Merge branch 'xdp: hints via kfuncs'

Stanislav Fomichev says:

====================

Please see the first patch in the series for the overall
design and use-cases.

See the following email from Toke for the per-packet metadata overhead:
https://lore.kernel.org/bpf/20221206024554.3826186-1-sdf@google.com/T/#m49d48ea08d525ec88360c7d14c4d34fb0e45e798

Recent changes:
- Keep new functions in en/xdp.c, do 'extern mlx5_xdp_metadata_ops' (Tariq)

- Remove mxbuf pointer and use xsk_buff_to_mxbuf (Tariq)

- Clarify xdp_buff vs 'XDP frame' (Jesper)

- Explicitly mention that AF_XDP RX descriptor lacks metadata size (Jesper)

- Drop libbpf_flags/xdp_flags from selftests and use ifindex instead
  of ifname (due to recent xsk.h refactoring)

Prior art (to record pros/cons for different approaches):

- Stable UAPI approach:
  https://lore.kernel.org/bpf/20220628194812.1453059-1-alexandr.lobakin@intel.com/
- Metadata+BTF_ID appoach:
  https://lore.kernel.org/bpf/166256538687.1434226.15760041133601409770.stgit@firesoul/
- v7:
  https://lore.kernel.org/bpf/20230112003230.3779451-1-sdf@google.com/
- v6:
  https://lore.kernel.org/bpf/20230104215949.529093-1-sdf@google.com/
- v5:
  https://lore.kernel.org/bpf/20221220222043.3348718-1-sdf@google.com/
- v4:
  https://lore.kernel.org/bpf/20221213023605.737383-1-sdf@google.com/
- v3:
  https://lore.kernel.org/bpf/20221206024554.3826186-1-sdf@google.com/
- v2:
  https://lore.kernel.org/bpf/20221121182552.2152891-1-sdf@google.com/
- v1:
  https://lore.kernel.org/bpf/20221115030210.3159213-1-sdf@google.com/
- kfuncs v2 RFC:
  https://lore.kernel.org/bpf/20221027200019.4106375-1-sdf@google.com/
- kfuncs v1 RFC:
  https://lore.kernel.org/bpf/20221104032532.1615099-1-sdf@google.com/

Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org

Stanislav Fomichev (13):
  bpf: Document XDP RX metadata
  bpf: Rename bpf_{prog,map}_is_dev_bound to is_offloaded
  bpf: Move offload initialization into late_initcall
  bpf: Reshuffle some parts of bpf/offload.c
  bpf: Introduce device-bound XDP programs
  selftests/bpf: Update expected test_offload.py messages
  bpf: XDP metadata RX kfuncs
  veth: Introduce veth_xdp_buff wrapper for xdp_buff
  veth: Support RX XDP metadata
  selftests/bpf: Verify xdp_metadata xdp->af_xdp path
  net/mlx4_en: Introduce wrapper for xdp_buff
  net/mlx4_en: Support RX XDP metadata
  selftests/bpf: Simple program to dump XDP RX metadata
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

5 files changed, 92 insertions, 8 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ae7771c7d750..ad4bb36d4c10 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1261,7 +1261,8 @@ struct bpf_prog_aux {
 	enum bpf_prog_type saved_dst_prog_type;
 	enum bpf_attach_type saved_dst_attach_type;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
-	bool offload_requested;
+	bool dev_bound; /* Program is bound to the netdev. */
+	bool offload_requested; /* Program is bound and offloaded to the netdev. */
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
 	bool sleepable;
@@ -2451,7 +2452,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
 
 int bpf_prog_offload_compile(struct bpf_prog *prog);
-void bpf_prog_offload_destroy(struct bpf_prog *prog);
+void bpf_prog_dev_bound_destroy(struct bpf_prog *prog);
 int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 			       struct bpf_prog *prog);
 
@@ -2479,14 +2480,26 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
 void unpriv_ebpf_notify(int new_state);
 
