Stanislav Fomichev wrote:
> This change actually defines the (initial) metadata layout
> that should be used by AF_XDP userspace (xsk_tx_metadata).
> The first field is flags which requests appropriate offloads,
> followed by the offload-specific fields. The supported per-device
> offloads are exported via netlink (new xsk-flags).
>
> The offloads themselves are still implemented in a bit of a
> framework-y fashion that's left from my initial kfunc attempt.
> I'm introducing new xsk_tx_metadata_ops which drivers are
> supposed to implement. The drivers are also supposed
> to call xsk_tx_metadata_request/xsk_tx_metadata_complete in
> the right places. Since xsk_tx_metadata_{request,_complete}
> are static inline, we don't incur any extra overhead doing
> indirect calls.
>
> The benefit of this scheme is as follows:
> - keeps all metadata layout parsing away from driver code
> - makes it easy to grep and see which drivers implement what
> - don't need any extra flags to maintain to keep track of that
> offloads are implemented; if the callback is implemented - the offload
> is supported (used by netlink reporting code)
>
> Two offloads are defined right now:
> 1. XDP_TX_METADATA_CHECKSUM: skb-style csum_start+csum_offset
> 2. XDP_TX_METADATA_TIMESTAMP: writes TX timestamp back into metadata
> area upon completion (tx_timestamp field)
>
> The offloads are also implemented for copy mode:
> 1. Extra XDP_TX_METADATA_CHECKSUM_SW to trigger skb_checksum_help; this
> might be useful as a reference implementation and for testing
> 2. XDP_TX_METADATA_TIMESTAMP writes SW timestamp from the skb
> destructor (note I'm reusing hwtstamps to pass metadata pointer)
>
> The struct is forward-compatible and can be extended in the future
> by appending more fields.
>
> Signed-off-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
> ---
> Documentation/netlink/specs/netdev.yaml | 19 ++++++++
> include/linux/netdevice.h | 27 +++++++++++
> include/linux/skbuff.h | 5 ++-
> include/net/xdp_sock.h | 60 +++++++++++++++++++++++++
> include/net/xdp_sock_drv.h | 13 ++++++
> include/uapi/linux/if_xdp.h | 35 +++++++++++++++
> include/uapi/linux/netdev.h | 15 +++++++
> net/core/netdev-genl.c | 12 ++++-
> net/xdp/xsk.c | 38 ++++++++++++++++
> net/xdp/xsk_queue.h | 2 +-
> tools/include/uapi/linux/if_xdp.h | 50 ++++++++++++++++++---
> 11 files changed, 268 insertions(+), 8 deletions(-)
>
> diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
> index e41015310a6e..bf9c1cc32614 100644
> --- a/Documentation/netlink/specs/netdev.yaml
> +++ b/Documentation/netlink/specs/netdev.yaml
> @@ -42,6 +42,19 @@ name: netdev
> doc:
> This feature informs if netdev implements non-linear XDP buffer
> support in ndo_xdp_xmit callback.
> + -
> + type: flags
> + name: xsk-flags
> + render-max: true
> + entries:
> + -
> + name: tx-timestamp
> + doc:
> + HW timestamping egress packets is supported by the driver.
> + -
> + name: tx-checksum
> + doc:
> + L3 checksum HW offload is supported by the driver.
>
> attribute-sets:
> -
> @@ -68,6 +81,12 @@ name: netdev
> type: u32
> checks:
> min: 1
> + -
> + name: xsk-features
> + doc: Bitmask of enabled AF_XDP features.
> + type: u64
> + enum: xsk-flags
> + enum-as-flags: true
>
> operations:
> list:
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 11652e464f5d..8b40c80557aa 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -1660,6 +1660,31 @@ struct xdp_metadata_ops {
> enum xdp_rss_hash_type *rss_type);
> };
>
> +/*
> + * This structure defines the AF_XDP TX metadata hooks for network devices.
> + * The following hooks can be defined; unless noted otherwise, they are
> + * optional and can be filled with a null pointer.
> + *
> + * int (*tmo_request_timestamp)(void *priv)
> + * This function is called when AF_XDP frame requested egress timestamp.
> + *
> + * int (*tmo_fill_timestamp)(void *priv)
> + * This function is called when AF_XDP frame, that had requested
> + * egress timestamp, received a completion. The hook needs to return
> + * the actual HW timestamp.
> + *
> + * int (*tmo_request_timestamp)(u16 csum_start, u16 csum_offset, void *priv)
typo: tmo_request_checksum
> + * This function is called when AF_XDP frame requested HW checksum
> + * offload. csum_start indicates position where checksumming should start.
> + * csum_offset indicates position where checksum should be stored.
> + *
> + */
> +struct xsk_tx_metadata_ops {
> + void (*tmo_request_timestamp)(void *priv);
> + u64 (*tmo_fill_timestamp)(void *priv);
> + void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
> +};
> +
> /**
> * enum netdev_priv_flags - &struct net_device priv_flags
> *
> @@ -1844,6 +1869,7 @@ enum netdev_ml_priv_type {
> * @netdev_ops: Includes several pointers to callbacks,
> * if one wants to override the ndo_*() functions
> * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks.
> + * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks.
> * @ethtool_ops: Management operations
> * @l3mdev_ops: Layer 3 master device operations
> * @ndisc_ops: Includes callbacks for different IPv6 neighbour
> @@ -2100,6 +2126,7 @@ struct net_device {
> unsigned long long priv_flags;
> const struct net_device_ops *netdev_ops;
> const struct xdp_metadata_ops *xdp_metadata_ops;
> + const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
> int ifindex;
> unsigned short gflags;
> unsigned short hard_header_len;
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index faaba050f843..5febc1a5131e 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -581,7 +581,10 @@ struct skb_shared_info {
> /* Warning: this field is not always filled in (UFO)! */
> unsigned short gso_segs;
> struct sk_buff *frag_list;
> - struct skb_shared_hwtstamps hwtstamps;
> + union {
> + struct skb_shared_hwtstamps hwtstamps;
> + struct xsk_tx_metadata *xsk_meta;
> + };
> unsigned int gso_type;
> u32 tskey;
>
> diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
> index 467b9fb56827..288fa58c4665 100644
> --- a/include/net/xdp_sock.h
> +++ b/include/net/xdp_sock.h
> @@ -90,6 +90,54 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
> int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
> void __xsk_map_flush(void);
>
> +/**
> + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
> + * and call appropriate xsk_tx_metadata_ops operation.
> + * @meta: pointer to AF_XDP metadata area
> + * @ops: pointer to struct xsk_tx_metadata_ops
> + * @priv: pointer to driver-private aread
> + *
> + * This function should be called by the networking device when
> + * it prepares AF_XDP egress packet.
> + */
> +static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
> + const struct xsk_tx_metadata_ops *ops,
> + void *priv)
> +{
> + if (!meta)
> + return;
> +
> + if (ops->tmo_request_timestamp)
> + if (meta->flags & XDP_TX_METADATA_TIMESTAMP)
> + ops->tmo_request_timestamp(priv);
> +
> + if (ops->tmo_request_checksum)
> + if (meta->flags & XDP_TX_METADATA_CHECKSUM)
> + ops->tmo_request_checksum(meta->csum_start, meta->csum_offset, priv);
> +}
Might be cheaper to test the flag in the hot cacheline before
dereferencing ops?
Also, just add these functions to net_device_ops directly,
rather than dereferencing another pointer to xsk_tx_metadata_ops?
