diff options
author | 2020-08-05 20:13:21 -0700 | |
---|---|---|
committer | 2020-08-05 20:13:21 -0700 | |
commit | 47ec5303d73ea344e84f46660fff693c57641386 (patch) | |
tree | a2252debab749de29620c43285295d60c4741119 /net/mptcp | |
parent | Merge tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm (diff) | |
parent | net: thunderx: initialize VF's mailbox mutex before first usage (diff) | |
download | linux-47ec5303d73ea344e84f46660fff693c57641386.tar.gz linux-47ec5303d73ea344e84f46660fff693c57641386.tar.bz2 linux-47ec5303d73ea344e84f46660fff693c57641386.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
Diffstat (limited to 'net/mptcp')
-rw-r--r-- | net/mptcp/Kconfig | 24 | ||||
-rw-r--r-- | net/mptcp/Makefile | 7 | ||||
-rw-r--r-- | net/mptcp/crypto.c | 63 | ||||
-rw-r--r-- | net/mptcp/crypto_test.c | 72 | ||||
-rw-r--r-- | net/mptcp/ctrl.c | 1 | ||||
-rw-r--r-- | net/mptcp/mptcp_diag.c | 169 | ||||
-rw-r--r-- | net/mptcp/options.c | 71 | ||||
-rw-r--r-- | net/mptcp/pm.c | 46 | ||||
-rw-r--r-- | net/mptcp/pm_netlink.c | 2 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 853 | ||||
-rw-r--r-- | net/mptcp/protocol.h | 130 | ||||
-rw-r--r-- | net/mptcp/subflow.c | 341 | ||||
-rw-r--r-- | net/mptcp/syncookies.c | 130 | ||||
-rw-r--r-- | net/mptcp/token.c | 373 | ||||
-rw-r--r-- | net/mptcp/token_test.c | 140 |
15 files changed, 1803 insertions, 619 deletions
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index a9ed3bf1d93f..698bc3525160 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -13,17 +13,29 @@ config MPTCP if MPTCP +config INET_MPTCP_DIAG + depends on INET_DIAG + def_tristate INET_DIAG + config MPTCP_IPV6 bool "MPTCP: IPv6 support for Multipath TCP" select IPV6 default y -config MPTCP_HMAC_TEST - bool "Tests for MPTCP HMAC implementation" +endif + +config MPTCP_KUNIT_TESTS + tristate "This builds the MPTCP KUnit tests" if !KUNIT_ALL_TESTS + select MPTCP + depends on KUNIT + default KUNIT_ALL_TESTS help - This option enable boot time self-test for the HMAC implementation - used by the MPTCP code + Currently covers the MPTCP crypto and token helpers. + Only useful for kernel devs running KUnit test harness and are not + for inclusion into a production build. - Say N if you are unsure. + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. -endif diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index baa0640527c7..a611968be4d7 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -3,3 +3,10 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ mib.o pm_netlink.o + +obj-$(CONFIG_SYN_COOKIES) += syncookies.o +obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o + +mptcp_crypto_test-objs := crypto_test.o +mptcp_token_test-objs := token_test.o +obj-$(CONFIG_MPTCP_KUNIT_TESTS) += mptcp_crypto_test.o mptcp_token_test.o diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c index 82bd2b54d741..05d398d3fde4 100644 --- a/net/mptcp/crypto.c +++ b/net/mptcp/crypto.c @@ -78,65 +78,6 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac) sha256(input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE, hmac); } -#ifdef CONFIG_MPTCP_HMAC_TEST -struct test_cast { - char *key; - char *msg; - char *result; -}; - -/* we can't reuse RFC 4231 test vectors, as we have constraint on the - * input and key size. - */ -static struct test_cast tests[] = { - { - .key = "0b0b0b0b0b0b0b0b", - .msg = "48692054", - .result = "8385e24fb4235ac37556b6b886db106284a1da671699f46db1f235ec622dcafa", - }, - { - .key = "aaaaaaaaaaaaaaaa", - .msg = "dddddddd", - .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492984e1eb71aff9022f71046e9", - }, - { - .key = "0102030405060708", - .msg = "cdcdcdcd", - .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6f23b4d8c4da736a5dbbc6e7d", - }, -}; - -static int __init test_mptcp_crypto(void) -{ - char hmac[32], hmac_hex[65]; - u32 nonce1, nonce2; - u64 key1, key2; - u8 msg[8]; - int i, j; - - for (i = 0; i < ARRAY_SIZE(tests); ++i) { - /* mptcp hmap will convert to be before computing the hmac */ - key1 = be64_to_cpu(*((__be64 *)&tests[i].key[0])); - key2 = be64_to_cpu(*((__be64 *)&tests[i].key[8])); - nonce1 = be32_to_cpu(*((__be32 *)&tests[i].msg[0])); - nonce2 = be32_to_cpu(*((__be32 *)&tests[i].msg[4])); - - put_unaligned_be32(nonce1, &msg[0]); - put_unaligned_be32(nonce2, &msg[4]); - - mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac); - for (j = 0; j < 32; ++j) - sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff); - hmac_hex[64] = 0; - - if (memcmp(hmac_hex, tests[i].result, 64)) - pr_err("test %d failed, got %s expected %s", i, - hmac_hex, tests[i].result); - else - pr_info("test %d [ ok ]", i); - } - return 0; -} - -late_initcall(test_mptcp_crypto); +#if IS_MODULE(CONFIG_MPTCP_KUNIT_TESTS) +EXPORT_SYMBOL_GPL(mptcp_crypto_hmac_sha); #endif diff --git a/net/mptcp/crypto_test.c b/net/mptcp/crypto_test.c new file mode 100644 index 000000000000..017248dea038 --- /dev/null +++ b/net/mptcp/crypto_test.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <kunit/test.h> + +#include "protocol.h" + +struct test_case { + char *key; + char *msg; + char *result; +}; + +/* we can't reuse RFC 4231 test vectors, as we have constraint on the + * input and key size. + */ +static struct test_case tests[] = { + { + .key = "0b0b0b0b0b0b0b0b", + .msg = "48692054", + .result = "8385e24fb4235ac37556b6b886db106284a1da671699f46db1f235ec622dcafa", + }, + { + .key = "aaaaaaaaaaaaaaaa", + .msg = "dddddddd", + .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492984e1eb71aff9022f71046e9", + }, + { + .key = "0102030405060708", + .msg = "cdcdcdcd", + .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6f23b4d8c4da736a5dbbc6e7d", + }, +}; + +static void mptcp_crypto_test_basic(struct kunit *test) +{ + char hmac[32], hmac_hex[65]; + u32 nonce1, nonce2; + u64 key1, key2; + u8 msg[8]; + int i, j; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + /* mptcp hmap will convert to be before computing the hmac */ + key1 = be64_to_cpu(*((__be64 *)&tests[i].key[0])); + key2 = be64_to_cpu(*((__be64 *)&tests[i].key[8])); + nonce1 = be32_to_cpu(*((__be32 *)&tests[i].msg[0])); + nonce2 = be32_to_cpu(*((__be32 *)&tests[i].msg[4])); + + put_unaligned_be32(nonce1, &msg[0]); + put_unaligned_be32(nonce2, &msg[4]); + + mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac); + for (j = 0; j < 32; ++j) + sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff); + hmac_hex[64] = 0; + + KUNIT_EXPECT_STREQ(test, &hmac_hex[0], tests[i].result); + } +} + +static struct kunit_case mptcp_crypto_test_cases[] = { + KUNIT_CASE(mptcp_crypto_test_basic), + {} +}; + +static struct kunit_suite mptcp_crypto_suite = { + .name = "mptcp-crypto", + .test_cases = mptcp_crypto_test_cases, +}; + +kunit_test_suite(mptcp_crypto_suite); + +MODULE_LICENSE("GPL"); diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 8e39585d37f3..54b888f94009 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -112,6 +112,7 @@ static struct pernet_operations mptcp_pernet_ops = { void __init mptcp_init(void) { + mptcp_join_cookie_init(); mptcp_proto_init(); if (register_pernet_subsys(&mptcp_pernet_ops) < 0) diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c new file mode 100644 index 000000000000..5f390a97f556 --- /dev/null +++ b/net/mptcp/mptcp_diag.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* MPTCP socket monitoring support + * + * Copyright (c) 2020 Red Hat + * + * Author: Paolo Abeni <pabeni@redhat.com> + */ + +#include <linux/kernel.h> +#include <linux/net.h> +#include <linux/inet_diag.h> +#include <net/netlink.h> +#include <uapi/linux/mptcp.h> +#include "protocol.h" + +static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *req, + struct nlattr *bc, bool net_admin) +{ + if (!inet_diag_bc_sk(bc, sk)) + return 0; + + return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, req, NLM_F_MULTI, + net_admin); +} + +static int mptcp_diag_dump_one(struct netlink_callback *cb, + const struct inet_diag_req_v2 *req) +{ + struct sk_buff *in_skb = cb->skb; + struct mptcp_sock *msk = NULL; + struct sk_buff *rep; + int err = -ENOENT; + struct net *net; + struct sock *sk; + + net = sock_net(in_skb->sk); + msk = mptcp_token_get_sock(req->id.idiag_cookie[0]); + if (!msk) + goto out_nosk; + + err = -ENOMEM; + sk = (struct sock *)msk; + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct mptcp_info)) + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, + GFP_KERNEL); + if (!rep) + goto out; + + err = inet_sk_diag_fill(sk, inet_csk(sk), rep, cb, req, 0, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(rep); + goto out; + } + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, + MSG_DONTWAIT); + if (err > 0) + err = 0; +out: + sock_put(sk); + +out_nosk: + return err; +} + +static void mptcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + const struct inet_diag_req_v2 *r) +{ + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); + struct net *net = sock_net(skb->sk); + struct inet_diag_dump_data *cb_data; + struct mptcp_sock *msk; + struct nlattr *bc; + + cb_data = cb->data; + bc = cb_data->inet_diag_nla_bc; + + while ((msk = mptcp_token_iter_next(net, &cb->args[0], &cb->args[1])) != + NULL) { + struct inet_sock *inet = (struct inet_sock *)msk; + struct sock *sk = (struct sock *)msk; + int ret = 0; + + if (!(r->idiag_states & (1 << sk->sk_state))) + goto next; + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next; + if (r->id.idiag_sport != inet->inet_sport && + r->id.idiag_sport) + goto next; + if (r->id.idiag_dport != inet->inet_dport && + r->id.idiag_dport) + goto next; + + ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin); +next: + sock_put(sk); + if (ret < 0) { + /* will retry on the same position */ + cb->args[1]--; + break; + } + cond_resched(); + } +} + +static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *_info) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_info *info = _info; + u32 flags = 0; + bool slow; + u8 val; + + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); + if (!info) + return; + + slow = lock_sock_fast(sk); + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); + info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); + info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); + info->mptcpi_subflows_max = READ_ONCE(msk->pm.subflows_max); + val = READ_ONCE(msk->pm.add_addr_signal_max); + info->mptcpi_add_addr_signal_max = val; + val = READ_ONCE(msk->pm.add_addr_accept_max); + info->mptcpi_add_addr_accepted_max = val; + if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) + flags |= MPTCP_INFO_FLAG_FALLBACK; + if (READ_ONCE(msk->can_ack)) + flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; + info->mptcpi_flags = flags; + info->mptcpi_token = READ_ONCE(msk->token); + info->mptcpi_write_seq = READ_ONCE(msk->write_seq); + info->mptcpi_snd_una = atomic64_read(&msk->snd_una); + info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + unlock_sock_fast(sk, slow); +} + +static const struct inet_diag_handler mptcp_diag_handler = { + .dump = mptcp_diag_dump, + .dump_one = mptcp_diag_dump_one, + .idiag_get_info = mptcp_diag_get_info, + .idiag_type = IPPROTO_MPTCP, + .idiag_info_size = sizeof(struct mptcp_info), +}; + +static int __init mptcp_diag_init(void) +{ + return inet_diag_register(&mptcp_diag_handler); +} + +static void __exit mptcp_diag_exit(void) +{ + inet_diag_unregister(&mptcp_diag_handler); +} + +module_init(mptcp_diag_init); +module_exit(mptcp_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8f940be42f98..7fa822b55c34 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -451,6 +451,8 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_ext *ext) { + u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq); + if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped @@ -458,10 +460,13 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; - ext->data_seq = subflow->data_fin_tx_seq; + /* The write_seq value has already been