From 887596095ec2a9ea39ffcf98f27bf2e77c5eb512 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:26 -0800 Subject: [PATCH 1/9] bpf: Clean up sockmap related Kconfigs As suggested by John, clean up sockmap related Kconfigs: Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream parser, to reflect its name. Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL and CONFIG_INET, the latter is still needed at this point because of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched, as it is used by non-sockmap cases. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Reviewed-by: Lorenz Bauer Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com --- include/linux/bpf.h | 26 ++++--- include/linux/bpf_types.h | 6 +- include/linux/skmsg.h | 18 +++++ include/net/tcp.h | 16 +++-- include/net/udp.h | 4 +- init/Kconfig | 1 + net/Kconfig | 6 +- net/core/Makefile | 6 +- net/core/skmsg.c | 145 +++++++++++++++++++++----------------- net/core/sock_map.c | 2 + net/ipv4/Makefile | 2 +- net/ipv4/tcp_bpf.c | 4 +- 12 files changed, 133 insertions(+), 103 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ae2c35641619..2be47ada5f2d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1778,7 +1778,7 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -#if defined(CONFIG_BPF_STREAM_PARSER) +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); @@ -1786,7 +1786,18 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); + +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); #else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL static inline int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which) @@ -1811,20 +1822,7 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } -#endif /* CONFIG_BPF_STREAM_PARSER */ -#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -void bpf_sk_reuseport_detach(struct sock *sk); -int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, - void *value); -int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags); -#else -static inline void bpf_sk_reuseport_detach(struct sock *sk) -{ -} - -#ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b9edee336d80..f883f01a5061 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -103,10 +103,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) -#if defined(CONFIG_BPF_STREAM_PARSER) -BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) -#endif #ifdef CONFIG_BPF_LSM BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) #endif @@ -116,6 +112,8 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) #endif #ifdef CONFIG_INET +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8edbbf5f2f93..db7a08be4725 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,9 @@ struct sk_psock_link { }; struct sk_psock_parser { +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; +#endif bool enabled; void (*saved_data_ready)(struct sock *sk); }; @@ -305,9 +307,25 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sk_psock *sk_psock_init(struct sock *sk, int node); +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); +#else +static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) +{ + return -EOPNOTSUPP; +} + +static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) +{ +} + +static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) +{ +} +#endif + void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); diff --git a/include/net/tcp.h b/include/net/tcp.h index 963cd86d12dd..c00e125dcfb9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2222,25 +2222,27 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +#ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); -#else -static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) -{ -} -#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif /* CONFIG_BPF_SYSCALL */ -#ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) +static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ +} +#endif + #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, diff --git a/include/net/udp.h b/include/net/udp.h index a132a02b2f2c..d4d064c59232 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -515,9 +515,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, return segs; } -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL struct sk_psock; struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); -#endif /* BPF_STREAM_PARSER */ +#endif #endif /* _UDP_H */ diff --git a/init/Kconfig b/init/Kconfig index 096e1af5c586..66cef5eac275 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1702,6 +1702,7 @@ config BPF_SYSCALL select BPF select IRQ_WORK select TASKS_TRACE_RCU + select NET_SOCK_MSG if INET default n help Enable the bpf() system call that allows to manipulate eBPF diff --git a/net/Kconfig b/net/Kconfig index 8cea808ad9e8..0ead7ec0d2bd 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -317,13 +317,9 @@ config BPF_STREAM_PARSER select STREAM_PARSER select NET_SOCK_MSG help - Enabling this allows a stream parser to be used with + Enabling this allows a TCP stream parser to be used with BPF_MAP_TYPE_SOCKMAP. - BPF_MAP_TYPE_SOCKMAP provides a map type to use with network sockets. - It can be used to enforce socket policy, implement socket redirects, - etc. - config NET_FLOW_LIMIT bool depends on RPS diff --git a/net/core/Makefile b/net/core/Makefile index 3e2c378e5f31..0c2233c826fd 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -16,7 +16,6 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o -obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_FIB_RULES) += fib_rules.o @@ -28,10 +27,13 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o -obj-$(CONFIG_BPF_STREAM_PARSER) += sock_map.