From dc50eab76b709d68175a358d6e23a5a3890764d3 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 19:39:57 +0200 Subject: Merging upstream version 6.7.7. Signed-off-by: Daniel Baumann --- net/mptcp/Makefile | 3 +- net/mptcp/crypto_test.c | 1 + net/mptcp/ctrl.c | 16 ++++ net/mptcp/diag.c | 8 +- net/mptcp/fastopen.c | 6 +- net/mptcp/mib.c | 1 + net/mptcp/mib.h | 8 ++ net/mptcp/mptcp_diag.c | 1 + net/mptcp/mptcp_pm_gen.c | 179 ++++++++++++++++++++++++++++++++++++++++++++ net/mptcp/mptcp_pm_gen.h | 58 +++++++++++++++ net/mptcp/options.c | 9 ++- net/mptcp/pm.c | 2 +- net/mptcp/pm_netlink.c | 188 ++++++++++++++++------------------------------- net/mptcp/pm_userspace.c | 115 ++++++++++++++++++++++------- net/mptcp/protocol.c | 149 +++++++++++++++++++++---------------- net/mptcp/protocol.h | 70 ++++++++++++------ net/mptcp/sockopt.c | 68 +++++++++++------ net/mptcp/subflow.c | 133 +++++++++++++++++++-------------- net/mptcp/token_test.c | 1 + 19 files changed, 693 insertions(+), 323 deletions(-) create mode 100644 net/mptcp/mptcp_pm_gen.c create mode 100644 net/mptcp/mptcp_pm_gen.h (limited to 'net/mptcp') diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 84e531f86b..bcf1dbf3a4 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/crypto_test.c b/net/mptcp/crypto_test.c index 017248dea0..220414e5c8 100644 --- a/net/mptcp/crypto_test.c +++ b/net/mptcp/crypto_test.c @@ -70,3 +70,4 @@ static struct kunit_suite mptcp_crypto_suite = { kunit_test_suite(mptcp_crypto_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for MPTCP Crypto"); diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index e72b518c5d..13fe0748dd 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/diag.c b/net/mptcp/diag.c index a536586742..6ff6f14674 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,19 @@ #include #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -63,17 +65,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 74698582a2..ad28da655f 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_unlock(sk); } -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb; - mptcp_data_lock(sk); skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); @@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_ } pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); - mptcp_data_unlock(sk); } diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index a0990c365a..c30405e768 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -66,6 +66,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED), SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE), SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT), + SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index cae71d9472..dd7fd1f246 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -65,6 +65,7 @@ enum linux_mptcp_mib_field { * conflict with another subflow while updating msk rcv wnd */ MPTCP_MIB_RCVWNDCONFLICT, /* Conflict with while updating msk rcv wnd */ + MPTCP_MIB_CURRESTAB, /* Current established MPTCP connections */ __MPTCP_MIB_MAX }; @@ -95,4 +96,11 @@ static inline void __MPTCP_INC_STATS(struct net *net, __SNMP_INC_STATS(net->mib.mptcp_statistics, field); } +static inline void MPTCP_DEC_STATS(struct net *net, + enum linux_mptcp_mib_field field) +{ + if (likely(net->mib.mptcp_statistics)) + SNMP_DEC_STATS(net->mib.mptcp_statistics, field); +} + bool mptcp_mib_alloc(struct net *net); diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 8df1bdb647..5409c2ea3f 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -245,4 +245,5 @@ static void __exit mptcp_diag_exit(void) module_init(mptcp_diag_init); module_exit(mptcp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MPTCP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */); diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c new file mode 100644 index 0000000000..a2325e70dd --- /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 +#include + +#include "mptcp_pm_gen.h" + +#include + +/* 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 0000000000..10579d1845 --- /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 +#include + +#include + +/* 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/options.c b/net/mptcp/options.c index d2527d189a..e3e96a49f9 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ - subflow->fully_established = 1; - WRITE_ONCE(msk->fully_established, true); - goto check_notify; + goto set_fully_established; } /* If the first established packet does not contain MP_CAPABLE + data @@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, set_fully_established: if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); - mptcp_subflow_fully_established(subflow, mp_opt); + + mptcp_data_lock((struct sock *)msk); + __mptcp_subflow_fully_established(msk, subflow, mp_opt); + mptcp_data_unlock((struct sock *)msk); check_notify: /* if the subflow is not already linked into the conn_list, we can't diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index d8da5374d9..4ae19113b8 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 3011bc3784..cccb720c1c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ @@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; + if (test_bit(addrs[i].id, unavail_id)) + continue; + if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; - if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); - if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +964,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1048,6 +1052,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; + /* We don't use mptcp_set_state() here because it needs to be called + * under the msk socket lock. For the moment, that will not bring + * anything more than only calling inet_sk_state_store(), because the + * old status is known (TCP_CLOSE). + */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); err = __inet_listen_sk(ssk, backlog); @@ -1087,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1104,29 +1113,6 @@ 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 +1174,7 @@ 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 +1289,21 @@ next: return 0; } -static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) +{ + 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; @@ -1344,7 +1342,8 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; @@ -1484,9 +1483,9 @@ 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; @@ -1620,7 +1619,7 @@ 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); @@ -1676,9 +1675,9 @@ 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; @@ -1726,8 +1725,8 @@ 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; @@ -1784,8 +1783,7 @@ 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; @@ -1810,8 +1808,7 @@ 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; @@ -1920,7 +1917,7 @@ 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 }, }; @@ -2000,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) @@ -2284,72 +2281,13 @@ 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 d042d32beb..01b3a8f2f0 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -130,10 +131,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, 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; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; @@ -142,16 +154,17 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } -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 +180,8 @@ 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; @@ -184,13 +199,13 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); 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 +215,49 @@ 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; } -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) +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 (READ_ONCE(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_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 +266,7 @@ 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 +284,19 @@ 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 +307,7 @@ 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 +315,19 @@ 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 +353,8 @@ 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 +372,6 @@ 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; @@ -322,7 +379,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; @@ -342,7 +399,7 @@ 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 +451,7 @@ 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 +476,8 @@ 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 +507,6 @@ 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 +526,7 @@ 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 +536,7 @@ 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 +545,8 @@ 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 +554,11 @@ 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 5c003a0f0f..5305f2ff0f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -99,7 +99,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); @@ -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; @@ -445,11 +443,11 @@ static void mptcp_check_data_fin_ack(struct sock *sk) switch (sk->sk_state) { case TCP_FIN_WAIT1: - inet_sk_state_store(sk, TCP_FIN_WAIT2); + mptcp_set_state(sk, TCP_FIN_WAIT2); break; case TCP_CLOSING: case TCP_LAST_ACK: - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); break; } @@ -610,13 +608,13 @@ static bool mptcp_check_data_fin(struct sock *sk) switch (sk->sk_state) { case TCP_ESTABLISHED: - inet_sk_state_store(sk, TCP_CLOSE_WAIT); + mptcp_set_state(sk, TCP_CLOSE_WAIT); break; case TCP_FIN_WAIT1: - inet_sk_state_store(sk, TCP_CLOSING); + mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); break; default: /* Other states not expected */ @@ -791,7 +789,7 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) */ ssk_state = inet_sk_state_load(ssk); if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); + mptcp_set_state(sk, ssk_state); WRITE_ONCE(sk->sk_err, -err); /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -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); } @@ -1274,7 +1271,7 @@ 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; @@ -1296,7 +1293,7 @@ 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. */ @@ -1522,8 +1519,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, @@ -1767,6 +1767,18 @@ 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); @@ -1840,11 +1852,10 @@ 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); @@ -1928,6 +1939,7 @@ 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; } @@ -1938,6 +1950,7 @@ 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) @@ -1964,6 +1977,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -2318,9 +2334,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(msk)) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue @@ -2397,8 +2410,8 @@ 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; @@ -2467,7 +2480,7 @@ out: inet_sk_state_load(msk->first) == TCP_CLOSE) { if (sk->sk_state != TCP_ESTABLISHED || msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); mptcp_close_wake_up(sk); } else { mptcp_start_tout_timer(sk); @@ -2484,7 +2497,7 @@ 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); } @@ -2523,7 +2536,7 @@ 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) @@ -2562,7 +2575,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) WRITE_ONCE(sk->sk_err, ECONNRESET); } - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); @@ -2666,7 +2679,7 @@ 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 @@ -2697,7 +2710,7 @@ static void mptcp_do_fastclose(struct sock *sk) struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, MPTCP_CF_FASTCLOSE); @@ -2762,6 +2775,7 @@ 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; @@ -2874,6 +2888,24 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) release_sock(ssk); } +void mptcp_set_state(struct sock *sk, int state) +{ + int oldstate = sk->sk_state; + + switch (state) { + case TCP_ESTABLISHED: + if (oldstate != TCP_ESTABLISHED) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); + break; + + default: + if (oldstate == TCP_ESTABLISHED) + MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); + } + + inet_sk_state_store(sk, state); +} + static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, @@ -2896,7 +2928,7 @@ static int mptcp_close_state(struct sock *sk) int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; - inet_sk_state_store(sk, ns); + mptcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } @@ -2971,16 +3003,9 @@ 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) @@ -3014,11 +3039,11 @@ bool __mptcp_close(struct sock *sk, long timeout) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_check_listen_stop(sk); - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); 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 */ @@ -3057,7 +3082,7 @@ cleanup: * state, let's not keep resources busy for no reasons */ if (subflows_alive == 0) - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); @@ -3123,7 +3148,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) return -EBUSY; mptcp_check_listen_stop(sk); - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); mptcp_stop_tout_timer(sk); @@ -3137,7 +3162,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3145,6 +3169,7 @@ 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); @@ -3152,6 +3177,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3174,6 +3200,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) @@ -3210,11 +3237,12 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ - inet_sk_state_store(nsk, TCP_ESTABLISHED); + mptcp_set_state(nsk, TCP_ESTABLISHED); /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); - list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + subflow = mptcp_subflow_ctx(ssk); + list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly @@ -3229,6 +3257,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); + + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3239,6 +3270,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3249,8 +3281,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err, @@ -3362,8 +3392,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3379,7 +3408,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); @@ -3507,13 +3535,8 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->write_seq, subflow->idsn + 1); - WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->snd_una, msk->write_seq); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) @@ -3669,7 +3692,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(ssk)) return PTR_ERR(ssk); - inet_sk_state_store(sk, TCP_SYN_SENT); + mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -3719,7 +3742,7 @@ out: if (unlikely(err)) { /* avoid leaving a dangling token in an unconnected socket */ mptcp_token_destroy(msk); - inet_sk_state_store(sk, TCP_CLOSE); + mptcp_set_state(sk, TCP_CLOSE); return err; } @@ -3809,13 +3832,13 @@ static int mptcp_listen(struct socket *sock, int backlog) goto unlock; } - inet_sk_state_store(sk, TCP_LISTEN); + mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); lock_sock(ssk); err = __inet_listen_sk(ssk, backlog); release_sock(ssk); - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + mptcp_set_state(sk, inet_sk_state_load(ssk)); if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -3875,7 +3898,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, __mptcp_close_ssk(newsk, msk->first, mptcp_subflow_ctx(msk->first), 0); if (unlikely(list_is_singular(&msk->conn_list))) - inet_sk_state_store(newsk, TCP_CLOSE); + mptcp_set_state(newsk, TCP_CLOSE); } } release_sock(newsk); @@ -3928,7 +3951,7 @@ 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 @@ -3966,6 +3989,7 @@ 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 = { @@ -4067,6 +4091,7 @@ 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 07c5ac37d0..3e50baba1b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -13,6 +13,8 @@ #include #include +#include "mptcp_pm_gen.h" + #define MPTCP_SUPPORTED_VERSION 1 /* MPTCP option bits */ @@ -268,6 +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; @@ -283,7 +286,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; @@ -302,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -436,11 +439,6 @@ 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; @@ -493,11 +491,10 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 9; - enum mptcp_data_avail data_avail; + __unused : 10; + bool data_avail; bool scheduled; u32 remote_nonce; u64 thmac; @@ -507,7 +504,7 @@ struct mptcp_subflow_context { u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ u64 iasn; /* initial ack sequence number, MPC subflows only */ }; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -558,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -621,10 +619,12 @@ 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, - const struct mptcp_options_received *mp_opt); +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -642,6 +642,7 @@ bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); void __mptcp_unaccepted_force_close(struct sock *sk); void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); +void mptcp_set_state(struct sock *sk, int state); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); @@ -669,6 +670,24 @@ 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 */ @@ -743,6 +762,7 @@ 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); @@ -873,7 +893,7 @@ 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); @@ -924,10 +944,6 @@ 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); @@ -937,8 +953,8 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); @@ -1006,6 +1022,15 @@ 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); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, @@ -1054,7 +1079,7 @@ 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; } @@ -1104,7 +1129,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && + return (1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && is_active_ssk(subflow) && !subflow->conn_finished; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 116e300823..3536807337 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -89,7 +89,7 @@ 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: @@ -735,7 +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); bool slow; @@ -919,7 +919,7 @@ 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; @@ -1347,7 +1347,7 @@ 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; @@ -1450,37 +1450,63 @@ 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 d3c5ecf8dd..71ba86246f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -9,8 +9,8 @@ #include #include #include -#include #include +#include #include #include #include @@ -421,29 +421,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk = msk->first; + + subflow = mptcp_subflow_ctx(ssk); + __mptcp_propagate_sndbuf(sk, ssk); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, ssk); - __mptcp_propagate_sndbuf(sk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { - inet_sk_state_store(sk, state); + /* subflow->idsn is always available is TCP_SYN_SENT state, + * even for the FASTOPEN scenarios + */ + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); + mptcp_set_state(sk, state); sk->sk_state_change(sk); } } -static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) { - __mptcp_sync_state(sk, ssk->sk_state); - } else { - msk->pending_state = ssk->sk_state; - __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); - } - mptcp_data_unlock(sk); -} - static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) @@ -465,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk, atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_data_lock(sk); + if (mp_opt) { + /* Options are available only in the non fallback cases + * avoid updating rx path fields otherwise + */ + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); + subflow_set_remote_key(msk, subflow, mp_opt); + } + + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -499,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; - subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -514,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -545,8 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } return; @@ -557,8 +577,8 @@ do_reset: static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -567,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -731,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); if (subflow->is_mptfo) - mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); + __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -834,7 +853,6 @@ create_child: * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { - mptcp_subflow_fully_established(ctx, &mp_opt); mptcp_pm_fully_established(owner, child); ctx->pm_notified = 1; } @@ -1244,7 +1262,7 @@ 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; @@ -1278,7 +1296,7 @@ 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; @@ -1300,7 +1318,7 @@ 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; } @@ -1317,7 +1335,7 @@ 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; } @@ -1329,7 +1347,7 @@ 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; } @@ -1341,7 +1359,7 @@ 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, @@ -1412,10 +1430,18 @@ 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) @@ -1532,8 +1558,6 @@ 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) @@ -1543,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; @@ -1644,7 +1668,7 @@ 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); @@ -1658,15 +1682,12 @@ 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 @@ -1686,6 +1707,11 @@ 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, @@ -1705,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1736,10 +1763,9 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } /* as recvmsg() does not acquire the subflow socket for ssk selection @@ -1941,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; @@ -2062,7 +2088,6 @@ 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; diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index 0758865ab6..bfff53e668 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -143,3 +143,4 @@ static struct kunit_suite mptcp_token_suite = { kunit_test_suite(mptcp_token_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for MPTCP Token"); -- cgit v1.2.3