diff options
Diffstat (limited to 'net/mptcp')
| -rw-r--r-- | net/mptcp/mib.c | 4 | ||||
| -rw-r--r-- | net/mptcp/mib.h | 4 | ||||
| -rw-r--r-- | net/mptcp/options.c | 82 | ||||
| -rw-r--r-- | net/mptcp/pm.c | 11 | ||||
| -rw-r--r-- | net/mptcp/pm_netlink.c | 200 | ||||
| -rw-r--r-- | net/mptcp/protocol.c | 5 | ||||
| -rw-r--r-- | net/mptcp/protocol.h | 32 | ||||
| -rw-r--r-- | net/mptcp/sockopt.c | 2 | ||||
| -rw-r--r-- | net/mptcp/subflow.c | 112 |
9 files changed, 284 insertions, 168 deletions
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 7558802a1435..e55d3dfbee0c 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -48,6 +48,10 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX), SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX), + SNMP_MIB_ITEM("MPFastcloseTx", MPTCP_MIB_MPFASTCLOSETX), + SNMP_MIB_ITEM("MPFastcloseRx", MPTCP_MIB_MPFASTCLOSERX), + SNMP_MIB_ITEM("MPRstTx", MPTCP_MIB_MPRSTTX), + SNMP_MIB_ITEM("MPRstRx", MPTCP_MIB_MPRSTRX), SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2966fcb6548b..00576179a619 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -41,6 +41,10 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ MPTCP_MIB_MPFAILTX, /* Transmit a MP_FAIL */ MPTCP_MIB_MPFAILRX, /* Received a MP_FAIL */ + MPTCP_MIB_MPFASTCLOSETX, /* Transmit a MP_FASTCLOSE */ + MPTCP_MIB_MPFASTCLOSERX, /* Received a MP_FASTCLOSE */ + MPTCP_MIB_MPRSTTX, /* Transmit a MP_RST */ + MPTCP_MIB_MPRSTRX, /* Received a MP_RST */ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ MPTCP_MIB_SUBFLOWSTALE, /* Subflows entered 'stale' status */ MPTCP_MIB_SUBFLOWRECOVER, /* Subflows returned to active status after being stale */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 645dd984fef0..325383646f5c 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -323,6 +323,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; + pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key); break; case MPTCPOPT_RST: @@ -336,6 +337,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; + pr_debug("MP_RST: transient=%u reason=%u", + mp_opt->reset_transient, mp_opt->reset_reason); break; case MPTCPOPT_MP_FAIL: @@ -353,8 +356,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } -void mptcp_get_options(const struct sock *sk, - const struct sk_buff *skb, +void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { const struct tcphdr *th = tcp_hdr(skb); @@ -651,7 +653,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * bool drop_other_suboptions = false; unsigned int opt_size = *size; bool echo; - bool port; int len; /* add addr will strip the existing options, be sure to avoid breaking @@ -660,12 +661,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr, - &echo, &port, &drop_other_suboptions)) + &echo, &drop_other_suboptions)) return false; if (drop_other_suboptions) remaining += opt_size; - len = mptcp_add_addr_len(opts->addr.family, echo, port); + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; @@ -832,11 +833,13 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); } /* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */ if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); } return true; } @@ -1084,8 +1087,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, &mp_opt->addr); pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n", - msk, (unsigned long long)hmac, - (unsigned long long)mp_opt->ahmac); + msk, hmac, mp_opt->ahmac); return hmac == mp_opt->ahmac; } @@ -1112,7 +1114,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return true; } - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); /* The subflow can be in close state only if check_fully_established() * just sent a reset. If so, tell the caller to ignore the current packet. @@ -1125,6 +1127,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) msk->local_key == mp_opt.rcvr_key) { WRITE_ONCE(msk->rcv_fastclose, true); mptcp_schedule_work((struct sock *)msk); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSERX); } if ((mp_opt.suboptions & OPTION_MPTCP_ADD_ADDR) && @@ -1159,6 +1162,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) subflow->reset_seen = 1; subflow->reset_reason = mp_opt.reset_reason; subflow->reset_transient = mp_opt.reset_transient; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTRX); } if (!