-
type: flags
name: xdp-rx-metadata
- render-max: true
entries:
-
name: timestamp
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:
-
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:
- xdp-features
- xdp-zc-max-segs
- xdp-rx-metadata-features
+ - xsk-features
dump:
reply: *dev-all
-
* @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
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;
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.
*/
/* 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;
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)
{
}
+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)
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);
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)
{
}
};
#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;
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_ */
#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;
*/
#define XDP_PKT_CONTD (1 << 0)
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
#endif /* _LINUX_IF_XDP_H */
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)
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/xdp.h>
+#include <net/xdp_sock.h>
#include "netdev-genl-gen.h"
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;
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;
}
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);
}
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) {
kfree_skb(skb);
goto free_err;
}
+
+ first_frag = true;
} else {
int nr_frags = skb_shinfo(skb)->nr_frags;
struct page *page;
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;
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,
*/
#define XDP_USE_NEED_WAKEUP (1 << 3)
/* By setting this option, userspace application indicates that it can
- * handle multiple descriptors per packet thus enabling xsk core to split
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
* multi-buffer XDP frames into multiple Rx descriptors. Without this set
- * such frames will be dropped by xsk.
+ * such frames will be dropped.
*/
-#define XDP_USE_SG (1 << 4)
+#define XDP_USE_SG (1 << 4)
/* Flags for xsk_umem_config flags */
#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
#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 union 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 union
+ * 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;
__u32 options;
};
-/* Flag indicating packet constitutes of multiple buffers*/
+/* UMEM descriptor is __u64 */
+
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
#define XDP_PKT_CONTD (1 << 0)
-/* UMEM descriptor is __u64 */
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
#endif /* _LINUX_IF_XDP_H */
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)
return netdev_xdp_rx_metadata_strmap[value];
}
+static const char * const netdev_xsk_flags_strmap[] = {
+ [0] = "tx-timestamp",
+ [1] = "tx-checksum",
+};
+
+const char *netdev_xsk_flags_str(enum netdev_xsk_flags value)
+{
+ value = ffs(value) - 1;
+ if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xsk_flags_strmap))
+ return NULL;
+ return netdev_xsk_flags_strmap[value];
+}
+
/* Policies */
struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
[NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, },
[NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, },
[NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, },
+ [NETDEV_A_DEV_XSK_FEATURES] = { .name = "xsk-features", .type = YNL_PT_U64, },
};
struct ynl_policy_nest netdev_dev_nest = {
return MNL_CB_ERROR;
dst->_present.xdp_rx_metadata_features = 1;
dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr);
+ } else if (type == NETDEV_A_DEV_XSK_FEATURES) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.xsk_features = 1;
+ dst->xsk_features = mnl_attr_get_u64(attr);
}
}
const char *netdev_op_str(int op);
const char *netdev_xdp_act_str(enum netdev_xdp_act value);
const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
+const char *netdev_xsk_flags_str(enum netdev_xsk_flags value);
/* Common nested types */
/* ============== NETDEV_CMD_DEV_GET ============== */
__u32 xdp_features:1;
__u32 xdp_zc_max_segs:1;
__u32 xdp_rx_metadata_features:1;
+ __u32 xsk_features:1;
} _present;
__u32 ifindex;
__u64 xdp_features;
__u32 xdp_zc_max_segs;
__u64 xdp_rx_metadata_features;
+ __u64 xsk_features;
};
void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp);
projects / linux.git / commitdiff