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o +ifeq ($(CONFIG_INET),y) +obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o +obj-$(CONFIG_BPF_SYSCALL) += sock_map.o +endif obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1261512d6807..e017744111e1 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -645,15 +645,15 @@ static void sk_psock_link_destroy(struct sk_psock *psock) } } +static void sk_psock_done_strp(struct sk_psock *psock); + static void sk_psock_destroy_deferred(struct work_struct *gc) { struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - /* Parser has been stopped */ - if (psock->progs.skb_parser) - strp_done(&psock->parser.strp); + sk_psock_done_strp(psock); cancel_work_sync(&psock->work); @@ -750,14 +750,6 @@ static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, return bpf_prog_run_pin_on_cpu(prog, skb); } -static struct sk_psock *sk_psock_from_strp(struct strparser *strp) -{ - struct sk_psock_parser *parser; - - parser = container_of(strp, struct sk_psock_parser, strp); - return container_of(parser, struct sk_psock, parser); -} - static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; @@ -866,6 +858,24 @@ out_free: } } +static void sk_psock_write_space(struct sock *sk) +{ + struct sk_psock *psock; + void (*write_space)(struct sock *sk) = NULL; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) { + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + } + rcu_read_unlock(); + if (write_space) + write_space(sk); +} + +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { struct sk_psock *psock; @@ -897,6 +907,14 @@ static int sk_psock_strp_read_done(struct strparser *strp, int err) return err; } +static struct sk_psock *sk_psock_from_strp(struct strparser *strp) +{ + struct sk_psock_parser *parser; + + parser = container_of(strp, struct sk_psock_parser, strp); + return container_of(parser, struct sk_psock, parser); +} + static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) { struct sk_psock *psock = sk_psock_from_strp(strp); @@ -933,6 +951,56 @@ static void sk_psock_strp_data_ready(struct sock *sk) rcu_read_unlock(); } +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) +{ + static const struct strp_callbacks cb = { + .rcv_msg = sk_psock_strp_read, + .read_sock_done = sk_psock_strp_read_done, + .parse_msg = sk_psock_strp_parse, + }; + + psock->parser.enabled = false; + return strp_init(&psock->parser.strp, sk, &cb); +} + +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (parser->enabled) + return; + + parser->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = sk_psock_strp_data_ready; + sk->sk_write_space = sk_psock_write_space; + parser->enabled = true; +} + +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (!parser->enabled) + return; + + sk->sk_data_ready = parser->saved_data_ready; + parser->saved_data_ready = NULL; + strp_stop(&parser->strp); + parser->enabled = false; +} + +static void sk_psock_done_strp(struct sk_psock *psock) +{ + /* Parser has been stopped */ + if (psock->progs.skb_parser) + strp_done(&psock->parser.strp); +} +#else +static void sk_psock_done_strp(struct sk_psock *psock) +{ +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, unsigned int offset, size_t orig_len) { @@ -984,35 +1052,6 @@ static void sk_psock_verdict_data_ready(struct sock *sk) sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv); } -static void sk_psock_write_space(struct sock *sk) -{ - struct sk_psock *psock; - void (*write_space)(struct sock *sk) = NULL; - - rcu_read_lock(); - psock = sk_psock(sk); - if (likely(psock)) { - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); - write_space = psock->saved_write_space; - } - rcu_read_unlock(); - if (write_space) - write_space(sk); -} - -int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) -{ - static const struct strp_callbacks cb = { - .rcv_msg = sk_psock_strp_read, - .read_sock_done = sk_psock_strp_read_done, - .parse_msg = sk_psock_strp_parse, - }; - - psock->parser.enabled = false; - return strp_init(&psock->parser.strp, sk, &cb); -} - void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) { struct sk_psock_parser *parser = &psock->parser; @@ -1026,32 +1065,6 