diff options
Diffstat (limited to 'net/mptcp')
| -rw-r--r-- | net/mptcp/ctrl.c | 42 | ||||
| -rw-r--r-- | net/mptcp/options.c | 26 | ||||
| -rw-r--r-- | net/mptcp/pm_netlink.c | 49 | ||||
| -rw-r--r-- | net/mptcp/pm_userspace.c | 295 | ||||
| -rw-r--r-- | net/mptcp/protocol.c | 35 | ||||
| -rw-r--r-- | net/mptcp/protocol.h | 46 |
6 files changed, 235 insertions, 258 deletions
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 38d8121331d4..2dd81e6c26bd 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -32,6 +32,7 @@ struct mptcp_pernet { unsigned int close_timeout; unsigned int stale_loss_cnt; atomic_t active_disable_times; + u8 syn_retrans_before_tcp_fallback; unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; @@ -92,6 +93,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->blackhole_timeout = 3600; + pernet->syn_retrans_before_tcp_fallback = 2; atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; @@ -102,16 +104,15 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) } #ifdef CONFIG_SYSCTL -static int mptcp_set_scheduler(const struct net *net, const char *name) +static int mptcp_set_scheduler(char *scheduler, const char *name) { - struct mptcp_pernet *pernet = mptcp_get_pernet(net); struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) - strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); @@ -122,7 +123,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name) static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - const struct net *net = current->nsproxy->net_ns; + char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -130,11 +131,11 @@ static int proc_scheduler(const struct ctl_table *ctl, int write, }; int ret; - strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = mptcp_set_scheduler(net, val); + ret = mptcp_set_scheduler(*scheduler, val); return ret; } @@ -161,7 +162,9 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns); + struct mptcp_pernet *pernet = container_of(table->data, + struct mptcp_pernet, + blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -228,7 +231,7 @@ static struct ctl_table mptcp_sysctl_table[] = { { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, - .mode = 0644, + .mode = 0444, .proc_handler = proc_available_schedulers, }, { @@ -244,6 +247,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .proc_handler = proc_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, + { + .procname = "syn_retrans_before_tcp_fallback", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -268,6 +277,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; table[9].data = &pernet->blackhole_timeout; + table[10].data = &pernet->syn_retrans_before_tcp_fallback; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -391,22 +401,26 @@ void mptcp_active_enable(struct sock *sk) void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; - u32 timeouts; if (!sk_is_mptcp(ssk)) return; - timeouts = inet_csk(ssk)->icsk_retransmits; subflow = mptcp_subflow_ctx(ssk); if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { - if (timeouts == 2 || (timeouts < 2 && expired)) { - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP); + struct net *net = sock_net(ssk); + u8 timeouts, to_max; + + timeouts = inet_csk(ssk)->icsk_retransmits; + to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; + + if (timeouts == to_max || (timeouts < to_max && expired)) { + MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); subflow->mpc_drop = 1; mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); - } else { - subflow->mpc_drop = 0; } + } else if (ssk->sk_state == TCP_SYN_SENT) { + subflow->mpc_drop = 0; } } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1603b3702e22..fd2de185bc93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -108,7 +108,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; - mp_opt->use_ack = 0; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } @@ -157,11 +156,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, pr_debug("DSS\n"); ptr++; - /* we must clear 'mpc_map' be able to detect MP_CAPABLE - * map vs DSS map in mptcp_incoming_options(), and reconstruct - * map info accordingly - */ - mp_opt->mpc_map = 0; flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; @@ -369,8 +363,11 @@ void mptcp_get_options(const struct sk_buff *skb, const unsigned char *ptr; int length; - /* initialize option status */ - mp_opt->suboptions = 0; + /* Ensure that casting the whole status to u32 is efficient and safe */ + BUILD_BUG_ON(sizeof_field(struct mptcp_options_received, status) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_options_received, status), + sizeof(u32))); + *(u32 *)&mp_opt->status = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -607,7 +604,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, } opts->ext_copy.use_ack = 1; opts->suboptions = OPTION_MPTCP_DSS; - WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ if (dss_size == 0) @@ -667,8 +663,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &echo, &drop_other_suboptions)) return false; + /* + * Later on, mptcp_write_options() will enforce mutually exclusion with + * DSS, bail out if such option is set and we can't drop it. + */ if (drop_other_suboptions) remaining += opt_size; + else if (opts->suboptions & OPTION_MPTCP_DSS) + return false; + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; @@ -1281,7 +1284,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); } - return; + goto update_wspace; } if (rcv_wnd_new != rcv_wnd_old) { @@ -1306,6 +1309,9 @@ raise_win: th->window = htons(new_win); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED); } + +update_wspace: + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 7a0f7998376a..572d160edca3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -107,8 +107,8 @@ static void remote_address(const struct sock_common *skc, #endif } -static bool lookup_subflow_by_saddr(const struct list_head *list, - const struct mptcp_addr_info *saddr) +bool mptcp_lookup_subflow_by_saddr(const struct list_head *list, + const struct mptcp_addr_info *saddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -1447,8 +1447,8 @@ out_free: return ret; } -static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, - const struct mptcp_addr_info *addr) +bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -1476,7 +1476,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); - ret = remove_anno_list_by_saddr(msk, addr); + ret = mptcp_remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); if (ret) { @@ -1520,7 +1520,7 @@ 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); + remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); @@ -1633,36 +1633,6 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) return ret; } -/* Called from the userspace PM only */ -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 (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); - } -} - -/* Called from the in-kernel PM only */ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { @@ -1671,11 +1641,11 @@ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, list_for_each_entry(entry, rm_list, list) { if (slist.nr < MPTCP_RM_IDS_MAX && - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); if (alist.nr < MPTCP_RM_IDS_MAX && - remove_anno_list_by_saddr(msk, &entry->addr)) + mptcp_remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } @@ -2050,7 +2020,8 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && - (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | + MPTCP_PM_ADDR_FLAG_IMPLICIT))) { spin_unlock_bh(&pernet->lock); GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index e35178f5205f..a3d477059b11 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -8,6 +8,10 @@ #include "mib.h" #include "mptcp_pm_gen.h" +#define mptcp_for_each_userspace_pm_addr(__msk, __entry) \ + list_for_each_entry(__entry, \ + &((__msk)->pm.userspace_pm_local_addr_list), list) + void mptcp_free_local_addr_list(struct mptcp_sock *msk) { struct mptcp_pm_addr_entry *entry, *tmp; @@ -26,6 +30,19 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } } +static struct mptcp_pm_addr_entry * +mptcp_userspace_pm_lookup_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) +{ + struct mptcp_pm_addr_entry *entry; + + mptcp_for_each_userspace_pm_addr(msk, entry) { + if (mptcp_addresses_equal(&entry->addr, addr, false)) + return entry; + } + return NULL; +} + static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry, bool needs_id) @@ -41,7 +58,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_lock_bh(&msk->pm.lock); - list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, e) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; @@ -90,22 +107,20 @@ append_err: static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *addr) { - struct mptcp_pm_addr_entry *entry, *tmp; struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry *entry; - list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) { - /* TODO: a refcount is needed because the entry can - * be used multiple times (e.g. fullmesh mode). - */ - list_del_rcu(&entry->list); - sock_kfree_s(sk, entry, sizeof(*entry)); - msk->pm.local_addr_used--; - return 0; - } - } - - return -EINVAL; + entry = mptcp_userspace_pm_lookup_addr(msk, &addr->addr); + if (!entry) + return -EINVAL; + + /* TODO: a refcount is needed because the entry can + * be used multiple times (e.g. fullmesh mode). + */ + list_del_rcu(&entry->list); + sock_kfree_s(sk, entry, sizeof(*entry)); + msk->pm.local_addr_used--; + return 0; } static struct mptcp_pm_addr_entry * @@ -113,7 +128,7 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) { struct mptcp_pm_addr_entry *entry; - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, entry) { if (entry->addr.id == id) return entry; } @@ -123,17 +138,12 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; + struct mptcp_pm_addr_entry *entry = NULL, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&e->addr, skc, false)) { - entry = e; - break; - } - } + entry = mptcp_userspace_pm_lookup_addr(msk, skc); spin_unlock_bh(&msk->pm.lock); if (entry) return entry->addr.id; @@ -153,50 +163,60 @@ bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct mptcp_pm_addr_entry *entry; - bool backup = false; + bool backup; 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; - } - } + entry = mptcp_userspace_pm_lookup_addr(msk, skc); + backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); spin_unlock_bh(&msk->pm.lock); return backup; } -int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) +static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct mptcp_sock *msk; + + if (!token) { + GENL_SET_ERR_MSG(info, "missing required token"); + return NULL; + } + + msk = mptcp_token_get_sock(genl_info_net(info), nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return NULL; + } + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + sock_put((struct sock *)msk); + return NULL; + } + + return