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
-int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
+int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
+			      struct bpf_prog_aux *prog_aux);
+void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id);
+int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr);
+int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog);
+void bpf_dev_bound_netdev_unregister(struct net_device *dev);
 
 static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
 {
+	return aux->dev_bound;
+}
+
+static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux)
+{
 	return aux->offload_requested;
 }
 
-static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
+bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs);
+
+static inline bool bpf_map_is_offloaded(struct bpf_map *map)
 {
 	return unlikely(map->ops == &bpf_map_offload_ops);
 }
@@ -2507,18 +2520,50 @@ void sock_map_unhash(struct sock *sk);
 void sock_map_destroy(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
-static inline int bpf_prog_offload_init(struct bpf_prog *prog,
-					union bpf_attr *attr)
+static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
+					    struct bpf_prog_aux *prog_aux)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog,
+						u32 func_id)
+{
+	return NULL;
+}
+
+static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog,
+					  union bpf_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog,
+					     struct bpf_prog *old_prog)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev)
+{
+}
+
+static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
+{
+	return false;
+}
+
+static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux)
+{
+	return false;
+}
+
+static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs)
 {
 	return false;
 }
 
-static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
+static inline bool bpf_map_is_offloaded(struct bpf_map *map)
 {
 	return false;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index aad12a179e54..90f2be194bc5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -74,6 +74,7 @@ struct udp_tunnel_nic_info;
 struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
+struct xdp_md;
 
 void synchronize_net(void);
 void netdev_set_default_ethtool_ops(struct net_device *dev,
@@ -1618,6 +1619,11 @@ struct net_device_ops {
 						  bool cycles);
 };
 
+struct xdp_metadata_ops {
+	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
+	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash);
+};
+
 /**
  * enum netdev_priv_flags - &struct net_device priv_flags
  *
@@ -1801,6 +1807,7 @@ 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.
  *	@ethtool_ops:	Management operations
  *	@l3mdev_ops:	Layer 3 master device operations
  *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
@@ -2050,6 +2057,7 @@ struct net_device {
 	unsigned int		flags;
 	unsigned long long	priv_flags;
 	const struct net_device_ops *netdev_ops;
+	const struct xdp_metadata_ops *xdp_metadata_ops;
 	int			ifindex;
 	unsigned short		gflags;
 	unsigned short		hard_header_len;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 55dbc68bfffc..91292aa13bc0 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -409,4 +409,25 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 
 #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
 
+#define XDP_METADATA_KFUNC_xxx	\
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \
+			   bpf_xdp_metadata_rx_timestamp) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \
+			   bpf_xdp_metadata_rx_hash) \
+
+enum {
+#define XDP_METADATA_KFUNC(name, _) name,
+XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+MAX_XDP_METADATA_KFUNC,
+};
+
+#ifdef CONFIG_NET
+u32 bpf_xdp_metadata_kfunc_id(int id);
+bool bpf_dev_bound_kfunc_id(u32 btf_id);
+#else
+static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; }
+static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; }
+#endif
+
 #endif /* __LINUX_NET_XDP_H__ */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index f787c3f524b0..3e952e569418 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -19,8 +19,11 @@ struct xdp_sock;
 struct device;
 struct page;
 
+#define XSK_PRIV_MAX 24
+
 struct xdp_buff_xsk {
 	struct xdp_buff xdp;
+	u8 cb[XSK_PRIV_MAX];
 	dma_addr_t dma;
 	dma_addr_t frame_dma;
 	struct xsk_buff_pool *pool;
@@ -28,6 +31,8 @@ struct xdp_buff_xsk {
 	struct list_head free_list_node;
 };
 
+#define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
+
 struct xsk_dma_map {
 	dma_addr_t *dma_pages;
 	struct device *dev;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index adae5b168f9d..ba0f0cfb5e42 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1156,6 +1156,11 @@ enum bpf_link_type {
  */
 #define BPF_F_XDP_HAS_FRAGS	(1U << 5)
 
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */