diff options
Diffstat (limited to 'net/mptcp')
-rw-r--r-- | net/mptcp/ctrl.c | 32 | ||||
-rw-r--r-- | net/mptcp/mib.c | 2 | ||||
-rw-r--r-- | net/mptcp/mib.h | 4 | ||||
-rw-r--r-- | net/mptcp/options.c | 6 | ||||
-rw-r--r-- | net/mptcp/pm.c | 12 | ||||
-rw-r--r-- | net/mptcp/pm_netlink.c | 94 | ||||
-rw-r--r-- | net/mptcp/pm_userspace.c | 19 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 48 | ||||
-rw-r--r-- | net/mptcp/protocol.h | 50 | ||||
-rw-r--r-- | net/mptcp/sched.c | 22 | ||||
-rw-r--r-- | net/mptcp/sockopt.c | 26 | ||||
-rw-r--r-- | net/mptcp/subflow.c | 117 |
12 files changed, 336 insertions, 96 deletions
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 2963ba84e2..98b1dd498f 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -92,7 +92,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; pernet->pm_type = MPTCP_PM_TYPE_KERNEL; - strcpy(pernet->scheduler, "default"); + strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler)); } #ifdef CONFIG_SYSCTL @@ -133,6 +133,24 @@ static int proc_scheduler(struct ctl_table *ctl, int write, return ret; } +static int proc_available_schedulers(struct ctl_table *ctl, + int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, }; + int ret; + + tbl.data = kmalloc(tbl.maxlen, GFP_USER); + if (!tbl.data) + return -ENOMEM; + + mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + kfree(tbl.data); + + return ret; +} + static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", @@ -188,12 +206,17 @@ static struct ctl_table mptcp_sysctl_table[] = { .proc_handler = proc_scheduler, }, { + .procname = "available_schedulers", + .maxlen = MPTCP_SCHED_BUF_MAX, + .mode = 0644, + .proc_handler = proc_available_schedulers, + }, + { .procname = "close_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - {} }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -215,7 +238,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; - table[7].data = &pernet->close_timeout; + /* table[7] is for available_schedulers which is read-only info */ + table[8].data = &pernet->close_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -235,7 +259,7 @@ err_alloc: static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) { - struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; + const struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; unregister_net_sysctl_table(pernet->ctl_table_hdr); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e768..7884217f33 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index dd7fd1f246..66aa67f49d 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <net/inet_common.h> + enum linux_mptcp_mib_field { MPTCP_MIB_NUM = 0, MPTCP_MIB_MPCAPABLEPASSIVE, /* Received SYN with MP_CAPABLE */ @@ -12,7 +14,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 27ca42c77b..ac2f1a54cc 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; @@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && + (!mp_opt->echo || subflow->mp_join)))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ @@ -1068,6 +1069,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } + msk->last_ack_recv = tcp_jiffies32; mptcp_data_unlock(sk); trace_ack_update_msk(mp_opt->data_ack, diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 55406720c6..23bb89c94e 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) +{ + struct mptcp_addr_info skc_local; + + mptcp_local_address((struct sock_common *)skc, &skc_local); + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_is_backup(msk, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); +} + int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 8bf7ed6d63..4cae2aa7be 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -14,6 +14,7 @@ #include "protocol.h" #include "mib.h" +#include "mptcp_pm_gen.h" static int pm_nl_pernet_id; @@ -347,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { - if (mptcp_pm_is_kernel(msk)) + if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, @@ -470,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -512,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { + struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL; struct sock *sk = (struct sock *)msk; - struct mptcp_pm_addr_entry *local; unsigned int add_addr_signal_max; unsigned int local_addr_max; struct pm_nl_pernet *pernet; @@ -555,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { - local = select_signal_address(pernet, msk); - /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -567,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - if (local) { - if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); - mptcp_pm_nl_addr_send_ack(msk); - } - } + local = select_signal_address(pernet, msk); + if (!local) + goto subflow; + + /* If the alloc fails, we are on memory pressure, not worth + * continuing, and trying to create subflows. + */ + if (!mptcp_pm_alloc_anno_list(msk, &local->addr)) + return; + + __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled++; + mptcp_pm_announce_addr(msk, &local->addr, false); + mptcp_pm_nl_addr_send_ack(msk); + + if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = local; } +subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { @@ -584,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - local = select_local_address(pernet, msk); - if (!local) - break; + if (signal_and_subflow) { + local = signal_and_subflow; + signal_and_subflow = NULL; + } else { + local = select_local_address(pernet, msk); + if (!local) + break; + } fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); @@ -1101,6 +1114,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 @@ -1310,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(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"); + if (addr.addr.port && !address_use_port(&addr)) { + GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } @@ -1400,6 +1431,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= ret; mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } @@ -1533,16 +1565,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } @@ -1555,17 +1596,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = entry->addr.id; - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 9f5d422d5e..8eaa9fbe3e 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -6,6 +6,7 @@ #include "protocol.h" #include "mib.h" +#include "mptcp_pm_gen.h" void mptcp_free_local_addr_list(struct mptcp_sock *msk) { @@ -164,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, + struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, false)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + spin_unlock_bh(&msk->pm.lock); + + return backup; +} + int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 68e4c08648..ff8292d0cf 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -20,6 +20,7 @@ #include <net/transp_v6.h> #endif #include <net/mptcp.h> +#include <net/hotdata.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include "protocol.h" @@ -349,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -706,6 +709,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } while (more_data_avail); + if (moved > 0) + msk->last_data_recv = tcp_jiffies32; *bytes += moved; return done; } @@ -841,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1270,7 +1273,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); - if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { + if (!can_coalesce && i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } @@ -1419,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1436,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); @@ -1556,6 +1561,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, err = copied; out: + if (err > 0) + msk->last_data_sent = tcp_jiffies32; return err; } @@ -2056,7 +2063,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); - tcp_sk(ssk)->window_clamp = window_clamp; + WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } @@ -2565,7 +2572,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { - tcp_send_active_reset(tcp_sk, GFP_ATOMIC); + mptcp_send_active_reset_reason(tcp_sk); tcp_set_state(tcp_sk, TCP_CLOSE); } unlock_sock_fast(tcp_sk, slow); @@ -2793,6 +2800,9 @@ static void __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; + msk->last_data_sent = tcp_jiffies32; + msk->last_data_recv = tcp_jiffies32; + msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); @@ -2806,7 +2816,8 @@ static void mptcp_ca_reset(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); tcp_assign_congestion_control(sk); - strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); + strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name, + sizeof(mptcp_sk(sk)->ca_name)); /* no need to keep a reference to the ops, the name will suffice */ tcp_cleanup_congestion_control(sk); @@ -3879,11 +3890,10 @@ unlock: } static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; - int err; pr_debug("msk=%p", msk); @@ -3895,9 +3905,9 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, return -EINVAL; pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); - newsk = inet_csk_accept(ssk, flags, &err, kern); + newsk = inet_csk_accept(ssk, arg); if (!newsk) - return err; + return arg->err; pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { @@ -3918,7 +3928,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); - newsk->sk_kern_sock = kern; + newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); @@ -3947,7 +3957,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, } } else { tcpfallback: - newsk->sk_kern_sock = kern; + newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); /* we are being invoked after accepting a non-mp-capable @@ -4167,7 +4177,7 @@ int __init mptcp_proto_v6_init(void) int err; mptcp_v6_prot = mptcp_prot; - strcpy(mptcp_v6_prot.name, "MPTCPv6"); + strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name)); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9d1ee19949..8357046732 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -12,8 +12,7 @@ #include <net/inet_connection_sock.h> #include <uapi/linux/mptcp.h> #include <net/genetlink.h> - -#include "mptcp_pm_gen.h" +#include <net/rstreason.h> #define MPTCP_SUPPORTED_VERSION 1 @@ -282,6 +281,9 @@ struct mptcp_sock { u64 bytes_acked; u64 snd_una; u64 wnd_end; + u32 last_data_sent; + u32 last_data_recv; + u32 last_ack_recv; unsigned long timer_ival; u32 token; int rmem_released; @@ -441,6 +443,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -561,7 +564,7 @@ struct mptcp_subflow_context { static inline struct mptcp_subflow_context * mptcp_subflow_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code */ return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data; @@ -581,6 +584,43 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) WRITE_ONCE(subflow->local_id, -1); } +/* Convert reset reasons in MPTCP to enum sk_rst_reason type */ +static inline enum sk_rst_reason +sk_rst_convert_mptcp_reason(u32 reason) +{ + switch (reason) { + case MPTCP_RST_EUNSPEC: + return SK_RST_REASON_MPTCP_RST_EUNSPEC; + case MPTCP_RST_EMPTCP: + return SK_RST_REASON_MPTCP_RST_EMPTCP; + case MPTCP_RST_ERESOURCE: + return SK_RST_REASON_MPTCP_RST_ERESOURCE; + case MPTCP_RST_EPROHIBIT: + return SK_RST_REASON_MPTCP_RST_EPROHIBIT; + case MPTCP_RST_EWQ2BIG: + return SK_RST_REASON_MPTCP_RST_EWQ2BIG; + case MPTCP_RST_EBADPERF: + return SK_RST_REASON_MPTCP_RST_EBADPERF; + case MPTCP_RST_EMIDDLEBOX: + return SK_RST_REASON_MPTCP_RST_EMIDDLEBOX; + default: + /* It should not happen, or else errors may occur + * in MPTCP layer + */ + return SK_RST_REASON_ERROR; + } +} + +static inline void +mptcp_send_active_reset_reason(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + enum sk_rst_reason reason; + + reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); + tcp_send_active_reset(sk, GFP_ATOMIC, reason); +} + static inline u64 mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow) { @@ -645,6 +685,7 @@ 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_get_available_schedulers(char *buf, size_t maxlen); void __mptcp_subflow_fully_established(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); @@ -1063,6 +1104,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 4ab0693c06..4a7fd0508a 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -51,6 +51,28 @@ struct mptcp_sched_ops *mptcp_sched_find(const char *name) return ret; } +/* Build string with list of available scheduler values. + * Similar to tcp_get_available_congestion_control() + */ +void mptcp_get_available_schedulers(char *buf, size_t maxlen) +{ + struct mptcp_sched_ops *sched; + size_t offs = 0; + + rcu_read_lock(); + spin_lock(&mptcp_sched_list_lock); + list_for_each_entry_rcu(sched, &mptcp_sched_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", sched->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; + } + spin_unlock(&mptcp_sched_list_lock); + rcu_read_unlock(); +} + int mptcp_register_scheduler(struct mptcp_sched_ops *sched) { if (!sched->get_subflow) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 19ee684f9e..f9a4fb17b5 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -616,7 +616,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t } if (ret == 0) - strcpy(msk->ca_name, name); + strscpy(msk->ca_name, name, sizeof(msk->ca_name)); release_sock(sk); return ret; @@ -937,6 +937,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) struct sock *sk = (struct sock *)msk; u32 flags = 0; bool slow; + u32 now; memset(info, 0, sizeof(*info)); @@ -965,11 +966,6 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - mptcp_data_lock(sk); - info->mptcpi_snd_una = msk->snd_una; - info->mptcpi_rcv_nxt = msk->ack_seq; - info->mptcpi_bytes_acked = msk->bytes_acked; - mptcp_data_unlock(sk); slow = lock_sock_fast(sk); info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); @@ -981,7 +977,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_retrans = msk->bytes_retrans; info->mptcpi_subflows_total = info->mptcpi_subflows + __mptcp_has_initial_subflow(msk); + now = tcp_jiffies32; + info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent); + info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv); unlock_sock_fast(sk, slow); + + mptcp_data_lock(sk); + info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); @@ -993,6 +999,10 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in if (get_user(len, optlen)) return -EFAULT; + /* When used only to check if a fallback to TCP happened. */ + if (len == 0) + return 0; + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); mptcp_diag_fill_info(msk, &m_info); @@ -1395,6 +1405,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes)); case TCP_NOTSENT_LOWAT: return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); + case TCP_IS_MPTCP: + return mptcp_put_int_option(msk, optval, optlen, 1); } return -EOPNOTSUPP; } @@ -1579,7 +1591,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val) slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, space); - tcp_sk(ssk)->window_clamp = val; + WRITE_ONCE(tcp_sk(ssk)->window_clamp, val); unlock_sock_fast(ssk, slow); } return 0; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6042a47da6..c330946384 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -20,6 +20,7 @@ #include <net/transp_v6.h> #endif #include <net/mptcp.h> + #include "protocol.h" #include "mib.h" @@ -99,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } @@ -150,8 +152,10 @@ static int subflow_check_req(struct request_sock *req, /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ - if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) + if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) { + subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); return -EINVAL; + } #endif mptcp_get_options(skb, &mp_opt); @@ -165,6 +169,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -219,6 +226,7 @@ again: ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); @@ -227,10 +235,12 @@ again: subflow_req_create_thmac(subflow_req); if (unlikely(req->syncookie)) { - if (mptcp_can_accept_new_subflow(subflow_req->msk)) - subflow_init_req_cookie_join_save(subflow_req, skb); - else + if (!mptcp_can_accept_new_subflow(subflow_req->msk)) { + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; + } + + subflow_init_req_cookie_join_save(subflow_req, skb); } pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, @@ -281,10 +291,21 