msk; +} + +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) +{ struct nlattr *addr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry addr_val; struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; - u32 token_val; - if (!addr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!addr) { + GENL_SET_ERR_MSG(info, "missing required address"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(sock_net(skb->sk), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto announce_err; - } - err = mptcp_pm_parse_entry(addr, info, true, &addr_val); if (err < 0) { GENL_SET_ERR_MSG(info, "error parsing local address"); @@ -267,40 +287,48 @@ remove_err: return err; } +void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry) +{ + struct mptcp_rm_list alist = { .nr = 0 }; + int anno_nr = 0; + + /* only delete if either announced or matching a subflow */ + if (mptcp_remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + return; + + alist.ids[alist.nr++] = entry->addr.id; + + 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); +} + int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; struct mptcp_pm_addr_entry *match; - struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; - LIST_HEAD(free_list); int err = -EINVAL; struct sock *sk; - u32 token_val; u8 id_val; - if (!id || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!id) { + GENL_SET_ERR_MSG(info, "missing required ID"); return err; } id_val = nla_get_u8(id); - token_val = nla_get_u32(token); - msk = mptcp_token_get_sock(sock_net(skb->sk), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - if (id_val == 0) { err = mptcp_userspace_pm_remove_id_zero_address(msk, info); goto out; @@ -317,16 +345,14 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) goto out; } - list_move(&match->list, &free_list); + list_del_rcu(&match->list); spin_unlock_bh(&msk->pm.lock); - mptcp_pm_remove_addrs(msk, &free_list); + mptcp_pm_remove_addr_entry(msk, match); release_sock(sk); - list_for_each_entry_safe(match, entry, &free_list, list) { - sock_kfree_s(sk, match, sizeof(*match)); - } + sock_kfree_s(sk, match, sizeof(*match)); err = 0; out: @@ -337,7 +363,6 @@ out: int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry entry = { 0 }; struct mptcp_addr_info addr_r; @@ -345,28 +370,18 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; - u32 token_val; - if (!laddr || !raddr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!laddr || !raddr) { + GENL_SET_ERR_MSG(info, "missing required address(es)"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(genl_info_net(info), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto create_err; - } - err = mptcp_pm_parse_entry(laddr, info, true, &entry); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); @@ -469,36 +484,25 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct mptcp_addr_info addr_l; + struct mptcp_pm_addr_entry addr_l; struct mptcp_addr_info addr_r; struct mptcp_sock *msk; struct sock *sk, *ssk; int err = -EINVAL; - u32 token_val; - if (!laddr || !raddr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!laddr || !raddr) { + GENL_SET_ERR_MSG(info, "missing required address(es)"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(genl_info_net(info), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto destroy_err; - } - - err = mptcp_pm_parse_addr(laddr, info, &addr_l); + err = mptcp_pm_parse_entry(laddr, info, true, &addr_l); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); goto destroy_err; @@ -511,43 +515,41 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info } #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { - ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6); - addr_l.family = AF_INET6; + if (addr_l.addr.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { + ipv6_addr_set_v4mapped(addr_l.addr.addr.s_addr, &addr_l.addr.addr6); + addr_l.addr.family = AF_INET6; } - if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) { + if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr.addr6)) { ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); addr_r.family = AF_INET6; } #endif - if (addr_l.family != addr_r.family) { + if (addr_l.addr.family != addr_r.family) { GENL_SET_ERR_MSG(info, "address families do not match"); err = -EINVAL; goto destroy_err; } - if (!addr_l.port || !addr_r.port) { + if (!addr_l.addr.port || !addr_r.port) { GENL_SET_ERR_MSG(info, "missing local or remote port"); err = -EINVAL; goto destroy_err; } lock_sock(sk); - ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); - if (ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - struct mptcp_pm_addr_entry entry = { .addr = addr_l }; - - spin_lock_bh(&msk->pm.lock); - mptcp_userspace_pm_delete_local_addr(msk, &entry); - spin_unlock_bh(&msk->pm.lock); - mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); - mptcp_close_ssk(sk, ssk, subflow); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); - err = 0; - } else { + ssk = mptcp_nl_find_ssk(msk, &addr_l.addr, &addr_r); + if (!ssk) { err = -ESRCH; + goto release_sock; } + + spin_lock_bh(&msk->pm.lock); + mptcp_userspace_pm_delete_local_addr(msk, &addr_l); + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); + mptcp_close_ssk(sk, ssk, mptcp_subflow_ctx(ssk)); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); +release_sock: release_sock(sk); destroy_err: @@ -560,31 +562,19 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; - u32 token_val; u8 bkup = 0; - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(net, token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "userspace