diff options
Diffstat (limited to 'net/mptcp/protocol.h')
| -rw-r--r-- | net/mptcp/protocol.h | 127 |
1 files changed, 87 insertions, 40 deletions
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ed61d6850cce..fe6f2d399ee8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -13,6 +13,8 @@ #include <uapi/linux/mptcp.h> #include <net/genetlink.h> +#include "mptcp_pm_gen.h" + #define MPTCP_SUPPORTED_VERSION 1 /* MPTCP option bits */ @@ -123,6 +125,7 @@ #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { u64 map_seq; @@ -267,6 +270,7 @@ struct mptcp_sock { atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; u64 bytes_retrans; + u64 bytes_consumed; int rmem_fwd_alloc; int snd_burst; int old_wspace; @@ -432,11 +436,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) return (struct mptcp_subflow_request_sock *)rsk; } -enum mptcp_data_avail { - MPTCP_SUBFLOW_NODATA, - MPTCP_SUBFLOW_DATA_AVAIL, -}; - struct mptcp_delegated_action { struct napi_struct napi; struct list_head head; @@ -444,9 +443,12 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -#define MPTCP_DELEGATE_SEND 0 -#define MPTCP_DELEGATE_ACK 1 +#define MPTCP_DELEGATE_SCHEDULED 0 +#define MPTCP_DELEGATE_SEND 1 +#define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_SNDBUF 3 +#define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ @@ -490,7 +492,7 @@ struct mptcp_subflow_context { valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ __unused : 9; - enum mptcp_data_avail data_avail; + bool data_avail; bool scheduled; u32 remote_nonce; u64 thmac; @@ -518,6 +520,9 @@ struct mptcp_subflow_context { u32 setsockopt_seq; u32 stale_rcv_tstamp; + int cached_sndbuf; /* sndbuf size when last synced with the msk sndbuf, + * protected by the msk socket lock + */ struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -564,23 +569,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) return subflow->map_seq + mptcp_subflow_get_map_offset(subflow); } -void mptcp_subflow_process_delegated(struct sock *ssk); +void mptcp_subflow_process_delegated(struct sock *ssk, long actions); static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { + long old, set_bits = BIT(MPTCP_DELEGATE_SCHEDULED) | BIT(action); struct mptcp_delegated_action *delegated; bool schedule; /* the caller held the subflow bh socket lock */ lockdep_assert_in_softirq(); - /* The implied barrier pairs with mptcp_subflow_delegated_done(), and - * ensures the below list check sees list updates done prior to status - * bit changes + /* The implied barrier pairs with tcp_release_cb_override() + * mptcp_napi_poll(), and ensures the below list check sees list + * updates done prior to delegated status bits changes */ - if (!test_and_set_bit(action, &subflow->delegated_status)) { - /* still on delegated list from previous scheduling */ - if (!list_empty(&subflow->delegated_node)) + old = set_mask_bits(&subflow->delegated_status, 0, set_bits); + if (!(old & BIT(MPTCP_DELEGATE_SCHEDULED))) { + if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node))) return; delegated = this_cpu_ptr(&mptcp_delegated_actions); @@ -605,25 +611,12 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) return ret; } -static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) -{ - return !!READ_ONCE(subflow->delegated_status); -} - -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) -{ - /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before - * touching the status bit - */ - smp_wmb(); - clear_bit(action, &subflow->delegated_status); -} - int mptcp_is_enabled(const struct net *net); unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); +unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, @@ -672,6 +665,24 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk); int mptcp_sched_get_send(struct mptcp_sock *msk); int mptcp_sched_get_retrans(struct mptcp_sock *msk); +static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) +{ + return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed); +} + +static inline bool mptcp_epollin_ready(const struct sock *sk) +{ + /* mptcp doesn't have to deal with small skbs in the receive queue, + * at it can always coalesce them + */ + return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) || + READ_ONCE(tcp_memory_pressure); +} + +int mptcp_set_rcvlowat(struct sock *sk, int val); + static inline bool __tcp_can_send(const struct sock *ssk) { /* only send if our side has not closed yet */ @@ -746,6 +757,7 @@ static inline bool mptcp_is_fully_established(struct sock *sk) return inet_sk_state_load(sk) == TCP_ESTABLISHED && READ_ONCE(mptcp_sk(sk)->fully_established); } + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); @@ -773,13 +785,52 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } -static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +static inline void __mptcp_sync_sndbuf(struct sock *sk) { - if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) - return false; + struct mptcp_subflow_context *subflow; + int ssk_sndbuf, new_sndbuf; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); + + subflow->cached_sndbuf = ssk_sndbuf; + new_sndbuf += ssk_sndbuf; + } + + /* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */ + WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); +} + +/* The called held both the msk socket and the subflow socket locks, + * possibly under BH + */ +static inline void __mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (READ_ONCE(ssk->sk_sndbuf) != subflow->cached_sndbuf) + __mptcp_sync_sndbuf(sk); +} + +/* the caller held only the subflow socket lock, either in process or + * BH context. Additionally this can be called under the msk data lock, + * so we can't acquire such lock here: let the delegate action acquires + * the needed locks in suitable order. + */ +static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (likely(READ_ONCE(ssk->sk_sndbuf) == subflow->cached_sndbuf)) + return; - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); - return true; + local_bh_disable(); + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SNDBUF); + local_bh_enable(); } static inline void mptcp_write_space(struct sock *sk) @@ -837,7 +888,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); void mptcp_pm_connection_closed(struct mptcp_sock *msk); void mptcp_pm_subflow_established(struct mptcp_sock *msk); bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk); -void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, +void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct mptcp_subflow_context *subflow); void mptcp_pm_add_addr_received(const struct sock *ssk, const struct mptcp_addr_info *addr); @@ -888,10 +939,6 @@ void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info); void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); @@ -1018,7 +1065,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk) static inline void __mptcp_do_fallback(struct mptcp_sock *msk) { - if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) { + if (__mptcp_check_fallback(msk)) { pr_debug("TCP fallback already done (msk=%p)", msk); return; } |