From: Stanislav Fomichev <sdf.kernel@gmail.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, anthony.l.nguyen@intel.com,
przemyslaw.kitszel@intel.com, andrew+netdev@lunn.ch,
saeedm@nvidia.com, tariqt@nvidia.com, mbloch@nvidia.com,
maxime.chevallier@bootlin.com, mcoquelin.stm32@gmail.com,
alexandre.torgue@foss.st.com, aleksander.lobakin@intel.com,
horms@kernel.org, magnus.karlsson@intel.com,
maciej.fijalkowski@intel.com, sdf@fomichev.me, ast@kernel.org,
daniel@iogearbox.net, hawk@kernel.org, john.fastabend@gmail.com,
alice.kernel@fastmail.im, dtatulea@nvidia.com, witu@nvidia.com,
martin.lau@kernel.org, yoong.siang.song@intel.com,
rohan.g.thomas@intel.com, intel-wired-lan@lists.osuosl.org,
linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-stm32@st-md-mailman.stormreply.com,
linux-arm-kernel@lists.infradead.org, bpf@vger.kernel.org,
leon@kernel.org
Subject: [PATCH net-next 2/3] xsk: honor XDP_TX_METADATA in zero-copy path
Date: Mon, 10 Aug 2026 11:47:52 -0700 [thread overview]
Message-ID: <20260810184753.135756-3-sdf@fomichev.me> (raw)
In-Reply-To: <20260810184753.135756-1-sdf@fomichev.me>
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 change the existing per-WQE metadata handling for mlx5
MPWQEs, where the descriptor that starts a session configures offload state
shared by the batch. Supporting mixed metadata states within one MPWQE
requires a separate fix.
Fixes: 48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
---
drivers/net/ethernet/intel/igc/igc_main.c | 3 ++-
.../ethernet/mellanox/mlx5/core/en/xsk/tx.c | 2 +-
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++-
include/net/libeth/xsk.h | 2 +-
include/net/xdp_sock_drv.h | 22 +++++++++++--------
include/net/xsk_buff_pool.h | 3 ++-
net/xdp/xsk_buff_pool.c | 7 ++++--
7 files changed, 26 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8b9ce7cbfff9..1fb5f3cbe93c 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3071,7 +3071,8 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT;
dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
- meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
+ meta = xsk_buff_get_metadata(pool, xdp_desc.addr,
+ xdp_desc.options);
xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len);
bi = &ring->tx_buffer_info[ntu];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 3d19dad8f868..d194eeddd7b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -99,7 +99,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr);
xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr);
xdptxd.len = desc.len;
- meta = xsk_buff_get_metadata(pool, desc.addr);
+ meta = xsk_buff_get_metadata(pool, desc.addr, desc.options);
xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b2b7d0242dd3..efa35cfecc4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2723,7 +2723,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
tx_desc = stmmac_get_tx_desc(priv, tx_q, entry);
dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
- meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
+ meta = xsk_buff_get_metadata(pool, xdp_desc.addr,
+ xdp_desc.options);
xsk_buff_raw_dma_sync_for_device(pool, dma_addr, xdp_desc.len);
/* To return XDP buffer to XSK pool, we simple call
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)
{
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 78c14f106395..9d2d94f1fb75 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -763,6 +763,7 @@ EXPORT_SYMBOL(xp_raw_get_dma);
* xp_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)
*
* Helper for getting desc's DMA address and metadata pointer, if present.
* Saves one call on hotpath and double calculation of the actual address.
@@ -771,14 +772,16 @@ EXPORT_SYMBOL(xp_raw_get_dma);
* Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
* pointer, if it is present (initialized to %NULL otherwise).
*/
-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)
{
struct xdp_desc_ctx ret;
addr = __xp_raw_get_addr(pool, addr);
ret.dma = __xp_raw_get_dma(pool, addr);
- ret.meta = __xsk_buff_get_metadata(pool, __xp_raw_get_data(pool, addr));
+ ret.meta = __xsk_buff_get_metadata(pool, __xp_raw_get_data(pool, addr),
+ options);
return ret;
}
--
2.53.0-Meta
next prev parent reply other threads:[~2026-08-10 18:47 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-10 18:47 [PATCH net-next 0/3] xsk: pre-existing AF_XDP TX metadata fixes from Sashiko Stanislav Fomichev
2026-08-10 18:47 ` [PATCH net-next 1/3] xsk: align TX metadata layout across ABIs Stanislav Fomichev
2026-08-10 18:47 ` Stanislav Fomichev [this message]
2026-08-10 18:47 ` [PATCH net-next 3/3] net: stmmac: skip queueMaxSDU check for AF_XDP Stanislav Fomichev
2026-08-10 18:52 ` [PATCH net-next 0/3] xsk: pre-existing AF_XDP TX metadata fixes from Sashiko Stanislav Fomichev
2026-08-10 19:40 ` Jakub Kicinski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260810184753.135756-3-sdf@fomichev.me \
--to=sdf.kernel@gmail.com \
--cc=aleksander.lobakin@intel.com \
--cc=alexandre.torgue@foss.st.com \
--cc=alice.kernel@fastmail.im \
--cc=andrew+netdev@lunn.ch \
--cc=anthony.l.nguyen@intel.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=horms@kernel.org \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-stm32@st-md-mailman.stormreply.com \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=martin.lau@kernel.org \
--cc=maxime.chevallier@bootlin.com \
--cc=mbloch@nvidia.com \
--cc=mcoquelin.stm32@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=przemyslaw.kitszel@intel.com \
--cc=rohan.g.thomas@intel.com \
--cc=saeedm@nvidia.com \
--cc=sdf@fomichev.me \
--cc=tariqt@nvidia.com \
--cc=witu@nvidia.com \
--cc=yoong.siang.song@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox