[PATCH net v4 8/8] xsk: fix u64 descriptor address truncation on 32-bit architectures

[Jason Xing <kerneljasonxing@gmail.com>]

From: Jason Xing <kernelxing@tencent.com>

In copy mode TX, xsk_skb_destructor_set_addr() stores the 64-bit
descriptor address into skb_shinfo(skb)->destructor_arg (void *) via a
uintptr_t cast:

    skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t)addr | 0x1UL);

On 32-bit architectures uintptr_t is 32 bits, so the upper 32 bits of
the descriptor address are silently dropped. In unaligned mode the chunk
offset is encoded in bits 48-63 of the descriptor address
(XSK_UNALIGNED_BUF_OFFSET_SHIFT = 48), meaning the offset is lost
entirely. The completion queue then returns a truncated address to
userspace, making buffer recycling impossible.

Fix this by handling the 32-bit case in the destructor_arg helpers:

- xsk_skb_destructor_set_addr(): on !CONFIG_64BIT, allocate an
  xsk_addrs struct via kmem_cache_zalloc() to store the full u64
  address. Leave num_descs as 0 (zalloc) so that the subsequent
  xsk_inc_num_desc() brings it to the correct count of 1.

- xsk_skb_destructor_is_addr(): on !CONFIG_64BIT, return true only
  when destructor_arg is NULL (not yet set), false when it points to
  an xsk_addrs struct.

- xsk_skb_init_misc(): call xsk_skb_destructor_set_addr() first
  before touching any other skb fields; on failure return early so
  the skb destructor is never changed from sock_wfree.

The existing xsk_consume_skb() already handles 32-bit correctly after
these changes: xsk_skb_destructor_is_addr() returns false for any
allocated xsk_addrs, so the kmem_cache_free path is always taken.

The overhead is one extra kmem_cache_zalloc per first descriptor on
32-bit only; 64-bit builds are completely unchanged.

Closes: https://lore.kernel.org/all/20260419045824.D9E5EC2BCAF@smtp.kernel.org/
Fixes: 0ebc27a4c67d ("xsk: avoid data corruption on cq descriptor number")
Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
 net/xdp/xsk.c | 38 +++++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 7 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ed96f6ec8ff2..fe88f47741b5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -558,7 +558,10 @@ static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
 
 static bool xsk_skb_destructor_is_addr(struct sk_buff *skb)
 {
-	return (uintptr_t)skb_shinfo(skb)->destructor_arg & 0x1UL;
+	if (IS_ENABLED(CONFIG_64BIT))
+		return (uintptr_t)skb_shinfo(skb)->destructor_arg & 0x1UL;
+	else
+		return !skb_shinfo(skb)->destructor_arg;
 }
 
 static u64 xsk_skb_destructor_get_addr(struct sk_buff *skb)
@@ -566,9 +569,21 @@ static u64 xsk_skb_destructor_get_addr(struct sk_buff *skb)
 	return (u64)((uintptr_t)skb_shinfo(skb)->destructor_arg & ~0x1UL);
 }
 
-static void xsk_skb_destructor_set_addr(struct sk_buff *skb, u64 addr)
+static int xsk_skb_destructor_set_addr(struct sk_buff *skb, u64 addr)
 {
+	if (!IS_ENABLED(CONFIG_64BIT)) {
+		struct xsk_addrs *xsk_addr;
+
+		xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+		if (!xsk_addr)
+			return -ENOMEM;
+		xsk_addr->addrs[0] = addr;
+		skb_shinfo(skb)->destructor_arg = (void *)xsk_addr;
+		return 0;
+	}
+
 	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t)addr | 0x1UL);
+	return 0;
 }
 
 static void xsk_inc_num_desc(struct sk_buff *skb)
@@ -644,14 +659,20 @@ void xsk_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static void xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs,
-			      u64 addr)
+static int xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs,
+			     u64 addr)
 {
+	int err;
+
+	err = xsk_skb_destructor_set_addr(skb, addr);
+	if (err)
+		return err;
+
 	skb->dev = xs->dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
-	xsk_skb_destructor_set_addr(skb, addr);
+	return 0;
 }
 
 static void xsk_consume_skb(struct sk_buff *skb)
@@ -886,8 +907,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 		}
 	}
 
-	if (!xs->skb)
-		xsk_skb_init_misc(skb, xs, desc->addr);
+	if (!xs->skb) {
+		err = xsk_skb_init_misc(skb, xs, desc->addr);
+		if (unlikely(err))
+			goto free_err;
+	}
 	xsk_inc_num_desc(skb);
 
 	return skb;
-- 
2.41.3