6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Stanislav Fomichev <sdf@xxxxxxxxxxx>
[ Upstream commit d5e726d9143c5624135f5dc9e4069799adeef734 ]
Julian reports that commit 341ac980eab9 ("xsk: Support tx_metadata_len")
can break existing use cases which don't zero-initialize xdp_umem_reg
padding. Introduce new XDP_UMEM_TX_METADATA_LEN to make sure we
interpret the padding as tx_metadata_len only when being explicitly
asked.
Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len")
Reported-by: Julian Schindel <mail@xxxxxxxxxxxxxxxx>
Signed-off-by: Stanislav Fomichev <sdf@xxxxxxxxxxx>
Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx>
Link: https://lore.kernel.org/bpf/20240713015253.121248-2-sdf@xxxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
Documentation/networking/xsk-tx-metadata.rst | 16 ++++++++++------
include/uapi/linux/if_xdp.h | 4 ++++
net/xdp/xdp_umem.c | 9 ++++++---
3 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
index bd033fe95cca5..e76b0cfc32f7d 100644
--- a/Documentation/networking/xsk-tx-metadata.rst
+++ b/Documentation/networking/xsk-tx-metadata.rst
@@ -11,12 +11,16 @@ metadata on the receive side.
General Design
==============
-The headroom for the metadata is reserved via ``tx_metadata_len`` in
-``struct xdp_umem_reg``. The metadata length is therefore the same for
-every socket that shares the same umem. The metadata layout is a fixed UAPI,
-refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
-Thus, generally, the ``tx_metadata_len`` field above should contain
-``sizeof(union xsk_tx_metadata)``.
+The headroom for the metadata is reserved via ``tx_metadata_len`` and
+``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata
+length is therefore the same for every socket that shares the same umem.
+The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in
+``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len``
+field above should contain ``sizeof(union xsk_tx_metadata)``.
+
+Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN``
+flag was not required. Applications might attempt to create a umem
+with a flag first and if it fails, do another attempt without a flag.
The headroom and the metadata itself should be located right before
``xdp_desc->addr`` in the umem frame. Within a frame, the metadata
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index d316984104107..42ec5ddaab8dc 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -41,6 +41,10 @@
*/
#define XDP_UMEM_TX_SW_CSUM (1 << 1)
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN (1 << 2)
+
struct sockaddr_xdp {
__u16 sxdp_family;
__u16 sxdp_flags;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index caa340134b0e1..9f76ca591d54f 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
#define XDP_UMEM_FLAGS_VALID ( \
XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
XDP_UMEM_TX_SW_CSUM | \
+ XDP_UMEM_TX_METADATA_LEN | \
0)
static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
@@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
return -EINVAL;
- if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
- return -EINVAL;
+ if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
+ if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+ return -EINVAL;
+ umem->tx_metadata_len = mr->tx_metadata_len;
+ }
umem->size = size;
umem->headroom = headroom;
@@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
umem->pgs = NULL;
umem->user = NULL;
umem->flags = mr->flags;
- umem->tx_metadata_len = mr->tx_metadata_len;
INIT_LIST_HEAD(&umem->xsk_dma_list);
refcount_set(&umem->users, 1);
--
2.43.0