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) parser->enabled = true; } -void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) -{ - struct sk_psock_parser *parser = &psock->parser; - - if (parser->enabled) - return; - - parser->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; - parser->enabled = true; -} - -void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) -{ - struct sk_psock_parser *parser = &psock->parser; - - if (!parser->enabled) - return; - - sk->sk_data_ready = parser->saved_data_ready; - parser->saved_data_ready = NULL; - strp_stop(&parser->strp); - parser->enabled = false; -} - void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { struct sk_psock_parser *parser = &psock->parser; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d758fb83c884..ee3334dd3a38 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1461,9 +1461,11 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, case BPF_SK_MSG_VERDICT: pprog = &progs->msg_parser; break; +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: pprog = &progs->skb_parser; break; +#endif case BPF_SK_SKB_STREAM_VERDICT: pprog = &progs->skb_verdict; break; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 5b77a46885b9..bbdd9c44f14e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -62,7 +62,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o -obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o +obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index bc7d2a586e18..17c322b875fd 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -229,7 +229,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, } EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL static bool tcp_bpf_stream_read(const struct sock *sk) { struct sk_psock *psock; @@ -629,4 +629,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) newsk->sk_prot = sk->sk_prot_creator; } -#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif /* CONFIG_BPF_SYSCALL */ From 5a685cd94b21a88efa6be77169eddef525368034 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:27 -0800 Subject: [PATCH 2/9] skmsg: Get rid of struct sk_psock_parser struct sk_psock_parser is embedded in sk_psock, it is unnecessary as skb verdict also uses ->saved_data_ready. We can simply fold these fields into sk_psock, and get rid of ->enabled. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 19 ++++++---------- net/core/skmsg.c | 53 +++++++++++++------------------------------ net/core/sock_map.c | 8 +++---- 3 files changed, 27 insertions(+), 53 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index db7a08be4725..22e26f82de33 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -70,14 +70,6 @@ struct sk_psock_link { void *link_raw; }; -struct sk_psock_parser { -#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) - struct strparser strp; -#endif - bool enabled; - void (*saved_data_ready)(struct sock *sk); -}; - struct sk_psock_work_state { struct sk_buff *skb; u32 len; @@ -92,7 +84,9 @@ struct sk_psock { u32 eval; struct sk_msg *cork; struct sk_psock_progs progs; - struct sk_psock_parser parser; +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) + struct strparser strp; +#endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; unsigned long state; @@ -102,6 +96,7 @@ struct sk_psock { void (*saved_unhash)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); + void (*saved_data_ready)(struct sock *sk); struct proto *sk_proto; struct sk_psock_work_state work_state; struct work_struct work; @@ -418,8 +413,8 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { - if (psock->parser.enabled) - psock->parser.saved_data_ready(sk); + if (psock->saved_data_ready) + psock->saved_data_ready(sk); else sk->sk_data_ready(sk); } @@ -458,6 +453,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) { if (!psock) return false; - return psock->parser.enabled; + return !!psock->saved_data_ready; } #endif /* _LINUX_SKMSG_H */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e017744111e1..d00c9a4b47e7 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -907,17 +907,9 @@ static int sk_psock_strp_read_done(struct strparser *strp, int err) return err; } -static struct sk_psock *sk_psock_from_strp(struct strparser *strp) -{ - struct sk_psock_parser *parser; - - parser = container_of(strp, struct sk_psock_parser, strp); - return container_of(parser, struct sk_psock, parser); -} - static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock = container_of(strp, struct sk_psock, strp); struct bpf_prog *prog; int ret = skb->len; @@ -941,10 +933,10 @@ static void sk_psock_strp_data_ready(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (tls_sw_has_ctx_rx(sk)) { - psock->parser.saved_data_ready(sk); + psock->saved_data_ready(sk); } else { write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->parser.strp); + strp_data_ready(&psock->strp); write_unlock_bh(&sk->sk_callback_lock); } } @@ -959,41 +951,34 