xsk: clear metadata pointer when no timestamp is requested

User space can change metadata flags after request processing. Rereading
them during completion can therefore make the kernel write a timestamp
that was not requested when the packet was submitted.

Clear the metadata pointer during request processing unless timestamp
completion is requested. Completion handling can then use the pointer
itself instead of rereading the flags.

On the mlx5 multi-packet WQE path metadata is evaluated per batch:
xsk_tx_metadata_request() runs only for the descriptor that starts a
session, just like the checksum offload that is applied once through the
shared WQE. Only that descriptor's pointer is reset, so completion
handling can record a timestamp for the other descriptors of the session
regardless of their own XDP_TXMD_FLAGS_TIMESTAMP bit. The write stays
inside the metadata area; the single-WQE, other zero-copy, and generic
paths reset the pointer per descriptor and are unaffected.

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/20260727161959.885642-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 06c081feff42d4f6895f2bfd8e30e32e851fffd8..2b2eb9b9d580e41079a1d8f64193e99f5cb3711e 100644 (file)
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -141,13 +141,16 @@ INDIRECT_CALLABLE_DECLARE(void xsk_destruct_skb(struct sk_buff *));
 static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
                                            struct xsk_tx_metadata_compl *compl)
 {
+       compl->tx_timestamp = NULL;
+
        if (!meta)
                return;
 
-       if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
-               compl->tx_timestamp = &meta->completion.tx_timestamp;
-       else
-               compl->tx_timestamp = NULL;
+       /* we can only arrive here if the completion timestamp has been
+        * requested via XDP_TXMD_FLAGS_TIMESTAMP, see xsk_tx_metadata_request
+        */
+
+       compl->tx_timestamp = &meta->completion.tx_timestamp;
 }
 
 /**
@@ -182,6 +185,9 @@ static inline void xsk_tx_metadata_request(struct xsk_tx_metadata **pmeta,
                if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
                        ops->tmo_request_checksum(meta->request.csum_start,
                                                  meta->request.csum_offset, priv);
+
+       if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP))
+               *pmeta = NULL;
 }
 
 /**

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index f906d51b6699045a8715be6075f41b9726a81cf1..fcc6f17f35760af3c36bcfdabc25960730927092 100644 (file)
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -998,6 +998,8 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer,
 
        if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
                skb->skb_mstamp_ns = meta->request.launch_time;
+       if (!(meta->flags & XDP_TXMD_FLAGS_TIMESTAMP))
+               meta = NULL;
        xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 
        return 0;