incremented, so + * the actual sequence number for the DATA_FIN is one less. + */ + ext->data_seq = data_fin_tx_seq - 1; ext->subflow_seq = 0; ext->data_len = 1; - } else if (ext->data_seq + ext->data_len == subflow->data_fin_tx_seq) { + } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { /* If there's an existing DSS mapping and it is the * final mapping, DATA_FIN consumes 1 additional byte of * mapping space. @@ -477,22 +482,17 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int dss_size = 0; + u64 snd_data_fin_enable; struct mptcp_ext *mpext; - struct mptcp_sock *msk; unsigned int ack_size; bool ret = false; - u8 tcp_fin; - if (skb) { - mpext = mptcp_get_ext(skb); - tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - } else { - mpext = NULL; - tcp_fin = 0; - } + mpext = skb ? mptcp_get_ext(skb) : NULL; + snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable); - if (!skb || (mpext && mpext->use_map) || tcp_fin) { + if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; @@ -502,7 +502,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (mpext) opts->ext_copy = *mpext; - if (skb && tcp_fin && subflow->data_fin_tx_enable) + if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; } @@ -511,7 +511,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, * if the first subflow may have the already the remote key handy */ opts->ext_copy.use_ack = 0; - msk = mptcp_sk(subflow->conn); if (!READ_ONCE(msk->can_ack)) { *size = ALIGN(dss_size, 4); return ret; @@ -624,6 +623,9 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, opts->suboptions = 0; + if (unlikely(mptcp_check_fallback(sk))) + return false; + if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) ret = true; else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, @@ -706,6 +708,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, * additional ack. */ subflow->fully_established = 1; + WRITE_ONCE(msk->fully_established, true); goto fully_established; } @@ -714,15 +717,14 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, */ if (!mp_opt->mp_capable) { subflow->mp_capable = 0; - tcp_sk(sk)->is_mptcp = 0; + pr_fallback(msk); + __mptcp_do_fallback(msk); return false; } if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); - subflow->fully_established = 1; - subflow->remote_key = mp_opt->sndr_key; - subflow->can_ack = 1; + mptcp_subflow_fully_established(subflow, mp_opt); fully_established: if (likely(subflow->pm_notified)) @@ -780,6 +782,22 @@ static void update_una(struct mptcp_sock *msk, } } +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) +{ + /* Skip if DATA_FIN was already received. + * If updating simultaneously with the recvmsg loop, values + * should match. If they mismatch, the peer is misbehaving and + * we will prefer the most recent information. + */ + if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first)) + return false; + + WRITE_ONCE(msk->rcv_data_fin_seq, data_fin_seq); + WRITE_ONCE(msk->rcv_data_fin, 1); + + return true; +} + static bool add_addr_hmac_valid(struct mptcp_sock *msk, struct mptcp_options_received *mp_opt) { @@ -814,6 +832,9 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, struct mptcp_options_received mp_opt; struct mptcp_ext *mpext; + if (__mptcp_check_fallback(msk)) + return; + mptcp_get_options(skb, &mp_opt); if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; @@ -847,6 +868,20 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, if (mp_opt.use_ack) update_una(msk, &mp_opt); + /* Zero-data-length packets are dropped by the caller and not + * propagated to the MPTCP layer, so the skb extension does not + * need to be allocated or populated. DATA_FIN information, if + * present, needs to be updated here before the skb is freed. + */ + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { + if (mp_opt.data_fin && mp_opt.data_len == 1 && + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq) && + schedule_work(&msk->work)) + sock_hold(subflow->conn); + + return; + } + mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) return; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 977d9c8b1453..a8ad20559aaa 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -10,8 +10,6 @@ #include <net/mptcp.h> #include "protocol.h" -static struct workqueue_struct *pm_wq; - /* path manager command handlers */ int mptcp_pm_announce_addr(struct mptcp_sock *msk, @@ -78,7 +76,7 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, return false; msk->pm.status |= BIT(new_status); - if (queue_work(pm_wq, &msk->pm.work)) + if (schedule_work(&msk->work)) sock_hold((struct sock *)msk); return true; } @@ -181,35 +179,6 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, skc); } -static void pm_worker(struct work_struct *work) -{ - struct mptcp_pm_data *pm = container_of(work, struct mptcp_pm_data, - work); - struct mptcp_sock *msk = container_of(pm, struct mptcp_sock, pm); - struct sock *sk = (struct sock *)msk; - - lock_sock(sk); - spin_lock_bh(&msk->pm.lock); - - pr_debug("msk=%p status=%x", msk, pm->status); - if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { - pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); - mptcp_pm_nl_add_addr_received(msk); - } - if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { - pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); - mptcp_pm_nl_fully_established(msk); - } - if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { - pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); - mptcp_pm_nl_subflow_established(msk); - } - - spin_unlock_bh(&msk->pm.lock); - release_sock(sk); - sock_put(sk); -} - void mptcp_pm_data_init(struct mptcp_sock *msk) { msk->pm.add_addr_signaled = 0; @@ -223,22 +192,11 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) msk->pm.status = 0; spin_lock_init(&msk->pm.lock); - INIT_WORK(&msk->pm.work, pm_worker); mptcp_pm_nl_data_init(msk); } -void mptcp_pm_close(struct mptcp_sock *msk) -{ - if (cancel_work_sync(&msk->pm.work)) - sock_put((struct sock *)msk); -} - -void mptcp_pm_init(void) +void __init mptcp_pm_init(void) { - pm_wq = alloc_workqueue("pm_wq", WQ_UNBOUND | WQ_MEM_RECLAIM, 8); - if (!pm_wq) - panic("Failed to allocate workqueue"); - mptcp_pm_nl_init(); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index b78edf237ba0..c8820c4156e6 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -851,7 +851,7 @@ static struct pernet_operations mptcp_pm_pernet_ops = { .size = sizeof(struct pm_nl_pernet), }; -void mptcp_pm_nl_init(void) +void __init mptcp_pm_nl_init(void) { if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0) panic("Failed to register MPTCP PM pernet subsystem.\n"); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c0abe738e7d3..8c1d1a595701 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -16,6 +16,7 @@ #include <net/inet_hashtables.h> #include <net/protocol.h> #include <net/tcp.h> +#include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> #endif @@ -52,18 +53,10 @@ static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) return msk->subflow; } -static bool __mptcp_needs_tcp_fallback(const struct mptcp_sock *msk) -{ - return msk->first && !sk_is_mptcp(msk->first); -} - -static struct socket *mptcp_is_tcpsk(struct sock *sk) +static bool mptcp_is_tcpsk(struct sock *sk) { struct socket *sock = sk->sk_socket; - if (sock->sk != sk) - return NULL; - if (unlikely(sk->sk_prot == &tcp_prot)) { /* we are being invoked after mptcp_accept() has * accepted a non-mp-capable flow: sk is a tcp_sk, @@ -73,59 +66,37 @@ static struct socket *mptcp_is_tcpsk(struct sock *sk) * bypass mptcp. */ sock->ops = &inet_stream_ops; - return sock; + return true; #if IS_ENABLED(CONFIG_MPTCP_IPV6) } else if (unlikely(sk->sk_prot == &tcpv6_prot)) { sock->ops = &inet6_stream_ops; - return sock; + return true; #endif } - return NULL; + return false; } -static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) +static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { - struct socket *sock; - sock_owned_by_me((const struct sock *)msk); - sock = mptcp_is_tcpsk((struct sock *)msk); - if (unlikely(sock)) - return sock; - - if (likely(!__mptcp_needs_tcp_fallback(msk))) + if (likely(!__mptcp_check_fallback(msk))) return NULL; - return msk->subflow; -} - -static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk) -{ - return !msk->first; + return msk->first; } -static struct socket *__mptcp_socket_create(struct mptcp_sock *msk, int state) +static int __mptcp_socket_create(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct socket *ssock; int err; - ssock = __mptcp_tcp_fallback(msk); - if (unlikely(ssock)) - return ssock; - - ssock = __mptcp_nmpc_socket(msk); - if (ssock) - goto set_state; - - if (!__mptcp_can_create_subflow(msk)) - return ERR_PTR(-EINVAL); - err = mptcp_subflow_create_socket(sk, &ssock); if (err) - return ERR_PTR(err); + return err; msk->first = ssock->sk; msk->subflow = ssock; @@ -133,10 +104,12 @@ static struct socket *__mptcp_socket_create(struct mptcp_sock *msk, int state) list_add(&subflow->node, &msk->conn_list); subflow->request_mptcp = 1; -set_state: - if (state != MPTCP_SAME_STATE) - inet_sk_state_store(sk, state); - return ssock; + /* accept() will wait on first subflow sk_wq, and we always wakes up + * via msk->sk_socket + */ + RCU_INIT_POINTER(msk->first->sk_wq, &sk->sk_socket->wq); + + return 0; } static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, @@ -170,6 +143,14 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->offset = offset; } +static void mptcp_stop_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + mptcp_sk(sk)->timer_ival = 0; +} + /* both sockets must be locked */ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk, struct sock *ssk) @@ -191,6 +172,139 @@ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk, return mptcp_subflow_data_available(ssk); } +static void mptcp_check_data_fin_ack(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (__mptcp_check_fallback(msk)) + return; + + /* Look for an acknowledged DATA_FIN */ + if (((1 << sk->sk_state) & + (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && + msk->write_seq == atomic64_read(&msk->snd_una)) { + mptcp_stop_timer(sk); + + WRITE_ONCE(msk->snd_data_fin_enable, 0); + + switch (sk->sk_state) { + case TCP_FIN_WAIT1: + inet_sk_state_store(sk, TCP_FIN_WAIT2); + sk->sk_state_change(sk); + break; + case TCP_CLOSING: + fallthrough; + case TCP_LAST_ACK: + inet_sk_state_store(sk, TCP_CLOSE); + sk->sk_state_change(sk); + break; + } + + if (sk->sk_shutdown == SHUTDOWN_MASK || + sk->sk_state == TCP_CLOSE) + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + else + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + } +} + +static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (READ_ONCE(msk->rcv_data_fin) && + ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { + u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); + + if (msk->ack_seq == rcv_data_fin_seq) { + if (seq) + *seq = rcv_data_fin_seq; + + return true; + } + } + + return false; +} + +static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) +{ + long tout = ssk && inet_csk(ssk)->icsk_pending ? + inet_csk(ssk)->icsk_timeout - jiffies : 0; + + if (tout <= 0) + tout = mptcp_sk(sk)->timer_ival; + mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; +} + +static void mptcp_check_data_fin(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + u64 rcv_data_fin_seq; + + if (__mptcp_check_fallback(msk) || !msk->first) + return; + + /* Need to ack a DATA_FIN received from a peer while this side + * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. + * msk->rcv_data_fin was set when parsing the incoming options + * at the subflow level and the msk lock was not held, so this + * is the first opportunity to act on the DATA_FIN and change + * the msk state. + * + * If we are caught up to the sequence number of the incoming + * DATA_FIN, send the DATA_ACK now and do state transition. If + * not caught up, do nothing