdp_ok_fwd_dev(rcv, frame->len) ||
+			     __ptr_ring_produce(&rcv_priv->xdp_tx_ring, frame))) {
+			xdp_return_frame_rx_napi(frame);
+			drops++;
+		}
+	}
+	spin_unlock(&rcv_priv->xdp_tx_ring.producer_lock);
+
+	if (flags & XDP_XMIT_FLUSH)
+		__veth_xdp_flush(rcv_priv);
+
+	return n - drops;
+}
+
 static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 					struct xdp_frame *frame)
 {
@@ -770,6 +808,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
+	.ndo_xdp_xmit		= veth_xdp_xmit,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 45fc0f5000d8..12777eb70b40 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -19,6 +19,7 @@
 #include <linux/cryptohash.h>
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
+#include <linux/if_vlan.h>
 
 #include <net/sch_generic.h>
 
@@ -786,6 +787,21 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
+static __always_inline int
+xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen)
+{
+	unsigned int len;
+
+	if (unlikely(!(fwd->flags & IFF_UP)))
+		return -ENETDOWN;
+
+	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+	if (pktlen > len)
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 /* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
  * same cpu context. Further for best results no more than a single map
  * for the do_redirect/do_flush pair should be used. This limitation is
diff --git a/net/core/filter.c b/net/core/filter.c
index 3d9ba7e5965a..05d9e84566a4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3216,16 +3216,7 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
 static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
 {
-	unsigned int len;
-
-	if (unlikely(!(fwd->flags & IFF_UP)))
-		return -ENETDOWN;
-
-	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len)
-		return -EMSGSIZE;
-
-	return 0;
+	return xdp_ok_fwd_dev(fwd, skb->len);
 }
 
 static int xdp_do_generic_redirect_map(struct net_device *dev,
-- 
2.14.3