[PATCH v2 net 2/5] xsk: drain continuation descs after overflow in xsk_build_skb()

[Maciej Fijalkowski <maciej.fijalkowski@intel.com>]

From: Jason Xing <kernelxing@tencent.com>

Fix generic xmit path multi-buffer logic when packets are either too big
(count of descriptors exceed MAX_SKB_FRAGS) or an invalid descriptor is
included in fragmented packet. Introduce xdp_sock::drain_cont and act
upon this flag - when it is set, keep on consuming descriptors from
AF_XDP Tx ring and put them directly onto Cq. Previously these
descriptors were silently lost and could never be reached again.

Fixes: cf24f5a5feea ("xsk: add support for AF_XDP multi-buffer on Tx path")
Closes: https://lore.kernel.org/all/20260425041726.85FB3C2BCB2@smtp.kernel.org/
Co-developed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # wrapped cq addr submission onto routine
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
 include/net/xdp_sock.h |  1 +
 net/xdp/xsk.c          | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index ebac60a3d8a1..8b51876efbed 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -80,6 +80,7 @@ struct xdp_sock {
 	 * call of __xsk_generic_xmit().
 	 */
 	struct sk_buff *skb;
+	bool drain_cont;
 
 	struct list_head map_list;
 	/* Protects map_list */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a7a83dc4546a..43791647cf18 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -737,6 +737,19 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
 	spin_unlock_irqrestore(&pool->cq_prod_lock, flags);
 }
 
+static void xsk_cq_submit_addr_single_locked(struct xsk_buff_pool *pool,
+					     struct xdp_desc *desc)
+{
+	unsigned long flags;
+	u32 idx;
+
+	spin_lock_irqsave(&pool->cq_prod_lock, flags);
+	idx = xskq_get_prod(pool->cq);
+	xskq_prod_write_addr(pool->cq, idx, desc->addr);
+	xskq_prod_submit_n(pool->cq, 1);
+	spin_unlock_irqrestore(&pool->cq_prod_lock, flags);
+}
+
 static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
 {
 	spin_lock(&pool->cq->cq_cached_prod_lock);
@@ -1063,11 +1076,22 @@ static int __xsk_generic_xmit(struct sock *sk)
 			goto out;
 		}
 
+		if (unlikely(xs->drain_cont)) {
+			xsk_cq_submit_addr_single_locked(xs->pool, &desc);
+
+			xs->tx->invalid_descs++;
+			xskq_cons_release(xs->tx);
+			xs->drain_cont = xp_mb_desc(&desc);
+			continue;
+		}
+
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
 			if (err != -EOVERFLOW)
 				goto out;
+			if (xp_mb_desc(&desc))
+				xs->drain_cont = true;
 			err = 0;
 			continue;
 		}
@@ -1101,9 +1125,24 @@ static int __xsk_generic_xmit(struct sock *sk)
 	}
 
 	if (xskq_has_descs(xs->tx)) {
+		bool reclaim_desc = xs->skb || xs->drain_cont;
+
+		if (reclaim_desc) {
+			err = xsk_cq_reserve_locked(xs->pool);
+			if (err) {
+				err = -EAGAIN;
+				goto out;
+			}
+		}
+
 		if (xs->skb)
 			xsk_drop_skb(xs->skb);
+
+		if (reclaim_desc)
+			xsk_cq_submit_addr_single_locked(xs->pool, &desc);
+
 		xskq_cons_release(xs->tx);
+		xs->drain_cont = xp_mb_desc(&desc);
 	}
 
 out:
-- 
2.43.0