and let the recv code send DATA_ACK + * when catching up. + */ + + if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { + struct mptcp_subflow_context *subflow; + + msk->ack_seq++; + WRITE_ONCE(msk->rcv_data_fin, 0); + + sk->sk_shutdown |= RCV_SHUTDOWN; + smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ + set_bit(MPTCP_DATA_READY, &msk->flags); + + switch (sk->sk_state) { + case TCP_ESTABLISHED: + inet_sk_state_store(sk, TCP_CLOSE_WAIT); + break; + case TCP_FIN_WAIT1: + inet_sk_state_store(sk, TCP_CLOSING); + break; + case TCP_FIN_WAIT2: + inet_sk_state_store(sk, TCP_CLOSE); + // @@ Close subflows now? + break; + default: + /* Other states not expected */ + WARN_ON_ONCE(1); + break; + } + + mptcp_set_timeout(sk, NULL); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + tcp_send_ack(ssk); + release_sock(ssk); + } + + sk->sk_state_change(sk); + + if (sk->sk_shutdown == SHUTDOWN_MASK || + sk->sk_state == TCP_CLOSE) + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + else + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + } +} + static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sock *ssk, unsigned int *bytes) @@ -207,13 +321,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, return false; } - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf); - - if (rcvbuf > sk->sk_rcvbuf) - sk->sk_rcvbuf = rcvbuf; - } - tp = tcp_sk(ssk); do { u32 map_remaining, offset; @@ -229,6 +336,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, if (!skb) break; + if (__mptcp_check_fallback(msk)) { + /* if we are running under the workqueue, TCP could have + * collapsed skbs between dummy map creation and now + * be sure to adjust the size + */ + map_remaining = skb->len; + subflow->map_data_len = skb->len; + } + offset = seq - TCP_SKB_CB(skb)->seq; fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (fin) { @@ -265,6 +381,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, *bytes = moved; + /* If the moves have caught up with the DATA_FIN sequence number + * it's time to ack the DATA_FIN and change socket state, but + * this is not a good place to change state. Let the workqueue + * do it. + */ + if (mptcp_pending_data_fin(sk, NULL) && + schedule_work(&msk->work)) + sock_hold(sk); + return done; } @@ -329,16 +454,6 @@ static void __mptcp_flush_join_list(struct mptcp_sock *msk) spin_unlock_bh(&msk->join_list_lock); } -static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) -{ - long tout = ssk && inet_csk(ssk)->icsk_pending ? - inet_csk(ssk)->icsk_timeout - jiffies : 0; - - if (tout <= 0) - tout = mptcp_sk(sk)->timer_ival; - mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; -} - static bool mptcp_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); @@ -360,7 +475,8 @@ void mptcp_data_acked(struct sock *sk) { mptcp_reset_timer(sk); - if (!sk_stream_is_writeable(sk) && + if ((!sk_stream_is_writeable(sk) || + (inet_sk_state_load(sk) != TCP_ESTABLISHED)) && schedule_work(&mptcp_sk(sk)->work)) sock_hold(sk); } @@ -395,14 +511,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) } } -static void mptcp_stop_timer(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); - mptcp_sk(sk)->timer_ival = 0; -} - static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) { const struct sock *sk = (const struct sock *)msk; @@ -466,8 +574,15 @@ static void mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - u64 snd_una = atomic64_read(&msk->snd_una); bool cleaned = false; + u64 snd_una; + + /* on fallback we just need to ignore snd_una, as this is really + * plain TCP + */ + if (__mptcp_check_fallback(msk)) + atomic64_set(&msk->snd_una, msk->write_seq); + snd_una = atomic64_read(&msk->snd_una); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) { if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) @@ -479,15 +594,20 @@ static void mptcp_clean_una(struct sock *sk) dfrag = mptcp_rtx_head(sk); if (dfrag && after64(snd_una, dfrag->data_seq)) { - u64 delta = dfrag->data_seq + dfrag->data_len - snd_una; + u64 delta = snd_una - dfrag->data_seq; + + if (WARN_ON_ONCE(delta > dfrag->data_len)) + goto out; dfrag->data_seq += delta; + dfrag->offset += delta; dfrag->data_len -= delta; dfrag_uncharge(sk, delta); cleaned = true; } +out: if (cleaned) { sk_mem_reclaim_partial(sk); @@ -673,7 +793,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, out: if (!retransmission) pfrag->offset += frag_truesize; - *write_seq += ret; + WRITE_ONCE(*write_seq, *write_seq + ret); mptcp_subflow_ctx(ssk)->rel_write_seq += ret; return ret; @@ -740,7 +860,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int mss_now = 0, size_goal = 0, ret = 0; struct mptcp_sock *msk = mptcp_sk(sk); struct page_frag *pfrag; - struct socket *ssock; size_t copied = 0; struct sock *ssk; bool tx_ok; @@ -759,19 +878,15 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out; } -fallback: - ssock = __mptcp_tcp_fallback(msk); - if (unlikely(ssock)) { - release_sock(sk); - pr_debug("fallback passthrough"); - ret = sock_sendmsg(ssock, msg); - return ret >= 0 ? ret + copied : (copied ? copied : ret); - } - pfrag = sk_page_frag(sk); restart: mptcp_clean_una(sk); + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) { + ret = -EPIPE; + goto out; + } + wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); @@ -819,17 +934,6 @@ wait_for_sndbuf: } break; } - if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) { - /* Can happen for passive sockets: - * 3WHS negotiated MPTCP, but first packet after is - * plain TCP (e.g. due to middlebox filtering unknown - * options). - * - * Fall back to TCP. - */ - release_sock(ssk); - goto fallback; - } copied += ret; @@ -880,7 +984,6 @@ wait_for_sndbuf: mptcp_set_timeout(sk, ssk); if (copied) { - ret = copied; tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, size_goal); @@ -893,7 +996,7 @@ wait_for_sndbuf: release_sock(ssk); out: release_sock(sk); - return ret; + return copied ? : ret; } static void mptcp_wait_data(struct sock *sk, long *timeo) @@ -949,6 +1052,100 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, return copied; } +/* receive buffer autotuning. See tcp_rcv_space_adjust for more information. + * + * Only difference: Use highest rtt estimate of the subflows in use. + */ +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + u32 time, advmss = 1; + u64 rtt_us, mstamp; + + sock_owned_by_me(sk); + + if (copied <= 0) + return; + + msk->rcvq_space.copied += copied; + + mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); + time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); + + rtt_us = msk->rcvq_space.rtt_us; + if (rtt_us && time < (rtt_us >> 3)) + return; + + rtt_us = 0; + mptcp_for_each_subflow(msk, subflow) { + const struct tcp_sock *tp; + u64 sf_rtt_us; + u32 sf_advmss; + + tp = tcp_sk(mptcp_subflow_tcp_sock(subflow)); + + sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us); + sf_advmss = READ_ONCE(tp->advmss); + + rtt_us = max(sf_rtt_us, rtt_us); + advmss = max(sf_advmss, advmss); + } + + msk->rcvq_space.rtt_us = rtt_us; + if (time < (rtt_us >> 3) || rtt_us == 0) + return; + + if (msk->rcvq_space.copied <= msk->rcvq_space.space) + goto new_measure; + + if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + int rcvmem, rcvbuf; + u64 rcvwin, grow; + + rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss; + + grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space); + + do_div(grow, msk->rcvq_space.space); + rcvwin += (grow << 1); + + rcvmem = SKB_TRUESIZE(advmss + MAX_TCP_HEADER); + while (tcp_win_from_space(sk, rcvmem) < advmss) + rcvmem += 128; + + do_div(rcvwin, advmss); + rcvbuf = min_t(u64, rcvwin * rcvmem, + sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + + if (rcvbuf > sk->sk_rcvbuf) { + u32 window_clamp; + + window_clamp = tcp_win_from_space(sk, rcvbuf); + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + + /* Make subflows follow along. If we do not do this, we + * get drops at subflow level if skbs can't be moved to + * the mptcp rx queue fast enough (announced rcv_win can + * exceed ssk->sk_rcvbuf). + */ + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk; + + ssk = mptcp_subflow_tcp_sock(subflow); + WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); + tcp_sk(ssk)->window_clamp = window_clamp; + } + } + } + + msk->rcvq_space.space = msk->rcvq_space.copied; +new_measure: + msk->rcvq_space.copied = 0; + msk->rcvq_space.time = mstamp; +} + static bool __mptcp_move_skbs(struct mptcp_sock *msk) { unsigned int moved = 0; @@ -972,7 +1169,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; int copied = 0; int target; long timeo; @@ -981,16 +1177,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return -EOPNOTSUPP; lock_sock(sk); - ssock = __mptcp_tcp_fallback(msk); - if (unlikely(ssock)) { -fallback: - release_sock(sk); - pr_debug("fallback-read subflow=%p", - mptcp_subflow_ctx(ssock->sk)); - copied = sock_recvmsg(ssock, msg, flags); - return copied; - } - timeo = sock_rcvtimeo(sk, nonblock); len = min_t(size_t, len, INT_MAX); @@ -1056,9 +1242,6 @@ fallback: pr_debug("block timeout %ld", timeo); mptcp_wait_data(sk, &timeo); - ssock = __mptcp_tcp_fallback(msk); - if (unlikely(ssock)) - goto fallback; } if (skb_queue_empty(&sk->sk_receive_queue)) { @@ -1075,6 +1258,8 @@ fallback: set_bit(MPTCP_DATA_READY, &msk->flags); } out_err: + mptcp_rcv_space_adjust(msk, copied); + release_sock(sk); return copied; } @@ -1083,7 +1268,7 @@ static void mptcp_retransmit_handler(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (atomic64_read(&msk->snd_una) == msk->write_seq) { + if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) { mptcp_stop_timer(sk); } else { set_bit(MPTCP_WORK_RTX, &msk->flags); @@ -1172,6 +1357,29 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } +static void pm_work(struct mptcp_sock *msk) +{ + struct mptcp_pm_data *pm = &msk->pm; + + spin_lock_bh(&msk->pm.lock); + + pr_debug("msk=%p status=%x", msk, pm->status); + if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { + pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); + mptcp_pm_nl_add_addr_received(msk); + } + if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { + pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); + mptcp_pm_nl_fully_established(msk); + } + if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { + pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); + mptcp_pm_nl_subflow_established(msk); + } + + spin_unlock_bh(&msk->pm.lock); +} + static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); @@ -1185,12 +1393,18 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); mptcp_clean_una(sk); + mptcp_check_data_fin_ack(sk); __mptcp_flush_join_list(msk); __mptcp_move_skbs(msk); + if (msk->pm.status) + pm_work(msk); + if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) mptcp_check_for_eof(msk); + mptcp_check_data_fin(sk); + if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) goto unlock; @@ -1283,7 +1497,12 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + ret = __mptcp_socket_create(mptcp_sk(sk)); + if (ret) + return ret; + sk_sockets_allocated_inc(sk); + sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2]; return 0; @@ -1308,8 +1527,7 @@ static void mptcp_cancel_work(struct sock *sk) sock_put(sk); } -static void mptcp_subflow_shutdown(struct sock *ssk, int how, - bool data_fin_tx_enable, u64 data_fin_tx_seq) +static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); @@ -1322,36 +1540,84 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how, tcp_disconnect(ssk, O_NONBLOCK); break; default: - if (data_fin_tx_enable) { - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->data_fin_tx_seq = data_fin_tx_seq; - subflow->data_fin_tx_enable = 1; + if (__mptcp_check_fallback(mptcp_sk(sk))) { + pr_debug("Fallback"); + ssk->sk_shutdown |= how; + tcp_shutdown(ssk, how); + } else { + pr_debug("Sending DATA_FIN on subflow %p", ssk); + mptcp_set_timeout(sk, ssk); + tcp_send_ack(ssk); } - - ssk->sk_shutdown |= how; - tcp_shutdown(ssk, how); break; } - /* Wake up anyone sleeping in poll. */ - ssk->sk_state_change(ssk); release_sock(ssk); } -/* Called with msk lock held, releases such lock before returning */ +static const unsigned char new_state[16] = { + /* current state: new state: action: */ + [0 /* (Invalid) */] = TCP_CLOSE, + [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_SYN_SENT] = TCP_CLOSE, + [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, + [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, + [TCP_TIME_WAIT] = TCP_CLOSE, /* should not happen ! */ + [TCP_CLOSE] = TCP_CLOSE, + [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, + [TCP_LAST_ACK] = TCP_LAST_ACK, + [TCP_LISTEN] = TCP_CLOSE, + [TCP_CLOSING] = TCP_CLOSING, + [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ +}; + +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); + + return next & TCP_ACTION_FIN; +} + static void mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); LIST_HEAD(conn_list); - u64 data_fin_tx_seq; lock_sock(sk); + sk->sk_shutdown = SHUTDOWN_MASK; + + if (sk->sk_state == TCP_LISTEN) { + inet_sk_state_store(sk, TCP_CLOSE); + goto cleanup; + } else if (sk->sk_state == TCP_CLOSE) { + goto cleanup; + } + + if (__mptcp_check_fallback(msk)) { + goto update_state; + } else if (mptcp_close_state(sk)) { + pr_debug("Sending DATA_FIN sk=%p", sk); + WRITE_ONCE(msk->write_seq, msk->write_seq + 1); + WRITE_ONCE(msk->snd_data_fin_enable, 1); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK); + } + } + + sk_stream_wait_close(sk, timeout); +update_state: inet_sk_state_store(sk, TCP_CLOSE); +cleanup: /* be sure to always acquire the join list lock, to sync vs * mptcp_finish_join(). */ @@ -1360,22 +1626,16 @@ static void mptcp_close(struct sock *sk, long timeout) spin_unlock_bh(&msk->join_list_lock); list_splice_init(&msk->conn_list, &conn_list); - data_fin_tx_seq = msk->write_seq; - __mptcp_clear_xmit(sk); release_sock(sk); list_for_each_entry_safe(subflow, tmp, &conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - - subflow->data_fin_tx_seq = data_fin_tx_seq; - subflow->data_fin_tx_enable = 1; __mptcp_close_ssk(sk, ssk, subflow, timeout); } mptcp_cancel_work(sk); - mptcp_pm_close(msk); __skb_queue_purge(&sk->sk_receive_queue); @@ -1447,20 +1707,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; msk->subflow = NULL; - - if (unlikely(mptcp_token_new_accept(subflow_req->token, nsk))) { - nsk->sk_state = TCP_CLOSE; - bh_unlock_sock(nsk); - - /* we can't call into mptcp_close() here - possible BH context - * free the sock directly. - * sk_clone_lock() sets nsk refcnt to two, hence call sk_free() - * too. - */ - sk_common_release(nsk); - sk_free(nsk); - return NULL; - } + WRITE_ONCE(msk->fully_established, false); msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); @@ -1482,6 +1729,22 @@ struct sock *mptcp_sk_clone(const struct sock *sk, return nsk; } +void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) +{ + const struct tcp_sock *tp = tcp_sk(ssk); + + msk->rcvq_space.copied = 0; + msk->rcvq_space.rtt_us = 0; + + msk->rcvq_space.time = tp->tcp_mstamp; + + /* initial rcv_space offering made to peer */ + msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, + TCP_INIT_CWND * tp->advmss); + if (msk->rcvq_space.space == 0) + msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; +} + static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, bool kern) { @@ -1501,7 +1764,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, return NULL; pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk)); - if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; @@ -1529,8 +1791,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, newsk = new_mptcp_sock; mptcp_copy_inaddrs(newsk, ssk); list_add(&subflow->node, &msk->conn_list); - inet_sk_state_store(newsk, TCP_ESTABLISHED); + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(new_mptcp_sock); __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); @@ -1547,21 +1809,82 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - mptcp_token_destroy(msk->token); + mptcp_token_destroy(msk); if (msk->cached_ext) __skb_ext_put(msk->cached_ext); sk_sockets_allocated_dec(sk); } +static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = (struct sock *)msk; + struct socket *ssock; + int ret; + + switch (optname) { + case SO_REUSEPORT: + case SO_REUSEADDR: + lock_sock(sk); + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + release_sock(sk); + return -EINVAL; + } + + ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen); + if (ret == 0) { + if (optname == SO_REUSEPORT) + sk->sk_reuseport = ssock->sk->sk_reuseport; + else if (optname == SO_REUSEADDR) + sk->sk_reuse = ssock->sk->sk_reuse; + } + release_sock(sk); + return ret; + } + + return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); +} + +static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = (struct sock *)msk; + int ret = -EOPNOTSUPP; + struct socket *ssock; + + switch (optname) { + case IPV6_V6ONLY: + lock_sock(sk); + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + release_sock(sk); + return -EINVAL; + } + + ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen); + if (ret == 0) + sk->sk_ipv6only = ssock->sk->sk_ipv6only; + + release_sock(sk); + break; + } + + return ret; +} + static int mptcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; + struct sock *ssk; pr_debug("msk=%p", msk); + if (level == SOL_SOCKET) + return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); + /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the * MPTCP-level socket to configure the subflows until the subflow @@ -1569,11 +1892,13 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_tcp_fallback(msk); + ssk = __mptcp_tcp_fallback(msk); release_sock(sk); - if (ssock) - return tcp_setsockopt(ssock->sk, level, optname, optval, - optlen); + if (ssk) + return tcp_setsockopt(ssk, level, optname, optval, optlen); + + if (level == SOL_IPV6) + return mptcp_setsockopt_v6(msk, optname, optval, optlen); return -EOPNOTSUPP; } @@ -1582,7 +1907,7 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); - struct socket *ssock; + struct sock *ssk; pr_debug("msk=%p", msk); @@ -1593,11 +1918,10 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_tcp_fallback(msk); + ssk = __mptcp_tcp_fallback(msk); release_sock(sk); - if (ssock) - return tcp_getsockopt(ssock->sk, level, optname, optval, - option); + if (ssk) + return tcp_getsockopt(ssk, level, optname, optval, option); return -EOPNOTSUPP; } @@ -1636,6 +1960,20 @@ static void mptcp_release_cb(struct sock *sk) } } +static int mptcp_hash(struct sock *sk) +{ + /* should never be called, + * we hash the TCP subflows not the master socket + */ + WARN_ON_ONCE(1); + return 0; +} + +static void mptcp_unhash(struct sock *sk) +{ + /* called from sk_common_release(), but nothing to do here */ +} + static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1660,32 +1998,26 @@ void mptcp_finish_connect(struct sock *ssk) sk = subflow->conn; msk = mptcp_sk(sk); - if (!subflow->mp_capable) { - MPTCP_INC_STATS(sock_net(sk), - MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); - return; - } - pr_debug("msk=%p, token=%u", sk, subflow->token); mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq); ack_seq++; subflow->map_seq = ack_seq; subflow->map_subflow_seq = 1; - subflow->rel_write_seq = 1; /* the socket is not connected yet, no msk/subflow ops can access/race * accessing the field below */ WRITE_ONCE(msk->remote_key, subflow->remote_key); WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->token, subflow->token); WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->ack_seq, ack_seq); WRITE_ONCE(msk->can_ack, 1); atomic64_set(&msk->snd_una, msk->write_seq); mptcp_pm_new_connection(msk, 0); + + mptcp_rcv_space_init(msk, ssk); } static void mptcp_sock_graft(struct sock *sk, struct socket *parent) @@ -1708,7 +2040,7 @@ bool mptcp_finish_join(struct sock *sk) pr_debug("msk=%p, subflow=%p", msk, subflow); /* mptcp socket already closing? */ - if (inet_sk_state_load(parent) != TCP_ESTABLISHED) + if (!mptcp_is_fully_established(parent)) return false; if (!msk->pm.server_side) @@ -1761,8 +2093,8 @@ static struct proto mptcp_prot = { .sendmsg = mptcp_sendmsg, .recvmsg = mptcp_recvmsg, .release_cb = mptcp_release_cb, - .hash = inet_hash, - .unhash = inet_unhash, + .hash = mptcp_hash, + .unhash = mptcp_unhash, .get_port = mptcp_get_port, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, @@ -1771,6 +2103,7 @@ static struct proto mptcp_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), + .slab_flags = SLAB_TYPESAFE_BY_RCU, .no_autobind = true, }; @@ -1781,9 +2114,9 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int err; lock_sock(sock->sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - err = PTR_ERR(ssock); + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + err = -EINVAL; goto unlock; } @@ -1796,10 +2129,18 @@ unlock: return err; } +static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow) +{ + subflow->request_mptcp = 0; + __mptcp_do_fallback(msk); +} + static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct mptcp_subflow_context *subflow; struct socket *ssock; int err; @@ -1812,19 +2153,24 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto do_connect; } - ssock = __mptcp_socket_create(msk, TCP_SYN_SENT); - if (IS_ERR(ssock)) { - err = PTR_ERR(ssock); + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + err = -EINVAL; goto unlock; } + mptcp_token_destroy(msk); + inet_sk_state_store(sock->sk, TCP_SYN_SENT); + subflow = mptcp_subflow_ctx(ssock->sk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) - mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0; + mptcp_subflow_early_fallback(msk, subflow); #endif + if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) + mptcp_subflow_early_fallback(msk, subflow); do_connect: err = ssock->ops->connect(ssock, uaddr, addr_len, flags); @@ -1843,42 +2189,6 @@ unlock: return err; } -static int mptcp_v4_getname(struct socket *sock, struct sockaddr *uaddr, - int peer) -{ - if (sock->sk->sk_prot == &tcp_prot) { - /* we are being invoked from __sys_accept4, after - * mptcp_accept() has just accepted a non-mp-capable - * flow: sk is a tcp_sk, not an mptcp one. - * - * Hand the socket over to tcp so all further socket ops - * bypass mptcp. - */ - sock->ops = &inet_stream_ops; - } - - return inet_getname(sock, uaddr, peer); -} - -#if IS_ENABLED(CONFIG_MPTCP_IPV6) -static int mptcp_v6_getname(struct socket *sock, struct sockaddr *uaddr, - int peer) -{ - if (sock->sk->sk_prot == &tcpv6_prot) { - /* we are being invoked from __sys_accept4 after - * mptcp_accept() has accepted a non-mp-capable - * subflow: sk is a tcp_sk, not mptcp. - * - * Hand the socket over to tcp so all further - * socket ops bypass mptcp. - */ - sock->ops = &inet6_stream_ops; - } - - return inet6_getname(sock, uaddr, peer); -} -#endif - static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); @@ -1888,12 +2198,14 @@ static int mptcp_listen(struct socket *sock, int backlog) pr_debug("msk=%p", msk); lock_sock(sock->sk); - ssock = __mptcp_socket_create(msk, TCP_LISTEN); - if (IS_ERR(ssock)) { - err = PTR_ERR(ssock); + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + err = -EINVAL; goto unlock; } + mptcp_token_destroy(msk); + inet_sk_state_store(sock->sk, TCP_LISTEN); sock_set_flag(sock->sk, SOCK_RCU_FREE); err = ssock->ops->listen(ssock, backlog); @@ -1906,15 +2218,6 @@ unlock: return err; } -static bool is_tcp_proto(const struct proto *p) -{ -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - return p == &tcp_prot || p == &tcpv6_prot; -#else - return p == &tcp_prot; -#endif -} - static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { @@ -1932,11 +2235,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssock) goto unlock_fail; + clear_bit(MPTCP_DATA_READY, &msk->flags); sock_hold(ssock->sk); release_sock(sock->sk); err = ssock->ops->accept(sock, newsock, flags, kern); - if (err == 0 && !is_tcp_proto(newsock->sk->sk_prot)) { + if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) { struct mptcp_sock *msk = mptcp_sk(newsock->sk); struct mptcp_subflow_context *subflow; @@ -1944,7 +2248,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, * This is needed so NOSPACE flag can be set from tcp stack. */ __mptcp_flush_join_list(msk); - list_for_each_entry(subflow, &msk->conn_list, node) { + mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!ssk->sk_socket) @@ -1952,6 +2256,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, } } + if (inet_csk_listen_poll(ssock->sk)) + set_bit(MPTCP_DATA_READY, &msk->flags); sock_put(ssock->sk); return err; @@ -1960,39 +2266,36 @@ unlock_fail: return -EINVAL; } +static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +{ + return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : + 0; +} + static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { struct sock *sk = sock->sk; struct mptcp_sock *msk; - struct socket *ssock; __poll_t mask = 0; + int state; msk = mptcp_sk(sk); - lock_sock(sk); - ssock = __mptcp_tcp_fallback(msk); - if (!ssock) - ssock = __mptcp_nmpc_socket(msk); - if (ssock) { - mask = ssock->ops->poll(file, ssock, wait); - release_sock(sk); - return mask; - } - - release_sock(sk); sock_poll_wait(file, sock, wait); - lock_sock(sk); - if (test_bit(MPTCP_DATA_READY, &msk->flags)) - mask = EPOLLIN | EPOLLRDNORM; - if (sk_stream_is_writeable(sk) && - test_bit(MPTCP_SEND_SPACE, &msk->flags)) - mask |= EPOLLOUT | EPOLLWRNORM; + state = inet_sk_state_load(sk); + if (state == TCP_LISTEN) + return mptcp_check_readable(msk); + + if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { + mask |= mptcp_check_readable(msk); + if (sk_stream_is_writeable(sk) && + test_bit(MPTCP_SEND_SPACE, &msk->flags)) + mask |= EPOLLOUT | EPOLLWRNORM; + } if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; - release_sock(sk); - return mask; } @@ -2000,23 +2303,13 @@ static int mptcp_shutdown(struct socket *sock, int how) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct mptcp_subflow_context *subflow; - struct socket *ssock; int ret = 0; pr_debug("sk=%p, how=%d", msk, how); lock_sock(sock->sk); - ssock = __mptcp_tcp_fallback(msk); - if (ssock) { - release_sock(sock->sk); - return inet_shutdown(ssock, how); - } - - if (how == SHUT_WR || how == SHUT_RDWR) - inet_sk_state_store(sock->sk, TCP_FIN_WAIT1); how++; - if ((how & ~SHUTDOWN_MASK) || !how) { ret = -EINVAL; goto out_unlock; @@ -2030,13 +2323,36 @@ static int mptcp_shutdown(struct socket *sock, int how) sock->state = SS_CONNECTED; } - __mptcp_flush_join_list(msk); - mptcp_for_each_subflow(msk, subflow) { - struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + /* If we've already sent a FIN, or it's a closed state, skip this. */ + if (__mptcp_check_fallback(msk)) { + if (how == SHUT_WR || how == SHUT_RDWR) + inet_sk_state_store(sock->sk, TCP_FIN_WAIT1); - mptcp_subflow_shutdown(tcp_sk, how, 1, msk->write_seq); + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(sock->sk, tcp_sk, how); + } + } else if ((how & SEND_SHUTDOWN) && + ((1 << sock->sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | + TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) && + mptcp_close_state(sock->sk)) { + __mptcp_flush_join_list(msk); + + WRITE_ONCE(msk->write_seq, msk->write_seq + 1); + WRITE_ONCE(msk->snd_data_fin_enable, 1); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(sock->sk, tcp_sk, how); + } } + /* Wake up anyone sleeping in poll. */ + sock->sk->sk_state_change(sock->sk); + out_unlock: release_sock(sock->sk); @@ -2051,7 +2367,7 @@ static const struct proto_ops mptcp_stream_ops = { .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, - .getname = mptcp_v4_getname, + .getname = inet_getname, .poll = mptcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, @@ -2063,10 +2379,6 @@ static const struct proto_ops mptcp_stream_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, -#endif }; static struct inet_protosw mptcp_protosw = { @@ -2077,7 +2389,7 @@ static struct inet_protosw mptcp_protosw = { .flags = INET_PROTOSW_ICSK, }; -void mptcp_proto_init(void) +void __init mptcp_proto_init(void) { mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; @@ -2086,6 +2398,7 @@ void mptcp_proto_init(void) mptcp_subflow_init(); mptcp_pm_init(); + mptcp_token_init(); if (proto_register(&mptcp_prot, 1) != 0) panic("Failed to register MPTCP proto.\n"); @@ -2104,7 +2417,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, - .getname = mptcp_v6_getname, + .getname = inet6_getname, .poll = mptcp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, @@ -2118,8 +2431,6 @@ static const struct proto_ops mptcp_v6_stream_ops = { .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, #endif }; @@ -2139,7 +2450,7 @@ static struct inet_protosw mptcp_v6_protosw = { .flags = INET_PROTOSW_ICSK, }; -int mptcp_proto_v6_init(void) +int __init mptcp_proto_v6_init(void) { int err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c6eeaf3e8dcb..60b27d44c184 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -89,6 +89,7 @@ #define MPTCP_SEND_SPACE 1 #define MPTCP_WORK_RTX 2 #define MPTCP_WORK_EOF 3 +#define MPTCP_FALLBACK_DONE 4 struct mptcp_options_received { u64 sndr_key; @@ -173,8 +174,6 @@ struct mptcp_pm_data { u8 local_addr_max; u8 subflows_max; u8 status; - - struct work_struct work; }; struct mptcp_data_frag { @@ -194,11 +193,15 @@ struct mptcp_sock { u64 remote_key; u64 write_seq; u64 ack_seq; + u64 rcv_data_fin_seq; atomic64_t snd_una; unsigned long timer_ival; u32 token; unsigned long flags; bool can_ack; + bool fully_established; + bool rcv_data_fin; + bool snd_data_fin_enable; spinlock_t join_list_lock; struct work_struct work; struct list_head conn_list; @@ -208,6 +211,12 @@ struct mptcp_sock { struct socket *subflow; /* outgoing connect/listener/!mp_capable */ struct sock *first; struct mptcp_pm_data pm; + struct { + u32 space; /* bytes copied in last measurement window */ + u32 copied; /* bytes copied in this measurement window */ + u64 time; /* start time of measurement window */ + u64 rtt_us; /* last maximum rtt of subflows */ + } rcvq_space; }; #define mptcp_for_each_subflow(__msk, __subflow) \ @@ -250,6 +259,7 @@ struct mptcp_subflow_request_sock { u32 local_nonce; u32 remote_nonce; struct mptcp_sock *msk; + struct hlist_nulls_node token_node; }; static inline struct mptcp_subflow_request_sock * @@ -284,10 +294,8 @@ struct mptcp_subflow_context { backup : 1, data_avail : 1, rx_eof : 1, - data_fin_tx_enable : 1, use_64bit_ack : 1, /* Set when we received a 64-bit DSN */ can_ack : 1; /* only after processing the remote a key */ - u64 data_fin_tx_seq; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -336,8 +344,10 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) } int mptcp_is_enabled(struct net *net); +void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, + struct mptcp_options_received *mp_opt); bool mptcp_subflow_data_available(struct sock *sk); -void mptcp_subflow_init(void); +void __init mptcp_subflow_init(void); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, int ifindex, @@ -355,14 +365,9 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk, inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; } -extern const struct inet_connection_sock_af_ops ipv4_specific; +void __init mptcp_proto_init(void); #if IS_ENABLED(CONFIG_MPTCP_IPV6) -extern const struct inet_connection_sock_af_ops ipv6_specific; -#endif - -void mptcp_proto_init(void); -#if IS_ENABLED(CONFIG_MPTCP_IPV6) -int mptcp_proto_v6_init(void); +int __init mptcp_proto_v6_init(void); #endif struct sock *mptcp_sk_clone(const struct sock *sk, @@ -372,36 +377,41 @@ void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); +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); void mptcp_data_acked(struct sock *sk); void mptcp_subflow_eof(struct sock *sk); +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq); + +void __init mptcp_token_init(void); +static inline void mptcp_token_init_request(struct request_sock *req) +{ + mptcp_subflow_rsk(req)->token_node.pprev = NULL; +} int mptcp_token_new_request(struct request_sock *req); -void mptcp_token_destroy_request(u32 token); +void mptcp_token_destroy_request(struct request_sock *req); int mptcp_token_new_connect(struct sock *sk); -int mptcp_token_new_accept(u32 token, struct sock *conn); +void mptcp_token_accept(struct mptcp_subflow_request_sock *r, + struct mptcp_sock *msk); +bool mptcp_token_exists(u32 token); struct mptcp_sock *mptcp_token_get_sock(u32 token); -void mptcp_token_destroy(u32 token); +struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, + long *s_num); +void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); -static inline void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn) -{ - /* we might consider a faster version that computes the key as a - * hash of some information available in the MPTCP socket. Use - * random data at the moment, as it's probably the safest option - * in case multiple sockets are opened in different namespaces at - * the same time. - */ - get_random_bytes(key, sizeof(u64)); - mptcp_crypto_key_sha(*key, token, idsn); -} void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); -void mptcp_pm_init(void); +void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); -void mptcp_pm_close(struct mptcp_sock *msk); void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side); void mptcp_pm_fully_established(struct mptcp_sock *msk); bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); @@ -433,7 +443,7 @@ bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_addr_info *saddr); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); -void mptcp_pm_nl_init(void); +void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_data_init(struct mptcp_sock *msk); void mptcp_pm_nl_fully_established(struct mptcp_sock *msk); void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk); @@ -454,4 +464,66 @@ static inline bool before64(__u64 seq1, __u64 seq2) void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops); +static inline bool __mptcp_check_fallback(struct mptcp_sock *msk) +{ + return test_bit(MPTCP_FALLBACK_DONE, &msk->flags); +} + +static inline bool mptcp_check_fallback(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + return __mptcp_check_fallback(msk); +} + +static inline void __mptcp_do_fallback(struct mptcp_sock *msk) +{ + if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) { + pr_debug("TCP fallback already done (msk=%p)", msk); + return; + } + set_bit(MPTCP_FALLBACK_DONE, &msk->flags); +} + +static inline void mptcp_do_fallback(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + __mptcp_do_fallback(msk); +} + +#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) + +static inline bool subflow_simultaneous_connect(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sock *parent = subflow->conn; + + return sk->sk_state == TCP_ESTABLISHED && + !mptcp_sk(parent)->pm.server_side && + !subflow->conn_finished; +} + +#ifdef CONFIG_SYN_COOKIES +void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb); +bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb); +void __init mptcp_join_cookie_init(void); +#else +static inline void +subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) {} +static inline bool +mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + return false; +} + +static inline void mptcp_join_cookie_init(void) {} +#endif + #endif /* __MPTCP_PROTOCOL_H */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3838a0b3a21f..96f4f2fe50ad 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -29,40 +29,6 @@ static void SUBFLOW_REQ_INC_STATS(struct request_sock *req, MPTCP_INC_STATS(sock_net(req_to_sk(req)), field); } -static int subflow_rebuild_header(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - int local_id, err = 0; - - if (subflow->request_mptcp && !subflow->token) { - pr_debug("subflow=%p", sk); - err = mptcp_token_new_connect(sk); - } else if (subflow->request_join && !subflow->local_nonce) { - struct mptcp_sock *msk = (struct mptcp_sock *)subflow->conn; - - pr_debug("subflow=%p", sk); - - do { - get_random_bytes(&subflow->local_nonce, sizeof(u32)); - } while (!subflow->local_nonce); - - if (subflow->local_id) - goto out; - - local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); - if (local_id < 0) - return -EINVAL; - - subflow->local_id = local_id; - } - -out: - if (err) - return err; - - return subflow->icsk_af_ops->rebuild_header(sk); -} - static void subflow_req_destructor(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); @@ -72,8 +38,7 @@ static void subflow_req_destructor(struct request_sock *req) if (subflow_req->msk) sock_put((struct sock *)subflow_req->msk); - if (subflow_req->mp_capable) - mptcp_token_destroy_request(subflow_req->token); + mptcp_token_destroy_request(req); tcp_request_sock_ops.destructor(req); } @@ -88,6 +53,12 @@ static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac); } +static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk) +{ + return mptcp_is_fully_established((void *)msk) && + READ_ONCE(msk->pm.accept_subflow); +} + /* validate received token and create truncated hmac and nonce for SYN-ACK */ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, const struct sk_buff *skb) @@ -120,30 +91,43 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, return msk; } -static void subflow_init_req(struct request_sock *req, - const struct sock *sk_listener, - struct sk_buff *skb) +static int __subflow_init_req(struct request_sock *req, const struct sock *sk_listener) { - struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - struct mptcp_options_received mp_opt; - - pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); - - mptcp_get_options(skb, &mp_opt); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; subflow_req->msk = NULL; + mptcp_token_init_request(req); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) - return; + return -EINVAL; #endif + return 0; +} + +static void subflow_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_options_received mp_opt; + int ret; + + pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + + ret = __subflow_init_req(req, sk_listener); + if (ret) + return; + + mptcp_get_options(skb, &mp_opt); + if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -154,13 +138,33 @@ static void subflow_init_req(struct request_sock *req, } if (mp_opt.mp_capable && listener->request_mptcp) { - int err; + int err, retries = 4; + + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; +again: + do { + get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key)); + } while (subflow_req->local_key == 0); + + if (unlikely(req->syncookie)) { + mptcp_crypto_key_sha(subflow_req->local_key, + &subflow_req->token, + &subflow_req->idsn); + if (mptcp_token_exists(subflow_req->token)) { + if (retries-- > 0) + goto again; + } else { + subflow_req->mp_capable = 1; + } + return; + } err = mptcp_token_new_request(req); if (err == 0) subflow_req->mp_capable = 1; + else if (retries-- > 0) + goto again; - subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; } else if (mp_opt.mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; @@ -169,11 +173,60 @@ static void subflow_init_req(struct request_sock *req, subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; subflow_req->msk = subflow_token_join_request(req, skb); + + if (unlikely(req->syncookie) && subflow_req->msk) { + if (mptcp_can_accept_new_subflow(subflow_req->msk)) + subflow_init_req_cookie_join_save(subflow_req, skb); + } + pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } } +int mptcp_subflow_init_cookie_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_options_received mp_opt; + int err; + + err = __subflow_init_req(req, sk_listener); + if (err) + return err; + + mptcp_get_options(skb, &mp_opt); + + if (mp_opt.mp_capable && mp_opt.mp_join) + return -EINVAL; + + if (mp_opt.mp_capable && listener->request_mptcp) { + if (mp_opt.sndr_key == 0) + return -EINVAL; + + subflow_req->local_key = mp_opt.rcvr_key; + err = mptcp_token_new_request(req); + if (err) + return err; + + subflow_req->mp_capable = 1; + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; + } else if (mp_opt.mp_join && listener->request_mptcp) { + if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) + return -EINVAL; + + if (mptcp_can_accept_new_subflow(subflow_req->msk)) + subflow_req->mp_join = 1; + + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req); + static void subflow_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) @@ -222,7 +275,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; - struct tcp_sock *tp = tcp_sk(sk); subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -235,46 +287,40 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (subflow->conn_finished) return; + subflow->rel_write_seq = 1; subflow->conn_finished = 1; + subflow->ssn_offset = TCP_SKB_CB(skb)->seq; + pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); mptcp_get_options(skb, &mp_opt); - if (subflow->request_mptcp && mp_opt.mp_capable) { + if (subflow->request_mptcp) { + if (!mp_opt.mp_capable) { + MPTCP_INC_STATS(sock_net(sk), + MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); + mptcp_do_fallback(sk); + pr_fallback(mptcp_sk(subflow->conn)); + goto fallback; + } + subflow->mp_capable = 1; subflow->can_ack = 1; subflow->remote_key = mp_opt.sndr_key; pr_debug("subflow=%p, remote_key=%llu", subflow, subflow->remote_key); - } else if (subflow->request_join && mp_opt.mp_join) { - subflow->mp_join = 1; + mptcp_finish_connect(sk); + } else if (subflow->request_join) { + u8 hmac[SHA256_DIGEST_SIZE]; + + if (!mp_opt.mp_join) + goto do_reset; + subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, subflow->thmac, subflow->remote_nonce); - } else if (subflow->request_mptcp) { - tp->is_mptcp = 0; - } - if (!tp->is_mptcp) - return; - - if (subflow->mp_capable) { - pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk), - subflow->remote_key); - mptcp_finish_connect(sk); - - if (skb) { - pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq); - subflow->ssn_offset = TCP_SKB_CB(skb)->seq; - } - } else if (subflow->mp_join) { - u8 hmac[SHA256_DIGEST_SIZE]; - - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", - subflow, subflow->thmac, - subflow->remote_nonce); if (!subflow_thmac_valid(subflow)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC); - subflow->mp_join = 0; goto do_reset; } @@ -282,24 +328,26 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->local_nonce, subflow->remote_nonce, hmac); - memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN); - if (skb) - subflow->ssn_offset = TCP_SKB_CB(skb)->seq; - if (!mptcp_finish_join(sk)) goto do_reset; + subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); - } else { -do_reset: - tcp_send_active_reset(sk, GFP_ATOMIC); - tcp_done(sk); + } else if (mptcp_check_fallback(sk)) { +fallback: + mptcp_rcv_space_init(mptcp_sk(parent), sk); } + return; + +do_reset: + tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_done(sk); } -static struct request_sock_ops subflow_request_sock_ops; +struct request_sock_ops mptcp_subflow_request_sock_ops; +EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops); static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -312,7 +360,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; - return tcp_conn_request(&subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_request_sock_ops, &subflow_request_sock_ipv4_ops, sk, skb); drop: @@ -337,7 +385,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - return tcp_conn_request(&subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_request_sock_ops, &subflow_request_sock_ipv6_ops, sk, skb); drop: @@ -386,7 +434,7 @@ static void mptcp_sock_destruct(struct sock *sk) sock_orphan(sk); } - mptcp_token_destroy(mptcp_sk(sk)->token); + mptcp_token_destroy(mptcp_sk(sk)); inet_sock_destruct(sk); } @@ -421,6 +469,17 @@ static void subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } +void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, + struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + subflow->remote_key = mp_opt->sndr_key; + subflow->fully_established = 1; + subflow->can_ack = 1; + WRITE_ONCE(msk->fully_established, true); +} + static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -444,7 +503,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, /* hopefully temporary handling for MP_JOIN+syncookie */ subflow_req = mptcp_subflow_rsk(req); - fallback_is_fatal = subflow_req->mp_join; + fallback_is_fatal = tcp_rsk(req)->is_mptcp && subflow_req->mp_join; fallback = !tcp_rsk(req)->is_mptcp; if (fallback) goto create_child; @@ -472,6 +531,7 @@ create_msk: } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); if (!mp_opt.mp_join || + !mptcp_can_accept_new_subflow(subflow_req->msk) || !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; @@ -500,20 +560,25 @@ create_child: } if (ctx->mp_capable) { + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED); + /* new mpc subflow takes ownership of the newly * created mptcp socket */ new_msk->sk_destruct = mptcp_sock_destruct; mptcp_pm_new_connection(mptcp_sk(new_msk), 1); + mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); ctx->conn = new_msk; new_msk = NULL; /* with OoO packets we can reach here without ingress * mpc option */ - ctx->remote_key = mp_opt.sndr_key; - ctx->fully_established = mp_opt.mp_capable; - ctx->can_ack = mp_opt.mp_capable; + if (mp_opt.mp_capable) + mptcp_subflow_fully_established(ctx, &mp_opt); } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -548,9 +613,9 @@ out: dispose_child: subflow_drop_ctx(child); tcp_rsk(req)->drop_req = true; - tcp_send_active_reset(child, GFP_ATOMIC); inet_csk_prepare_for_destroy_sock(child); tcp_done(child); + req->rsk_ops->send_reset(sk, skb); /* The last child reference will be released by the caller */ return child; @@ -562,7 +627,8 @@ enum mapping_status { MAPPING_OK, MAPPING_INVALID, MAPPING_EMPTY, - MAPPING_DATA_FIN + MAPPING_DATA_FIN, + MAPPING_DUMMY }; static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) @@ -614,7 +680,8 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) return true; } -static enum mapping_status get_mapping_status(struct sock *ssk) +static enum mapping_status get_mapping_status(struct sock *ssk, + struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_ext *mpext; @@ -626,6 +693,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk) if (!skb) return MAPPING_EMPTY; + if (mptcp_check_fallback(ssk)) + return MAPPING_DUMMY; + mpext = mptcp_get_ext(skb); if (!mpext || !mpext->use_map) { if (!subflow->map_valid && !skb->len) { @@ -661,7 +731,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk) if (mpext->data_fin == 1) { if (data_len == 1) { - pr_debug("DATA_FIN with no payload"); + mptcp_update_rcv_data_fin(msk, mpext->data_seq); + pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping @@ -673,6 +744,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk) } else { return MAPPING_DATA_FIN; } + } else { + mptcp_update_rcv_data_fin(msk, mpext->data_seq + data_len); + pr_debug("DATA_FIN with mapping seq=%llu", mpext->data_seq + data_len); } /* Adjust for DATA_FIN using 1 byte of sequence space */ @@ -761,12 +835,22 @@ static bool subflow_check_data_avail(struct sock *ssk) u64 ack_seq; u64 old_ack; - status = get_mapping_status(ssk); + status = get_mapping_status(ssk, msk); pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status); if (status == MAPPING_INVALID) { ssk->sk_err = EBADMSG; goto fatal; } + if (status == MAPPING_DUMMY) { + __mptcp_do_fallback(msk); + skb = skb_peek(&ssk->sk_receive_queue); + subflow->map_valid = 1; + 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; + return