PM not selected"); - goto set_flags_err; - } - ret = mptcp_pm_parse_entry(attr, info, false, &loc); if (ret < 0) goto set_flags_err; @@ -606,13 +596,12 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) bkup = 1; 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, &loc.addr, false)) { - if (bkup) - entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else - entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; - } + entry = mptcp_userspace_pm_lookup_addr(msk, &loc.addr); + if (entry) { + if (bkup) + entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; } spin_unlock_bh(&msk->pm.lock); @@ -632,33 +621,23 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, DECLARE_BITMAP(map, MPTCP_PM_MAX_ADDR_ID + 1); } *bitmap; const struct genl_info *info = genl_info_dump(cb); - struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; - struct nlattr *token; int ret = -EINVAL; struct sock *sk; void *hdr; bitmap = (struct id_bitmap *)cb->ctx; - token = info->attrs[MPTCP_PM_ATTR_TOKEN]; - msk = mptcp_token_get_sock(net, nla_get_u32(token)); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - lock_sock(sk); spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, entry) { if (test_bit(entry->addr.id, bitmap->map)) continue; @@ -680,7 +659,6 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, release_sock(sk); ret = msg->len; -out: sock_put(sk); return ret; } @@ -689,28 +667,19 @@ int mptcp_userspace_pm_get_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct mptcp_pm_addr_entry addr, *entry; - struct net *net = sock_net(skb->sk); struct mptcp_sock *msk; struct sk_buff *msg; int ret = -EINVAL; struct sock *sk; void *reply; - msk = mptcp_token_get_sock(net, nla_get_u32(token)); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) goto out; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08a72242428c..6bd819047470 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -47,7 +47,7 @@ static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -static struct net_device mptcp_napi_dev; +static struct net_device *mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) @@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, int delta; if (MPTCP_SKB_CB(from)->offset || + ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; @@ -528,13 +529,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +552,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +560,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -1766,8 +1767,10 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ - if (!mptcp_disconnect(sk, 0)) + if (!mptcp_disconnect(sk, 0)) { + sk->sk_disconnects++; sk->sk_socket->state = SS_UNCONNECTED; + } } inet_clear_bit(DEFER_CONNECT, sk); @@ -1939,6 +1942,8 @@ do_error: goto out; } +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); + static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, @@ -1992,6 +1997,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, break; } + mptcp_rcv_space_adjust(msk, copied); return copied; } @@ -2217,9 +2223,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2268,7 +2271,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2276,7 +2279,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { @@ -4146,11 +4149,13 @@ void __init mptcp_proto_init(void) if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); - init_dummy_netdev(&mptcp_napi_dev); + mptcp_napi_dev = alloc_netdev_dummy(0); + if (!mptcp_napi_dev) + panic("Failed to allocate MPTCP dummy netdev\n"); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); - netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi, + netif_napi_add_tx(mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a93e661ef5c4..f6a207958459 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -149,22 +149,24 @@ struct mptcp_options_received { u32 subflow_seq; u16 data_len; __sum16 csum; - u16 suboptions; + struct_group(status, + u16 suboptions; + u16 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + reset_reason:4, + reset_transient:1, + echo:1, + backup:1, + deny_join_id0:1, + __unused:2; + ); + u8 join_id; u32 token; u32 nonce; - u16 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - reset_reason:4, - reset_transient:1, - echo:1, - backup:1, - deny_join_id0:1, - __unused:2; - u8 join_id; u64 thmac; u8 hmac[MPTCPOPT_HMAC_LEN]; struct mptcp_addr_info addr; @@ -760,10 +762,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) static inline bool mptcp_epollin_ready(const struct sock *sk) { + u64 data_avail = mptcp_data_avail(mptcp_sk(sk)); + + if (!data_avail) + return false; + /* mptcp doesn't have to deal with small skbs in the receive queue, - * at it can always coalesce them + * as it can always coalesce them */ - return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + return (data_avail >= sk->sk_rcvlowat) || (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) || READ_ONCE(tcp_memory_pressure); @@ -1027,6 +1034,10 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, const struct mptcp_addr_info *addr); +bool mptcp_lookup_subflow_by_saddr(const struct list_head *list, + const struct mptcp_addr_info *saddr); +bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr); int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); @@ -1034,7 +1045,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); +void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry); void mptcp_free_local_addr_list(struct mptcp_sock *msk); |