diff options
Diffstat (limited to 'net/sctp')
| -rw-r--r-- | net/sctp/Kconfig | 49 | ||||
| -rw-r--r-- | net/sctp/Makefile | 3 | ||||
| -rw-r--r-- | net/sctp/associola.c | 33 | ||||
| -rw-r--r-- | net/sctp/auth.c | 168 | ||||
| -rw-r--r-- | net/sctp/chunk.c | 3 | ||||
| -rw-r--r-- | net/sctp/diag.c | 29 | ||||
| -rw-r--r-- | net/sctp/endpointola.c | 23 | ||||
| -rw-r--r-- | net/sctp/input.c | 33 | ||||
| -rw-r--r-- | net/sctp/inqueue.c | 27 | ||||
| -rw-r--r-- | net/sctp/ipv6.c | 94 | ||||
| -rw-r--r-- | net/sctp/offload.c | 2 | ||||
| -rw-r--r-- | net/sctp/output.c | 2 | ||||
| -rw-r--r-- | net/sctp/outqueue.c | 16 | ||||
| -rw-r--r-- | net/sctp/proc.c | 18 | ||||
| -rw-r--r-- | net/sctp/protocol.c | 112 | ||||
| -rw-r--r-- | net/sctp/sm_make_chunk.c | 102 | ||||
| -rw-r--r-- | net/sctp/sm_sideeffect.c | 46 | ||||
| -rw-r--r-- | net/sctp/sm_statefuns.c | 49 | ||||
| -rw-r--r-- | net/sctp/socket.c | 418 | ||||
| -rw-r--r-- | net/sctp/stream.c | 18 | ||||
| -rw-r--r-- | net/sctp/stream_interleave.c | 5 | ||||
| -rw-r--r-- | net/sctp/stream_sched.c | 25 | ||||
| -rw-r--r-- | net/sctp/stream_sched_fc.c | 225 | ||||
| -rw-r--r-- | net/sctp/stream_sched_prio.c | 54 | ||||
| -rw-r--r-- | net/sctp/stream_sched_rr.c | 2 | ||||
| -rw-r--r-- | net/sctp/sysctl.c | 105 | ||||
| -rw-r--r-- | net/sctp/transport.c | 65 |
27 files changed, 860 insertions, 866 deletions
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index 5da599ff84a9..e947646a380c 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -7,10 +7,10 @@ menuconfig IP_SCTP tristate "The SCTP Protocol" depends on INET depends on IPV6 || IPV6=n - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_SHA1 - select LIBCRC32C + select CRYPTO_LIB_SHA1 + select CRYPTO_LIB_SHA256 + select CRYPTO_LIB_UTILS + select NET_CRC32C select NET_UDP_TUNNEL help Stream Control Transmission Protocol @@ -49,46 +49,25 @@ config SCTP_DBG_OBJCNT 'cat /proc/net/sctp/sctp_dbg_objcnt' If unsure, say N + choice - prompt "Default SCTP cookie HMAC encoding" - default SCTP_DEFAULT_COOKIE_HMAC_MD5 + prompt "Default SCTP cookie authentication method" + default SCTP_DEFAULT_COOKIE_HMAC_SHA256 help - This option sets the default sctp cookie hmac algorithm - when in doubt select 'md5' + This option sets the default SCTP cookie authentication method, for + when a method hasn't been explicitly selected via the + net.sctp.cookie_hmac_alg sysctl. -config SCTP_DEFAULT_COOKIE_HMAC_MD5 - bool "Enable optional MD5 hmac cookie generation" - help - Enable optional MD5 hmac based SCTP cookie generation - select SCTP_COOKIE_HMAC_MD5 + If unsure, choose the default (HMAC-SHA256). -config SCTP_DEFAULT_COOKIE_HMAC_SHA1 - bool "Enable optional SHA1 hmac cookie generation" - help - Enable optional SHA1 hmac based SCTP cookie generation - select SCTP_COOKIE_HMAC_SHA1 +config SCTP_DEFAULT_COOKIE_HMAC_SHA256 + bool "HMAC-SHA256" config SCTP_DEFAULT_COOKIE_HMAC_NONE - bool "Use no hmac alg in SCTP cookie generation" - help - Use no hmac algorithm in SCTP cookie generation + bool "None" endchoice -config SCTP_COOKIE_HMAC_MD5 - bool "Enable optional MD5 hmac cookie generation" - help - Enable optional MD5 hmac based SCTP cookie generation - select CRYPTO_HMAC if SCTP_COOKIE_HMAC_MD5 - select CRYPTO_MD5 if SCTP_COOKIE_HMAC_MD5 - -config SCTP_COOKIE_HMAC_SHA1 - bool "Enable optional SHA1 hmac cookie generation" - help - Enable optional SHA1 hmac based SCTP cookie generation - select CRYPTO_HMAC if SCTP_COOKIE_HMAC_SHA1 - select CRYPTO_SHA1 if SCTP_COOKIE_HMAC_SHA1 - config INET_SCTP_DIAG depends on INET_DIAG def_tristate INET_DIAG diff --git a/net/sctp/Makefile b/net/sctp/Makefile index e845e4588535..0448398408d8 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -13,7 +13,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ offload.o stream_sched.o stream_sched_prio.o \ - stream_sched_rr.o stream_interleave.o + stream_sched_rr.o stream_sched_fc.o \ + stream_interleave.o sctp_diag-y := diag.o diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 63ba5551c13f..5793d71852b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -137,7 +137,8 @@ static struct sctp_association *sctp_association_init( = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; - asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = + (unsigned long)sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) @@ -361,7 +362,7 @@ void sctp_association_free(struct sctp_association *asoc) * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { - if (del_timer(&asoc->timers[i])) + if (timer_delete(&asoc->timers[i])) sctp_association_put(asoc); } @@ -735,24 +736,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return peer; } -/* Delete a transport address from an association. */ -void sctp_assoc_del_peer(struct sctp_association *asoc, - const union sctp_addr *addr) -{ - struct list_head *pos; - struct list_head *temp; - struct sctp_transport *transport; - - list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { - transport = list_entry(pos, struct sctp_transport, transports); - if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) { - /* Do book keeping for removing the peer and free it. */ - sctp_assoc_rm_peer(asoc, transport); - break; - } - } -} - /* Lookup a transport by address. */ struct sctp_transport *sctp_assoc_lookup_paddr( const struct sctp_association *asoc, @@ -1159,8 +1142,7 @@ int sctp_assoc_update(struct sctp_association *asoc, /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && - !sctp_assoc_add_peer(asoc, &trans->ipaddr, + if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; @@ -1521,7 +1503,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; - if (del_timer(timer)) + if (timer_delete(timer)) sctp_association_put(asoc); } } @@ -1597,9 +1579,10 @@ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, struct sctp_cookie *cookie, gfp_t gfp) { - int var_size2 = ntohs(cookie->peer_init->chunk_hdr.length); + struct sctp_init_chunk *peer_init = (struct sctp_init_chunk *)(cookie + 1); + int var_size2 = ntohs(peer_init->chunk_hdr.length); int var_size3 = cookie->raw_addr_list_len; - __u8 *raw = (__u8 *)cookie->peer_init + var_size2; + __u8 *raw = (__u8 *)peer_init + var_size2; return sctp_raw_to_bind_addrs(&asoc->base.bind_addr, raw, var_size3, asoc->ep->base.bind_addr.port, gfp); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 34964145514e..82aad477590e 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -12,36 +12,37 @@ * Vlad Yasevich <vladislav.yasevich@hp.com> */ -#include <crypto/hash.h> +#include <crypto/sha1.h> +#include <crypto/sha2.h> #include <linux/slab.h> #include <linux/types.h> -#include <linux/scatterlist.h> #include <net/sctp/sctp.h> #include <net/sctp/auth.h> -static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = { +static const struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = { { /* id 0 is reserved. as all 0 */ .hmac_id = SCTP_AUTH_HMAC_ID_RESERVED_0, }, { .hmac_id = SCTP_AUTH_HMAC_ID_SHA1, - .hmac_name = "hmac(sha1)", - .hmac_len = SCTP_SHA1_SIG_SIZE, + .hmac_len = SHA1_DIGEST_SIZE, }, { /* id 2 is reserved as well */ .hmac_id = SCTP_AUTH_HMAC_ID_RESERVED_2, }, -#if IS_ENABLED(CONFIG_CRYPTO_SHA256) { .hmac_id = SCTP_AUTH_HMAC_ID_SHA256, - .hmac_name = "hmac(sha256)", - .hmac_len = SCTP_SHA256_SIG_SIZE, + .hmac_len = SHA256_DIGEST_SIZE, } -#endif }; +static bool sctp_hmac_supported(__u16 hmac_id) +{ + return hmac_id < ARRAY_SIZE(sctp_hmac_list) && + sctp_hmac_list[hmac_id].hmac_len != 0; +} void sctp_auth_key_put(struct sctp_auth_bytes *key) { @@ -444,76 +445,7 @@ struct sctp_shared_key *sctp_auth_get_shkey( return NULL; } -/* - * Initialize all the possible digest transforms that we can use. Right - * now, the supported digests are SHA1 and SHA256. We do this here once - * because of the restrictiong that transforms may only be allocated in - * user context. This forces us to pre-allocated all possible transforms - * at the endpoint init time. - */ -int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) -{ - struct crypto_shash *tfm = NULL; - __u16 id; - - /* If the transforms are already allocated, we are done */ - if (ep->auth_hmacs) - return 0; - - /* Allocated the array of pointers to transorms */ - ep->auth_hmacs = kcalloc(SCTP_AUTH_NUM_HMACS, - sizeof(struct crypto_shash *), - gfp); - if (!ep->auth_hmacs) - return -ENOMEM; - - for (id = 0; id < SCTP_AUTH_NUM_HMACS; id++) { - - /* See is we support the id. Supported IDs have name and - * length fields set, so that we can allocated and use - * them. We can safely just check for name, for without the - * name, we can't allocate the TFM. - */ - if (!sctp_hmac_list[id].hmac_name) - continue; - - /* If this TFM has been allocated, we are all set */ - if (ep->auth_hmacs[id]) - continue; - - /* Allocate the ID */ - tfm = crypto_alloc_shash(sctp_hmac_list[id].hmac_name, 0, 0); - if (IS_ERR(tfm)) - goto out_err; - - ep->auth_hmacs[id] = tfm; - } - - return 0; - -out_err: - /* Clean up any successful allocations */ - sctp_auth_destroy_hmacs(ep->auth_hmacs); - ep->auth_hmacs = NULL; - return -ENOMEM; -} - -/* Destroy the hmac tfm array */ -void sctp_auth_destroy_hmacs(struct crypto_shash *auth_hmacs[]) -{ - int i; - - if (!auth_hmacs) - return; - - for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++) { - crypto_free_shash(auth_hmacs[i]); - } - kfree(auth_hmacs); -} - - -struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id) +const struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id) { return &sctp_hmac_list[hmac_id]; } @@ -521,7 +453,8 @@ struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id) /* Get an hmac description information that we can use to build * the AUTH chunk */ -struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) +const struct sctp_hmac * +sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) { struct sctp_hmac_algo_param *hmacs; __u16 n_elt; @@ -543,26 +476,10 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) sizeof(struct sctp_paramhdr)) >> 1; for (i = 0; i < n_elt; i++) { id = ntohs(hmacs->hmac_ids[i]); - - /* Check the id is in the supported range. And - * see if we support the id. Supported IDs have name and - * length fields set, so that we can allocate and use - * them. We can safely just check for name, for without the - * name, we can't allocate the TFM. - */ - if (id > SCTP_AUTH_HMAC_ID_MAX || - !sctp_hmac_list[id].hmac_name) { - id = 0; - continue; - } - - break; + if (sctp_hmac_supported(id)) + return &sctp_hmac_list[id]; } - - if (id == 0) - return NULL; - - return &sctp_hmac_list[id]; + return NULL; } static int __sctp_auth_find_hmacid(__be16 *hmacs, int n_elts, __be16 hmac_id) @@ -606,7 +523,6 @@ int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc, void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, struct sctp_hmac_algo_param *hmacs) { - struct sctp_endpoint *ep; __u16 id; int i; int n_params; @@ -617,16 +533,9 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, n_params = (ntohs(hmacs->param_hdr.length) - sizeof(struct sctp_paramhdr)) >> 1; - ep = asoc->ep; for (i = 0; i < n_params; i++) { id = ntohs(hmacs->hmac_ids[i]); - - /* Check the id is in the supported range */ - if (id > SCTP_AUTH_HMAC_ID_MAX) - continue; - - /* If this TFM has been allocated, use this id */ - if (ep->auth_hmacs[id]) { + if (sctp_hmac_supported(id)) { asoc->default_hmac_id = id; break; } @@ -709,10 +618,9 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc, struct sctp_shared_key *ep_key, gfp_t gfp) { struct sctp_auth_bytes *asoc_key; - struct crypto_shash *tfm; __u16 key_id, hmac_id; - unsigned char *end; int free_key = 0; + size_t data_len; __u8 *digest; /* Extract the info we need: @@ -733,19 +641,17 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc, free_key = 1; } - /* set up scatter list */ - end = skb_tail_pointer(skb); - - tfm = asoc->ep->auth_hmacs[hmac_id]; - - digest = auth->auth_hdr.hmac; - if (crypto_shash_setkey(tfm, &asoc_key->data[0], asoc_key->len)) - goto free; - - crypto_shash_tfm_digest(tfm, (u8 *)auth, end - (unsigned char *)auth, - digest); + data_len = skb_tail_pointer(skb) - (unsigned char *)auth; + digest = (u8 *)(&auth->auth_hdr + 1); + if (hmac_id == SCTP_AUTH_HMAC_ID_SHA1) { + hmac_sha1_usingrawkey(asoc_key->data, asoc_key->len, + (const u8 *)auth, data_len, digest); + } else { + WARN_ON_ONCE(hmac_id != SCTP_AUTH_HMAC_ID_SHA256); + hmac_sha256_usingrawkey(asoc_key->data, asoc_key->len, + (const u8 *)auth, data_len, digest); + } -free: if (free_key) sctp_auth_key_put(asoc_key); } @@ -788,14 +694,11 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, for (i = 