true; + } if (status != MAPPING_OK) return false; @@ -889,15 +973,20 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) static void subflow_data_ready(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); struct sock *parent = subflow->conn; + struct mptcp_sock *msk; - if (!subflow->mp_capable && !subflow->mp_join) { - subflow->tcp_data_ready(sk); - + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; } + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); } @@ -974,19 +1063,34 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct sockaddr_storage addr; + int local_id = loc->id; struct socket *sf; + struct sock *ssk; u32 remote_token; int addrlen; int err; - if (sk->sk_state != TCP_ESTABLISHED) + if (!mptcp_is_fully_established(sk)) return -ENOTCONN; err = mptcp_subflow_create_socket(sk, &sf); if (err) return err; - subflow = mptcp_subflow_ctx(sf->sk); + ssk = sf->sk; + subflow = mptcp_subflow_ctx(ssk); + do { + get_random_bytes(&subflow->local_nonce, sizeof(u32)); + } while (!subflow->local_nonce); + + if (!local_id) { + err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk); + if (err < 0) + goto failed; + + local_id = err; + } + subflow->remote_key = msk->remote_key; subflow->local_key = msk->local_key; subflow->token = msk->token; @@ -997,15 +1101,16 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, if (loc->family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - sf->sk->sk_bound_dev_if = ifindex; + ssk->sk_bound_dev_if = ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) goto failed; mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u", msk, remote_token); + pr_debug("msk=%p remote_token=%u local_id=%d", msk, remote_token, + local_id); subflow->remote_token = remote_token; - subflow->local_id = loc->id; + subflow->local_id = local_id; subflow->request_join = 1; subflow->request_bkup = 1; mptcp_info2sockaddr(remote, &addr); @@ -1032,6 +1137,12 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) struct socket *sf; int err; + /* un-accepted server sockets can reach here - on bad configuration + * bail early to avoid greater trouble later + */ + if (unlikely(!sk->sk_socket)) + return -EINVAL; + err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP, &sf); if (err) @@ -1118,14 +1229,26 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); + if (subflow_simultaneous_connect(sk)) { + mptcp_do_fallback(sk); + mptcp_rcv_space_init(mptcp_sk(parent), sk); + pr_fallback(mptcp_sk(parent)); + subflow->conn_finished = 1; + if (inet_sk_state_load(parent) == TCP_SYN_SENT) { + inet_sk_state_store(parent, TCP_ESTABLISHED); + parent->sk_state_change(parent); + } + } + /* as recvmsg() does not acquire the subflow socket for ssk selection * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. */ - if (subflow->mp_capable && mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); - if (!(parent->sk_shutdown & RCV_SHUTDOWN) && + if (__mptcp_check_fallback(mptcp_sk(parent)) && + !(parent->sk_shutdown & RCV_SHUTDOWN) && !subflow->rx_eof && subflow_is_done(sk)) { subflow->rx_eof = 1; mptcp_subflow_eof(parent); @@ -1255,10 +1378,10 @@ static int subflow_ops_init(struct request_sock_ops *subflow_ops) return 0; } -void mptcp_subflow_init(void) +void __init mptcp_subflow_init(void) { - subflow_request_sock_ops = tcp_request_sock_ops; - if (subflow_ops_init(&subflow_request_sock_ops) != 0) + mptcp_subflow_request_sock_ops = tcp_request_sock_ops; + if (subflow_ops_init(&mptcp_subflow_request_sock_ops) != 0) panic("MPTCP: failed to init subflow request sock ops\n"); subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; @@ -1268,7 +1391,6 @@ void mptcp_subflow_init(void) subflow_specific.conn_request = subflow_v4_conn_request; subflow_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_specific.sk_rx_dst_set = subflow_finish_connect; - subflow_specific.rebuild_header = subflow_rebuild_header; #if IS_ENABLED(CONFIG_MPTCP_IPV6) subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; @@ -1278,7 +1400,6 @@ void mptcp_subflow_init(void) subflow_v6_specific.conn_request = subflow_v6_conn_request; subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect; - subflow_v6_specific.rebuild_header = subflow_rebuild_header; subflow_v6m_specific = subflow_v6_specific; subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit; diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c new file mode 100644 index 000000000000..abe0fd099746 --- /dev/null +++ b/net/mptcp/syncookies.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/skbuff.h> + +#include "protocol.h" + +/* Syncookies do not work for JOIN requests. + * + * Unlike MP_CAPABLE, where the ACK cookie contains the needed MPTCP + * options to reconstruct the initial syn state, MP_JOIN does not contain + * the token to obtain the mptcp socket nor the server-generated nonce + * that was used in the cookie SYN/ACK response. + * + * Keep a small best effort state table to store the syn/synack data, + * indexed by skb hash. + * + * A MP_JOIN SYN packet handled by syn cookies is only stored if the 32bit + * token matches a known mptcp connection that can still accept more subflows. + * + * There is no timeout handling -- state is only re-constructed + * when the TCP ACK passed the cookie validation check. + */ + +struct join_entry { + u32 token; + u32 remote_nonce; + u32 local_nonce; + u8 join_id; + u8 local_id; + u8 backup; + u8 valid; +}; + +#define COOKIE_JOIN_SLOTS 1024 + +static struct join_entry join_entries[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp; +static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp; + +static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net) +{ + u32 i = skb_get_hash(skb) ^ net_hash_mix(net); + + return i % ARRAY_SIZE(join_entries); +} + +static void mptcp_join_store_state(struct join_entry *entry, + const struct mptcp_subflow_request_sock *subflow_req) +{ + entry->token = subflow_req->token; + entry->remote_nonce = subflow_req->remote_nonce; + entry->local_nonce = subflow_req->local_nonce; + entry->backup = subflow_req->backup; + entry->join_id = subflow_req->remote_id; + entry->local_id = subflow_req->local_id; + entry->valid = 1; +} + +void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + struct net *net = read_pnet(&subflow_req->sk.req.ireq_net); + u32 i = mptcp_join_entry_hash(skb, net); + + /* No use in waiting if other cpu is already using this slot -- + * would overwrite the data that got stored. + */ + spin_lock_bh(&join_entry_locks[i]); + mptcp_join_store_state(&join_entries[i], subflow_req); + spin_unlock_bh(&join_entry_locks[i]); +} + +/* Called for a cookie-ack with MP_JOIN option present. + * Look up the saved state based on skb hash & check token matches msk + * in same netns. + * + * Caller will check msk can still accept another subflow. The hmac + * present in the cookie ACK mptcp option space will be checked later. + */ +bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + struct net *net = read_pnet(&subflow_req->sk.req.ireq_net); + u32 i = mptcp_join_entry_hash(skb, net); + struct mptcp_sock *msk; + struct join_entry *e; + + e = &join_entries[i]; + + spin_lock_bh(&join_entry_locks[i]); + + if (e->valid == 0) { + spin_unlock_bh(&join_entry_locks[i]); + return false; + } + + e->valid = 0; + + msk = mptcp_token_get_sock(e->token); + if (!msk) { + spin_unlock_bh(&join_entry_locks[i]); + return false; + } + + /* If this fails, the token got re-used in the mean time by another + * mptcp socket in a different netns, i.e. entry is outdated. + */ + if (!net_eq(sock_net((struct sock *)msk), net)) + goto err_put; + + subflow_req->remote_nonce = e->remote_nonce; + subflow_req->local_nonce = e->local_nonce; + subflow_req->backup = e->backup; + subflow_req->remote_id = e->join_id; + subflow_req->token = e->token; + subflow_req->msk = msk; + spin_unlock_bh(&join_entry_locks[i]); + return true; + +err_put: + spin_unlock_bh(&join_entry_locks[i]); + sock_put((struct sock *)msk); + return false; +} + +void __init mptcp_join_cookie_init(void) +{ + int i; + + for (i = 0; i < COOKIE_JOIN_SLOTS; i++) + spin_lock_init(&join_entry_locks[i]); +} diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 33352dd99d4d..8b47c4bb1c6b 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -24,7 +24,7 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/radix-tree.h> +#include <linux/memblock.h> #include <linux/ip.h> #include <linux/tcp.h> #include <net/sock.h> @@ -33,10 +33,67 @@ #include <net/mptcp.h> #include "protocol.h" -static RADIX_TREE(token_tree, GFP_ATOMIC); -static RADIX_TREE(token_req_tree, GFP_ATOMIC); -static DEFINE_SPINLOCK(token_tree_lock); -static int token_used __read_mostly; +#define TOKEN_MAX_RETRIES 4 +#define TOKEN_MAX_CHAIN_LEN 4 + +struct token_bucket { + spinlock_t lock; + int chain_len; + struct hlist_nulls_head req_chain; + struct hlist_nulls_head msk_chain; +}; + +static struct token_bucket *token_hash __read_mostly; +static unsigned int token_mask __read_mostly; + +static struct token_bucket *token_bucket(u32 token) +{ + return &token_hash[token & token_mask]; +} + +/* called with bucket lock held */ +static struct mptcp_subflow_request_sock * +__token_lookup_req(struct token_bucket *t, u32 token) +{ + struct mptcp_subflow_request_sock *req; + struct hlist_nulls_node *pos; + + hlist_nulls_for_each_entry_rcu(req, pos, &t->req_chain, token_node) + if (req->token == token) + return req; + return NULL; +} + +/* called with bucket lock held */ +static struct mptcp_sock * +__token_lookup_msk(struct token_bucket *t, u32 token) +{ + struct hlist_nulls_node *pos; + struct sock *sk; + + sk_nulls_for_each_rcu(sk, pos, &t->msk_chain) + if (mptcp_sk(sk)->token == token) + return mptcp_sk(sk); + return NULL; +} + +static bool __token_bucket_busy(struct token_bucket *t, u32 token) +{ + return !token || t->chain_len >= TOKEN_MAX_CHAIN_LEN || + __token_lookup_req(t, token) || __token_lookup_msk(t, token); +} + +static void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn) +{ + /* we might consider a faster version that computes the key as a + * hash of some information available in the MPTCP socket. Use + * random data at the moment, as it's probably the safest option + * in case multiple sockets are opened in different namespaces at + * the same time. + */ + get_random_bytes(key, sizeof(u64)); + mptcp_crypto_key_sha(*key, token, idsn); +} /** * mptcp_token_new_request - create new key/idsn/token for subflow_request @@ -52,30 +109,28 @@ static int token_used __read_mostly; int mptcp_token_new_request(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - int err; - - while (1) { - u32 token; - - mptcp_crypto_key_gen_sha(&subflow_req->local_key, - &subflow_req->token, - &subflow_req->idsn); - pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n", - req, subflow_req->local_key, subflow_req->token, - subflow_req->idsn); - - token = subflow_req->token; - spin_lock_bh(&token_tree_lock); - if (!radix_tree_lookup(&token_req_tree, token) && - !radix_tree_lookup(&token_tree, token)) - break; - spin_unlock_bh(&token_tree_lock); + struct token_bucket *bucket; + u32 token; + + mptcp_crypto_key_sha(subflow_req->local_key, + &subflow_req->token, + &subflow_req->idsn); + pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n", + req, subflow_req->local_key, subflow_req->token, + subflow_req->idsn); + + token = subflow_req->token; + bucket = token_bucket(token); + spin_lock_bh(&bucket->lock); + if (__token_bucket_busy(bucket, token)) { + spin_unlock_bh(&bucket->lock); + return -EBUSY; } - err = radix_tree_insert(&token_req_tree, - subflow_req->token, &token_used); - spin_unlock_bh(&token_tree_lock); - return err; + hlist_nulls_add_head_rcu(&subflow_req->token_node, &bucket->req_chain); + bucket->chain_len++; + spin_unlock_bh(&bucket->lock); + return 0; } /** @@ -97,48 +152,82 @@ int mptcp_token_new_request(struct request_sock *req) int mptcp_token_new_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct sock *mptcp_sock = subflow->conn; - int err; - - while (1) { - u32 token; + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + int retries = TOKEN_MAX_RETRIES; + struct token_bucket *bucket; - mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token, - &subflow->idsn); + pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", + sk, subflow->local_key, subflow->token, subflow->idsn); - pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", - sk, subflow->local_key, subflow->token, subflow->idsn); +again: + mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token, + &subflow->idsn); - token = subflow->token; - spin_lock_bh(&token_tree_lock); - if (!radix_tree_lookup(&token_req_tree, token) && - !radix_tree_lookup(&token_tree, token)) - break; - spin_unlock_bh(&token_tree_lock); + bucket = token_bucket(subflow->token); + spin_lock_bh(&bucket->lock); + if (__token_bucket_busy(bucket, subflow->token)) { + spin_unlock_bh(&bucket->lock); + if (!--retries) + return -EBUSY; + goto again; } - err = radix_tree_insert(&token_tree, subflow->token, mptcp_sock); - spin_unlock_bh(&token_tree_lock); - return err; + WRITE_ONCE(msk->token, subflow->token); + __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); + bucket->chain_len++; + spin_unlock_bh(&bucket->lock); + return 0; } /** - * mptcp_token_new_accept - insert token for later processing - * @token: the token to insert to the tree - * @conn: the just cloned socket linked to the new connection + * mptcp_token_accept - replace a req sk with full sock in token hash + * @req: the request socket to be removed + * @msk: the just cloned socket linked to the new connection * * Called when a SYN packet creates a new logical connection, i.e. * is not a join request. */ -int mptcp_token_new_accept(u32 token, struct sock *conn) +void mptcp_token_accept(struct mptcp_subflow_request_sock *req, + struct mptcp_sock *msk) { - int err; + struct mptcp_subflow_request_sock *pos; + struct token_bucket *bucket; - spin_lock_bh(&token_tree_lock); - err = radix_tree_insert(&token_tree, token, conn); - spin_unlock_bh(&token_tree_lock); + bucket = token_bucket(req->token); + spin_lock_bh(&bucket->lock); - return err; + /* pedantic lookup check for the moved token */ + pos = __token_lookup_req(bucket, req->token); + if (!WARN_ON_ONCE(pos != req)) + hlist_nulls_del_init_rcu(&req->token_node); + __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); + spin_unlock_bh(&bucket->lock); +} + +bool mptcp_token_exists(u32 token) +{ + struct hlist_nulls_node *pos; + struct token_bucket *bucket; + struct mptcp_sock *msk; + struct sock *sk; + + rcu_read_lock(); + bucket = token_bucket(token); + +again: + sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { + msk = mptcp_sk(sk); + if (READ_ONCE(msk->token) == token) + goto found; + } + if (get_nulls_value(pos) != (token & token_mask)) + goto again; + + rcu_read_unlock(); + return false; +found: + rcu_read_unlock(); + return true; } /** @@ -152,45 +241,171 @@ int mptcp_token_new_accept(u32 token, struct sock *conn) */ struct mptcp_sock *mptcp_token_get_sock(u32 token) { - struct sock *conn; - - spin_lock_bh(&token_tree_lock); - conn = radix_tree_lookup(&token_tree, token); - if (conn) { - /* token still reserved? */ - if (conn == (struct sock *)&token_used) - conn = NULL; - else - sock_hold(conn); + struct hlist_nulls_node *pos; + struct token_bucket *bucket; + struct mptcp_sock *msk; + struct sock *sk; + + rcu_read_lock(); + bucket = token_bucket(token); + +again: + sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { + msk = mptcp_sk(sk); + if (READ_ONCE(msk->token) != token) + continue; + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + goto not_found; + if (READ_ONCE(msk->token) != token) { + sock_put(sk); + goto again; + } + goto found; + } + if (get_nulls_value(pos) != (token & token_mask)) + goto again; + +not_found: + msk = NULL; + +found: + rcu_read_unlock(); + return msk; +} +EXPORT_SYMBOL_GPL(mptcp_token_get_sock); + +/** + * mptcp_token_iter_next - iterate over the token container from given pos + * @net: namespace to be iterated + * @s_slot: start slot number + * @s_num: start number inside the given lock + * + * This function returns the first mptcp connection structure found inside the + * token container starting from the specified position, or NULL. + * + * On successful iteration, the iterator is move to the next position and the + * the acquires a reference to the returned socket. + */ +struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, + long *s_num) +{ + struct mptcp_sock *ret = NULL; + struct hlist_nulls_node *pos; + int slot, num; + + for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) { + struct token_bucket *bucket = &token_hash[slot]; + struct sock *sk; + + num = 0; + + if (hlist_nulls_empty(&bucket->msk_chain)) + continue; + + rcu_read_lock(); + sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { + ++num; + if (!net_eq(sock_net(sk), net)) + continue; + + if (num <= *s_num) + continue; + + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + continue; + + if (!net_eq(sock_net(sk), net)) { + sock_put(sk); + continue; + } + + ret = mptcp_sk(sk); + rcu_read_unlock(); + goto out; + } + rcu_read_unlock(); } - spin_unlock_bh(&token_tree_lock); - return mptcp_sk(conn); +out: + *s_slot = slot; + *s_num = num; + return ret; } +EXPORT_SYMBOL_GPL(mptcp_token_iter_next); /** * mptcp_token_destroy_request - remove mptcp connection/token - * @token: token of mptcp connection to remove + * @req: mptcp request socket dropping the token * - * Remove not-yet-fully-established incoming connection identified - * by @token. + * Remove the token associated to @req. */ -void mptcp_token_destroy_request(u32 token) +void mptcp_token_destroy_request(struct request_sock *req) { - spin_lock_bh(&token_tree_lock); - radix_tree_delete(&token_req_tree, token); - spin_unlock_bh(&token_tree_lock); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_subflow_request_sock *pos; + struct token_bucket *bucket; + + if (hlist_nulls_unhashed(&subflow_req->token_node)) + return; + + bucket = token_bucket(subflow_req->token); + spin_lock_bh(&bucket->lock); + pos = __token_lookup_req(bucket, subflow_req->token); + if (!WARN_ON_ONCE(pos != subflow_req)) { + hlist_nulls_del_init_rcu(&pos->token_node); + bucket->chain_len--; + } + spin_unlock_bh(&bucket->lock); } /** * mptcp_token_destroy - remove mptcp connection/token - * @token: token of mptcp connection to remove + * @msk: mptcp connection dropping the token * - * Remove the connection identified by @token. + * Remove the token associated to @msk */ -void mptcp_token_destroy(u32 token) +void mptcp_token_destroy(struct mptcp_sock *msk) { - spin_lock_bh(&token_tree_lock); - radix_tree_delete(&token_tree, token); - spin_unlock_bh(&token_tree_lock); + struct token_bucket *bucket; + struct mptcp_sock *pos; + + if (sk_unhashed((struct sock *)msk)) + return; + + bucket = token_bucket(msk->token); + spin_lock_bh(&bucket->lock); + pos = __token_lookup_msk(bucket, msk->token); + if (!WARN_ON_ONCE(pos != msk)) { + __sk_nulls_del_node_init_rcu((struct sock *)pos); + bucket->chain_len--; + } + spin_unlock_bh(&bucket->lock); } + +void __init mptcp_token_init(void) +{ + int i; + + token_hash = alloc_large_system_hash("MPTCP token", + sizeof(struct token_bucket), + 0, + 20,/* one slot per 1MB of memory */ + HASH_ZERO, + NULL, + &token_mask, + 0, + 64 * 1024); + for (i = 0; i < token_mask + 1; ++i) { + INIT_HLIST_NULLS_HEAD(&token_hash[i].req_chain, i); + INIT_HLIST_NULLS_HEAD(&token_hash[i].msk_chain, i); + spin_lock_init(&token_hash[i].lock); + } +} + +#if IS_MODULE(CONFIG_MPTCP_KUNIT_TESTS) +EXPORT_SYMBOL_GPL(mptcp_token_new_request); +EXPORT_SYMBOL_GPL(mptcp_token_new_connect); +EXPORT_SYMBOL_GPL(mptcp_token_accept); +EXPORT_SYMBOL_GPL(mptcp_token_destroy_request); +EXPORT_SYMBOL_GPL(mptcp_token_destroy); +#endif diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c new file mode 100644 index 000000000000..e1bd6f0a0676 --- /dev/null +++ b/net/mptcp/token_test.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <kunit/test.h> + +#include "protocol.h" + +static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test) +{ + struct mptcp_subflow_request_sock *req; + + req = kunit_kzalloc(test, sizeof(struct mptcp_subflow_request_sock), + GFP_USER); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req); + mptcp_token_init_request((struct request_sock *)req); + return req; +} + +static void mptcp_token_test_req_basic(struct kunit *test) +{ + struct mptcp_subflow_request_sock *req = build_req_sock(test); + struct mptcp_sock *null_msk = NULL; + + KUNIT_ASSERT_EQ(test, 0, + mptcp_token_new_request((struct request_sock *)req)); + KUNIT_EXPECT_NE(test, 0, (int)req->token); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token)); + + /* cleanup */ + mptcp_token_destroy_request((struct request_sock *)req); +} + +static struct inet_connection_sock *build_icsk(struct kunit *test) +{ + struct inet_connection_sock *icsk; + + icsk = kunit_kzalloc(test, sizeof(struct inet_connection_sock), + GFP_USER); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, icsk); + return icsk; +} + +static struct mptcp_subflow_context *build_ctx(struct kunit *test) +{ + struct mptcp_subflow_context *ctx; + + ctx = kunit_kzalloc(test, sizeof(struct mptcp_subflow_context), + GFP_USER); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, ctx); + return ctx; +} + +static struct mptcp_sock *build_msk(struct kunit *test) +{ + struct mptcp_sock *msk; + + msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); + refcount_set(&((struct sock *)msk)->sk_refcnt, 1); + return msk; +} + +static void mptcp_token_test_msk_basic(struct kunit *test) +{ + struct inet_connection_sock *icsk = build_icsk(test); + struct mptcp_subflow_context *ctx = build_ctx(test); + struct mptcp_sock *msk = build_msk(test); + struct mptcp_sock *null_msk = NULL; + struct sock *sk; + + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + ctx->conn = (struct sock *)msk; + sk = (struct sock *)msk; + + KUNIT_ASSERT_EQ(test, 0, + mptcp_token_new_connect((struct sock *)icsk)); + KUNIT_EXPECT_NE(test, 0, (int)ctx->token); + KUNIT_EXPECT_EQ(test, ctx->token, msk->token); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt)); + + mptcp_token_destroy(msk); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token)); +} + +static void mptcp_token_test_accept(struct kunit *test) +{ + struct mptcp_subflow_request_sock *req = build_req_sock(test); + struct mptcp_sock *msk = build_msk(test); + + KUNIT_ASSERT_EQ(test, 0, + mptcp_token_new_request((struct request_sock *)req)); + msk->token = req->token; + mptcp_token_accept(req, msk); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + + /* this is now a no-op */ + mptcp_token_destroy_request((struct request_sock *)req); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + + /* cleanup */ + mptcp_token_destroy(msk); +} + +static void mptcp_token_test_destroyed(struct kunit *test) +{ + struct mptcp_subflow_request_sock *req = build_req_sock(test); + struct mptcp_sock *msk = build_msk(test); + struct mptcp_sock *null_msk = NULL; + struct sock *sk; + + sk = (struct sock *)msk; + + KUNIT_ASSERT_EQ(test, 0, + mptcp_token_new_request((struct request_sock *)req)); + msk->token = req->token; + mptcp_token_accept(req, msk); + + /* simulate race on removal */ + refcount_set(&sk->sk_refcnt, 0); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token)); + + /* cleanup */ + mptcp_token_destroy(msk); +} + +static struct kunit_case mptcp_token_test_cases[] = { + KUNIT_CASE(mptcp_token_test_req_basic), + KUNIT_CASE(mptcp_token_test_msk_basic), + KUNIT_CASE(mptcp_token_test_accept), + KUNIT_CASE(mptcp_token_test_destroyed), + {} +}; + +static struct kunit_suite mptcp_token_suite = { + .name = "mptcp-token", + .test_cases = mptcp_token_test_cases, +}; + +kunit_test_suite(mptcp_token_suite); + +MODULE_LICENSE("GPL"); |