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) .parse_msg = sk_psock_strp_parse, }; - psock->parser.enabled = false; - return strp_init(&psock->parser.strp, sk, &cb); + return strp_init(&psock->strp, sk, &cb); } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (parser->enabled) + if (psock->saved_data_ready) return; - parser->saved_data_ready = sk->sk_data_ready; + psock->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = sk_psock_strp_data_ready; sk->sk_write_space = sk_psock_write_space; - parser->enabled = true; } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (!parser->enabled) + if (!psock->saved_data_ready) return; - sk->sk_data_ready = parser->saved_data_ready; - parser->saved_data_ready = NULL; - strp_stop(&parser->strp); - parser->enabled = false; + sk->sk_data_ready = psock->saved_data_ready; + psock->saved_data_ready = NULL; + strp_stop(&psock->strp); } static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ if (psock->progs.skb_parser) - strp_done(&psock->parser.strp); + strp_done(&psock->strp); } #else static void sk_psock_done_strp(struct sk_psock *psock) @@ -1054,25 +1039,19 @@ static void sk_psock_verdict_data_ready(struct sock *sk) void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (parser->enabled) + if (psock->saved_data_ready) return; - parser->saved_data_ready = sk->sk_data_ready; + psock->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = sk_psock_verdict_data_ready; sk->sk_write_space = sk_psock_write_space; - parser->enabled = true; } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (!parser->enabled) + if (!psock->saved_data_ready) return; - sk->sk_data_ready = parser->saved_data_ready; - parser->saved_data_ready = NULL; - parser->enabled = false; + sk->sk_data_ready = psock->saved_data_ready; + psock->saved_data_ready = NULL; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index ee3334dd3a38..1a28a5c2c61e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -148,9 +148,9 @@ static void sock_map_del_link(struct sock *sk, struct bpf_map *map = link->map; struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - if (psock->parser.enabled && stab->progs.skb_parser) + if (psock->saved_data_ready && stab->progs.skb_parser) strp_stop = true; - if (psock->parser.enabled && stab->progs.skb_verdict) + if (psock->saved_data_ready && stab->progs.skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); @@ -283,14 +283,14 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, goto out_drop; write_lock_bh(&sk->sk_callback_lock); - if (skb_parser && skb_verdict && !psock->parser.enabled) { + if (skb_parser && skb_verdict && !psock->saved_data_ready) { ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; psock_set_prog(&psock->progs.skb_verdict, skb_verdict); psock_set_prog(&psock->progs.skb_parser, skb_parser); sk_psock_start_strp(sk, psock); - } else if (!skb_parser && skb_verdict && !psock->parser.enabled) { + } else if (!skb_parser && skb_verdict && !psock->saved_data_ready) { psock_set_prog(&psock->progs.skb_verdict, skb_verdict); sk_psock_start_verdict(sk,psock); } From 16137b09a66f2b75090f1e56a9ba0e27ef845ebc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:28 -0800 Subject: [PATCH 3/9] bpf: Compute data_end dynamically with JIT code Currently, we compute ->data_end with a compile-time constant offset of skb. But as Jakub pointed out, we can actually compute it in eBPF JIT code at run-time, so that we can competely get rid of ->data_end. This is similar to skb_shinfo(skb) computation in bpf_convert_shinfo_access(). Suggested-by: Jakub Sitnicki Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-4-xiyou.wangcong@gmail.com --- include/net/tcp.h | 6 ------ net/core/filter.c | 48 +++++++++++++++++++++++++++-------------------- net/core/skmsg.c | 1 - 3 files changed, 28 insertions(+), 27 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index c00e125dcfb9..947ef5da6867 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -886,18 +886,12 @@ struct tcp_skb_cb { struct { __u32 flags; struct sock *sk_redir; - void *data_end; } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) -static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); -} - static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; diff --git a/net/core/filter.c b/net/core/filter.c index adfdad234674..13bcf248ee7b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1863,10 +1863,7 @@ static const struct bpf_func_proto bpf_sk_fullsock_proto = { static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { - int err = __bpf_try_make_writable(skb, write_len); - - bpf_compute_data_end_sk_skb(skb); - return err; + return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) @@ -3577,7 +3574,6 @@ BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, return -ENOMEM; __skb_pull(skb, len_diff_abs); } - bpf_compute_data_end_sk_skb(skb); if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); @@ -3742,10 +3738,7 