0; i < hmacs->shmac_num_idents; i++) { id = hmacs->shmac_idents[i]; - if (id > SCTP_AUTH_HMAC_ID_MAX) + if (!sctp_hmac_supported(id)) return -EOPNOTSUPP; if (SCTP_AUTH_HMAC_ID_SHA1 == id) has_sha1 = 1; - - if (!sctp_hmac_list[id].hmac_name) - return -EOPNOTSUPP; } if (!has_sha1) @@ -1021,8 +924,6 @@ int sctp_auth_deact_key_id(struct sctp_endpoint *ep, int sctp_auth_init(struct sctp_endpoint *ep, gfp_t gfp) { - int err = -ENOMEM; - /* Allocate space for HMACS and CHUNKS authentication * variables. There are arrays that we encode directly * into parameters to make the rest of the operations easier. @@ -1060,13 +961,6 @@ int sctp_auth_init(struct sctp_endpoint *ep, gfp_t gfp) ep->auth_chunk_list = auth_chunks; } - /* Allocate and initialize transorms arrays for supported - * HMACs. - */ - err = sctp_auth_init_hmacs(ep, gfp); - if (err) - goto nomem; - return 0; nomem: @@ -1075,7 +969,7 @@ nomem: kfree(ep->auth_chunk_list); ep->auth_hmacs_list = NULL; ep->auth_chunk_list = NULL; - return err; + return -ENOMEM; } void sctp_auth_free(struct sctp_endpoint *ep) @@ -1084,6 +978,4 @@ void sctp_auth_free(struct sctp_endpoint *ep) kfree(ep->auth_chunk_list); ep->auth_hmacs_list = NULL; ep->auth_chunk_list = NULL; - sctp_auth_destroy_hmacs(ep->auth_hmacs); - ep->auth_hmacs = NULL; } diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index fd4f8243cc35..c655b571ca01 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -184,7 +184,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, * DATA. */ if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) { - struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); + const struct sctp_hmac *hmac_desc = + sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) + diff --git a/net/sctp/diag.c b/net/sctp/diag.c index a557009e9832..2afb376299fe 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -73,19 +73,26 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, struct nlattr *attr; void *info = NULL; + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) addrcnt++; + rcu_read_unlock(); attr = nla_reserve(skb, INET_DIAG_LOCALS, addrlen * addrcnt); if (!attr) return -EMSGSIZE; info = nla_data(attr); + rcu_read_lock(); list_for_each_entry_rcu(laddr, address_list, list) { memcpy(info, &laddr->a, sizeof(laddr->a)); memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a)); info += addrlen; + + if (!--addrcnt) + break; } + rcu_read_unlock(); return 0; } @@ -173,7 +180,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); - mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); + mem[SK_MEMINFO_DROPS] = sk_drops_read(sk); if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0) goto errout; @@ -223,14 +230,15 @@ struct sctp_comm_param { bool net_admin; }; -static size_t inet_assoc_attr_size(struct sctp_association *asoc) +static size_t inet_assoc_attr_size(struct sock *sk, + struct sctp_association *asoc) { int addrlen = sizeof(struct sockaddr_storage); int addrcnt = 0; struct sctp_sockaddr_entry *laddr; list_for_each_entry_rcu(laddr, &asoc->base.bind_addr.address_list, - list) + list, lockdep_sock_is_held(sk)) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) @@ -256,11 +264,14 @@ static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *t if (err) return err; - rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL); - if (!rep) + lock_sock(sk); + + rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL); + if (!rep) { + release_sock(sk); return -ENOMEM; + } - lock_sock(sk); if (ep != assoc->ep) { err = -EAGAIN; goto out; @@ -343,11 +354,9 @@ static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; - struct sctp_association *assoc = - list_entry(ep->asocs.next, struct sctp_association, asocs); /* find the ep only once through the transports by this condition */ - if (tsp->asoc != assoc) + if (!list_is_first(&tsp->asoc->asocs, &ep->asocs)) return 0; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) @@ -509,6 +518,7 @@ done: } static const struct inet_diag_handler sctp_diag_handler = { + .owner = THIS_MODULE, .dump = sctp_diag_dump, .dump_one = sctp_diag_dump_one, .idiag_get_info = sctp_diag_get_info, @@ -529,4 +539,5 @@ static void __exit sctp_diag_exit(void) module_init(sctp_diag_init); module_exit(sctp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SCTP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 7e77b450697c..31e989dfe846 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -35,6 +35,15 @@ /* Forward declarations for internal helpers. */ static void sctp_endpoint_bh_rcv(struct work_struct *work); +static void gen_cookie_auth_key(struct hmac_sha256_key *key) +{ + u8 raw_key[SCTP_COOKIE_KEY_SIZE]; + + get_random_bytes(raw_key, sizeof(raw_key)); + hmac_sha256_preparekey(key, raw_key, sizeof(raw_key)); + memzero_explicit(raw_key, sizeof(raw_key)); +} + /* * Initialize the base fields of the endpoint structure. */ @@ -45,10 +54,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, struct net *net = sock_net(sk); struct sctp_shared_key *null_key; - ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp); - if (!ep->digest) - return NULL; - ep->asconf_enable = net->sctp.addip_enable; ep->auth_enable = net->sctp.auth_enable; if (ep->auth_enable) { @@ -90,8 +95,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Get the receive buffer policy for this endpoint */ ep->rcvbuf_policy = net->sctp.rcvbuf_policy; - /* Initialize the secret key used with cookie. */ - get_random_bytes(ep->secret_key, sizeof(ep->secret_key)); + /* Generate the cookie authentication key. */ + gen_cookie_auth_key(&ep->cookie_auth_key); /* SCTP-AUTH extensions*/ INIT_LIST_HEAD(&ep->endpoint_shared_keys); @@ -118,7 +123,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, nomem_shkey: sctp_auth_free(ep); nomem: - kfree(ep->digest); return NULL; } @@ -205,9 +209,6 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) return; } - /* Free the digest buffer */ - kfree(ep->digest); - /* SCTP-AUTH: Free up AUTH releated data such as shared keys * chunks and hmacs arrays that were allocated */ @@ -218,7 +219,7 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) sctp_inq_free(&ep->base.inqueue); sctp_bind_addr_free(&ep->base.bind_addr); - memset(ep->secret_key, 0, sizeof(ep->secret_key)); + memzero_explicit(&ep->cookie_auth_key, sizeof(ep->cookie_auth_key)); sk = ep->base.sk; /* Remove and free the port */ diff --git a/net/sctp/input.c b/net/sctp/input.c index bf70371301ff..e119e460ccde 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -117,7 +117,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!is_gso && skb_linearize(skb)) || + if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; @@ -190,7 +190,7 @@ int sctp_rcv(struct sk_buff *skb) goto discard_release; nf_reset_ct(skb); - if (sk_filter(sk, skb)) + if (sk_filter(sk, skb) || skb->len < sizeof(struct sctp_chunkhdr)) goto discard_release; /* Create an SCTP packet structure. */ @@ -446,7 +446,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, pr_debug("%s: unrecognized next header type " "encountered!\n", __func__); - if (del_timer(&t->proto_unreach_timer)) + if (timer_delete(&t->proto_unreach_timer)) sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, @@ -581,11 +581,11 @@ static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, default: return; } - if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ - sk->sk_err_soft = err; + WRITE_ONCE(sk->sk_err_soft, err); } } @@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -752,7 +756,7 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk2 = ep2->base.sk; if (!net_eq(sock_net(sk2), net) || sk2 == sk || - !uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) || + !uid_eq(sk_uid(sk2), sk_uid(sk)) || !sk2->sk_reuseport) continue; @@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } @@ -1150,7 +1153,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, init = (struct sctp_init_chunk *)skb->data; /* Walk the parameters looking for embedded addresses. */ - sctp_walk_params(params, init, init_hdr.params) { + sctp_walk_params(params, init) { /* Note: Ignoring hostname addresses. */ af = sctp_get_af_specific(param_type2af(params.p->type)); diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 7182c5a450fb..f5a7d5a38755 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue) INIT_WORK(&queue->immediate, NULL); } +/* Properly release the chunk which is being worked on. */ +static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk) +{ + if (chunk->head_skb) + chunk->skb = chunk->head_skb; + sctp_chunk_free(chunk); +} + /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { @@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue) * free it as well. */ if (queue->in_progress) { - sctp_chunk_free(queue->in_progress); + sctp_inq_chunk_free(queue->in_progress); queue->in_progress = NULL; } } @@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) goto new_skb; } - if (chunk->head_skb) - chunk->skb = chunk->head_skb; - sctp_chunk_free(chunk); + sctp_inq_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ @@ -163,13 +169,14 @@ next_chunk: chunk->head_skb = chunk->skb; /* skbs with "cover letter" */ - if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) + if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) { + if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), + SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } chunk->skb = skb_shinfo(chunk->skb)->frag_list; - - if (WARN_ON(!chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; } } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 097bd60ce964..069b7e45d8bd 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -103,10 +103,10 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr) && addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { - sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); + sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); break; } } @@ -128,7 +128,6 @@ static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, { struct sctp_association *asoc = t->asoc; struct sock *sk = asoc->base.sk; - struct ipv6_pinfo *np; int err = 0; switch (type) { @@ -149,13 +148,12 @@ static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, break; } - np = inet6_sk(sk); icmpv6_err_convert(type, code, &err); - if (!sock_owned_by_user(sk) && np->recverr) { + if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { sk->sk_err = err; sk_error_report(sk); } else { - sk->sk_err_soft = err; + WRITE_ONCE(sk->sk_err_soft, err); } } @@ -249,7 +247,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) rcu_read_lock(); res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), - tclass, sk->sk_priority); + tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); return res; } @@ -263,9 +261,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) skb_set_inner_ipproto(skb, IPPROTO_SCTP); label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6); - return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, - &fl6->daddr, tclass, ip6_dst_hoplimit(dst), - label, sctp_sk(sk)->udp_port, t->encap_port, false); + udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, &fl6->daddr, + tclass, ip6_dst_hoplimit(dst), label, + sctp_sk(sk)->udp_port, t->encap_port, false, 0); + return 0; } /* Returns the dst cache entry for the given source and destination ip @@ -298,7 +297,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK) fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK); - if (np->sndflow && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) { + if (inet6_test_bit(SNDFLOW, sk) && + (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); @@ -416,7 +416,7 @@ out: if (!IS_ERR_OR_NULL(dst)) { struct rt6_info *rt; - rt = (struct rt6_info *)dst; + rt = dst_rt6_info(dst); t->dst_cookie = rt6_get_cookie(rt); pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", &rt->rt6i_dst.addr, rt->rt6i_dst.plen, @@ -547,7 +547,9 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = 0; + addr->v6.sin6_flowinfo = 0; addr->v6.sin6_addr = sk->sk_v6_rcv_saddr; + addr->v6.sin6_scope_id = 0; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -684,7 +686,7 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) struct sock *sk = &sp->inet.sk; struct net *net = sock_net(sk); struct net_device *dev = NULL; - int type; + int type, res, bound_dev_if; type = ipv6_addr_type(in6); if (IPV6_ADDR_ANY == type) @@ -698,14 +700,21 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - if (sk->sk_bound_dev_if) { - dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + rcu_read_lock(); + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if) { + res = 0; + dev = dev_get_by_index_rcu(net, bound_dev_if); if (!dev) - return 0; + goto out; } - return ipv6_can_nonlocal_bind(net, &sp->inet) || - ipv6_chk_addr(net, in6, dev, 0); + res = ipv6_can_nonlocal_bind(net, &sp->inet) || + ipv6_chk_addr(net, in6, dev, 0); + +out: + rcu_read_unlock(); + return res; } /* This function checks if the address is a valid address to be used for @@ -768,56 +777,6 @@ static enum sctp_scope sctp_v6_scope(union sctp_addr *addr) return retval; } -/* Create and initialize a new sk for the socket to be returned by accept(). */ -static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc, - bool kern) -{ - struct sock *newsk; - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); - struct sctp6_sock *newsctp6sk; - - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); - if (!newsk) - goto out; - - sock_init_data(NULL, newsk); - - sctp_copy_sock(newsk, sk, asoc); - sock_reset_flag(sk, SOCK_ZAPPED); - - newsctp6sk = (struct sctp6_sock *)newsk; - inet_sk(newsk)->pinet6 = &newsctp6sk->inet6; - - sctp_sk(newsk)->v4mapped = sctp_sk(sk)->v4mapped; - - newnp = inet6_sk(newsk); - - memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->ipv6_mc_list = NULL; - newnp->ipv6_ac_list = NULL; - newnp->ipv6_fl_list = NULL; - - sctp_v6_copy_ip_options(sk, newsk); - - /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() - * and getpeername(). - */ - sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk); - - newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - - sk_refcnt_debug_inc(newsk); - - if (newsk->sk_prot->init(newsk)) { - sk_common_release(newsk); - newsk = NULL; - } - -out: - return newsk; -} - /* Format a sockaddr for return to user space. This makes sure the return is * AF_INET or AF_INET6 depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. */ @@ -1164,7 +1123,6 @@ static struct sctp_pf sctp_pf_inet6 = { .bind_verify = sctp_inet6_bind_verify, .send_verify = sctp_inet6_send_verify, .supported_addrs = sctp_inet6_supported_addrs, - .create_accept_sk = sctp_v6_create_accept_sk, .addr_to_user = sctp_v6_addr_to_user, .to_sk_saddr = sctp_v6_to_sk_saddr, .to_sk_daddr = sctp_v6_to_sk_daddr, diff --git a/net/sctp/offload.c b/net/sctp/offload.c index eb874e3c399a..e6f863c031b4 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -22,6 +22,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/checksum.h> #include <net/protocol.h> +#include <net/gso.h> static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { @@ -110,7 +111,6 @@ int __init sctp_offload_init(void) if (ret) goto ipv4; - crc32c_csum_stub = &sctp_csum_ops; return ret; ipv4: diff --git a/net/sctp/output.c b/net/sctp/output.c index a63df055ac57..23e96305cad7 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -312,7 +312,7 @@ static enum sctp_xmit sctp_packet_bundle_sack(struct sctp_packet *pkt, SCTP_MIB_OUTCTRLCHUNKS); asoc->stats.octrlchunks++; asoc->peer.sack_needed = 0; - if (del_timer(timer)) + if (timer_delete(timer)) sctp_association_put(asoc); } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 20831079fb09..f6b8c13dafa4 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1231,7 +1231,7 @@ static void sctp_sack_update_unack_data(struct sctp_association *assoc, unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1; - frags = sack->variable; + frags = (union sctp_sack_variable *)(sack + 1); for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) { unack_data -= ((ntohs(frags[i].gab.end) - ntohs(frags[i].gab.start) + 1)); @@ -1252,7 +1252,6 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) struct sctp_transport *transport; struct sctp_chunk *tchunk = NULL; struct list_head *lchunk, *transport_list, *temp; - union sctp_sack_variable *frags = sack->variable; __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; @@ -1313,8 +1312,12 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) /* Get the highest TSN in the sack. */ highest_tsn = sack_ctsn; - if (gap_ack_blocks) + if (gap_ack_blocks) { + union sctp_sack_variable *frags = + (union sctp_sack_variable *)(sack + 1); + highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end); + } if (TSN_lt(asoc->highest_sacked, highest_tsn)) asoc->highest_sacked = highest_tsn; @@ -1627,8 +1630,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * as the receiver acknowledged any data. */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && - del_timer(&asoc->timers - [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) + timer_delete(&asoc->timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) sctp_association_put(asoc); /* Mark the destination transport address as @@ -1685,7 +1687,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * address. */ if (!transport->flight_size) { - if (del_timer(&transport->T3_rtx_timer)) + if (timer_delete(&transport->T3_rtx_timer)) sctp_transport_put(transport); } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, @@ -1789,7 +1791,7 @@ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) * Block are assumed to have been received correctly. */ - frags = sack->variable; + frags = (union sctp_sack_variable *)(sack + 1); blocks = ntohs(sack->num_gap_ack_blocks); tsn_offset = tsn - ctsn; for (i = 0; i < blocks; ++i) { diff --git a/net/sctp/proc.c b/net/sctp/proc.c index f13d6a34f32f..1ed281f3c355 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -52,21 +52,21 @@ static const struct snmp_mib sctp_snmp_list[] = { SNMP_MIB_ITEM("SctpInPktBacklog", SCTP_MIB_IN_PKT_BACKLOG), SNMP_MIB_ITEM("SctpInPktDiscards", SCTP_MIB_IN_PKT_DISCARDS), SNMP_MIB_ITEM("SctpInDataChunkDiscards", SCTP_MIB_IN_DATA_CHUNK_DISCARDS), - SNMP_MIB_SENTINEL }; /* Display sctp snmp mib statistics(/proc/net/sctp/snmp). */ static int sctp_snmp_seq_show(struct seq_file *seq, void *v) { - unsigned long buff[SCTP_MIB_MAX]; + unsigned long buff[ARRAY_SIZE(sctp_snmp_list)]; + const int cnt = ARRAY_SIZE(sctp_snmp_list); struct net *net = seq->private; int i; - memset(buff, 0, sizeof(unsigned long) * SCTP_MIB_MAX); + memset(buff, 0, sizeof(buff)); - snmp_get_cpu_field_batch(buff, sctp_snmp_list, - net->sctp.sctp_statistics); - for (i = 0; sctp_snmp_list[i].name; i++) + snmp_get_cpu_field_batch_cnt(buff, sctp_snmp_list, cnt, + net->sctp.sctp_statistics); + for (i = 0; i < cnt; i++) seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name, buff[i]); @@ -177,7 +177,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%8pK %8pK %-3d %-3d %-4d %-5d %5u %5lu ", ep, sk, sctp_sk(sk)->type, sk->sk_state, hash, ep->base.bind_addr.port, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), + from_kuid_munged(seq_user_ns(seq), sk_uid(sk)), sock_i_ino(sk)); sctp_seq_dump_local_addrs(seq, &ep->base); @@ -267,7 +267,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc->assoc_id, assoc->sndbuf_used, atomic_read(&assoc->rmem_alloc), - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), + from_kuid_munged(seq_user_ns(seq), sk_uid(sk)), sock_i_ino(sk), epb->bind_addr.port, assoc->peer.port); @@ -282,7 +282,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, refcount_read(&sk->sk_wmem_alloc), - sk->sk_wmem_queued, + READ_ONCE(sk->sk_wmem_queued), sk->sk_sndbuf, sk->sk_rcvbuf); seq_printf(seq, "\n"); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 909a89a1cff4..2c3398f75d76 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -34,6 +34,7 @@ #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/slab.h> +#include <net/flow.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> @@ -43,7 +44,9 @@ #include <net/addrconf.h> #include <net/inet_common.h> #include <net/inet_ecn.h> +#include <net/inet_sock.h> #include <net/udp_tunnel.h> +#include <net/inet_dscp.h> #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) @@ -183,12 +186,9 @@ static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk) rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { - newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); - if (newopt) - memcpy(newopt, inet_opt, sizeof(*inet_opt) + - inet_opt->opt.optlen); - else + if (!newopt) pr_err("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); @@ -360,7 +360,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id); if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && - !sp->inet.freebind && + !inet_test_bit(FREEBIND, sk) && !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; @@ -426,16 +426,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; - __u8 tos = inet_sk(sk)->tos; + dscp_t dscp; if (t->dscp & SCTP_DSCP_SET_MASK) - tos = t->dscp & SCTP_DSCP_VAL_MASK; + dscp = inet_dsfield_to_dscp(t->dscp); + else + dscp = inet_sk_dscp(inet_sk(sk)); + memset(&_fl, 0x0, sizeof(_fl)); fl4->daddr = daddr->v4.sin_addr.s_addr; fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { - fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos); + fl4->flowi4_dscp = dscp; + fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); } @@ -500,9 +504,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS_TOS(asoc->base.sk, tos), + flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); @@ -553,7 +555,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk, struct flowi *fl) { union sctp_addr *saddr = &t->saddr; - struct rtable *rt = (struct rtable *)t->dst; + struct rtable *rt = dst_rtable(t->dst); if (rt) { saddr->v4.sin_family = AF_INET; @@ -578,40 +580,6 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) return INET_ECN_is_ce(ip_hdr(skb)->tos); } -/* Create and initialize a new sk for the socket returned by accept(). */ -static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc, - bool kern) -{ - struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, kern); - struct inet_sock *newinet; - - if (!newsk) - goto out; - - sock_init_data(NULL, newsk); - - sctp_copy_sock(newsk, sk, asoc); - sock_reset_flag(newsk, SOCK_ZAPPED); - - sctp_v4_copy_ip_options(sk, newsk); - - newinet = inet_sk(newsk); - - newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; - - sk_refcnt_debug_inc(newsk); - - if (newsk->sk_prot->init(newsk)) { - sk_common_release(newsk); - newsk = NULL; - } - -out: - return newsk; -} - static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ @@ -632,7 +600,7 @@ static void sctp_v4_ecn_capable(struct sock *sk) static void sctp_addr_wq_timeout_handler(struct timer_list *t) { - struct net *net = from_timer(net, t, sctp.addr_wq_timer); + struct net *net = timer_container_of(net, t, sctp.addr_wq_timer); struct sctp_sockaddr_entry *addrw, *temp; struct sctp_sock *sp; @@ -696,7 +664,7 @@ static void sctp_free_addr_wq(struct net *net) struct sctp_sockaddr_entry *temp; spin_lock_bh(&net->sctp.addr_wq_lock); - del_timer(&net->sctp.addr_wq_timer); + timer_delete(&net->sctp.addr_wq_timer); list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) { list_del(&addrw->list); kfree(addrw); @@ -740,6 +708,20 @@ void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cm */ spin_lock_bh(&net->sctp.addr_wq_lock); + + /* Avoid searching the queue or modifying it if there are no consumers, + * as it can lead to performance degradation if addresses are modified + * en-masse. + * + * If the queue already contains some events, update it anyway to avoid + * ugly races between new sessions and new address events. + */ + if (list_empty(&net->sctp.auto_asconf_splist) && + list_empty(&net->sctp.addr_waitq)) { + spin_unlock_bh(&net->sctp.addr_wq_lock); + return; + } + /* Offsets existing events in addr_wq */ addrw = sctp_addr_wq_lookup(net, addr); if (addrw) { @@ -810,10 +792,10 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, if (addr->a.sa.sa_family == AF_INET && addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { - sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); + sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); break; } } @@ -1060,7 +1042,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) struct flowi4 *fl4 = &t->fl.u.ip4; struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); - __u8 dscp = inet->tos; + __u8 dscp = READ_ONCE(inet->tos); __be16 df = 0; pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, @@ -1088,9 +1070,10 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) skb_reset_inner_mac_header(skb); skb_reset_inner_transport_header(skb); skb_set_inner_ipproto(skb, IPPROTO_SCTP); - udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr, + udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr, fl4->daddr, dscp, ip4_dst_hoplimit(dst), df, - sctp_sk(sk)->udp_port, t->encap_port, false, false); + sctp_sk(sk)->udp_port, t->encap_port, false, false, + 0); return 0; } @@ -1104,7 +1087,6 @@ static struct sctp_pf sctp_pf_inet = { .bind_verify = sctp_inet_bind_verify, .send_verify = sctp_inet_send_verify, .supported_addrs = sctp_inet_supported_addrs, - .create_accept_sk = sctp_v4_create_accept_sk, .addr_to_user = sctp_v4_addr_to_user, .to_sk_saddr = sctp_v4_to_sk_saddr, .to_sk_daddr = sctp_v4_to_sk_daddr, @@ -1137,7 +1119,6 @@ static const struct proto_ops inet_seqpacket_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; /* Registration with AF_INET family. */ @@ -1321,14 +1302,9 @@ static int __net_init sctp_defaults_init(struct net *net) /* Whether Cookie Preservative is enabled(1) or not(0) */ net->sctp.cookie_preserve_enable = 1; - /* Default sctp sockets to use md5 as their hmac alg */ -#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5) - net->sctp.sctp_hmac_alg = "md5"; -#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1) - net->sctp.sctp_hmac_alg = "sha1"; -#else - net->sctp.sctp_hmac_alg = NULL; -#endif + /* Whether cookie authentication is enabled(1) or not(0) */ + net->sctp.cookie_auth_enable = + !IS_ENABLED(CONFIG_SCTP_DEFAULT_COOKIE_HMAC_NONE); /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; @@ -1499,17 +1475,11 @@ static __init int sctp_init(void) /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; - sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket", - sizeof(struct sctp_bind_bucket), - 0, SLAB_HWCACHE_ALIGN, - NULL); + sctp_bucket_cachep = KMEM_CACHE(sctp_bind_bucket, SLAB_HWCACHE_ALIGN); if (!sctp_bucket_cachep) goto out; - sctp_chunk_cachep = kmem_cache_create("sctp_chunk", - sizeof(struct sctp_chunk), - 0, SLAB_HWCACHE_ALIGN, - NULL); + sctp_chunk_cachep = KMEM_CACHE(sctp_chunk, SLAB_HWCACHE_ALIGN); if (!sctp_chunk_cachep) goto err_chunk_cachep; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index c7503fd64915..2c0017d058d4 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -30,7 +30,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <crypto/hash.h> +#include <crypto/utils.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/ip.h> @@ -115,14 +115,6 @@ static void sctp_control_set_owner_w(struct sctp_chunk *chunk) skb->destructor = sctp_control_release_owner; } -/* What was the inbound interface for this chunk? */ -int sctp_chunk_iif(const struct sctp_chunk *chunk) -{ - struct sk_buff *skb = chunk->skb; - - return SCTP_INPUT_CB(skb)->af->skb_iif(skb); -} - /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 2: The ECN capable field is reserved for future use of @@ -1327,7 +1319,7 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc, __u16 key_id) { struct sctp_authhdr auth_hdr; - struct sctp_hmac *hmac_desc; + const struct sctp_hmac *hmac_desc; struct sctp_chunk *retval; /* Get the first hmac that the peer told us to use */ @@ -1682,8 +1674,10 @@ static struct sctp_cookie_param *sctp_pack_cookie( * out on the network. */ retval = kzalloc(*cookie_len, GFP_ATOMIC); - if (!retval) - goto nodata; + if (!retval) { + *cookie_len = 0; + return NULL; + } cookie = (struct sctp_signed_cookie *) retval->body; @@ -1707,33 +1701,21 @@ static struct sctp_cookie_param *sctp_pack_cookie( ktime_get_real()); /* Copy the peer's init packet. */ - memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr, + memcpy(cookie + 1, init_chunk->chunk_hdr, ntohs(init_chunk->chunk_hdr->length)); /* Copy the raw local address list of the association. */ - memcpy((__u8 *)&cookie->c.peer_init[0] + + memcpy((__u8 *)(cookie + 1) + ntohs(init_chunk->chunk_hdr->length), raw_addrs, addrs_len); - if (sctp_sk(ep->base.sk)->hmac) { - struct crypto_shash *tfm = sctp_sk(ep->base.sk)->hmac; - int err; - - /* Sign the message. */ - err = crypto_shash_setkey(tfm, ep->secret_key, - sizeof(ep->secret_key)) ?: - crypto_shash_tfm_digest(tfm, (u8 *)&cookie->c, bodysize, - cookie->signature); - if (err) - goto free_cookie; + /* Sign the cookie, if cookie authentication is enabled. */ + if (sctp_sk(ep->base.sk)->cookie_auth_enable) { + static_assert(sizeof(cookie->mac) == SHA256_DIGEST_SIZE); + hmac_sha256(&ep->cookie_auth_key, (const u8 *)&cookie->c, + bodysize, cookie->mac); } return retval; - -free_cookie: - kfree(retval); -nodata: - *cookie_len = 0; - return NULL; } /* Unpack the cookie from COOKIE ECHO chunk, recreating the association. */ @@ -1748,7 +1730,6 @@ struct sctp_association *sctp_unpack_cookie( struct sctp_signed_cookie *cookie; struct sk_buff *skb = chunk->skb; struct sctp_cookie *bear_cookie; - __u8 *digest = ep->digest; enum sctp_scope scope; unsigned int len; ktime_t kt; @@ -1778,30 +1759,19 @@ struct sctp_association *sctp_unpack_cookie( cookie = chunk->subh.cookie_hdr; bear_cookie = &cookie->c; - if (!sctp_sk(ep->base.sk)->hmac) - goto no_hmac; - - /* Check the signature. */ - { - struct crypto_shash *tfm = sctp_sk(ep->base.sk)->hmac; - int err; + /* Verify the cookie's MAC, if cookie authentication is enabled. */ + if (sctp_sk(ep->base.sk)->cookie_auth_enable) { + u8 mac[SHA256_DIGEST_SIZE]; - err = crypto_shash_setkey(tfm, ep->secret_key, - sizeof(ep->secret_key)) ?: - crypto_shash_tfm_digest(tfm, (u8 *)bear_cookie, bodysize, - digest); - if (err) { - *error = -SCTP_IERROR_NOMEM; + hmac_sha256(&ep->cookie_auth_key, (const u8 *)bear_cookie, + bodysize, mac); + static_assert(sizeof(cookie->mac) == sizeof(mac)); + if (crypto_memneq(mac, cookie->mac, sizeof(mac))) { + *error = -SCTP_IERROR_BAD_SIG; goto fail; } } - if (memcmp(digest, cookie->signature, SCTP_SIGNATURE_SIZE)) { - *error = -SCTP_IERROR_BAD_SIG; - goto fail; - } - -no_hmac: /* IG Section 2.35.2: * 3) Compare the port numbers and the verification tag contained * within the COOKIE ECHO chunk to the actual port numbers and the @@ -2207,7 +2177,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, break; case SCTP_PARAM_HOST_NAME_ADDRESS: - /* Tell the peer, we won't support this param. */ + /* This param has been Deprecated, send ABORT. */ sctp_process_hn_param(asoc, param, chunk, err_chunk); retval = SCTP_IERROR_ABORT; break; @@ -2306,7 +2276,7 @@ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, ntohl(peer_init->init_hdr.a_rwnd) < SCTP_DEFAULT_MINWINDOW) return sctp_process_inv_mandatory(asoc, chunk, errp); - sctp_walk_params(param, peer_init, init_hdr.params) { + sctp_walk_params(param, peer_init) { if (param.p->type == SCTP_PARAM_STATE_COOKIE) has_cookie = true; } @@ -2329,7 +2299,7 @@ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, chunk, errp); /* Verify all the variable length parameters */ - sctp_walk_params(param, peer_init, init_hdr.params) { + sctp_walk_params(param, peer_init) { result = sctp_verify_param(net, ep, asoc, param, cid, chunk, errp); switch (result) { @@ -2381,7 +2351,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, src_match = 1; /* Process the initialization parameters. */ - sctp_walk_params(param, peer_init, init_hdr.params) { + sctp_walk_params(param, peer_init) { if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { @@ -2589,10 +2559,6 @@ do_addr_param: asoc->cookie_life = ktime_add_ms(asoc->cookie_life, stale); break; - case SCTP_PARAM_HOST_NAME_ADDRESS: - pr_debug("%s: unimplemented SCTP_HOST_NAME_ADDRESS\n", __func__); - break; - case SCTP_PARAM_SUPPORTED_ADDRESS_TYPES: /* Turn off the default values first so we'll know which * ones are really set by the peer. @@ -2624,10 +2590,6 @@ do_addr_param: asoc->peer.ipv6_address = 1; break; - case SCTP_PARAM_HOST_NAME_ADDRESS: - asoc->peer.hostname_address = 1; - break; - default: /* Just ignore anything else. */ break; } @@ -3210,7 +3172,7 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, union sctp_params param; addip = (struct sctp_addip_chunk *)chunk->chunk_hdr; - sctp_walk_params(param, addip, addip_hdr.params) { + sctp_walk_params(param, addip) { size_t length = ntohs(param.p->length); *errp = param.p; @@ -3223,14 +3185,14 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, /* ensure there is only one addr param and it's in the * beginning of addip_hdr params, or we reject it. */ - if (param.v != addip->addip_hdr.params) + if (param.v != (addip + 1)) return false; addr_param_seen = true; break; case SCTP_PARAM_IPV6_ADDRESS: if (length != sizeof(struct sctp_ipv6addr_param)) return false; - if (param.v != addip->addip_hdr.params) + if (param.v != (addip + 1)) return false; addr_param_seen = true; break; @@ -3310,8 +3272,8 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; /* Process the TLVs contained within the ASCONF chunk. */ - sctp_walk_params(param, addip, addip_hdr.params) { - /* Skip preceeding address parameters. */ + sctp_walk_params(param, addip) { + /* Skip preceding address parameters. */ if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || param.p->type == SCTP_PARAM_IPV6_ADDRESS) continue; @@ -3644,7 +3606,7 @@ static struct sctp_chunk *sctp_make_reconf(const struct sctp_association *asoc, return NULL; reconf = (struct sctp_reconf_chunk *)retval->chunk_hdr; - retval->param_hdr.v = reconf->params; + retval->param_hdr.v = (u8 *)(reconf + 1); return retval; } @@ -3886,7 +3848,7 @@ bool sctp_verify_reconf(const struct sctp_association *asoc, __u16 cnt = 0; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; - sctp_walk_params(param, hdr, params) { + sctp_walk_params(param, hdr) { __u16 length = ntohs(param.p->length); *errp = param.p; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 463c4a58d2c3..424f10a6fdba 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -231,7 +231,7 @@ nomem: void sctp_generate_t3_rtx_event(struct timer_list *t) { struct sctp_transport *transport = - from_timer(transport, t, T3_rtx_timer); + timer_container_of(transport, t, T3_rtx_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -308,7 +308,8 @@ out_unlock: static void sctp_generate_t1_cookie_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_COOKIE]); + timer_container_of(asoc, t, + timers[SCTP_EVENT_TIMEOUT_T1_COOKIE]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_COOKIE); } @@ -316,7 +317,8 @@ static void sctp_generate_t1_cookie_event(struct timer_list *t) static void sctp_generate_t1_init_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_INIT]); + timer_container_of(asoc, t, + timers[SCTP_EVENT_TIMEOUT_T1_INIT]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_INIT); } @@ -324,7 +326,8 @@ static void sctp_generate_t1_init_event(struct timer_list *t) static void sctp_generate_t2_shutdown_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN]); + timer_container_of(asoc, t, + timers[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T2_SHUTDOWN); } @@ -332,7 +335,7 @@ static void sctp_generate_t2_shutdown_event(struct timer_list *t) static void sctp_generate_t4_rto_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T4_RTO]); + timer_container_of(asoc, t, timers[SCTP_EVENT_TIMEOUT_T4_RTO]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T4_RTO); } @@ -340,8 +343,8 @@ static void sctp_generate_t4_rto_event(struct timer_list *t) static void sctp_generate_t5_shutdown_guard_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, - timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]); + timer_container_of(asoc, t, + timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD); @@ -351,7 +354,8 @@ static void sctp_generate_t5_shutdown_guard_event(struct timer_list *t) static void sctp_generate_autoclose_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]); + timer_container_of(asoc, t, + timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_AUTOCLOSE); } @@ -361,7 +365,8 @@ static void sctp_generate_autoclose_event(struct timer_list *t) */ void sctp_generate_heartbeat_event(struct timer_list *t) { - struct sctp_transport *transport = from_timer(transport, t, hb_timer); + struct sctp_transport *transport = timer_container_of(transport, t, + hb_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -407,7 +412,7 @@ out_unlock: void sctp_generate_proto_unreach_event(struct timer_list *t) { struct sctp_transport *transport = - from_timer(transport, t, proto_unreach_timer); + timer_container_of(transport, t, proto_unreach_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -442,7 +447,7 @@ out_unlock: void sctp_generate_reconf_event(struct timer_list *t) { struct sctp_transport *transport = - from_timer(transport, t, reconf_timer); + timer_container_of(transport, t, reconf_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -478,7 +483,8 @@ out_unlock: /* Handle the timeout of the probe timer. */ void sctp_generate_probe_event(struct timer_list *t) { - struct sctp_transport *transport = from_timer(transport, t, probe_timer); + struct sctp_transport *transport = timer_container_of(transport, t, + probe_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -511,7 +517,7 @@ out_unlock: static void sctp_generate_sack_event(struct timer_list *t) { struct sctp_association *asoc = - from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_SACK]); + timer_container_of(asoc, t, timers[SCTP_EVENT_TIMEOUT_SACK]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_SACK); } @@ -734,7 +740,7 @@ static void sctp_cmd_hb_timers_stop(struct sctp_cmd_seq *cmds, list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - if (del_timer(&t->hb_timer)) + if (timer_delete(&t->hb_timer)) sctp_transport_put(t); } } @@ -747,7 +753,7 @@ static void sctp_cmd_t3_rtx_timers_stop(struct sctp_cmd_seq *cmds, list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - if (del_timer(&t->T3_rtx_timer)) + if (timer_delete(&t->T3_rtx_timer)) sctp_transport_put(t); } } @@ -984,8 +990,7 @@ static void sctp_cmd_process_operr(struct sctp_cmd_seq *cmds, { struct sctp_chunkhdr *unk_chunk_hdr; - unk_chunk_hdr = (struct sctp_chunkhdr *) - err_hdr->variable; + unk_chunk_hdr = (struct sctp_chunkhdr *)(err_hdr + 1); switch (unk_chunk_hdr->type) { /* ADDIP 4.1 A9) If the peer responds to an ASCONF with * an ERROR chunk reporting that it did not recognized @@ -1251,7 +1256,10 @@ static int sctp_side_effects(enum sctp_event_type event_type, default: pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n", status, state, event_type, subtype.chunk); - BUG(); + error = status; + if (error >= 0) + error = -EINVAL; + WARN_ON_ONCE(1); break; } @@ -1555,7 +1563,7 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, case SCTP_CMD_TIMER_STOP: timer = &asoc->timers[cmd->obj.to]; - if (del_timer(timer)) + if (timer_delete(timer)) sctp_association_put(asoc); break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index ce5426171206..3755ba079d07 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -30,6 +30,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <crypto/utils.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/ip.h> @@ -38,6 +39,7 @@ #include <linux/inet.h> #include <linux/slab.h> #include <net/sock.h> +#include <net/proto_memory.h> #include <net/inet_ecn.h> #include <linux/skbuff.h> #include <net/sctp/sctp.h> @@ -794,8 +796,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, /* This is a brand-new association, so these are not yet side * effects--it is safe to run them here. */ - peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; - + peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, &chunk->subh.cookie_hdr->c.peer_addr, peer_init, GFP_ATOMIC)) @@ -885,7 +886,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, return SCTP_DISPOSITION_CONSUME; nomem_authev: - sctp_ulpevent_free(ai_ev); + if (ai_ev) + sctp_ulpevent_free(ai_ev); nomem_aiev: sctp_ulpevent_free(ev); nomem_ev: @@ -1337,7 +1339,7 @@ static int sctp_sf_send_restart_abort(struct net *net, union sctp_addr *ssa, * throughout the code today. */ errhdr = (struct sctp_errhdr *)buffer; - addrparm = (union sctp_addr_param *)errhdr->variable; + addrparm = (union sctp_addr_param *)(errhdr + 1); /* Copy into a parm format. */ len = af->to_addr_param(ssa, addrparm); @@ -1869,8 +1871,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( /* new_asoc is a brand-new association, so these are not yet * side effects--it is safe to run them here. */ - peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; - + peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; @@ -1990,7 +1991,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( /* new_asoc is a brand-new association, so these are not yet * side effects--it is safe to run them here. */ - peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; + peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; @@ -2261,12 +2262,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } } - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; @@ -2275,6 +2270,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( */ action = sctp_tietags_compare(new_asoc, asoc); + /* In cases C and E the association doesn't enter the ESTABLISHED + * state, so there is no need to call security_sctp_assoc_request(). + */ + switch (action) { + case 'A': /* Association restart. */ + case 'B': /* Collision case B. */ + case 'D': /* Collision case D. */ + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_association *)asoc, + chunk->head_skb ?: chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + break; + } + switch (action) { case 'A': /* Association restart. */ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands, @@ -3742,7 +3753,7 @@ enum sctp_disposition sctp_sf_ootb(struct net *net, } ch = (struct sctp_chunkhdr *)ch_end; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); if (ootb_shut_ack) return sctp_sf_shut_8_4_5(net, ep, asoc, type, arg, commands); @@ -4142,7 +4153,7 @@ enum sctp_disposition sctp_sf_do_reconf(struct net *net, (void *)err_param, commands); hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; - sctp_walk_params(param, hdr, params) { + sctp_walk_params(param, hdr) { struct sctp_chunk *reply = NULL; struct sctp_ulpevent *ev = NULL; @@ -4352,7 +4363,7 @@ static enum sctp_ierror sctp_sf_authenticate( struct sctp_shared_key *sh_key = NULL; struct sctp_authhdr *auth_hdr; __u8 *save_digest, *digest; - struct sctp_hmac *hmac; + const struct sctp_hmac *hmac; unsigned int sig_len; __u16 key_id; @@ -4393,7 +4404,7 @@ static enum sctp_ierror sctp_sf_authenticate( * 3. Compute the new digest * 4. Compare saved and new digests. */ - digest = auth_hdr->hmac; + digest = (u8 *)(auth_hdr + 1); skb_pull(chunk->skb, sig_len); save_digest = kmemdup(digest, sig_len, GFP_ATOMIC); @@ -4407,7 +4418,7 @@ static enum sctp_ierror sctp_sf_authenticate( sh_key, GFP_ATOMIC); /* Discard the packet if the digests do not match */ - if (memcmp(save_digest, digest, sig_len)) { + if (crypto_memneq(save_digest, digest, sig_len)) { kfree(save_digest); return SCTP_IERROR_BAD_SIG; } @@ -4484,7 +4495,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, SCTP_AUTH_NEW_KEY, GFP_ATOMIC); if (!ev) - return -ENOMEM; + return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 84021a6c4f9d..d808096f5ab1 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -37,7 +37,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <crypto/hash.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/wait.h> @@ -59,6 +58,7 @@ #include <net/ipv6.h> #include <net/inet_common.h> #include <net/busy_poll.h> +#include <trace/events/sock.h> #include <linux/socket.h> /* for sa_family_t */ #include <linux/export.h> @@ -66,12 +66,14 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <net/rps.h> /* Forward declarations for internal helper functions. */ -static bool sctp_writeable(struct sock *sk); +static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); -static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len); +static int sctp_wait_for_sndbuf(struct sctp_association *asoc, + struct sctp_transport *transport, + long *timeo_p, size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -98,7 +100,7 @@ struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); } @@ -139,7 +141,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk); - sk->sk_wmem_queued += chunk->skb->truesize + sizeof(struct sctp_chunk); + sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk)); sk_mem_charge(sk, chunk->skb->truesize); } @@ -304,7 +306,8 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, * sockaddr_in6 [RFC 2553]), * addr_len - the size of the address structure. */ -static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) +static int sctp_bind(struct sock *sk, struct sockaddr_unsized *addr, + int addr_len) { int retval = 0; @@ -363,9 +366,9 @@ static void sctp_auto_asconf_init(struct sctp_sock *sp) struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { - spin_lock(&net->sctp.addr_wq_lock); + spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); - spin_unlock(&net->sctp.addr_wq_lock); + spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } @@ -1051,13 +1054,13 @@ static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr *addrs, } } -static int sctp_bind_add(struct sock *sk, struct sockaddr *addrs, - int addrlen) +static int sctp_bind_add(struct sock *sk, struct sockaddr_unsized *addrs, + int addrlen) { int err; lock_sock(sk); - err = sctp_setsockopt_bindx(sk, addrs, addrlen, SCTP_BINDX_ADD_ADDR); + err = sctp_setsockopt_bindx(sk, (struct sockaddr *)addrs, addrlen, SCTP_BINDX_ADD_ADDR); release_sock(sk); return err; } @@ -1551,8 +1554,6 @@ static void sctp_close(struct sock *sk, long timeout) spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); - - SCTP_DBG_OBJCNT_DEC(sock); } /* Handle EPIPE error. */ @@ -1826,9 +1827,13 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); + err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { @@ -2094,6 +2099,13 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n", __func__, sk, msg, len, flags, addr_len); + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + + if (sk_can_busy_loop(sk) && + skb_queue_empty_lockless(&sk->sk_receive_queue)) + sk_busy_loop(sk, flags & MSG_DONTWAIT); + lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && @@ -2445,6 +2457,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); + sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); @@ -4808,7 +4821,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, return err; } -int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, +int sctp_inet_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { if (addr_len < sizeof(uaddr->sa_family)) @@ -4817,13 +4830,86 @@ int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, if (uaddr->sa_family == AF_UNSPEC) return -EOPNOTSUPP; - return sctp_connect(sock->sk, uaddr, addr_len, flags); + return sctp_connect(sock->sk, (struct sockaddr *)uaddr, addr_len, flags); } -/* FIXME: Write comments. */ +/* Only called when shutdown a listening SCTP socket. */ static int sctp_disconnect(struct sock *sk, int flags) { - return -EOPNOTSUPP; /* STUB */ + if (!sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + sk->sk_shutdown |= RCV_SHUTDOWN; + return 0; +} + +static struct sock *sctp_clone_sock(struct sock *sk, + struct sctp_association *asoc, + enum sctp_socket_type type) +{ + struct sock *newsk = sk_clone(sk, GFP_KERNEL, false); + struct inet_sock *newinet; + struct sctp_sock *newsp; + int err = -ENOMEM; + + if (!newsk) + return ERR_PTR(err); + + /* sk_clone() sets refcnt to 2 */ + sock_put(newsk); + + newinet = inet_sk(newsk); + newsp = sctp_sk(newsk); + + newsp->pf->to_sk_daddr(&asoc->peer.primary_addr, newsk); + newinet->inet_dport = htons(asoc->peer.port); + + newsp->pf->copy_ip_options(sk, newsk); + atomic_set(&newinet->inet_id, get_random_u16()); + + inet_set_bit(MC_LOOP, newsk); + newinet->mc_ttl = 1; + newinet->mc_index = 0; + newinet->mc_list = NULL; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *newnp = inet6_sk(newsk); + + newinet->pinet6 = &((struct sctp6_sock *)newsk)->inet6; + newinet->ipv6_fl_list = NULL; + + memcpy(newnp, inet6_sk(sk), sizeof(struct ipv6_pinfo)); + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + } +#endif + + newsp->do_auto_asconf = 0; + skb_queue_head_init(&newsp->pd_lobby); + + newsp->ep = sctp_endpoint_new(newsk, GFP_KERNEL); + if (!newsp->ep) + goto out_release; + + SCTP_DBG_OBJCNT_INC(sock); + sk_sockets_allocated_inc(newsk); + sock_prot_inuse_add(sock_net(sk), newsk->sk_prot, 1); + + err = sctp_sock_migrate(sk, newsk, asoc, type); + if (err) + goto out_release; + + /* Set newsk security attributes from original sk and connection + * security attribute from asoc. + */ + security_sctp_sk_clone(asoc, sk, newsk); + + return newsk; + +out_release: + sk_common_release(newsk); + return ERR_PTR(err); } /* 4.1.4 accept() - TCP Style Syntax @@ -4833,31 +4919,27 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) +static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) { - struct sctp_sock *sp; - struct sctp_endpoint *ep; - struct sock *newsk = NULL; struct sctp_association *asoc; - long timeo; + struct sock *newsk = NULL; int error = 0; + long timeo; lock_sock(sk); - sp = sctp_sk(sk); - ep = sp->ep; - if (!sctp_style(sk, TCP)) { error = -EOPNOTSUPP; goto out; } - if (!sctp_sstate(sk, LISTENING)) { + if (!sctp_sstate(sk, LISTENING) || + (sk->sk_shutdown & RCV_SHUTDOWN)) { error = -EINVAL; goto out; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); error = sctp_wait_for_accept(sk, timeo); if (error) @@ -4866,31 +4948,23 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) /* We treat the list