(mp_opt.suboptions & OPTION_MPTCP_DSS)) @@ -1264,22 +1268,30 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { - if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->send_mp_fail = 0; - - *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, - TCPOLEN_MPTCP_FAIL, - 0, 0); - put_unaligned_be64(opts->fail_seq, ptr); - ptr += 2; - } - - /* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive, - * see mptcp_established_options*() + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + /* Which options can be used together? + * + * X: mutually exclusive + * O: often used together + * C: can be used together in some cases + * P: could be used together but we prefer not to (optimisations) + * + * Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC | + * ------|------|------|------|------|------|------|------|------| + * MPC |------|------|------|------|------|------|------|------| + * MPJ | X |------|------|------|------|------|------|------| + * DSS | X | X |------|------|------|------|------|------| + * ADD | X | X | P |------|------|------|------|------| + * RM | C | C | C | P |------|------|------|------| + * PRIO | X | C | C | C | C |------|------|------| + * FAIL | X | X | C | X | X | X |------|------| + * FC | X | X | X | X | X | X | X |------| + * RST | X | X | X | X | X | X | O | O | + * ------|------|------|------|------|------|------|------|------| + * + * The same applies in mptcp_established_options() function. */ if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { struct mptcp_ext *mpext = &opts->ext_copy; @@ -1336,6 +1348,10 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, } ptr += 1; } + + /* We might need to add MP_FAIL options in rare cases */ + if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) + goto mp_fail; } else if (OPTIONS_MPTCP_MPC & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; @@ -1479,6 +1495,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (OPTION_MPTCP_RST & opts->suboptions) goto mp_rst; return; + } else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { +mp_fail: + /* MP_FAIL is mutually exclusive with others except RST */ + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_fail = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, + TCPOLEN_MPTCP_FAIL, + 0, 0); + put_unaligned_be64(opts->fail_seq, ptr); + ptr += 2; + + if (OPTION_MPTCP_RST & opts->suboptions) + goto mp_rst; + return; } else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { mp_rst: *ptr++ = mptcp_option(MPTCPOPT_RST, @@ -1489,9 +1520,6 @@ mp_rst: } if (OPTION_MPTCP_PRIO & opts->suboptions) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - subflow = mptcp_subflow_ctx(ssk); subflow->send_mp_prio = 0; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 7bea318ac5f2..01809eef29b4 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -221,7 +221,7 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, } void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + const struct mptcp_addr_info *addr) { struct mptcp_pm_data *pm = &msk->pm; @@ -279,14 +279,15 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) /* path manager helpers */ -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, unsigned int opt_size, unsigned int remaining, struct mptcp_addr_info *addr, bool *echo, - bool *port, bool *drop_other_suboptions) + bool *drop_other_suboptions) { int ret = false; u8 add_addr; u8 family; + bool port; spin_lock_bh(&msk->pm.lock); @@ -304,10 +305,10 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, } *echo = mptcp_pm_should_add_signal_echo(msk); - *port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); + port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); family = *echo ? msk->pm.remote.family : msk->pm.local.family; - if (remaining < mptcp_add_addr_len(family, *echo, *port)) + if (remaining < mptcp_add_addr_len(family, *echo, port)) goto out_unlock; if (*echo) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4b5d795383cd..b5e8de6f7507 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -83,16 +83,6 @@ static bool addresses_equal(const struct mptcp_addr_info *a, return a->port == b->port; } -static bool address_zero(const struct mptcp_addr_info *addr) -{ - struct mptcp_addr_info zero; - - memset(&zero, 0, sizeof(zero)); - zero.family = addr->family; - - return addresses_equal(addr, &zero, true); -} - static void local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { @@ -120,7 +110,7 @@ static void remote_address(const struct sock_common *skc, } static bool lookup_subflow_by_saddr(const struct list_head *list, - struct mptcp_addr_info *saddr) + const struct mptcp_addr_info *saddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -138,7 +128,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, } static bool lookup_subflow_by_daddr(const struct list_head *list, - struct mptcp_addr_info *daddr) + const struct mptcp_addr_info *daddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -157,10 +147,10 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, static struct mptcp_pm_addr_entry * select_local_address(const struct pm_nl_pernet *pernet, - struct mptcp_sock *msk) + const struct mptcp_sock *msk) { + const struct sock *sk = (const struct sock *)msk; struct mptcp_pm_addr_entry *entry, *ret = NULL; - struct sock *sk = (struct sock *)msk; msk_owned_by_me(msk); @@ -190,7 +180,7 @@ select_local_address(const struct pm_nl_pernet *pernet, } static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, struct mptcp_sock *msk) +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) { struct mptcp_pm_addr_entry *entry, *ret = NULL; @@ -214,16 +204,16 @@ select_signal_address(struct pm_nl_pernet *pernet, struct mptcp_sock *msk) return ret; } -unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) { - struct pm_nl_pernet *pernet; + const struct pm_nl_pernet *pernet; - pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + pernet = net_generic(sock_net((const struct sock *)msk), pm_nl_pernet_id); return READ_ONCE(pernet->add_addr_signal_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max); -unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -232,7 +222,7 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max); -unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -241,7 +231,7 @@ unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); -unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -264,8 +254,8 @@ bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk) } struct mptcp_pm_add_entry * -mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) +mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -346,7 +336,7 @@ out: struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, bool check_id) + const struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; @@ -364,7 +354,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, } static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + const struct mptcp_pm_addr_entry *entry) { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; @@ -410,8 +400,8 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr, - struct mptcp_addr_info *addr) +static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, + const struct mptcp_addr_info *addr) { int i; @@ -493,9 +483,9 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, } static int -lookup_id_by_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr) +lookup_id_by_addr(const struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr) { - struct mptcp_pm_addr_entry *entry; + const struct mptcp_pm_addr_entry *entry; int ret = -1; rcu_read_lock(); @@ -660,7 +650,6 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; - bool reset_port = false; int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); @@ -671,14 +660,15 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) msk->pm.remote.family); remote = msk->pm.remote; + mptcp_pm_announce_addr(msk, &remote, true); + mptcp_pm_nl_addr_send_ack(msk); + if (lookup_subflow_by_daddr(&msk->conn_list, &remote)) - goto add_addr_echo; + return; /* pick id 0 port, if none is provided the remote address */ - if (!remote.port) { - reset_port = true; + if (!remote.port) remote.port = sk->sk_dport; - } /* connect to the specified remote address, using whatever * local address the routing configuration will pick. @@ -694,14 +684,6 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) for (i = 0; i < nr; i++) __mptcp_subflow_connect(sk, &addrs[i], &remote); spin_lock_bh(&msk->pm.lock); - - /* be sure to echo exactly the received address */ - if (reset_port) - remote.port = 0; - -add_addr_echo: - mptcp_pm_announce_addr(msk, &remote, true); - mptcp_pm_nl_addr_send_ack(msk); } void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) @@ -877,10 +859,18 @@ static bool address_use_port(struct mptcp_pm_addr_entry *entry) MPTCP_PM_ADDR_FLAG_SIGNAL; } +/* caller must ensure the RCU grace period is already elapsed */ +static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) +{ + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); +} + static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry) { - struct mptcp_pm_addr_entry *cur; + struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; int ret = -EINVAL; @@ -901,8 +891,22 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, list_for_each_entry(cur, &pernet->local_addr_list, list) { if (addresses_equal(&cur->addr, &entry->addr, address_use_port(entry) && - address_use_port(cur))) - goto out; + address_use_port(cur))) { + /* allow replacing the exiting endpoint only if such + * endpoint is an implicit one and the user-space + * did not provide an endpoint id + */ + if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) + goto out; + if (entry->addr.id) + goto out; + + pernet->addrs--; + entry->addr.id = cur->addr.id; + list_del_rcu(&cur->list); + del_entry = cur; + break; + } } if (!entry->addr.id) { @@ -938,6 +942,12 @@ find_next: out: spin_unlock_bh(&pernet->lock); + + /* just replaced an existing entry, free it */ + if (del_entry) { + synchronize_rcu(); + __mptcp_pm_release_addr_entry(del_entry); + } return ret; } @@ -1011,9 +1021,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) if (addresses_equal(&msk_local, &skc_local, false)) return 0; - if (address_zero(&skc_local)) - return 0; - pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); rcu_read_lock(); @@ -1036,7 +1043,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->addr.id = 0; entry->addr.port = 0; entry->ifindex = 0; - entry->flags = 0; + entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) @@ -1197,14 +1204,8 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); - if (tb[MPTCP_PM_ADDR_ATTR_PORT]) { - if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - NL_SET_ERR_MSG_ATTR(info->extack, attr, - "flags must have signal when using port"); - return -EINVAL; - } + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); - } return 0; } @@ -1250,6 +1251,22 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; + if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + return -EINVAL; + } + + if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL && + addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh"); + return -EINVAL; + } + + if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { + GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint"); + return -EINVAL; + } + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); @@ -1301,7 +1318,7 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, } static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -1316,7 +1333,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, } static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, + const struct mptcp_addr_info *addr, bool force) { struct mptcp_rm_list list = { .nr = 0 }; @@ -1334,11 +1351,12 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, } static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, - struct mptcp_addr_info *addr) + const struct mptcp_pm_addr_entry *entry) { - struct mptcp_sock *msk; - long s_slot = 0, s_num = 0; + const struct mptcp_addr_info *addr = &entry->addr; struct mptcp_rm_list list = { .nr = 0 }; + long s_slot = 0, s_num = 0; + struct mptcp_sock *msk; pr_debug("remove_id=%d", addr->id); @@ -1355,7 +1373,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, lock_sock(sk); remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); - mptcp_pm_remove_anno_addr(msk, addr, remove_subflow); + mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && + !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); if (remove_subflow) mptcp_pm_remove_subflow(msk, &list); release_sock(sk); @@ -1368,14 +1387,6 @@ next: return 0; } -/* caller must ensure the RCU grace period is already elapsed */ -static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) -{ - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); -} - static int mptcp_nl_remove_id_zero_address(struct net *net, struct mptcp_addr_info *addr) { @@ -1452,7 +1463,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) __clear_bit(entry->addr.id, pernet->id_bitmap); spin_unlock_bh(&pernet->lock); - mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); + mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry); synchronize_rcu(); __mptcp_pm_release_addr_entry(entry); @@ -1467,14 +1478,12 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, list_for_each_entry(entry, rm_list, list) { if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX && - slist.nr < MPTCP_RM_IDS_MAX) { - alist.ids[alist.nr++] = entry->addr.id; + slist.nr < MPTCP_RM_IDS_MAX) slist.ids[slist.nr++] = entry->addr.id; - } else if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) { + + if (remove_anno_list_by_saddr(msk, &entry->addr) && + alist.nr < MPTCP_RM_IDS_MAX) alist.ids[alist.nr++] = entry->addr.id; - } } if (alist.nr) { @@ -1751,9 +1760,20 @@ fail: return -EMSGSIZE; } -static int mptcp_nl_addr_backup(struct net *net, - struct mptcp_addr_info *addr, - u8 bkup) +static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_rm_list list = { .nr = 0 }; + + list.ids[list.nr++] = addr->id; + + mptcp_pm_nl_rm_subflow_received(msk, &list); + mptcp_pm_create_subflow_or_signal_addr(msk); +} + +static int mptcp_nl_set_flags(struct net *net, + struct mptcp_addr_info *addr, + u8 bkup, u8 changed) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; @@ -1767,7 +1787,10 @@ static int mptcp_nl_addr_backup(struct net *net, lock_sock(sk); spin_lock_bh(&msk->pm.lock); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) + mptcp_pm_nl_fullmesh(msk, addr); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1784,6 +1807,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); + u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | + MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = sock_net(skb->sk); u8 bkup = 0, lookup_by_id = 0; int ret; @@ -1806,15 +1831,18 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); return -EINVAL; } + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; + } - if (bkup) - entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else - entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); addr = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_addr_backup(net, &addr.addr, bkup); + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1c72f25f083e..0cbea3b6d0a4 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -117,6 +117,9 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; + + /* This is the first subflow, always with id 0 */ + subflow->local_id_valid = 1; mptcp_sock_graft(msk->first, sk->sk_socket); return 0; @@ -1196,6 +1199,7 @@ static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, g tcp_skb_entail(ssk, skb); return skb; } + tcp_skb_tsorted_anchor_cleanup(skb); kfree_skb(skb); return NULL; } @@ -1356,6 +1360,7 @@ alloc_skb: out: if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); + trace_mptcp_sendmsg_frag(mpext); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; return copy; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 85317ce38e3f..3c1a3036550f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -442,7 +442,8 @@ struct mptcp_subflow_context { rx_eof : 1, can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ - stale : 1; /* unable to snd/rcv data, do not use for xmit */ + stale : 1, /* unable to snd/rcv data, do not use for xmit */ + local_id_valid : 1; /* local_id is correctly initialized */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -468,9 +469,7 @@ struct mptcp_subflow_context { struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ const struct inet_connection_sock_af_ops *icsk_af_ops; - void (*tcp_data_ready)(struct sock *sk); void (*tcp_state_change)(struct sock *sk); - void (*tcp_write_space)(struct sock *sk); void (*tcp_error_report)(struct sock *sk); struct rcu_head rcu; @@ -614,9 +613,9 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) { - sk->sk_data_ready = ctx->tcp_data_ready; + sk->sk_data_ready = sock_def_readable; sk->sk_state_change = ctx->tcp_state_change; - sk->sk_write_space = ctx->tcp_write_space; + sk->sk_write_space = sk_stream_write_space; sk->sk_error_report = ctx->tcp_error_report; inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; @@ -643,8 +642,7 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sock *sk, - const struct sk_buff *skb, +void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); @@ -743,7 +741,7 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); + const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, @@ -754,10 +752,10 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, bool check_id); + const struct mptcp_addr_info *addr, bool check_id); struct mptcp_pm_add_entry * -mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); +mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, + const struct mptcp_addr_info *addr); int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, u8 *flags, int *ifindex); @@ -816,10 +814,10 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, unsigned int opt_size, unsigned int remaining, struct mptcp_addr_info *addr, bool *echo, - bool *port, bool *drop_other_suboptions); + bool *drop_other_suboptions); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); @@ -830,10 +828,10 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); -unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index dacf3cee0027..f949d22f52bd 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -343,6 +343,8 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_RCVLOWAT: case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: case SO_BUSY_POLL: case SO_PREFER_BUSY_POLL: case SO_BUSY_POLL_BUDGET: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bea47a1180dc..aba260f547da 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -153,7 +153,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif - mptcp_get_options(sk_listener, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); @@ -250,7 +250,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err; subflow_init_req(req, sk_listener); - mptcp_get_options(sk_listener, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); @@ -344,9 +344,7 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) thmac = get_unaligned_be64(hmac); pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n", - subflow, subflow->token, - (unsigned long long)thmac, - (unsigned long long)subflow->thmac); + subflow, subflow->token, thmac, subflow->thmac); return thmac == subflow->thmac; } @@ -410,7 +408,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { MPTCP_INC_STATS(sock_net(sk), @@ -483,9 +481,53 @@ do_reset: mptcp_subflow_reset(sk); } +static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) +{ + subflow->local_id = local_id; + subflow->local_id_valid = 1; +} + +static int subflow_chk_local_id(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + int err; + + if (likely(subflow->local_id_valid)) + return 0; + + err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); + if (err < 0) + return err; + + subflow_set_local_id(subflow, err); + return 0; +} + +static int subflow_rebuild_header(struct sock *sk) +{ + int err = subflow_chk_local_id(sk); + + if (unlikely(err < 0)) + return err; + + return inet_sk_rebuild_header(sk); +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int subflow_v6_rebuild_header(struct sock *sk) +{ + int err = subflow_chk_local_id(sk); + + if (unlikely(err < 0)) + return err; + + return inet6_sk_rebuild_header(sk); +} +#endif + struct request_sock_ops mptcp_subflow_request_sock_ops; -EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops); -static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; +static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -506,9 +548,9 @@ drop: } #if IS_ENABLED(CONFIG_MPTCP_IPV6) -static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; -static struct inet_connection_sock_af_ops subflow_v6_specific; -static struct inet_connection_sock_af_ops subflow_v6m_specific; +static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; static struct proto tcpv6_prot_override; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) @@ -663,7 +705,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { fallback = true; goto create_child; @@ -673,7 +715,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { @@ -790,7 +832,7 @@ dispose_child: return child; } -static struct inet_connection_sock_af_ops subflow_specific; +static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; static struct proto tcp_prot_override; enum mapping_status { @@ -1107,7 +1149,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - WRITE_ONCE(subflow->data_avail, 0); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); if (subflow->data_avail) return true; @@ -1172,7 +1214,7 @@ fallback: subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, 0); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); return true; } @@ -1185,7 +1227,7 @@ fallback: subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, 0); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); return false; } @@ -1207,7 +1249,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - WRITE_ONCE(subflow->data_avail, 0); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1311,7 +1353,7 @@ static void subflow_write_space(struct sock *ssk) mptcp_write_space(sk); } -static struct inet_connection_sock_af_ops * +static const struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1326,7 +1368,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_connection_sock_af_ops *target; + const struct inet_connection_sock_af_ops *target; target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); @@ -1401,13 +1443,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, get_random_bytes(&subflow->local_nonce, sizeof(u32)); } while (!subflow->local_nonce); - if (!local_id) { - err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk); - if (err < 0) - goto failed; - - local_id = err; - } + if (local_id) + subflow_set_local_id(subflow, local_id); mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id, &flags, &ifindex); @@ -1432,7 +1469,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->local_id = local_id; subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); @@ -1657,10 +1693,12 @@ static int subflow_ulp_init(struct sock *sk) tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; icsk->icsk_af_ops = subflow_default_af_ops(sk); - ctx->tcp_data_ready = sk->sk_data_ready; ctx->tcp_state_change = sk->sk_state_change; - ctx->tcp_write_space = sk->sk_write_space; ctx->tcp_error_report = sk->sk_error_report; + + WARN_ON_ONCE(sk->sk_data_ready != sock_def_readable); + WARN_ON_ONCE(sk->sk_write_space != sk_stream_write_space); + sk->sk_data_ready = subflow_data_ready; sk->sk_write_space = subflow_write_space; sk->sk_state_change = subflow_state_change; @@ -1715,9 +1753,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->conn_finished = 1; new_ctx->icsk_af_ops = old_ctx->icsk_af_ops; - new_ctx->tcp_data_ready = old_ctx->tcp_data_ready; new_ctx->tcp_state_change = old_ctx->tcp_state_change; - new_ctx->tcp_write_space = old_ctx->tcp_write_space; new_ctx->tcp_error_report = old_ctx->tcp_error_report; new_ctx->rel_write_seq = 1; new_ctx->tcp_sock = newsk; @@ -1731,15 +1767,22 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->token = subflow_req->token; new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->idsn = subflow_req->idsn; + + /* this is the first subflow, id is always 0 */ + new_ctx->local_id_valid = 1; } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; - new_ctx->local_id = subflow_req->local_id; new_ctx->remote_id = subflow_req->remote_id; new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; + + /* the subflow req id is valid, fetched via subflow_check_req() + * and subflow_token_join_request() + */ + subflow_set_local_id(new_ctx, subflow_req->local_id); } } @@ -1792,6 +1835,7 @@ void __init mptcp_subflow_init(void) subflow_specific.conn_request = subflow_v4_conn_request; subflow_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_specific.sk_rx_dst_set = subflow_finish_connect; + subflow_specific.rebuild_header = subflow_rebuild_header; tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; @@ -1804,6 +1848,7 @@ void __init mptcp_subflow_init(void) subflow_v6_specific.conn_request = subflow_v6_conn_request; subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect; + subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header; subflow_v6m_specific = subflow_v6_specific; subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit; @@ -1811,6 +1856,7 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; subflow_v6m_specific.net_frag_header_len = 0; + subflow_v6m_specific.rebuild_header = subflow_rebuild_header; tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; |