xsk: honor XDP_TX_METADATA in zero-copy path

The zero-copy path reads TX metadata whenever the UMEM has metadata space,
even if the descriptor does not set XDP_TX_METADATA. Pass descriptor
options through the metadata helpers and ignore metadata unless the option
is set.

This does not fix the existing per-WQE metadata handling for mlx5 MPWQEs.
Only the descriptor that starts a session passes through
xsk_tx_metadata_request() and configures offload state shared by the batch.
Metadata on descriptors joining an open session is therefore not validated
and does not configure its requested offloads. In addition, a non-NULL
metadata pointer from such a descriptor is treated as a timestamp
completion request even when XDP_TXMD_FLAGS_TIMESTAMP is not set, so its
metadata union can be overwritten with an unrequested timestamp. Fixing
mixed metadata states within one MPWQE requires a separate change.

Fixes: 48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Link: https://patch.msgid.link/20260819160535.1472459-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 16 insertions, 11 deletions

diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index 5dcc0d7f65b7..a452b7828ce4 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -196,7 +196,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc,
 	struct libeth_xdp_tx_desc desc;
 	struct xdp_desc_ctx ctx;
 
-	ctx = xsk_buff_raw_get_ctx(sq->pool, xdesc->addr);
+	ctx = xsk_buff_raw_get_ctx(sq->pool, xdesc->addr, xdesc->options);
 	desc = (typeof(desc)){
 		.addr	= ctx.dma,
 		__libeth_xdp_tx_len(xdesc->len),
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index b344789f5df8..d94aeb506379 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -240,6 +240,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
  * xsk_buff_raw_get_ctx - get &xdp_desc context
  * @pool: XSk buff pool desc address belongs to
  * @addr: desc address (from userspace)
+ * @options: desc options (from userspace)
  *
  * Wrapper for xp_raw_get_ctx() to be used in drivers, see its kdoc for
  * details.
@@ -248,9 +249,9 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
  * 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)
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr, u32 options)
 {
-	return xp_raw_get_ctx(pool, addr);
+	return xp_raw_get_ctx(pool, addr, options);
 }
 
 #define XDP_TXMD_FLAGS_VALID ( \
@@ -318,18 +319,20 @@ xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
 }
 
 static inline struct xsk_tx_metadata *
-__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
+__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data,
+			unsigned int options)
 {
-	if (!pool->tx_metadata_len)
+	if (!pool->tx_metadata_len || !(options & XDP_TX_METADATA))
 		return NULL;
 
 	return data - pool->tx_metadata_len;
 }
 
 static inline struct xsk_tx_metadata *
-xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr, u32 options)
 {
-	return __xsk_buff_get_metadata(pool, xp_raw_get_data(pool, addr));
+	return __xsk_buff_get_metadata(pool, xp_raw_get_data(pool, addr),
+				       options);
 }
 
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
@@ -510,7 +513,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 }
 
 static inline struct xdp_desc_ctx
-xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr, u32 options)
 {
 	return (struct xdp_desc_ctx){ };
 }
@@ -530,13 +533,14 @@ xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
 }
 
 static inline struct xsk_tx_metadata *
-__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
+__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data,
+			unsigned int options)
 {
 	return NULL;
 }
 
 static inline struct xsk_tx_metadata *
-xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr, u32 options)
 {
 	return NULL;
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 2bb1d122b1bc..a7df573784fd 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -154,7 +154,8 @@ struct xdp_desc_ctx {
 	struct xsk_tx_metadata *meta;
 };
 
-struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr);
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr,
+				   u32 options);
 
 static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
 {