net: tun: fix tun_xdp_one() for IFF_TUN mode

In tun_get_user(), skb->protocol is either taken from the tun_pi header
or inferred from the first byte of the packet in IFF_TUN mode, while
eth_type_trans() is called only in the IFF_TAP mode where the payload
is expected to be an Ethernet frame.

The equivalent code path in tun_xdp_one() was unconditionally using
eth_type_trans(), which is the wrong thing to do in IFF_TUN mode and
corrupts packets.

Pull the logic out to a separate tun_skb_set_protocol() function, and
call it from both tun_get_user() and tun_xdp_one().

XX: It is not entirely clear to me why it's OK to call eth_type_trans()
in some cases without first checking that enough of the Ethernet header
is linearly present by calling pskb_may_pull(). Such a check was never
present in the tun_xdp_one() code path, and commit 96aa1b22bd6bb ("tun:
correct header offsets in napi frags mode") deliberately added it *only*
for the IFF_NAPI_FRAGS mode.

I would like to see specific explanations of *why* it's ever valid and
necessary (is it so much faster?) to skip the pskb_may_pull() by setting
the 'no_pull_check' flag to tun_skb_set_protocol(), but for now I'll
settle for faithfully preserving the existing behaviour and pretending
it's someone else's problem.

Cc: Willem de Bruijn <willemb@google.com>
Fixes: 043d222f93ab ("tuntap: accept an array of XDP buffs through sendmsg()")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1b553f79adb023d8d7ccb9d6e75d29fb34f476f1..9379fa86fae94bffa51dc5a7aede8280d70ac033 100644 (file)
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1641,6 +1641,47 @@ out:
        return NULL;
 }
 
+static int tun_skb_set_protocol(struct tun_struct *tun, struct sk_buff *skb,
+                               __be16 pi_proto, bool no_pull_check)
+{
+       switch (tun->flags & TUN_TYPE_MASK) {
+       case IFF_TUN:
+               if (tun->flags & IFF_NO_PI) {
+                       u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+                       switch (ip_version) {
+                       case 4:
+                               pi_proto = htons(ETH_P_IP);
+                               break;
+                       case 6:
+                               pi_proto = htons(ETH_P_IPV6);
+                               break;
+                       default:
+                               return -EINVAL;
+                       }
+               }
+
+               skb_reset_mac_header(skb);
+               skb->protocol = pi_proto;
+               skb->dev = tun->dev;
+               break;
+       case IFF_TAP:
+               /* As an optimisation, no_pull_check can be set in the cases
+                * where the caller *knows* that eth_type_trans() will be OK
+                * because the Ethernet header is linearised at skb->data.
+                *
+                * XX: Or so I was reliably assured when I moved this code
+                * and didn't make it unconditional. dwmw2.
+                */
+               if (!no_pull_check && !pskb_may_pull(skb, ETH_HLEN))
+                       return -ENOMEM;
+
+               skb->protocol = eth_type_trans(skb, tun->dev);
+               break;
+       }
+       return 0;
+}
+
 /* Get packet from user space buffer */
 static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
                            void *msg_control, struct iov_iter *from,
@@ -1784,37 +1825,9 @@ drop:
                return -EINVAL;
        }
 
-       switch (tun->flags & TUN_TYPE_MASK) {
-       case IFF_TUN:
-               if (tun->flags & IFF_NO_PI) {
-                       u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
-
-                       switch (ip_version) {
-                       case 4:
-                               pi.proto = htons(ETH_P_IP);
-                               break;
-                       case 6:
-                               pi.proto = htons(ETH_P_IPV6);
-                               break;
-                       default:
-                               atomic_long_inc(&tun->dev->rx_dropped);
-                               kfree_skb(skb);
-                               return -EINVAL;
-                       }
-               }
-
-               skb_reset_mac_header(skb);
-               skb->protocol = pi.proto;
-               skb->dev = tun->dev;
-               break;
-       case IFF_TAP:
-               if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
-                       err = -ENOMEM;
-                       goto drop;
-               }
-               skb->protocol = eth_type_trans(skb, tun->dev);
-               break;
-       }
+       err = tun_skb_set_protocol(tun, skb, pi.proto, !frags);
+       if (err)
+               goto drop;
 
        /* copy skb_ubuf_info for callback when skb has no error */
        if (zerocopy) {
@@ -2335,12 +2348,24 @@ static int tun_xdp_one(struct tun_struct *tun,
        struct virtio_net_hdr *gso = NULL;
        struct bpf_prog *xdp_prog;
        struct sk_buff *skb = NULL;
+       __be16 proto = 0;
        u32 rxhash = 0, act;
        int buflen = hdr->buflen;
        int err = 0;
        bool skb_xdp = false;
        struct page *page;
 
+       if (!(tun->flags & IFF_NO_PI)) {
+               struct tun_pi *pi = tun_hdr;
+               tun_hdr += sizeof(*pi);
+
+               if (tun_hdr > xdp->data) {
+                       atomic_long_inc(&tun->rx_frame_errors);
+                       return -EINVAL;
+               }
+               proto = pi->proto;
+       }
+
        if (tun->flags & IFF_VNET_HDR) {
                gso = tun_hdr;
                tun_hdr += sizeof(*gso);
@@ -2413,7 +2438,13 @@ build:
                goto out;
        }
 
-       skb->protocol = eth_type_trans(skb, tun->dev);
+       err = tun_skb_set_protocol(tun, skb, proto, true);
+       if (err) {
+               atomic_long_inc(&tun->dev->rx_dropped);
+               kfree_skb(skb);
+               goto out;
+       }
+
        skb_reset_network_header(skb);
        skb_probe_transport_header(skb);
        skb_record_rx_queue(skb, tfile->queue_index);