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { - int ret = __bpf_skb_change_tail(skb, new_len, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { @@ -3808,10 +3801,7 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { - int ret = __bpf_skb_change_head(skb, head_room, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { @@ -9655,22 +9645,40 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +/* data_end = skb->data + skb_headlen() */ +static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + /* si->dst_reg = skb->data */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, data)); + /* AX = skb->len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, len)); + /* si->dst_reg = skb->data + skb->len */ + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + /* AX = skb->data_len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, data_len)); + /* si->dst_reg = skb->data + skb->len - skb->data_len */ + *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX); + + return insn; +} + static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; - int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): - off = si->off; - off -= offsetof(struct __sk_buff, data_end); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct tcp_skb_cb, bpf.data_end); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); + insn = bpf_convert_data_end_access(si, insn); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d00c9a4b47e7..8822001ab3dc 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -746,7 +746,6 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, struct sk_buff *skb) { - bpf_compute_data_end_sk_skb(skb); return bpf_prog_run_pin_on_cpu(prog, skb); } From e3526bb92a2084cdaec6cb2855bcec98b280426c Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:29 -0800 Subject: [PATCH 4/9] skmsg: Move sk_redir from TCP_SKB_CB to skb Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly does not work for any other non-TCP protocols. We can move them to skb ext, but it introduces a memory allocation on fast path. Fortunately, we only need to a word-size to store all the information, because the flags actually only contains 1 bit so can be just packed into the lowest bit of the "pointer", which is stored as unsigned long. Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is no longer needed after ->sk_data_ready() so we can just drop it. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com --- include/linux/skbuff.h | 3 +++ include/linux/skmsg.h | 38 ++++++++++++++++++++++++++++++++++++++ include/net/tcp.h | 19 ------------------- net/core/skmsg.c | 31 +++++++++++++++++++------------ net/core/sock_map.c | 8 ++------ 5 files changed, 62 insertions(+), 37 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6d0a33d1c0db..bd84f799c952 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -755,6 +755,9 @@ struct sk_buff { void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; +#ifdef CONFIG_NET_SOCK_MSG + unsigned long _sk_redir; +#endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 22e26f82de33..e0de45527bb6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -455,4 +455,42 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return false; return !!psock->saved_data_ready; } + +#if IS_ENABLED(CONFIG_NET_SOCK_MSG) + +/* We only have one bit so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) + +static inline bool skb_bpf_ingress(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_INGRESS; +} + +static inline void skb_bpf_set_ingress(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_INGRESS; +} + +static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir, + bool ingress) +{ + skb->_sk_redir = (unsigned long)sk_redir; + if (ingress) + skb->_sk_redir |= BPF_F_INGRESS; +} + +static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return (struct sock *)(sk_redir & BPF_F_PTR_MASK); +} + +static inline void skb_bpf_redirect_clear(struct sk_buff *skb) +{ + skb->_sk_redir = 0; +} +#endif /* CONFIG_NET_SOCK_MSG */ #endif /* _LINUX_SKMSG_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 947ef5da6867..075de26f449d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -883,30 +883,11 @@ struct tcp_skb_cb { struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ - struct { - __u32 flags; - struct sock *sk_redir; - } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) -static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; -} - -static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.sk_redir; -} - -static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.sk_redir = NULL; -} - extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 8822001ab3dc..409258367bea 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -525,7 +525,8 @@ static void sk_psock_backlog(struct work_struct *work) len = skb->len; off = 0; start: - ingress = tcp_skb_bpf_ingress(skb); + ingress = skb_bpf_ingress(skb); + skb_bpf_redirect_clear(skb); do { ret = -EIO; if (likely(psock->sk->sk_socket)) @@ -631,7 +632,12 @@ void __sk_psock_purge_ingress_msg(struct sk_psock *psock) static void sk_psock_zap_ingress(struct sk_psock *psock) { - __skb_queue_purge(&psock->ingress_skb); + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&psock->ingress_skb)) != NULL) { + skb_bpf_redirect_clear(skb); + kfree_skb(skb); + } __sk_psock_purge_ingress_msg(psock); } @@ -754,7 +760,7 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) struct sk_psock *psock_other; struct sock *sk_other; - sk_other = tcp_skb_bpf_redirect_fetch(skb); + sk_other = skb_bpf_redirect_fetch(skb); /* This error is a buggy BPF program, it returned a redirect * return code, but then didn't set a redirect interface. */ @@ -804,9 +810,10 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) * TLS context. */ skb->sk = psock->sk; - tcp_skb_bpf_redirect_clear(skb); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } sk_psock_tls_verdict_apply(skb, psock->sk, ret); @@ -818,7 +825,6 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); static void sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, int verdict) { - struct tcp_skb_cb *tcp; struct sock *sk_other; int err = -EIO; @@ -830,8 +836,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, goto out_free; } - tcp = TCP_SKB_CB(skb); - tcp->bpf.flags |= BPF_F_INGRESS; + skb_bpf_set_ingress(skb); /* If the queue is empty then we can submit directly * into the msg queue. If its not empty we have to @@ -892,9 +897,10 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - tcp_skb_bpf_redirect_clear(skb); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); out: @@ -1011,9 +1017,10 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - tcp_skb_bpf_redirect_clear(skb); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); out: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 1a28a5c2c61e..dbfcd7006338 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -657,7 +657,6 @@ const struct bpf_func_proto bpf_sock_map_update_proto = { BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) @@ -667,8 +666,7 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = sk; + skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } @@ -1250,7 +1248,6 @@ const struct bpf_func_proto bpf_sock_hash_update_proto = { BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) @@ -1260,8 +1257,7 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = sk; + skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } From ae8b8332fbb512f53bf50ff6a7586dd0f90ed18a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:30 -0800 Subject: [PATCH 5/9] sock_map: Rename skb_parser and skb_verdict These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact they are only used for TCP. And save the name 'skb_verdict' for general use later. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Reviewed-by: Lorenz Bauer Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 8 +-- net/core/skmsg.c | 14 ++--- net/core/sock_map.c | 60 +++++++++---------- .../selftests/bpf/prog_tests/sockmap_listen.c | 8 +-- .../selftests/bpf/progs/test_sockmap_listen.c | 4 +- 5 files changed, 47 insertions(+), 47 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e0de45527bb6..d9f6ec4a9cf2 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -56,8 +56,8 @@ struct sk_msg { struct sk_psock_progs { struct bpf_prog *msg_parser; - struct bpf_prog *skb_parser; - struct bpf_prog *skb_verdict; + struct bpf_prog *stream_parser; + struct bpf_prog *stream_verdict; }; enum sk_psock_state_bits { @@ -443,8 +443,8 @@ static inline int psock_replace_prog(struct bpf_prog **pprog, static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); - psock_set_prog(&progs->skb_parser, NULL); - psock_set_prog(&progs->skb_verdict, NULL); + psock_set_prog(&progs->stream_parser, NULL); + psock_set_prog(&progs->stream_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 409258367bea..35f9caa3b125 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -691,9 +691,9 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); - if (psock->progs.skb_parser) + if (psock->progs.stream_parser) sk_psock_stop_strp(sk, psock); - else if (psock->progs.skb_verdict) + else if (psock->progs.stream_verdict) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); @@ -803,7 +803,7 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) int ret = __SK_PASS; rcu_read_lock(); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { /* We skip full set_owner_r here because if we do a SK_PASS * or SK_DROP we can skip skb memory accounting and use the @@ -895,7 +895,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) goto out; } skb_set_owner_r(skb, sk); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); @@ -919,7 +919,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) int ret = skb->len; rcu_read_lock(); - prog = READ_ONCE(psock->progs.skb_parser); + prog = READ_ONCE(psock->progs.stream_parser); if (likely(prog)) { skb->sk = psock->sk; ret = sk_psock_bpf_run(psock, prog, skb); @@ -982,7 +982,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.skb_parser) + if (psock->progs.stream_parser) strp_done(&psock->strp); } #else @@ -1015,7 +1015,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, goto out; } skb_set_owner_r(skb, sk); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index dbfcd7006338..69785070f02d 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -148,9 +148,9 @@ static void sock_map_del_link(struct sock *sk, struct bpf_map *map = link->map; struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - if (psock->saved_data_ready && stab->progs.skb_parser) + if (psock->saved_data_ready && stab->progs.stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && stab->progs.stream_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); @@ -224,23 +224,23 @@ out: static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, struct sock *sk) { - struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; + struct bpf_prog *msg_parser, *stream_parser, *stream_verdict; struct sk_psock *psock; int ret; - skb_verdict = READ_ONCE(progs->skb_verdict); - if (skb_verdict) { - skb_verdict = bpf_prog_inc_not_zero(skb_verdict); - if (IS_ERR(skb_verdict)) - return PTR_ERR(skb_verdict); + stream_verdict = READ_ONCE(progs->stream_verdict); + if (stream_verdict) { + stream_verdict = bpf_prog_inc_not_zero(stream_verdict); + if (IS_ERR(stream_verdict)) + return PTR_ERR(stream_verdict); } - skb_parser = READ_ONCE(progs->skb_parser); - if (skb_parser) { - skb_parser = bpf_prog_inc_not_zero(skb_parser); - if (IS_ERR(skb_parser)) { - ret = PTR_ERR(skb_parser); - goto out_put_skb_verdict; + stream_parser = READ_ONCE(progs->stream_parser); + if (stream_parser) { + stream_parser = bpf_prog_inc_not_zero(stream_parser); + if (IS_ERR(stream_parser)) { + ret = PTR_ERR(stream_parser); + goto out_put_stream_verdict; } } @@ -249,7 +249,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); - goto out_put_skb_parser; + goto out_put_stream_parser; } } @@ -261,8 +261,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || - (skb_parser && READ_ONCE(psock->progs.skb_parser)) || - (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) { + (stream_parser && READ_ONCE(psock->progs.stream_parser)) || + (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; @@ -283,15 +283,15 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, goto out_drop; write_lock_bh(&sk->sk_callback_lock); - if (skb_parser && skb_verdict && !psock->saved_data_ready) { + if (stream_parser && stream_verdict && !psock->saved_data_ready) { ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); - psock_set_prog(&psock->progs.skb_parser, skb_parser); + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); + psock_set_prog(&psock->progs.stream_parser, stream_parser); sk_psock_start_strp(sk, psock); - } else if (!skb_parser && skb_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); } write_unlock_bh(&sk->sk_callback_lock); @@ -303,12 +303,12 @@ out_drop: out_progs: if (msg_parser) bpf_prog_put(msg_parser); -out_put_skb_parser: - if (skb_parser) - bpf_prog_put(skb_parser); -out_put_skb_verdict: - if (skb_verdict) - bpf_prog_put(skb_verdict); +out_put_stream_parser: + if (stream_parser) + bpf_prog_put(stream_parser); +out_put_stream_verdict: + if (stream_verdict) + bpf_prog_put(stream_verdict); return ret; } @@ -1459,11 +1459,11 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - pprog = &progs->skb_parser; + pprog = &progs->stream_parser; break; #endif case BPF_SK_SKB_STREAM_VERDICT: - pprog = &progs->skb_verdict; + pprog = &progs->stream_verdict; break; default: return -EOPNOTSUPP; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index d7d65a700799..c26e6bf05e49 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1014,8 +1014,8 @@ static void test_skb_redir_to_connected(struct test_sockmap_listen *skel, struct bpf_map *inner_map, int family, int sotype) { - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int parser = bpf_program__fd(skel->progs.prog_skb_parser); + int verdict = bpf_program__fd(skel->progs.prog_stream_verdict); + int parser = bpf_program__fd(skel->progs.prog_stream_parser); int verdict_map = bpf_map__fd(skel->maps.verdict_map); int sock_map = bpf_map__fd(inner_map); int err; @@ -1125,8 +1125,8 @@ static void test_skb_redir_to_listening(struct test_sockmap_listen *skel, struct bpf_map *inner_map, int family, int sotype) { - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int parser = bpf_program__fd(skel->progs.prog_skb_parser); + int verdict = bpf_program__fd(skel->progs.prog_stream_verdict); + int parser = bpf_program__fd(skel->progs.prog_stream_parser); int verdict_map = bpf_map__fd(skel->maps.verdict_map); int sock_map = bpf_map__fd(inner_map); int err; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a3a366c57ce1..fa221141e9c1 