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>

Documentation/netlink/specs/netdev.yaml

@@ -45,7 +45,6 @@ definitions:
   -
     type: flags
     name: xdp-rx-metadata
-    render-max: true
     entries:
       -
         name: timestamp
@@ -55,6 +54,18 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+  -
+    type: flags
+    name: xsk-flags
+    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:
   -
@@ -86,6 +97,11 @@ attribute-sets:
              See Documentation/networking/xdp-rx-metadata.rst for more details.
         type: u64
         enum: xdp-rx-metadata
+      -
+        name: xsk-features
+        doc: Bitmask of enabled AF_XDP features.
+        type: u64
+        enum: xsk-flags
 
 operations:
   list:
@@ -103,6 +119,7 @@ operations:
             - xdp-features
             - xdp-zc-max-segs
             - xdp-rx-metadata-features
+            - xsk-features
       dump:
         reply: *dev-all
     -

include/linux/netdevice.h

@@ -1865,6 +1865,7 @@ enum netdev_stat_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
@@ -2128,6 +2129,7 @@ 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;

include/linux/skbuff.h

@@ -566,6 +566,15 @@ struct ubuf_info_msgzc {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
+/* Preserve some data across TX submission and completion.
+ *
+ * Note, this state is stored in the driver. Extending the layout
+ * might need some special care.
+ */
+struct xsk_tx_metadata_compl {
+	__u64 *tx_timestamp;
+};
+
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -578,7 +587,10 @@ 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_compl xsk_meta;
+	};
 	unsigned int	gso_type;
 	u32		tskey;
 

include/net/xdp_sock.h

@@ -93,12 +93,105 @@ struct xdp_sock {
 	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
 
+/*
+ * 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.
+ *
+ * void (*tmo_request_timestamp)(void *priv)
+ *     Called when AF_XDP frame requested egress timestamp.
+ *
+ * u64 (*tmo_fill_timestamp)(void *priv)
+ *     Called when AF_XDP frame, that had requested egress timestamp,
+ *     received a completion. The hook needs to return the actual HW timestamp.
+ *
+ * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv)
+ *     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);
+};
+
 #ifdef CONFIG_XDP_SOCKETS
 
 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_to_compl - Save enough relevant metadata information
+ *  to perform tx completion in the future.
+ *  @meta: pointer to AF_XDP metadata area
+ *  @compl: pointer to output struct xsk_tx_metadata_to_compl
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet. The value of @compl should be stored
+ *  and passed to xsk_tx_metadata_complete upon TX completion.
+ */
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+	if (!meta)
+		return;
+
+	if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+		compl->tx_timestamp = &meta->completion.tx_timestamp;
+	else
+		compl->tx_timestamp = NULL;
+}
+
+/**
+ *  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_TXMD_FLAGS_TIMESTAMP)
+			ops->tmo_request_timestamp(priv);
+
+	if (ops->tmo_request_checksum)
+		if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
+			ops->tmo_request_checksum(meta->request.csum_start,
+						  meta->request.csum_offset, priv);
+}
+
+/**
+ *  xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private aread
+ *
+ *  This function should be called by the networking device upon
+ *  AF_XDP egress completion.
+ */
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+	if (!compl)
+		return;
+
+	*compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
+}
+
 #else
 
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -115,6 +208,23 @@ static inline void __xsk_map_flush(void)
 {
 }
 
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+}
+
+static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta,
+					   const struct xsk_tx_metadata_ops *ops,
+					   void *priv)
+{
+}
+
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+}
+
 #endif /* CONFIG_XDP_SOCKETS */
 
 #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET)

include/net/xdp_sock_drv.h

@@ -165,6 +165,14 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	if (!pool->tx_metadata_len)
+		return NULL;
+
+	return xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
@@ -324,6 +332,11 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 }

include/net/xsk_buff_pool.h

@@ -33,6 +33,7 @@ struct xdp_buff_xsk {
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
+#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t))
 
 struct xsk_dma_map {
 	dma_addr_t *dma_pages;
@@ -234,4 +235,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
 	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
 }
 
+static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool)
+{
+	return pool->tx_metadata_len > 0;
+}
+
 #endif /* XSK_BUFF_POOL_H_ */

include/uapi/linux/if_xdp.h

@@ -106,6 +106,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of struct
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -122,4 +157,7 @@ struct xdp_desc {
  */
 #define XDP_PKT_CONTD (1 << 0)
 
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
 #endif /* _LINUX_IF_XDP_H */

include/uapi/linux/netdev.h

@@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_MASK = 3,
 };
 
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+
+	/* private: */
+	NETDEV_XSK_FLAGS_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)

net/core/netdev-genl.c

@@ -6,13 +6,15 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/xdp.h>
+#include <net/xdp_sock.h>
 
 #include "netdev-genl-gen.h"
 
 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;
 	}