of associations on the endpoint as the accept * queue and pick the first association on the list. */ - asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); + asoc = list_entry(sctp_sk(sk)->ep->asocs.next, + struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc, kern); - if (!newsk) { - error = -ENOMEM; - goto out; - } - - /* Populate the fields of the newsk from the oldsk and migrate the - * asoc to the newsk. - */ - error = sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); - if (error) { - sk_common_release(newsk); + newsk = sctp_clone_sock(sk, asoc, SCTP_SOCKET_TCP); + if (IS_ERR(newsk)) { + error = PTR_ERR(newsk); newsk = NULL; } out: release_sock(sk); - *err = error; + arg->err = error; return newsk; } /* The SCTP ioctl handler. */ -static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int sctp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; @@ -4906,7 +4980,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCINQ: { struct sk_buff *skb; - unsigned int amount = 0; + *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { @@ -4914,9 +4988,9 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) * We will only return the amount of this packet since * that is all that will be read. */ - amount = skb->len; + *karg = skb->len; } - rc = put_user(amount, (int __user *)arg); + rc = 0; break; } default: @@ -4967,7 +5041,7 @@ static int sctp_init_sock(struct sock *sk) sp->default_rcv_context = 0; sp->max_burst = net->sctp.max_burst; - sp->sctp_hmac_alg = net->sctp.sctp_hmac_alg; + sp->cookie_auth_enable = net->sctp.cookie_auth_enable; /* Initialize default setup parameters. These parameters * can be modified with the SCTP_INITMSG socket option or @@ -5059,8 +5133,6 @@ static int sctp_init_sock(struct sock *sk) if (!sp->ep) return -ENOMEM; - sp->hmac = NULL; - sk->sk_destruct = sctp_destruct_sock; SCTP_DBG_OBJCNT_INC(sock); @@ -5092,23 +5164,16 @@ static void sctp_destroy_sock(struct sock *sk) sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); } + sctp_endpoint_free(sp->ep); + sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); -} - -/* Triggered when there are no references on the socket anymore */ -static void sctp_destruct_common(struct sock *sk) -{ - struct sctp_sock *sp = sctp_sk(sk); - - /* Free up the HMAC transform. */ - crypto_free_shash(sp->hmac); + SCTP_DBG_OBJCNT_DEC(sock); } static void sctp_destruct_sock(struct sock *sk) { - sctp_destruct_common(sk); inet_sock_destruct(sk); } @@ -5187,10 +5252,11 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_peer_rwnd = asoc->peer.rwnd; info->sctpi_peer_tag = asoc->c.peer_vtag; - mask = asoc->peer.ecn_capable << 1; + mask = asoc->peer.intl_capable << 1; + mask = (mask | asoc->peer.ecn_capable) << 1; mask = (mask | asoc->peer.ipv4_address) << 1; mask = (mask | asoc->peer.ipv6_address) << 1; - mask = (mask | asoc->peer.hostname_address) << 1; + mask = (mask | asoc->peer.reconf_capable) << 1; mask = (mask | asoc->peer.asconf_capable) << 1; mask = (mask | asoc->peer.prsctp_capable) << 1; mask = (mask | asoc->peer.auth_capable); @@ -5606,11 +5672,12 @@ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optv } /* Helper routine to branch off an association to a new socket. */ -int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) +static int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, + struct socket **sockp) { struct sctp_association *asoc = sctp_id2assoc(sk, id); - struct sctp_sock *sp = sctp_sk(sk); struct socket *sock; + struct sock *newsk; int err = 0; /* Do not peel off from one netns to another one. */ @@ -5626,35 +5693,28 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) if (!sctp_style(sk, UDP)) return -EINVAL; - /* Create a new socket. */ - err = sock_create(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); - if (err < 0) + err = sock_create_lite(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); + if (err) return err; - sctp_copy_sock(sock->sk, sk, asoc); - - /* Make peeled-off sockets more like 1-1 accepted sockets. - * Set the daddr and initialize id to something more random and also - * copy over any ip options. - */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); - sp->pf->copy_ip_options(sk, sock->sk); - - /* Populate the fields of the newsk from the oldsk and migrate the - * asoc to the newsk. - */ - err = sctp_sock_migrate(sk, sock->sk, asoc, - SCTP_SOCKET_UDP_HIGH_BANDWIDTH); - if (err) { + newsk = sctp_clone_sock(sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); + if (IS_ERR(newsk)) { sock_release(sock); - sock = NULL; + *sockp = NULL; + return PTR_ERR(newsk); } + lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); + __inet_accept(sk->sk_socket, sock, newsk); + release_sock(newsk); + + sock->ops = sk->sk_socket->ops; + __module_get(sock->ops->owner); + *sockp = sock; return err; } -EXPORT_SYMBOL(sctp_do_peeloff); static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *peeloff, struct file **newfile, unsigned flags) @@ -7104,6 +7164,7 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_ids *ids; + size_t ids_size; u32 num = 0; if (sctp_style(sk, TCP)) @@ -7116,11 +7177,11 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, num++; } - if (len < sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num) + ids_size = struct_size(ids, gaids_assoc_id, num); + if (len < ids_size) return -EINVAL; - len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num; - + len = ids_size; ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; @@ -8275,6 +8336,22 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, return retval; } +static bool sctp_bpf_bypass_getsockopt(int level, int optname) +{ + if (level == SOL_SCTP) { + switch (optname) { + case SCTP_SOCKOPT_PEELOFF: + case SCTP_SOCKOPT_PEELOFF_FLAGS: + case SCTP_SOCKOPT_CONNECTX3: + return true; + default: + return false; + } + } + + return false; +} + static int sctp_hash(struct sock *sk) { /* STUB */ @@ -8283,7 +8360,7 @@ static int sctp_hash(struct sock *sk) static void sctp_unhash(struct sock *sk) { - /* STUB */ + sock_rps_delete_flow(sk); } /* Check if port is acceptable. Possibly find first available port. @@ -8307,8 +8384,8 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) bool reuse = (sk->sk_reuse || sp->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct net *net = sock_net(sk); - kuid_t uid = sock_i_uid(sk); struct sctp_bind_bucket *pp; + kuid_t uid = sk_uid(sk); unsigned short snum; int ret; @@ -8321,7 +8398,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) int low, high, remaining, index; unsigned int rover; - inet_get_local_port_range(net, &low, &high); + inet_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_below(remaining) + low; @@ -8406,7 +8483,7 @@ pp_found: (reuse && (sk2->sk_reuse || sp2->reuse) && sk2->sk_state != SCTP_SS_LISTENING) || (sk->sk_reuseport && sk2->sk_reuseport && - uid_eq(uid, sock_i_uid(sk2)))) + uid_eq(uid, sk_uid(sk2)))) continue; if ((!sk->sk_bound_dev_if || !bound_dev_if2 || @@ -8492,20 +8569,7 @@ static int sctp_listen_start(struct sock *sk, int backlog) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; - struct crypto_shash *tfm = NULL; - char alg[32]; - - /* Allocate HMAC for generating cookie. */ - if (!sp->hmac && sp->sctp_hmac_alg) { - sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg); - tfm = crypto_alloc_shash(alg, 0, 0); - if (IS_ERR(tfm)) { - net_info_ratelimited("failed to load transform for %s: %ld\n", - sp->sctp_hmac_alg, PTR_ERR(tfm)); - return -ENOSYS; - } - sctp_sk(sk)->hmac = tfm; - } + int err; /* * If a bind() or sctp_bindx() is not called prior to a listen() @@ -8520,17 +8584,26 @@ static int sctp_listen_start(struct sock *sk, int backlog) */ inet_sk_set_state(sk, SCTP_SS_LISTENING); if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) - return -EAGAIN; + if (sctp_autobind(sk)) { + err = -EAGAIN; + goto err; + } } else { if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { - inet_sk_set_state(sk, SCTP_SS_CLOSED); - return -EADDRINUSE; + err = -EADDRINUSE; + goto err; } } WRITE_ONCE(sk->sk_max_ack_backlog, backlog); - return sctp_hash_endpoint(ep); + err = sctp_hash_endpoint(ep); + if (err) + goto err; + + return 0; +err: + inet_sk_set_state(sk, SCTP_SS_CLOSED); + return err; } /* @@ -9020,12 +9093,6 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, int *err) if (sk->sk_shutdown & RCV_SHUTDOWN) break; - if (sk_can_busy_loop(sk)) { - sk_busy_loop(sk, flags & MSG_DONTWAIT); - - if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) - continue; - } /* User doesn't want to wait. */ error = -EAGAIN; @@ -9058,7 +9125,8 @@ static void __sctp_write_space(struct sctp_association *asoc) wq = rcu_dereference(sk->sk_wq); if (wq) { if (waitqueue_active(&wq->wait)) - wake_up_interruptible(&wq->wait); + wake_up_interruptible_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. @@ -9122,7 +9190,7 @@ static void sctp_wfree(struct sk_buff *skb) struct sock *sk = asoc->base.sk; sk_mem_uncharge(sk, skb->truesize); - sk->sk_wmem_queued -= skb->truesize + sizeof(struct sctp_chunk); + sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk))); asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk); WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); @@ -9173,8 +9241,9 @@ void sctp_sock_rfree(struct sk_buff *skb) /* Helper function to wait for space in the sndbuf. */ -static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len) +static int sctp_wait_for_sndbuf(struct sctp_association *asoc, + struct sctp_transport *transport, + long *timeo_p, size_t msg_len) { struct sock *sk = asoc->base.sk; long current_timeo = *timeo_p; @@ -9184,7 +9253,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); - /* Increment the association's refcnt. */ + /* Increment the transport and association's refcnt. */ + if (transport) + sctp_transport_hold(transport); sctp_association_hold(asoc); /* Wait on the association specific sndbuf space. */ @@ -9193,7 +9264,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, TASK_INTERRUPTIBLE); if (asoc->base.dead) goto do_dead; - if (!*timeo_p) + if ((!*timeo_p) || (transport && transport->dead)) goto do_nonblock; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING) goto do_error; @@ -9218,7 +9289,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, out: finish_wait(&asoc->wait, &wait); - /* Release the association's refcnt. */ + /* Release the transport and association's refcnt. */ + if (transport) + sctp_transport_put(transport); sctp_association_put(asoc); return err; @@ -9244,12 +9317,14 @@ void sctp_data_ready(struct sock *sk) { struct socket_wq *wq; + trace_sk_data_ready(sk); + rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } @@ -9275,9 +9350,9 @@ void sctp_write_space(struct sock *sk) * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ -static bool sctp_writeable(struct sock *sk) +static bool sctp_writeable(const struct sock *sk) { - return sk->sk_sndbuf > sk->sk_wmem_queued; + return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued); } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, @@ -9365,7 +9440,8 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) } err = -EINVAL; - if (!sctp_sstate(sk, LISTENING)) + if (!sctp_sstate(sk, LISTENING) || + (sk->sk_shutdown & RCV_SHUTDOWN)) break; err = 0; @@ -9417,71 +9493,6 @@ done: sctp_skb_set_owner_r(skb, sk); } -void sctp_copy_sock(struct sock *newsk, struct sock *sk, - struct sctp_association *asoc) -{ - struct inet_sock *inet = inet_sk(sk); - struct inet_sock *newinet; - struct sctp_sock *sp = sctp_sk(sk); - - newsk->sk_type = sk->sk_type; - newsk->sk_bound_dev_if = sk->sk_bound_dev_if; - newsk->sk_flags = sk->sk_flags; - newsk->sk_tsflags = sk->sk_tsflags; - newsk->sk_no_check_tx = sk->sk_no_check_tx; - newsk->sk_no_check_rx = sk->sk_no_check_rx; - newsk->sk_reuse = sk->sk_reuse; - sctp_sk(newsk)->reuse = sp->reuse; - - newsk->sk_shutdown = sk->sk_shutdown; - newsk->sk_destruct = sk->sk_destruct; - newsk->sk_family = sk->sk_family; - newsk->sk_protocol = IPPROTO_SCTP; - newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; - newsk->sk_sndbuf = sk->sk_sndbuf; - newsk->sk_rcvbuf = sk->sk_rcvbuf; - newsk->sk_lingertime = sk->sk_lingertime; - newsk->sk_rcvtimeo = sk->sk_rcvtimeo; - newsk->sk_sndtimeo = sk->sk_sndtimeo; - newsk->sk_rxhash = sk->sk_rxhash; - - newinet = inet_sk(newsk); - - /* Initialize sk's sport, dport, rcv_saddr and daddr for - * getsockname() and getpeername() - */ - newinet->inet_sport = inet->inet_sport; - newinet->inet_saddr = inet->inet_saddr; - newinet->inet_rcv_saddr = inet->inet_rcv_saddr; - newinet->inet_dport = htons(asoc->peer.port); - newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = get_random_u16(); - - newinet->uc_ttl = inet->uc_ttl; - newinet->mc_loop = 1; - newinet->mc_ttl = 1; - newinet->mc_index = 0; - newinet->mc_list = NULL; - - if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); - - /* Set newsk security attributes from original sk and connection - * security attribute from asoc. - */ - security_sctp_sk_clone(asoc, sk, newsk); -} - -static inline void sctp_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - size_t ancestor_size = sizeof(struct inet_sock); - - ancestor_size += sk_from->sk_prot->obj_size; - ancestor_size -= offsetof(struct sctp_sock, pd_lobby); - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ @@ -9498,19 +9509,10 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_bind_hashbucket *head; int err; - /* Migrate socket buffer sizes and all the socket level options to the - * new socket. - */ - newsk->sk_sndbuf = oldsk->sk_sndbuf; - newsk->sk_rcvbuf = oldsk->sk_rcvbuf; - /* Brute force copy old sctp opt. */ - sctp_copy_descendant(newsk, oldsk); - /* Restore the ep value that was overwritten with the above structure * copy. */ newsp->ep = newep; - newsp->hmac = NULL; /* Hook this new socket in to the bind_hash list. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(oldsk), @@ -9530,16 +9532,6 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, if (err) return err; - /* New ep's auth_hmacs should be set if old ep's is set, in case - * that net->sctp.auth_enable has been changed to 0 by users and - * new ep's auth_hmacs couldn't be set in sctp_endpoint_init(). - */ - if (oldsp->ep->auth_hmacs) { - err = sctp_auth_init_hmacs(newsp->ep, GFP_KERNEL); - if (err) - return err; - } - sctp_auto_asconf_init(newsp); /* Move any messages in the old socket's receive queue that are for the @@ -9642,6 +9634,7 @@ struct proto sctp_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, @@ -9671,7 +9664,6 @@ struct proto sctp_prot = { static void sctp_v6_destruct_sock(struct sock *sk) { - sctp_destruct_common(sk); inet6_sock_destruct(sk); } @@ -9697,6 +9689,7 @@ struct proto sctpv6_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, @@ -9706,6 +9699,7 @@ struct proto sctpv6_prot = { .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), + .ipv6_pinfo_offset = offsetof(struct sctp6_sock, inet6), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - offsetof(struct sctp6_sock, sctp.subscribe) + diff --git a/net/sctp/stream.c b/net/sctp/stream.c index ee6514af830f..0615e4426341 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -54,7 +54,7 @@ static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) static void sctp_stream_free_ext(struct sctp_stream *stream, __u16 sid) { - struct sctp_sched_ops *sched; + const struct sctp_sched_ops *sched; if (!SCTP_SO(stream, sid)->ext) return; @@ -130,7 +130,7 @@ out: int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i, ret = 0; gfp |= __GFP_NOWARN; @@ -182,7 +182,7 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) void sctp_stream_free(struct sctp_stream *stream) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; sched->unsched_all(stream); @@ -207,7 +207,7 @@ void sctp_stream_clear(struct sctp_stream *stream) void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); sched->unsched_all(stream); sctp_stream_outq_migrate(stream, new, new->outcnt); @@ -491,7 +491,7 @@ static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( return NULL; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; - sctp_walk_params(param, hdr, params) { + sctp_walk_params(param, hdr) { /* sctp_strreset_tsnreq is actually the basic structure * of all stream reconf params, so it's safe to use it * to access request_seq. @@ -576,7 +576,7 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_transport *t; t = asoc->strreset_chunk->transport; - if (del_timer(&t->reconf_timer)) + if (timer_delete(&t->reconf_timer)) sctp_transport_put(t); sctp_chunk_put(asoc->strreset_chunk); @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); @@ -825,7 +825,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_transport *t; t = asoc->strreset_chunk->transport; - if (del_timer(&t->reconf_timer)) + if (timer_delete(&t->reconf_timer)) sctp_transport_put(t); sctp_chunk_put(asoc->strreset_chunk); @@ -1076,7 +1076,7 @@ struct sctp_chunk *sctp_process_strreset_resp( /* remove everything for this reconf request */ if (!asoc->strreset_outstanding) { t = asoc->strreset_chunk->transport; - if (del_timer(&t->reconf_timer)) + if (timer_delete(&t->reconf_timer)) sctp_transport_put(t); sctp_chunk_put(asoc->strreset_chunk); diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..840f24045ae2 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1153,8 +1153,9 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) } #define _sctp_walk_ifwdtsn(pos, chunk, end) \ - for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + for (pos = (void *)(chunk->subh.ifwdtsn_hdr + 1); \ + (void *)pos <= (void *)(chunk->subh.ifwdtsn_hdr + 1) + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 330067002deb..50f8b5240359 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -91,7 +91,7 @@ static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream) { } -static struct sctp_sched_ops sctp_sched_fcfs = { +static const struct sctp_sched_ops sctp_sched_fcfs = { .set = sctp_sched_fcfs_set, .get = sctp_sched_fcfs_get, .init = sctp_sched_fcfs_init, @@ -111,10 +111,10 @@ static void sctp_sched_ops_fcfs_init(void) /* API to other parts of the stack */ -static struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1]; +static const struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1]; void sctp_sched_ops_register(enum sctp_sched_type sched, - struct sctp_sched_ops *sched_ops) + const struct sctp_sched_ops *sched_ops) { sctp_sched_ops[sched] = sched_ops; } @@ -124,11 +124,13 @@ void sctp_sched_ops_init(void) sctp_sched_ops_fcfs_init(); sctp_sched_ops_prio_init(); sctp_sched_ops_rr_init(); + sctp_sched_ops_fc_init(); + sctp_sched_ops_wfq_init(); } static void sctp_sched_free_sched(struct sctp_stream *stream) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); struct sctp_stream_out_ext *soute; int i; @@ -146,18 +148,19 @@ static void sctp_sched_free_sched(struct sctp_stream *stream) int sctp_sched_set_sched(struct sctp_association *asoc, enum sctp_sched_type sched) { - struct sctp_sched_ops *n = sctp_sched_ops[sched]; - struct sctp_sched_ops *old = asoc->outqueue.sched; + const struct sctp_sched_ops *old = asoc->outqueue.sched; struct sctp_datamsg *msg = NULL; + const struct sctp_sched_ops *n; struct sctp_chunk *ch; int i, ret = 0; - if (old == n) - return ret; - if (sched > SCTP_SS_MAX) return -EINVAL; + n = sctp_sched_ops[sched]; + if (old == n) + return ret; + if (old) sctp_sched_free_sched(&asoc->stream); @@ -260,14 +263,14 @@ void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext; INIT_LIST_HEAD(&ext->outq); return sched->init_sid(stream, sid, gfp); } -struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) +const struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) { struct sctp_association *asoc; diff --git a/net/sctp/stream_sched_fc.c b/net/sctp/stream_sched_fc.c new file mode 100644 index 000000000000..776c6de46c22 --- /dev/null +++ b/net/sctp/stream_sched_fc.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2022 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Xin Long <lucien.xin@gmail.com> + */ + +#include <linux/list.h> +#include <net/sctp/sctp.h> +#include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> + +/* Fair Capacity and Weighted Fair Queueing handling + * RFC 8260 section 3.5 and 3.6 + */ +static void sctp_sched_fc_unsched_all(struct sctp_stream *stream); + +static int sctp_sched_wfq_set(struct sctp_stream *stream, __u16 sid, + __u16 weight, gfp_t gfp) +{ + struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; + + if (!weight) + return -EINVAL; + + soute->fc_weight = weight; + return 0; +} + +static int sctp_sched_wfq_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; + + *value = soute->fc_weight; + return 0; +} + +static int sctp_sched_fc_set(struct sctp_stream *stream, __u16 sid, + __u16 weight, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_fc_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + return 0; +} + +static int sctp_sched_fc_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->fc_list); + + return 0; +} + +static int sctp_sched_fc_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext; + + INIT_LIST_HEAD(&soute->fc_list); + soute->fc_length = 0; + soute->fc_weight = 1; + + return 0; +} + +static void sctp_sched_fc_free_sid(struct sctp_stream *stream, __u16 sid) +{ +} + +static void sctp_sched_fc_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + struct sctp_stream_out_ext *pos; + + if (!list_empty(&soute->fc_list)) + return; + + list_for_each_entry(pos, &stream->fc_list, fc_list) + if ((__u64)pos->fc_length * soute->fc_weight >= + (__u64)soute->fc_length * pos->fc_weight) + break; + list_add_tail(&soute->fc_list, &pos->fc_list); +} + +static void sctp_sched_fc_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext); +} + +static struct sctp_chunk *sctp_sched_fc_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + return NULL; + + /* Find which chunk is next */ + if (stream->out_curr) + soute = stream->out_curr->ext; + else + soute = list_entry(stream->fc_list.next, struct sctp_stream_out_ext, fc_list); + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + + sctp_sched_dequeue_common(q, ch); + return ch; +} + +static void sctp_sched_fc_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_out_ext *soute, *pos; + __u16 sid, i; + + sid = sctp_chunk_stream_no(ch); + soute = SCTP_SO(stream, sid)->ext; + /* reduce all fc_lengths by U32_MAX / 4 if the current fc_length overflows. */ + if (soute->fc_length > U32_MAX - ch->skb->len) { + for (i = 0; i < stream->outcnt; i++) { + pos = SCTP_SO(stream, i)->ext; + if (!pos) + continue; + if (pos->fc_length <= (U32_MAX >> 2)) { + pos->fc_length = 0; + continue; + } + pos->fc_length -= (U32_MAX >> 2); + } + } + soute->fc_length += ch->skb->len; + + if (list_empty(&soute->outq)) { + list_del_init(&soute->fc_list); + return; + } + + pos = soute; + list_for_each_entry_continue(pos, &stream->fc_list, fc_list) + if ((__u64)pos->fc_length * soute->fc_weight >= + (__u64)soute->fc_length * pos->fc_weight) + break; + list_move_tail(&soute->fc_list, &pos->fc_list); +} + +static void sctp_sched_fc_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid = sctp_chunk_stream_no(ch); + + if (SCTP_SO(stream, sid)->ext) + sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext); + } +} + +static void sctp_sched_fc_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_out_ext *soute, *tmp; + + list_for_each_entry_safe(soute, tmp, &stream->fc_list, fc_list) + list_del_init(&soute->fc_list); +} + +static const struct sctp_sched_ops sctp_sched_fc = { + .set = sctp_sched_fc_set, + .get = sctp_sched_fc_get, + .init = sctp_sched_fc_init, + .init_sid = sctp_sched_fc_init_sid, + .free_sid = sctp_sched_fc_free_sid, + .enqueue = sctp_sched_fc_enqueue, + .dequeue = sctp_sched_fc_dequeue, + .dequeue_done = sctp_sched_fc_dequeue_done, + .sched_all = sctp_sched_fc_sched_all, + .unsched_all = sctp_sched_fc_unsched_all, +}; + +void sctp_sched_ops_fc_init(void) +{ + sctp_sched_ops_register(SCTP_SS_FC, &sctp_sched_fc); +} + +static const struct sctp_sched_ops sctp_sched_wfq = { + .set = sctp_sched_wfq_set, + .get = sctp_sched_wfq_get, + .init = sctp_sched_fc_init, + .init_sid = sctp_sched_fc_init_sid, + .free_sid = sctp_sched_fc_free_sid, + .enqueue = sctp_sched_fc_enqueue, + .dequeue = sctp_sched_fc_dequeue, + .dequeue_done = sctp_sched_fc_dequeue_done, + .sched_all = sctp_sched_fc_sched_all, + .unsched_all = sctp_sched_fc_unsched_all, +}; + +void sctp_sched_ops_wfq_init(void) +{ + sctp_sched_ops_register(SCTP_SS_WFQ, &sctp_sched_wfq); +} diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 42d4800f263d..fb6c55e5615d 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -25,6 +25,18 @@ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); +static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p) +{ + p->users++; + return p; +} + +static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p) +{ + if (p && --p->users == 0) + kfree(p); +} + static struct sctp_stream_priorities *sctp_sched_prio_new_head( struct sctp_stream *stream, int prio, gfp_t gfp) { @@ -38,6 +50,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_new_head( INIT_LIST_HEAD(&p->active); p->next = NULL; p->prio = prio; + p->users = 1; return p; } @@ -53,7 +66,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ list_for_each_entry(p, &stream->prio_list, prio_sched) { if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); if (p->prio > prio) break; } @@ -70,7 +83,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ break; if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); } /* If not even there, allocate a new one. */ @@ -154,32 +167,21 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; - int i; + + old = soute->prio_head; + if (old && old->prio == prio) + return 0; prio_head = sctp_sched_prio_get_head(stream, prio, gfp); if (!prio_head) return -ENOMEM; reschedule = sctp_sched_prio_unsched(soute); - old = soute->prio_head; soute->prio_head = prio_head; if (reschedule) sctp_sched_prio_sched(stream, soute); - if (!old) - /* Happens when we set the priority for the first time */ - return 0; - - for (i = 0; i < stream->outcnt; i++) { - soute = SCTP_SO(stream, i)->ext; - if (soute && soute->prio_head == old) - /* It's still in use, nothing else to do here. */ - return 0; - } - - /* No hits, we are good to free it. */ - kfree(old); - + sctp_sched_prio_head_put(old); return 0; } @@ -206,20 +208,8 @@ static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) { - struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head; - int i; - - if (!prio) - return; - + sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head); SCTP_SO(stream, sid)->ext->prio_head = NULL; - for (i = 0; i < stream->outcnt; i++) { - if (SCTP_SO(stream, i)->ext && - SCTP_SO(stream, i)->ext->prio_head == prio) - return; - } - - kfree(prio); } static void sctp_sched_prio_enqueue(struct sctp_outq *q, @@ -310,7 +300,7 @@ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) sctp_sched_prio_unsched(soute); } -static struct sctp_sched_ops sctp_sched_prio = { +static const struct sctp_sched_ops sctp_sched_prio = { .set = sctp_sched_prio_set, .get = sctp_sched_prio_get, .init = sctp_sched_prio_init, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index 1f235e7f643a..9157b653f196 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -171,7 +171,7 @@ static void sctp_sched_rr_unsched_all(struct sctp_stream *stream) sctp_sched_rr_unsched(stream, soute); } -static struct sctp_sched_ops sctp_sched_rr = { +static const struct sctp_sched_ops sctp_sched_rr = { .set = sctp_sched_rr_set, .get = sctp_sched_rr_get, .init = sctp_sched_rr_init, diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index a7a9136198fd..15e7db9a3ab2 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -43,19 +43,19 @@ static unsigned long max_autoclose_max = (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, +static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, +static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, +static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, +static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_auth(struct ctl_table *ctl, int write, +static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, +static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { @@ -80,8 +80,6 @@ static struct ctl_table sctp_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - - { /* sentinel */ } }; /* The following index defines are used in sctp_sysctl_net_register(). @@ -176,7 +174,7 @@ static struct ctl_table sctp_net_table[] = { }, { .procname = "cookie_hmac_alg", - .data = &init_net.sctp.sctp_hmac_alg, + .data = &init_net.sctp.cookie_auth_enable, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, @@ -384,17 +382,14 @@ static struct ctl_table sctp_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &pf_expose_max, }, - - { /* sentinel */ } }; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, +static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.cookie_auth_enable); struct ctl_table tbl; - bool changed = false; - char *none = "none"; char tmp[8] = {0}; int ret; @@ -402,41 +397,32 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, if (write) { tbl.data = tmp; - tbl.maxlen = sizeof(tmp); - } else { - tbl.data = net->sctp.sctp_hmac_alg ? : none; - tbl.maxlen = strlen(tbl.data); - } - - ret = proc_dostring(&tbl, write, buffer, lenp, ppos); - if (write && ret == 0) { -#ifdef CONFIG_CRYPTO_MD5 - if (!strncmp(tmp, "md5", 3)) { - net->sctp.sctp_hmac_alg = "md5"; - changed = true; + tbl.maxlen = sizeof(tmp) - 1; + ret = proc_dostring(&tbl, 1, buffer, lenp, ppos); + if (ret) + return ret; + if (!strcmp(tmp, "sha256")) { + net->sctp.cookie_auth_enable = 1; + return 0; } -#endif -#ifdef CONFIG_CRYPTO_SHA1 - if (!strncmp(tmp, "sha1", 4)) { - net->sctp.sctp_hmac_alg = "sha1"; - changed = true; + if (!strcmp(tmp, "none")) { + net->sctp.cookie_auth_enable = 0; + return 0; } -#endif - if (!strncmp(tmp, "none", 4)) { - net->sctp.sctp_hmac_alg = NULL; - changed = true; - } - if (!changed) - ret = -EINVAL; + return -EINVAL; } - - return ret; + if (net->sctp.cookie_auth_enable) + tbl.data = (char *)"sha256"; + else + tbl.data = (char *)"none"; + tbl.maxlen = strlen(tbl.data); + return proc_dostring(&tbl, 0, buffer, lenp, ppos); } -static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_min); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -461,10 +447,10 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_max); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -489,7 +475,7 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, +static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write) @@ -499,10 +485,10 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static int proc_sctp_do_auth(struct ctl_table *ctl, int write, +static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.auth_enable); struct ctl_table tbl; int new_value, ret; @@ -528,10 +514,12 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, +static DEFINE_MUTEX(sctp_sysctl_mutex); + +static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.udp_port); unsigned int min = *(unsigned int *)ctl->extra1; unsigned int max = *(unsigned int *)ctl->extra2; struct ctl_table tbl; @@ -552,6 +540,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -564,15 +553,17 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; } -static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, +static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.probe_interval); struct ctl_table tbl; int ret, new_value; @@ -597,6 +588,7 @@ static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { + size_t table_size = ARRAY_SIZE(sctp_net_table); struct ctl_table *table; int i; @@ -604,7 +596,7 @@ int sctp_sysctl_net_register(struct net *net) if (!table) return -ENOMEM; - for (i = 0; table[i].data; i++) + for (i = 0; i < table_size; i++) table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; table[SCTP_RTO_MIN_IDX].extra2 = &net->sctp.rto_max; @@ -612,7 +604,8 @@ int sctp_sysctl_net_register(struct net *net) table[SCTP_PF_RETRANS_IDX].extra2 = &net->sctp.ps_retrans; table[SCTP_PS_RETRANS_IDX].extra1 = &net->sctp.pf_retrans; - net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); + net->sctp.sysctl_header = register_net_sysctl_sz(net, "net/sctp", + table, table_size); if (net->sctp.sysctl_header == NULL) { kfree(table); return -ENOMEM; @@ -622,7 +615,7 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index ca1eba95c293..0c56d9673cc1 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -37,10 +37,10 @@ /* 1st Level Abstractions. */ /* Initialize a new transport from provided memory. */ -static struct sctp_transport *sctp_transport_init(struct net *net, - struct sctp_transport *peer, - const union sctp_addr *addr, - gfp_t gfp) +static void sctp_transport_init(struct net *net, + struct sctp_transport *peer, + const union sctp_addr *addr, + gfp_t gfp) { /* Copy in the address. */ peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); @@ -83,8 +83,6 @@ static struct sctp_transport *sctp_transport_init(struct net *net, get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); refcount_set(&peer->refcnt, 1); - - return peer; } /* Allocate and initialize a new transport. */ @@ -96,20 +94,13 @@ struct sctp_transport *sctp_transport_new(struct net *net, transport = kzalloc(sizeof(*transport), gfp); if (!transport) - goto fail; + return NULL; - if (!sctp_transport_init(net, transport, addr, gfp)) - goto fail_init; + sctp_transport_init(net, transport, addr, gfp); SCTP_DBG_OBJCNT_INC(transport); return transport; - -fail_init: - kfree(transport); - -fail: - return NULL; } /* This transport is no longer needed. Free up if possible, or @@ -117,8 +108,10 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { + transport->dead = 1; + /* Try to delete the heartbeat timer. */ - if (del_timer(&transport->hb_timer)) + if (timer_delete(&transport->hb_timer)) sctp_transport_put(transport); /* Delete the T3_rtx timer if it's active. @@ -126,17 +119,17 @@ void sctp_transport_free(struct sctp_transport *transport) * structure hang around in memory since we know * the transport is going away. */ - if (del_timer(&transport->T3_rtx_timer)) + if (timer_delete(&transport->T3_rtx_timer)) sctp_transport_put(transport); - if (del_timer(&transport->reconf_timer)) + if (timer_delete(&transport->reconf_timer)) sctp_transport_put(transport); - if (del_timer(&transport->probe_timer)) + if (timer_delete(&transport->probe_timer)) sctp_transport_put(transport); /* Delete the ICMP proto unreachable timer if it's active. */ - if (del_timer(&transport->proto_unreach_timer)) + if (timer_delete(&transport->proto_unreach_timer)) sctp_transport_put(transport); sctp_transport_put(transport); @@ -196,9 +189,7 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if ((time_before(transport->hb_timer.expires, expires) || - !timer_pending(&transport->hb_timer)) && - !mod_timer(&transport->hb_timer, + if (!mod_timer(&transport->hb_timer, expires + get_random_u32_below(transport->rto))) sctp_transport_hold(transport); } @@ -240,7 +231,7 @@ void sctp_transport_set_owner(struct sctp_transport *transport, void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) { /* If we don't have a fresh route, look one up */ - if (!transport->dst || transport->dst->obsolete) { + if (!transport->dst || READ_ONCE(transport->dst->obsolete)) { sctp_transport_dst_release(transport); transport->af_specific->get_dst(transport, &transport->saddr, &transport->fl, sk); @@ -326,9 +317,12 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_SEARCH) { if (!t->pl.probe_high) { - t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, - SCTP_MAX_PLPMTU); - return false; + if (t->pl.probe_size < SCTP_MAX_PLPMTU) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return false; + } + t->pl.probe_high = SCTP_MAX_PLPMTU; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -343,7 +337,7 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) } else if (t->pl.state == SCTP_PL_COMPLETE) { /* Raise probe_size again after 30 * interval in Search Complete */ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU); } return t->pl.state == SCTP_PL_COMPLETE; @@ -492,6 +486,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) if (tp->rttvar || tp->srtt) { struct net *net = tp->asoc->base.net; + unsigned int rto_beta, rto_alpha; /* 6.3.1 C3) When a new RTT measurement R' is made, set * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'| * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R' @@ -503,10 +498,14 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) * For example, assuming the default value of RTO.Alpha of * 1/8, rto_alpha would be expressed as 3. */ - tp->rttvar = tp->rttvar - (tp->rttvar >> net->sctp.rto_beta) - + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> net->sctp.rto_beta); - tp->srtt = tp->srtt - (tp->srtt >> net->sctp.rto_alpha) - + (rtt >> net->sctp.rto_alpha); + rto_beta = READ_ONCE(net->sctp.rto_beta); + if (rto_beta < 32) + tp->rttvar = tp->rttvar - (tp->rttvar >> rto_beta) + + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> rto_beta); + rto_alpha = READ_ONCE(net->sctp.rto_alpha); + if (rto_alpha < 32) + tp->srtt = tp->srtt - (tp->srtt >> rto_alpha) + + (rtt >> rto_alpha); } else { /* 6.3.1 C2) When the first RTT measurement R is made, set * SRTT <- R, RTTVAR <- R/2. @@ -828,7 +827,7 @@ void sctp_transport_reset(struct sctp_transport *t) void sctp_transport_immediate_rtx(struct sctp_transport *t) { /* Stop pending T3_rtx_timer */ - if (del_timer(&t->T3_rtx_timer)) + if (timer_delete(&t->T3_rtx_timer)) sctp_transport_put(t); sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX); |
