veth: Adjust hard_start offset on redirect XDP frames

When native XDP redirect into a veth device, the frame arrives in the
xdp_frame structure. It is then processed in veth_xdp_rcv_one(),
which can run a new XDP bpf_prog on the packet. Doing so requires
converting xdp_frame to xdp_buff, but the tricky part is that
xdp_frame memory area is located in the top (data_hard_start) memory
area that xdp_buff will point into.

The current code tried to protect the xdp_frame area, by assigning
xdp_buff.data_hard_start past this memory. This results in 32 bytes
less headroom to expand into via BPF-helper bpf_xdp_adjust_head().

This protect step is actually not needed, because BPF-helper
bpf_xdp_adjust_head() already reserve this area, and don't allow
BPF-prog to expand into it. Thus, it is safe to point data_hard_start
directly at xdp_frame memory area.

Fixes: 9fc8d518d9d5 ("veth: Handle xdp_frames in xdp napi ring")
Reported-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/158945338331.97035.5923525383710752178.stgit@firesoul

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index aece0e5..d5691bb 100644 (file)
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -564,13 +564,15 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
                                        struct veth_stats *stats)
 {
        void *hard_start = frame->data - frame->headroom;
-       void *head = hard_start - sizeof(struct xdp_frame);
        int len = frame->len, delta = 0;
        struct xdp_frame orig_frame;
        struct bpf_prog *xdp_prog;
        unsigned int headroom;
        struct sk_buff *skb;
 
+       /* bpf_xdp_adjust_head() assures BPF cannot access xdp_frame area */
+       hard_start -= sizeof(struct xdp_frame);
+
        rcu_read_lock();
        xdp_prog = rcu_dereference(rq->xdp_prog);
        if (likely(xdp_prog)) {
@@ -592,7 +594,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
                        break;
                case XDP_TX:
                        orig_frame = *frame;
-                       xdp.data_hard_start = head;
                        xdp.rxq->mem = frame->mem;
                        if (unlikely(veth_xdp_tx(rq, &xdp, bq) < 0)) {
                                trace_xdp_exception(rq->dev, xdp_prog, act);
@@ -605,7 +606,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
                        goto xdp_xmit;
                case XDP_REDIRECT:
                        orig_frame = *frame;
-                       xdp.data_hard_start = head;
                        xdp.rxq->mem = frame->mem;
                        if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
                                frame = &orig_frame;
@@ -629,7 +629,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
        rcu_read_unlock();
 
        headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
-       skb = veth_build_skb(head, headroom, len, 0);
+       skb = veth_build_skb(hard_start, headroom, len, 0);
        if (!skb) {
                xdp_return_frame(frame);
                stats->rx_drops++;