xsk: Add TX timestamp and TX checksum offload support

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 what
  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_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset
2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata
   area upon completion (tx_timestamp field)

XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it 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.

Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 47 insertions, 2 deletions

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index fe61f85bcf33..10f2124e9e23 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -6,6 +6,7 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/xdp.h>
+#include <net/xdp_sock.h>
 
 #include "netdev-genl-gen.h"
 
@@ -13,6 +14,7 @@ static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		   const struct genl_info *info)
 {
+	u64 xsk_features = 0;
 	u64 xdp_rx_meta = 0;
 	void *hdr;
 
@@ -26,11 +28,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 
+	if (netdev->xsk_tx_metadata_ops) {
+		if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
+		if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
+	}
+
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
 			      netdev->xdp_features, NETDEV_A_DEV_PAD) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
-			      xdp_rx_meta, NETDEV_A_DEV_PAD)) {
+			      xdp_rx_meta, NETDEV_A_DEV_PAD) ||
+	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES,
+			      xsk_features, NETDEV_A_DEV_PAD)) {
 		genlmsg_cancel(rsp, hdr);
 		return -EINVAL;
 	}
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index c904356e2800..e83ade32f1fd 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -571,6 +571,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb)
 
 static void xsk_destruct_skb(struct sk_buff *skb)
 {
+	struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
+
+	if (compl->tx_timestamp) {
+		/* sw completion timestamp, not a real one */
+		*compl->tx_timestamp = ktime_get_tai_fast_ns();
+	}
+
 	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
@@ -655,8 +662,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
+	struct xsk_tx_metadata *meta = NULL;
 	struct net_device *dev = xs->dev;
 	struct sk_buff *skb = xs->skb;
+	bool first_frag = false;
 	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
@@ -687,6 +696,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				kfree_skb(skb);
 				goto free_err;
 			}
+
+			first_frag = true;
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
@@ -709,12 +720,35 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
+
+		if (first_frag && desc->options & XDP_TX_METADATA) {
+			if (unlikely(xs->pool->tx_metadata_len == 0)) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			meta = buffer - xs->pool->tx_metadata_len;
+
+			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+				if (unlikely(meta->request.csum_start +
+					     meta->request.csum_offset +
+					     sizeof(__sum16) > len)) {
+					err = -EINVAL;
+					goto free_err;
+				}
+
+				skb->csum_start = hr + meta->request.csum_start;
+				skb->csum_offset = meta->request.csum_offset;
+				skb->ip_summed = CHECKSUM_PARTIAL;
+			}
+		}
 	}
 
 	skb->dev = dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 	xsk_set_destructor_arg(skb);
 
 	return skb;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index c74a1372bcb9..6f2d1621c992 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -137,7 +137,7 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xp_unused_options_set(u32 options)
 {
-	return options & ~XDP_PKT_CONTD;
+	return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA);
 }
 
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,