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -31,13 +31,13 @@ struct { static volatile bool test_sockmap; /* toggled by user-space */ SEC("sk_skb/stream_parser") -int prog_skb_parser(struct __sk_buff *skb) +int prog_stream_parser(struct __sk_buff *skb) { return skb->len; } SEC("sk_skb/stream_verdict") -int prog_skb_verdict(struct __sk_buff *skb) +int prog_stream_verdict(struct __sk_buff *skb) { unsigned int *count; __u32 zero = 0; From 4675e234b9e15159894b90ead9340e1dc202b670 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:31 -0800 Subject: [PATCH 6/9] sock_map: Make sock_map_prog_update() static It is only used within sock_map.c so can become static. Suggested-by: Jakub Sitnicki Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-7-xiyou.wangcong@gmail.com --- include/linux/bpf.h | 9 --------- net/core/sock_map.c | 7 +++++-- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be47ada5f2d..e1e4d2f60527 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1779,8 +1779,6 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); @@ -1798,13 +1796,6 @@ static inline void bpf_sk_reuseport_detach(struct sock *sk) } #ifdef CONFIG_BPF_SYSCALL -static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, - struct bpf_prog *old, u32 which) -{ - return -EOPNOTSUPP; -} - static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 69785070f02d..dd53a7771d7e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -24,6 +24,9 @@ struct bpf_stab { #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); + static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; @@ -1444,8 +1447,8 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog **pprog; From cd81cefb1abc52bd164f4d9760cd22eadc0e4468 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:32 -0800 Subject: [PATCH 7/9] skmsg: Make __sk_psock_purge_ingress_msg() static It is only used within skmsg.c so can become static. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-8-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 2 -- net/core/skmsg.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9f6ec4a9cf2..676d48e08159 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -340,8 +340,6 @@ static inline void sk_psock_free_link(struct sk_psock_link *link) struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); -void __sk_psock_purge_ingress_msg(struct sk_psock *psock); - static inline void sk_psock_cork_free(struct sk_psock *psock) { if (psock->cork) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 35f9caa3b125..46e29d2c0c48 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -619,7 +619,7 @@ struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock) return link; } -void __sk_psock_purge_ingress_msg(struct sk_psock *psock) +static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) { struct sk_msg *msg, *tmp; From 533342322276b06b4db260c413ce907238851e9b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:33 -0800 Subject: [PATCH 8/9] skmsg: Get rid of sk_psock_bpf_run() It is now nearly identical to bpf_prog_run_pin_on_cpu() and it has an unused parameter 'psock', so we can just get rid of it and call bpf_prog_run_pin_on_cpu() directly. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com --- net/core/skmsg.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 46e29d2c0c48..07f54015238a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -749,12 +749,6 @@ out: } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); -static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, - struct sk_buff *skb) -{ - return bpf_prog_run_pin_on_cpu(prog, skb); -} - static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; @@ -812,7 +806,7 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) skb->sk = psock->sk; skb_dst_drop(skb); skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -899,7 +893,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); @@ -922,7 +916,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) prog = READ_ONCE(psock->progs.stream_parser); if (likely(prog)) { skb->sk = psock->sk; - ret = sk_psock_bpf_run(psock, prog, skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); skb->sk = NULL; } rcu_read_unlock(); @@ -1019,7 +1013,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); From ff9614b81be65d648ec4615b593c6e4b2dac6375 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 23 Feb 2021 10:49:34 -0800 Subject: [PATCH 9/9] skmsg: Remove unused sk_psock_stop() declaration It is not defined or used anywhere. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210223184934.6054-10-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 676d48e08159..6c09d94be2e9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -400,7 +400,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk) return psock; } -void sk_psock_stop(struct sock *sk, struct sk_psock *psock); void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)