xsk: Fix zero-copy AF_XDP fragment drop

AF_XDP should ensure that only a complete packet is sent to application.
In the zero-copy case, if the Rx queue gets full as fragments are being
enqueued, the remaining fragments are dropped.

For the multi-buffer case, add a check to ensure that the Rx queue has
enough space for all fragments of a packet before starting to enqueue
them.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-3-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index be882a8d473c3d44992577139e14899bb527643d..6149f6a798971fdf98bccffe4183e5e8af1ab070 100644 (file)
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,25 +167,31 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
        struct xdp_buff_xsk *pos, *tmp;
        struct list_head *xskb_list;
        u32 contd = 0;
+       u32 num_desc;
        int err;
 
-       if (frags)
-               contd = XDP_PKT_CONTD;
+       if (likely(!frags)) {
+               err = __xsk_rcv_zc(xs, xskb, len, contd);
+               if (err)
+                       goto err;
+               return 0;
+       }
 
-       err = __xsk_rcv_zc(xs, xskb, len, contd);
-       if (err)
+       contd = XDP_PKT_CONTD;
+       num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1;
+       if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+               xs->rx_queue_full++;
+               err = -ENOBUFS;
                goto err;
-       if (likely(!frags))
-               return 0;
+       }
 
+       __xsk_rcv_zc(xs, xskb, len, contd);
        xskb_list = &xskb->pool->xskb_list;
        list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
                if (list_is_singular(xskb_list))
                        contd = 0;
                len = pos->xdp.data_end - pos->xdp.data;
-               err = __xsk_rcv_zc(xs, pos, len, contd);
-               if (err)
-                       goto err;
+               __xsk_rcv_zc(xs, pos, len, contd);
                list_del_init(&pos->list_node);
        }