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, } EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req); +static enum sk_rst_reason mptcp_get_rst_reason(const struct sk_buff *skb) +{ + const struct mptcp_ext *mpext = mptcp_get_ext(skb); + + if (!mpext) + return SK_RST_REASON_NOT_SPECIFIED; + + return sk_rst_convert_mptcp_reason(mpext->reset_reason); +} + static struct dst_entry *subflow_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { struct dst_entry *dst; int err; @@ -292,7 +313,7 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk, tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); - dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req); + dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; @@ -302,7 +323,8 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk, dst_release(dst); if (!req->syncookie) - tcp_request_sock_ops.send_reset(sk, skb); + tcp_request_sock_ops.send_reset(sk, skb, + mptcp_get_rst_reason(skb)); return NULL; } @@ -351,7 +373,8 @@ static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst, static struct dst_entry *subflow_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { struct dst_entry *dst; int err; @@ -359,7 +382,7 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk, tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); - dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req); + dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; @@ -369,7 +392,8 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk, dst_release(dst); if (!req->syncookie) - tcp6_request_sock_ops.send_reset(sk, skb); + tcp6_request_sock_ops.send_reset(sk, skb, + mptcp_get_rst_reason(skb)); return NULL; } #endif @@ -405,7 +429,7 @@ void mptcp_subflow_reset(struct sock *ssk) /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); - tcp_send_active_reset(ssk, GFP_ATOMIC); + mptcp_send_active_reset_reason(ssk); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) mptcp_schedule_work(sk); @@ -557,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { pr_debug("synack inet_dport=%d %d", ntohs(inet_sk(sk)->inet_dport), @@ -594,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk) return err; subflow_set_local_id(subflow, err); + subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); + return 0; } @@ -774,6 +803,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_subflow_request_sock *subflow_req; struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; + enum sk_rst_reason reason; struct mptcp_sock *owner; struct sock *child; @@ -873,13 +903,18 @@ create_child: ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); } - if (!mptcp_finish_join(child)) + if (!mptcp_finish_join(child)) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(child); + + subflow_add_reset_reason(skb, subflow->reset_reason); goto dispose_child; + } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; @@ -887,7 +922,7 @@ create_child: } /* check for expected invariant - should never trigger, just help - * catching eariler subtle bugs + * catching earlier subtle bugs */ WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || @@ -899,7 +934,8 @@ dispose_child: tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); - req->rsk_ops->send_reset(sk, skb); + reason = mptcp_get_rst_reason(skb); + req->rsk_ops->send_reset(sk, skb, reason); /* The last child reference will be released by the caller */ return child; @@ -1092,6 +1128,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, } if (mpext->data_fin == 1) { + u64 data_fin_seq; + if (data_len == 1) { bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, mpext->dsn64); @@ -1104,26 +1142,26 @@ static enum mapping_status get_mapping_status(struct sock *ssk, */ skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; - } else { - if (updated) - mptcp_schedule_work((struct sock *)msk); - - return MAPPING_DATA_FIN; } - } else { - u64 data_fin_seq = mpext->data_seq + data_len - 1; - /* If mpext->data_seq is a 32-bit value, data_fin_seq - * must also be limited to 32 bits. - */ - if (!mpext->dsn64) - data_fin_seq &= GENMASK_ULL(31, 0); + if (updated) + mptcp_schedule_work((struct sock *)msk); - mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); - pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", - data_fin_seq, mpext->dsn64); + return MAPPING_DATA_FIN; } + data_fin_seq = mpext->data_seq + data_len - 1; + + /* If mpext->data_seq is a 32-bit value, data_fin_seq must also + * be limited to 32 bits. + */ + if (!mpext->dsn64) + data_fin_seq &= GENMASK_ULL(31, 0); + + mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", + data_fin_seq, mpext->dsn64); + /* Adjust for DATA_FIN using 1 byte of sequence space */ data_len--; } @@ -1192,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; - incr = limit >= skb->len ? skb->len + fin : limit; + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; + + pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -1234,7 +1280,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); unsigned long fail_tout; - /* greceful failure can happen only on the MPC subflow */ + /* graceful failure can happen only on the MPC subflow */ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) return; @@ -1336,7 +1382,7 @@ reset: tcp_set_state(ssk, TCP_CLOSE); while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); - tcp_send_active_reset(ssk, GFP_ATOMIC); + mptcp_send_active_reset_reason(ssk); WRITE_ONCE(subflow->data_avail, false); return false; } @@ -1976,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; |