diff options
Diffstat (limited to 'net/mptcp')
| -rw-r--r-- | net/mptcp/Makefile | 3 | ||||
| -rw-r--r-- | net/mptcp/ctrl.c | 16 | ||||
| -rw-r--r-- | net/mptcp/fastopen.c | 1 | ||||
| -rw-r--r-- | net/mptcp/mptcp_pm_gen.c | 179 | ||||
| -rw-r--r-- | net/mptcp/mptcp_pm_gen.h | 58 | ||||
| -rw-r--r-- | net/mptcp/pm.c | 2 | ||||
| -rw-r--r-- | net/mptcp/pm_netlink.c | 114 | ||||
| -rw-r--r-- | net/mptcp/pm_userspace.c | 89 | ||||
| -rw-r--r-- | net/mptcp/protocol.c | 75 | ||||
| -rw-r--r-- | net/mptcp/protocol.h | 92 | ||||
| -rw-r--r-- | net/mptcp/sockopt.c | 73 | ||||
| -rw-r--r-- | net/mptcp/subflow.c | 46 |
12 files changed, 541 insertions, 207 deletions
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 84e531f86b82..bcf1dbf3a432 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -2,7 +2,8 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o + mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o \ + mptcp_pm_gen.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index e72b518c5d02..13fe0748dde8 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -27,6 +27,7 @@ struct mptcp_pernet { #endif unsigned int add_addr_timeout; + unsigned int close_timeout; unsigned int stale_loss_cnt; u8 mptcp_enabled; u8 checksum_enabled; @@ -65,6 +66,13 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net) return mptcp_get_pernet(net)->stale_loss_cnt; } +unsigned int mptcp_close_timeout(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_DEAD)) + return TCP_TIMEWAIT_LEN; + return mptcp_get_pernet(sock_net(sk))->close_timeout; +} + int mptcp_get_pm_type(const struct net *net) { return mptcp_get_pernet(net)->pm_type; @@ -79,6 +87,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; @@ -141,6 +150,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dostring, }, + { + .procname = "close_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, {} }; @@ -163,6 +178,7 @@ 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; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index bceaab8dd8e4..74698582a285 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -52,6 +52,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); + mptcp_sk(sk)->bytes_received += skb->len; sk->sk_data_ready(sk); diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c new file mode 100644 index 000000000000..a2325e70ddab --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "mptcp_pm_gen.h" + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1] = { + [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, + [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = NLA_POLICY_EXACT_LEN(16), + [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32, }, +}; + +/* MPTCP_PM_CMD_ADD_ADDR - do */ +const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_DEL_ADDR - do */ +const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_GET_ADDR - do */ +const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_FLUSH_ADDRS - do */ +const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SET_LIMITS - do */ +const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_GET_LIMITS - do */ +const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_SET_FLAGS - do */ +const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_ANNOUNCE - do */ +const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_REMOVE - do */ +const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1] = { + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, +}; + +/* MPTCP_PM_CMD_SUBFLOW_CREATE - do */ +const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SUBFLOW_DESTROY - do */ +const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* Ops table for mptcp_pm */ +const struct genl_ops mptcp_pm_nl_ops[11] = { + { + .cmd = MPTCP_PM_CMD_ADD_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_add_addr_doit, + .policy = mptcp_pm_add_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_DEL_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_del_addr_doit, + .policy = mptcp_pm_del_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_addr_doit, + .dumpit = mptcp_pm_nl_get_addr_dumpit, + .policy = mptcp_pm_get_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_flush_addrs_doit, + .policy = mptcp_pm_flush_addrs_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_limits_doit, + .policy = mptcp_pm_set_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_limits_doit, + .policy = mptcp_pm_get_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + }, + { + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_flags_doit, + .policy = mptcp_pm_set_flags_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_ANNOUNCE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_announce_doit, + .policy = mptcp_pm_announce_nl_policy, + .maxattr = MPTCP_PM_ATTR_TOKEN, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_REMOVE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_remove_doit, + .policy = mptcp_pm_remove_nl_policy, + .maxattr = MPTCP_PM_ATTR_LOC_ID, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_create_doit, + .policy = mptcp_pm_subflow_create_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_destroy_doit, + .policy = mptcp_pm_subflow_destroy_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, +}; diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h new file mode 100644 index 000000000000..10579d184587 --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_MPTCP_PM_GEN_H +#define _LINUX_MPTCP_PM_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +extern const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1]; + +extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1]; + +extern const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1]; + +extern const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +/* Ops table for mptcp_pm */ +extern const struct genl_ops mptcp_pm_nl_ops[11]; + +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, + struct genl_info *info); +int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, + struct genl_info *info); + +#endif /* _LINUX_MPTCP_PM_GEN_H */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index d8da5374d9e1..4ae19113b8eb 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -184,7 +184,7 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk) spin_unlock_bh(&pm->lock); } -void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, +void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct mptcp_subflow_context *subflow) { struct mptcp_pm_data *pm = &msk->pm; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9661f3812682..1529ec358815 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1104,29 +1104,6 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = { }, }; -static const struct nla_policy -mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { - [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, - [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = - NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, - [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, - [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, -}; - -static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { - [MPTCP_PM_ATTR_ADDR] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), - [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ATTR_ADDR_REMOTE] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), -}; - void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); @@ -1188,7 +1165,7 @@ static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, - mptcp_pm_addr_policy, info->extack); + mptcp_pm_address_nl_policy, info->extack); if (err) return err; @@ -1303,9 +1280,9 @@ next: return 0; } -static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; int ret; @@ -1484,9 +1461,9 @@ next: return 0; } -static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; unsigned int addr_max; @@ -1619,7 +1596,7 @@ static void __reset_counters(struct pm_nl_pernet *pernet) pernet->addrs = 0; } -static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); LIST_HEAD(free_list); @@ -1675,9 +1652,9 @@ nla_put_failure: return -EMSGSIZE; } -static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct sk_buff *msg; @@ -1725,8 +1702,8 @@ fail: return ret; } -static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg, - struct netlink_callback *cb) +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; @@ -1783,8 +1760,7 @@ static int parse_limit(struct genl_info *info, int id, unsigned int *limit) return 0; } -static int -mptcp_nl_cmd_set_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); unsigned int rcv_addrs, subflows; @@ -1809,8 +1785,7 @@ unlock: return ret; } -static int -mptcp_nl_cmd_get_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct sk_buff *msg; @@ -1919,7 +1894,7 @@ int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 return 0; } -static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; @@ -2283,72 +2258,13 @@ nla_put_failure: nlmsg_free(skb); } -static const struct genl_small_ops mptcp_pm_ops[] = { - { - .cmd = MPTCP_PM_CMD_ADD_ADDR, - .doit = mptcp_nl_cmd_add_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_DEL_ADDR, - .doit = mptcp_nl_cmd_del_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, - .doit = mptcp_nl_cmd_flush_addrs, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_ADDR, - .doit = mptcp_nl_cmd_get_addr, - .dumpit = mptcp_nl_cmd_dump_addrs, - }, - { - .cmd = MPTCP_PM_CMD_SET_LIMITS, - .doit = mptcp_nl_cmd_set_limits, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_LIMITS, - .doit = mptcp_nl_cmd_get_limits, - }, - { - .cmd = MPTCP_PM_CMD_SET_FLAGS, - .doit = mptcp_nl_cmd_set_flags, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_ANNOUNCE, - .doit = mptcp_nl_cmd_announce, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_REMOVE, - .doit = mptcp_nl_cmd_remove, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, - .doit = mptcp_nl_cmd_sf_create, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, - .doit = mptcp_nl_cmd_sf_destroy, - .flags = GENL_UNS_ADMIN_PERM, - }, -}; - static struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, - .maxattr = MPTCP_PM_ATTR_MAX, - .policy = mptcp_pm_policy, .netnsok = true, .module = THIS_MODULE, - .small_ops = mptcp_pm_ops, - .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), + .ops = mptcp_pm_nl_ops, + .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index d042d32beb4d..5c01b9bc619a 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -145,13 +145,14 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); } -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; 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) { @@ -167,6 +168,8 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) 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; @@ -190,7 +193,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - lock_sock((struct sock *)msk); + lock_sock(sk); spin_lock_bh(&msk->pm.lock); if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) { @@ -200,15 +203,49 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) } spin_unlock_bh(&msk->pm.lock); - release_sock((struct sock *)msk); + release_sock(sk); err = 0; announce_err: - sock_put((struct sock *)msk); + sock_put(sk); + return err; +} + +static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, + struct genl_info *info) +{ + struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + bool has_id_0 = false; + int err = -EINVAL; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + if (subflow->local_id == 0) { + has_id_0 = true; + break; + } + } + if (!has_id_0) { + GENL_SET_ERR_MSG(info, "address with id 0 not found"); + goto remove_err; + } + + list.ids[list.nr++] = 0; + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &list); + spin_unlock_bh(&msk->pm.lock); + + err = 0; + +remove_err: + release_sock(sk); return err; } -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) +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]; @@ -217,6 +254,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) struct mptcp_sock *msk; LIST_HEAD(free_list); int err = -EINVAL; + struct sock *sk; u32 token_val; u8 id_val; @@ -234,12 +272,19 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) return err; } + sk = (struct sock *)msk; + if (!mptcp_pm_is_userspace(msk)) { GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); goto remove_err; } - lock_sock((struct sock *)msk); + if (id_val == 0) { + err = mptcp_userspace_pm_remove_id_zero_address(msk, info); + goto remove_err; + } + + lock_sock(sk); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { if (entry->addr.id == id_val) { @@ -250,7 +295,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); - release_sock((struct sock *)msk); + release_sock(sk); goto remove_err; } @@ -258,19 +303,19 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) mptcp_pm_remove_addrs(msk, &free_list); - release_sock((struct sock *)msk); + release_sock(sk); list_for_each_entry_safe(match, entry, &free_list, list) { - sock_kfree_s((struct sock *)msk, match, sizeof(*match)); + sock_kfree_s(sk, match, sizeof(*match)); } err = 0; remove_err: - sock_put((struct sock *)msk); + sock_put(sk); return err; } -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) +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]; @@ -296,6 +341,8 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) 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; @@ -313,8 +360,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } - sk = (struct sock *)msk; - if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) { GENL_SET_ERR_MSG(info, "families mismatch"); err = -EINVAL; @@ -342,7 +387,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&msk->pm.lock); create_err: - sock_put((struct sock *)msk); + sock_put(sk); return err; } @@ -394,7 +439,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, return NULL; } -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) +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]; @@ -419,6 +464,8 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) 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; @@ -448,7 +495,6 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) goto destroy_err; } - sk = (struct sock *)msk; lock_sock(sk); ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); if (ssk) { @@ -468,7 +514,7 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) release_sock(sk); destroy_err: - sock_put((struct sock *)msk); + sock_put(sk); return err; } @@ -478,6 +524,7 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, { struct mptcp_sock *msk; int ret = -EINVAL; + struct sock *sk; u32 token_val; token_val = nla_get_u32(token); @@ -486,6 +533,8 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, if (!msk) return ret; + sk = (struct sock *)msk; + if (!mptcp_pm_is_userspace(msk)) goto set_flags_err; @@ -493,11 +542,11 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, rem->addr.family == AF_UNSPEC) goto set_flags_err; - lock_sock((struct sock *)msk); + lock_sock(sk); ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); - release_sock((struct sock *)msk); + release_sock(sk); set_flags_err: - sock_put((struct sock *)msk); + sock_put(sk); return ret; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 886ab689a8ae..a0b8356cd8c5 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -121,8 +121,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); - - mptcp_sockopt_sync(msk, msk->first); } return msk->first; @@ -863,9 +861,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); - mptcp_data_unlock(sk); } @@ -893,6 +890,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); + __mptcp_propagate_sndbuf(sk, ssk); return true; } @@ -1079,15 +1077,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; - sk_stream_moderate_sndbuf(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); + first = false; } + __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of @@ -1268,7 +1267,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, * queue management operation, to avoid breaking the ext <-> * SSN association set here */ - mpext = skb_ext_find(skb, SKB_EXT_MPTCP); + mpext = mptcp_get_ext(skb); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; goto alloc_skb; @@ -1290,7 +1289,7 @@ alloc_skb: i = skb_shinfo(skb)->nr_frags; reuse_skb = false; - mpext = skb_ext_find(skb, SKB_EXT_MPTCP); + mpext = mptcp_get_ext(skb); } /* Zero window and all data acked? Probe. */ @@ -1761,6 +1760,18 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return ret; } +static int do_copy_data_nocache(struct sock *sk, int copy, + struct iov_iter *from, char *to) +{ + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { + if (!copy_from_iter_full_nocache(to, copy, from)) + return -EFAULT; + } else if (!copy_from_iter_full(to, copy, from)) { + return -EFAULT; + } + return 0; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1834,11 +1845,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; - if (copy_page_from_iter(dfrag->page, offset, psize, - &msg->msg_iter) != psize) { - ret = -EFAULT; + ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, + page_address(dfrag->page) + offset); + if (ret) goto do_error; - } /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); @@ -1922,6 +1932,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; + msk->bytes_consumed += count; } break; } @@ -1932,6 +1943,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); + msk->bytes_consumed += count; } if (copied >= len) @@ -2391,8 +2403,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ - mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); + mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; @@ -2448,6 +2460,7 @@ out_release: WRITE_ONCE(msk->first, NULL); out: + __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); @@ -2477,7 +2490,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ - mptcp_pm_subflow_check_next(mptcp_sk(sk), ssk, subflow); + mptcp_pm_subflow_check_next(mptcp_sk(sk), subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH); } @@ -2516,7 +2529,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk) return false; return time_after32(tcp_jiffies32, - inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); + inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2659,7 +2672,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) return; close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + - TCP_TIMEWAIT_LEN; + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active @@ -2755,6 +2768,7 @@ static void __mptcp_init_sock(struct sock *sk) msk->rmem_fwd_alloc = 0; WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; + msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -2964,16 +2978,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk) __mptcp_destroy_sock(sk); } -static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +static __poll_t mptcp_check_readable(struct sock *sk) { - /* Concurrent splices from sk_receive_queue into receive_queue will - * always show at least one non-empty queue when checked in this order. - */ - if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && - skb_queue_empty_lockless(&msk->receive_queue)) - return 0; - - return EPOLLIN | EPOLLRDNORM; + return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) @@ -3011,7 +3018,7 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } - if (mptcp_check_readable(msk) || timeout < 0) { + if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ @@ -3138,6 +3145,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->snd_data_fin_enable = false; msk->rcv_fastclose = false; msk->use_64bit_ack = false; + msk->bytes_consumed = 0; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); @@ -3219,7 +3227,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); - mptcp_propagate_sndbuf(nsk, ssk); + __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); @@ -3397,6 +3405,8 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_set_connected(sk); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); + if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) + __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); @@ -3441,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } + if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_sync_sndbuf(sk); + else + __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); + mptcp_data_unlock(sk); + } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } @@ -3525,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk) /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); + mptcp_propagate_sndbuf(parent, ssk); return true; } @@ -3909,7 +3928,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { - mask |= mptcp_check_readable(msk); + mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else @@ -3947,6 +3966,7 @@ static const struct proto_ops mptcp_stream_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { @@ -4048,6 +4068,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3612545fa62e..fe6f2d399ee8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -13,6 +13,8 @@ #include <uapi/linux/mptcp.h> #include <net/genetlink.h> +#include "mptcp_pm_gen.h" + #define MPTCP_SUPPORTED_VERSION 1 /* MPTCP option bits */ @@ -123,6 +125,7 @@ #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { u64 map_seq; @@ -267,6 +270,7 @@ struct mptcp_sock { atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; u64 bytes_retrans; + u64 bytes_consumed; int rmem_fwd_alloc; int snd_burst; int old_wspace; @@ -432,11 +436,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) return (struct mptcp_subflow_request_sock *)rsk; } -enum mptcp_data_avail { - MPTCP_SUBFLOW_NODATA, - MPTCP_SUBFLOW_DATA_AVAIL, -}; - struct mptcp_delegated_action { struct napi_struct napi; struct list_head head; @@ -447,6 +446,7 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SCHEDULED 0 #define MPTCP_DELEGATE_SEND 1 #define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_SNDBUF 3 #define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ @@ -492,7 +492,7 @@ struct mptcp_subflow_context { valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ __unused : 9; - enum mptcp_data_avail data_avail; + bool data_avail; bool scheduled; u32 remote_nonce; u64 thmac; @@ -520,6 +520,9 @@ struct mptcp_subflow_context { u32 setsockopt_seq; u32 stale_rcv_tstamp; + int cached_sndbuf; /* sndbuf size when last synced with the msk sndbuf, + * protected by the msk socket lock + */ struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -613,6 +616,7 @@ unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); +unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, @@ -661,6 +665,24 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk); int mptcp_sched_get_send(struct mptcp_sock *msk); int mptcp_sched_get_retrans(struct mptcp_sock *msk); +static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) +{ + return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed); +} + +static inline bool mptcp_epollin_ready(const struct sock *sk) +{ + /* mptcp doesn't have to deal with small skbs in the receive queue, + * at it can always coalesce them + */ + return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) || + READ_ONCE(tcp_memory_pressure); +} + +int mptcp_set_rcvlowat(struct sock *sk, int val); + static inline bool __tcp_can_send(const struct sock *ssk) { /* only send if our side has not closed yet */ @@ -735,6 +757,7 @@ static inline bool mptcp_is_fully_established(struct sock *sk) return inet_sk_state_load(sk) == TCP_ESTABLISHED && READ_ONCE(mptcp_sk(sk)->fully_established); } + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); @@ -762,13 +785,52 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } -static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +static inline void __mptcp_sync_sndbuf(struct sock *sk) { - if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) - return false; + struct mptcp_subflow_context *subflow; + int ssk_sndbuf, new_sndbuf; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); + + subflow->cached_sndbuf = ssk_sndbuf; + new_sndbuf += ssk_sndbuf; + } + + /* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */ + WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); +} + +/* The called held both the msk socket and the subflow socket locks, + * possibly under BH + */ +static inline void __mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (READ_ONCE(ssk->sk_sndbuf) != subflow->cached_sndbuf) + __mptcp_sync_sndbuf(sk); +} + +/* the caller held only the subflow socket lock, either in process or + * BH context. Additionally this can be called under the msk data lock, + * so we can't acquire such lock here: let the delegate action acquires + * the needed locks in suitable order. + */ +static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (likely(READ_ONCE(ssk->sk_sndbuf) == subflow->cached_sndbuf)) + return; - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); - return true; + local_bh_disable(); + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SNDBUF); + local_bh_enable(); } static inline void mptcp_write_space(struct sock *sk) @@ -826,7 +888,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); void mptcp_pm_connection_closed(struct mptcp_sock *msk); void mptcp_pm_subflow_established(struct mptcp_sock *msk); bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk); -void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, +void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct mptcp_subflow_context *subflow); void mptcp_pm_add_addr_received(const struct sock *ssk, const struct mptcp_addr_info *addr); @@ -877,10 +939,6 @@ void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info); void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); @@ -1007,7 +1065,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk) static inline void __mptcp_do_fallback(struct mptcp_sock *msk) { - if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) { + if (__mptcp_check_fallback(msk)) { pr_debug("TCP fallback already done (msk=%p)", msk); return; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 8260202c0066..77f5e8932abf 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -89,12 +89,13 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val); break; case SO_PRIORITY: - ssk->sk_priority = val; + WRITE_ONCE(ssk->sk_priority, val); break; case SO_SNDBUF: case SO_SNDBUFFORCE: ssk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; break; case SO_RCVBUF: case SO_RCVBUFFORCE: @@ -734,7 +735,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, lock_sock(sk); sockopt_seq_inc(msk); - val = inet_sk(sk)->tos; + val = READ_ONCE(inet_sk(sk)->tos); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -915,7 +916,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) mptcp_pm_get_local_addr_max(msk); } - if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) + if (__mptcp_check_fallback(msk)) flags |= MPTCP_INFO_FLAG_FALLBACK; if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; @@ -1343,7 +1344,7 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname, switch (optname) { case IP_TOS: - return mptcp_put_int_option(msk, optval, optlen, inet_sk(sk)->tos); + return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos)); } return -EOPNOTSUPP; @@ -1415,8 +1416,10 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_userlocks & tx_rx_locks) { ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks; - if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) { WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; + } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); } @@ -1444,37 +1447,63 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } -static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) -{ - bool slow = lock_sock_fast(ssk); - - sync_socket_options(msk, ssk); - - unlock_sock_fast(ssk, slow); -} - -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) +void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); msk_owned_by_me(msk); + ssk->sk_rcvlowat = 0; + + /* subflows must ignore any latency-related settings: will not affect + * the user-space - only the msk is relevant - but will foul the + * mptcp scheduler + */ + tcp_sk(ssk)->notsent_lowat = UINT_MAX; + if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - __mptcp_sockopt_sync(msk, ssk); + sync_socket_options(msk, ssk); subflow->setsockopt_seq = msk->setsockopt_seq; } } -void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) +/* unfortunately this is different enough from the tcp version so + * that we can't factor it out + */ +int mptcp_set_rcvlowat(struct sock *sk, int val) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_subflow_context *subflow; + int space, cap; - msk_owned_by_me(msk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + cap = sk->sk_rcvbuf >> 1; + else + cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; + val = min(val, cap); + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); - if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - sync_socket_options(msk, ssk); + /* Check if we need to signal EPOLLIN right now */ + if (mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); - subflow->setsockopt_seq = msk->setsockopt_seq; + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val); + if (space <= sk->sk_rcvbuf) + return 0; + + /* propagate the rcvbuf changes to all the subflows */ + WRITE_ONCE(sk->sk_rcvbuf, space); + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + WRITE_ONCE(ssk->sk_rcvbuf, space); + 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 9c1f8d1d63d2..e120e9616454 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,6 +421,7 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_set_connected(struct sock *sk) { + __mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first); if (sk->sk_state == TCP_SYN_SENT) { inet_sk_state_store(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -472,7 +473,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) return; msk = mptcp_sk(parent); - mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -1237,7 +1237,7 @@ 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, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); if (subflow->data_avail) return true; @@ -1271,7 +1271,7 @@ static bool subflow_check_data_avail(struct sock *ssk) continue; } - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); break; } return true; @@ -1293,7 +1293,7 @@ fallback: goto reset; } mptcp_subflow_fail(msk, ssk); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1310,7 +1310,7 @@ reset: while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); return false; } @@ -1322,7 +1322,7 @@ reset: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1334,7 +1334,7 @@ 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, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1405,10 +1405,18 @@ static void subflow_data_ready(struct sock *sk) WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); - if (mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + + /* subflow-level lowat test are not relevant. + * respect the msk-level threshold eventually mandating an immediate ack + */ + if (mptcp_data_avail(msk) < parent->sk_rcvlowat && + (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); + } } static void subflow_write_space(struct sock *ssk) @@ -1525,8 +1533,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - mptcp_sockopt_sync(msk, ssk); - ssk->sk_bound_dev_if = ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) @@ -1637,7 +1643,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, err = security_mptcp_add_subflow(sk, sf->sk); if (err) - goto release_ssk; + goto err_free; /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); @@ -1651,15 +1657,12 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); + if (err) + goto err_free; -release_ssk: + mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk); release_sock(sf->sk); - if (err) { - sock_release(sf); - return err; - } - /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed * by a kernel workqueue. Adjust inode references, so that the @@ -1679,6 +1682,11 @@ release_ssk: mptcp_subflow_ops_override(sf->sk); return 0; + +err_free: + release_sock(sf->sk); + sock_release(sf); + return err; } static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, @@ -1728,7 +1736,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { - mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(msk, sk); pr_fallback(msk); @@ -2044,7 +2051,6 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.send_check = ipv4_specific.send_check; 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; |