In the __xsk_rcv() multi-buffer path, xsk_buff_alloc() is called in a loop without checking its return value. xsk_buff_can_alloc() only counts fill queue entries without validating their addresses, so it can succeed while xsk_buff_alloc() rejects all remaining entries and returns NULL. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000 KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:__xsk_rcv+0x426/0xc20 (net/xdp/xsk.c:350) Call Trace: xsk_generic_rcv+0x26d/0x5f0 xdp_do_generic_redirect+0x3c5/0xcf0 do_xdp_generic+0x92f/0xe70 __netif_receive_skb_core.constprop.0+0xf7e/0x2b30 Fix this with a two-stage transaction. First allocate and stage all buffers required for the packet using the pool's xskb_list, recycling them with xsk_buff_free() if any allocation fails. Only after the allocation stage succeeds, copy the data, reserve the RX descriptors, and release the buffers in an error-free loop using xsk_buff_get_frag(). Fixes: 804627751b42 ("xsk: add support for AF_XDP multi-buffer on Rx path") Reported-by: AutonomousCodeSecurity@microsoft.com Signed-off-by: Cen Zhang (Microsoft) --- v3: - Use pool's xskb_list and xsk_buff_get_frag() instead of a local staging list, per Maciej and Jason's review. - Set frags flag on head so xsk_buff_free() recycles the entire staged group in one call. - Guard against duplicate aligned Fill Ring addresses. v2: - Allocate all packet buffers before reserving RX descriptors. - Recycle partially allocated buffers instead of only cancelling the RX producer reservations. Link: https://lore.kernel.org/netdev/20260724164719.99563-1-blbllhy@gmail.com net/xdp/xsk.c | 39 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7855ee09c4b6..02ff3ad97410 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -297,10 +297,11 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { u32 frame_size = __xsk_pool_get_rx_frame_size(xs->pool); void *copy_from = xsk_copy_xdp_start(xdp), *copy_to; + struct xdp_buff *first, *next, *xsk_xdp; u32 from_len, meta_len, rem, num_desc; struct xdp_buff_xsk *xskb; - struct xdp_buff *xsk_xdp; skb_frag_t *frag; + u32 i; from_len = xdp->data_end - copy_from; meta_len = xdp->data - copy_from; @@ -343,11 +344,34 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) frag = &sinfo->frags[0]; } + if (WARN_ON_ONCE(!list_empty(&xs->pool->xskb_list))) + goto err_alloc; + + first = xsk_buff_alloc(xs->pool); + if (!first) + goto err_alloc; + + xdp_buff_set_frags_flag(first); + for (i = 1; i < num_desc; i++) { + xsk_xdp = xsk_buff_alloc(xs->pool); + if (!xsk_xdp) + goto err_free; + + xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); + if (unlikely(xsk_xdp == first || + !list_empty(&xskb->list_node))) + goto err_free; + + list_add_tail(&xskb->list_node, &xs->pool->xskb_list); + } + + xdp_buff_clear_frags_flag(first); + xsk_xdp = first; do { u32 to_len = frame_size + meta_len; u32 copied; - xsk_xdp = xsk_buff_alloc(xs->pool); + next = xsk_buff_get_frag(xsk_xdp); copy_to = xsk_xdp->data - meta_len; copied = xsk_copy_xdp(copy_to, ©_from, to_len, &from_len, &frag, rem); @@ -356,10 +380,21 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); __xsk_rcv_zc_safe(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0); + xsk_xdp = next; meta_len = 0; } while (rem); return 0; + +err_free: + /* Re-set frags flag; xsk_buff_alloc() may have cleared first->flags + * if the same Fill Ring address aliased back to first. + */ + xdp_buff_set_frags_flag(first); + xsk_buff_free(first); +err_alloc: + xs->rx_dropped++; + return -ENOMEM; } static bool xsk_tx_writeable(struct xdp_sock *xs) -- 2.53.0