xsk: validate metadata when processing requests

The zero-copy path validates TX metadata while obtaining the descriptor
context, then reads it again later when preparing the hardware request.
User space can change the metadata between those operations and bypass the
original validation.

Validate the metadata in xsk_tx_metadata_request() and use the resulting
flags snapshot for every feature check. Read request fields once so all
zero-copy drivers process only values observed after successful
validation.

Fixes: ca4419f15abd ("xsk: Add launch time hardware offload support to XDP Tx metadata")
Cc: Cen Zhang (Microsoft) <blbllhy@gmail.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260727161959.885642-7-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 28 insertions, 25 deletions

diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index e2fa6bf6b1b3..5dcc0d7f65b7 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -205,7 +205,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc,
 	BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo));
 	tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo;
 
-	xsk_tx_metadata_request(&ctx.meta, tmo, &desc);
+	xsk_tx_metadata_request(sq->pool, &ctx.meta, tmo, &desc);
 
 	return desc;
 }
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index f87c4215673e..b344789f5df8 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -245,7 +245,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
  * details.
  *
  * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
- * pointer, if it is present and valid (initialized to %NULL otherwise).
+ * pointer, if it is present (initialized to %NULL otherwise).
  */
 static inline struct xdp_desc_ctx
 xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
@@ -274,54 +274,56 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
 /**
  *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
  *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @pool: pointer to AF_XDP buffer pool, used to validate the metadata
  *  @pmeta: pointer to pointer to AF_XDP metadata area
  *  @ops: pointer to struct xsk_tx_metadata_ops
- *  @priv: pointer to driver-private aread
+ *  @priv: pointer to driver-private area
  *
  *  This function should be called by the networking device when
  *  it prepares AF_XDP egress packet.
  */
-static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta,
-					   const struct xsk_tx_metadata_ops *ops,
-					   void *priv)
+static inline void
+xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
+			struct xsk_tx_metadata **pmeta,
+			const struct xsk_tx_metadata_ops *ops, void *priv)
 {
 	const struct xsk_tx_metadata *meta = *pmeta;
+	u64 flags;
 
 	if (!meta)
 		return;
 
+	if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) {
+		*pmeta = NULL;
+		return; /* no way to signal the error to the user */
+	}
+
 	if (ops->tmo_request_launch_time)
-		if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
-			ops->tmo_request_launch_time(meta->request.launch_time,
-						     priv);
+		if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+			ops->tmo_request_launch_time(
+				READ_ONCE(meta->request.launch_time), priv);
 
 	if (ops->tmo_request_timestamp)
-		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+		if (flags & XDP_TXMD_FLAGS_TIMESTAMP)
 			ops->tmo_request_timestamp(priv);
 
 	if (ops->tmo_request_checksum)
-		if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
-			ops->tmo_request_checksum(meta->request.csum_start,
-						  meta->request.csum_offset, priv);
+		if (flags & XDP_TXMD_FLAGS_CHECKSUM)
+			ops->tmo_request_checksum(
+				READ_ONCE(meta->request.csum_start),
+				READ_ONCE(meta->request.csum_offset), priv);
 
-	if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP))
+	if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP))
 		*pmeta = NULL;
 }
 
 static inline struct xsk_tx_metadata *
 __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
 {
-	struct xsk_tx_metadata *meta;
-	u64 flags;
-
 	if (!pool->tx_metadata_len)
 		return NULL;
 
-	meta = data - pool->tx_metadata_len;
-	if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags)))
-		return NULL; /* no way to signal the error to the user */
-
-	return meta;
+	return data - pool->tx_metadata_len;
 }
 
 static inline struct xsk_tx_metadata *
@@ -520,9 +522,10 @@ xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
 	return false;
 }
 
-static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta,
-					   const struct xsk_tx_metadata_ops *ops,
-					   void *priv)
+static inline void
+xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
+			struct xsk_tx_metadata **pmeta,
+			const struct xsk_tx_metadata_ops *ops, void *priv)
 {
 }